diff options
304 files changed, 6140 insertions, 3293 deletions
diff --git a/.gitignore b/.gitignore index b3c4363af0..39635d7eef 100644 --- a/.gitignore +++ b/.gitignore @@ -1,7 +1,10 @@ *~ *.swp +*.ipr *.iml +*.iws .idea/ +sbt/*.jar .settings .cache /build/ @@ -13,20 +13,22 @@ This README file only contains basic setup instructions. ## Building Spark requires Scala 2.10. The project is built using Simple Build Tool (SBT), -which is packaged with it. To build Spark and its example programs, run: +which can be obtained [here](http://www.scala-sbt.org). If SBT is installed we +will use the system version of sbt otherwise we will attempt to download it +automatically. To build Spark and its example programs, run: - sbt/sbt assembly + ./sbt/sbt assembly Once you've built Spark, the easiest way to start using it is the shell: - ./spark-shell + ./bin/spark-shell -Or, for the Python API, the Python shell (`./pyspark`). +Or, for the Python API, the Python shell (`./bin/pyspark`). Spark also comes with several sample programs in the `examples` directory. -To run one of them, use `./run-example <class> <params>`. For example: +To run one of them, use `./bin/run-example <class> <params>`. For example: - ./run-example org.apache.spark.examples.SparkLR local[2] + ./bin/run-example org.apache.spark.examples.SparkLR local[2] will run the Logistic Regression example locally on 2 CPUs. @@ -36,7 +38,13 @@ All of the Spark samples take a `<master>` parameter that is the cluster URL to connect to. This can be a mesos:// or spark:// URL, or "local" to run locally with one thread, or "local[N]" to run locally with N threads. +## Running tests +Testing first requires [Building](#building) Spark. Once Spark is built, tests +can be run using: + +`./sbt/sbt test` + ## A Note About Hadoop Versions Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported diff --git a/assembly/lib/PY4J_LICENSE.txt b/assembly/lib/PY4J_LICENSE.txt deleted file mode 100644 index a70279ca14..0000000000 --- a/assembly/lib/PY4J_LICENSE.txt +++ /dev/null @@ -1,27 +0,0 @@ - -Copyright (c) 2009-2011, Barthelemy Dagenais All rights reserved. - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - -- Redistributions of source code must retain the above copyright notice, this -list of conditions and the following disclaimer. - -- Redistributions in binary form must reproduce the above copyright notice, -this list of conditions and the following disclaimer in the documentation -and/or other materials provided with the distribution. - -- The name of the author may not be used to endorse or promote products -derived from this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. diff --git a/assembly/lib/PY4J_VERSION.txt b/assembly/lib/PY4J_VERSION.txt deleted file mode 100644 index 04a0cd52a8..0000000000 --- a/assembly/lib/PY4J_VERSION.txt +++ /dev/null @@ -1 +0,0 @@ -b7924aabe9c5e63f0a4d8bbd17019534c7ec014e diff --git a/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.jar b/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.jar Binary files differdeleted file mode 100644 index 73b7ddb7d1..0000000000 --- a/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.jar +++ /dev/null diff --git a/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.pom b/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.pom deleted file mode 100644 index 1c730e19b4..0000000000 --- a/assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.pom +++ /dev/null @@ -1,9 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" xmlns="http://maven.apache.org/POM/4.0.0" - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> - <modelVersion>4.0.0</modelVersion> - <groupId>net.sf.py4j</groupId> - <artifactId>py4j</artifactId> - <version>0.7</version> - <description>POM was created from install:install-file</description> -</project> diff --git a/assembly/lib/net/sf/py4j/py4j/maven-metadata-local.xml b/assembly/lib/net/sf/py4j/py4j/maven-metadata-local.xml deleted file mode 100644 index 6942ff45e7..0000000000 --- a/assembly/lib/net/sf/py4j/py4j/maven-metadata-local.xml +++ /dev/null @@ -1,12 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<metadata> - <groupId>net.sf.py4j</groupId> - <artifactId>py4j</artifactId> - <versioning> - <release>0.7</release> - <versions> - <version>0.7</version> - </versions> - <lastUpdated>20130828020333</lastUpdated> - </versioning> -</metadata> diff --git a/assembly/pom.xml b/assembly/pom.xml index fc2adc1fbb..54a25910ce 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -67,7 +67,7 @@ <dependency> <groupId>net.sf.py4j</groupId> <artifactId>py4j</artifactId> - <version>0.7</version> + <version>0.8.1</version> </dependency> </dependencies> @@ -108,12 +108,12 @@ <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> <resource>META-INF/services/org.apache.hadoop.fs.FileSystem</resource> </transformer> - </transformers> - <transformers> - <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" /> <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> <resource>reference.conf</resource> </transformer> + <transformer implementation="org.apache.maven.plugins.shade.resource.DontIncludeResourceTransformer"> + <resource>log4j.properties</resource> + </transformer> </transformers> </configuration> </execution> @@ -124,7 +124,17 @@ <profiles> <profile> - <id>hadoop2-yarn</id> + <id>yarn-alpha</id> + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-yarn-alpha_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + </dependencies> + </profile> + <profile> + <id>yarn</id> <dependencies> <dependency> <groupId>org.apache.spark</groupId> diff --git a/assembly/src/main/assembly/assembly.xml b/assembly/src/main/assembly/assembly.xml index 47d3fa93d0..6af383db65 100644 --- a/assembly/src/main/assembly/assembly.xml +++ b/assembly/src/main/assembly/assembly.xml @@ -39,23 +39,20 @@ </fileSet> <fileSet> <directory> - ${project.parent.basedir}/bin/ + ${project.parent.basedir}/sbin/ </directory> - <outputDirectory>/bin</outputDirectory> + <outputDirectory>/sbin</outputDirectory> <includes> <include>**/*</include> </includes> </fileSet> <fileSet> <directory> - ${project.parent.basedir} + ${project.parent.basedir}/bin/ </directory> <outputDirectory>/bin</outputDirectory> <includes> - <include>run-example*</include> - <include>spark-class*</include> - <include>spark-shell*</include> - <include>spark-executor*</include> + <include>**/*</include> </includes> </fileSet> </fileSets> diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd index 9e3e10ecaa..4f60bff19c 100644 --- a/bin/compute-classpath.cmd +++ b/bin/compute-classpath.cmd @@ -29,7 +29,7 @@ rem Load environment variables from conf\spark-env.cmd, if it exists if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd" rem Build up classpath -set CLASSPATH=%SPARK_CLASSPATH%;%FWDIR%conf +set CLASSPATH=%FWDIR%conf if exist "%FWDIR%RELEASE" ( for %%d in ("%FWDIR%jars\spark-assembly*.jar") do ( set ASSEMBLY_JAR=%%d diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh index 40555089fc..0c82310421 100755 --- a/bin/compute-classpath.sh +++ b/bin/compute-classpath.sh @@ -26,7 +26,7 @@ SCALA_VERSION=2.10 FWDIR="$(cd `dirname $0`/..; pwd)" # Load environment variables from conf/spark-env.sh, if it exists -if [ -e $FWDIR/conf/spark-env.sh ] ; then +if [ -e "$FWDIR/conf/spark-env.sh" ] ; then . $FWDIR/conf/spark-env.sh fi @@ -18,7 +18,7 @@ # # Figure out where the Scala framework is installed -FWDIR="$(cd `dirname $0`; pwd)" +FWDIR="$(cd `dirname $0`/..; pwd)" # Export this as SPARK_HOME export SPARK_HOME="$FWDIR" @@ -37,7 +37,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then fi # Load environment variables from conf/spark-env.sh, if it exists -if [ -e $FWDIR/conf/spark-env.sh ] ; then +if [ -e "$FWDIR/conf/spark-env.sh" ] ; then . $FWDIR/conf/spark-env.sh fi @@ -59,12 +59,7 @@ if [ -n "$IPYTHON_OPTS" ]; then fi if [[ "$IPYTHON" = "1" ]] ; then - # IPython <1.0.0 doesn't honor PYTHONSTARTUP, while 1.0.0+ does. - # Hence we clear PYTHONSTARTUP and use the -c "%run $IPYTHONSTARTUP" command which works on all versions - # We also force interactive mode with "-i" - IPYTHONSTARTUP=$PYTHONSTARTUP - PYTHONSTARTUP= - exec ipython "$IPYTHON_OPTS" -i -c "%run $IPYTHONSTARTUP" + exec ipython $IPYTHON_OPTS else exec "$PYSPARK_PYTHON" "$@" fi diff --git a/pyspark.cmd b/bin/pyspark.cmd index 7c26fbbac2..7c26fbbac2 100644 --- a/pyspark.cmd +++ b/bin/pyspark.cmd diff --git a/pyspark2.cmd b/bin/pyspark2.cmd index 21f9a34388..95791095ec 100644 --- a/pyspark2.cmd +++ b/bin/pyspark2.cmd @@ -20,7 +20,7 @@ rem set SCALA_VERSION=2.10 rem Figure out where the Spark framework is installed -set FWDIR=%~dp0 +set FWDIR=%~dp0..\ rem Export this as SPARK_HOME set SPARK_HOME=%FWDIR% diff --git a/run-example b/bin/run-example index a78192d31d..2e9d51440b 100755 --- a/run-example +++ b/bin/run-example @@ -25,13 +25,13 @@ esac SCALA_VERSION=2.10 # Figure out where the Scala framework is installed -FWDIR="$(cd `dirname $0`; pwd)" +FWDIR="$(cd `dirname $0`/..; pwd)" # Export this as SPARK_HOME export SPARK_HOME="$FWDIR" # Load environment variables from conf/spark-env.sh, if it exists -if [ -e $FWDIR/conf/spark-env.sh ] ; then +if [ -e "$FWDIR/conf/spark-env.sh" ] ; then . $FWDIR/conf/spark-env.sh fi @@ -45,20 +45,15 @@ fi EXAMPLES_DIR="$FWDIR"/examples SPARK_EXAMPLES_JAR="" if [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then - # Use the JAR from the SBT build export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar` fi -if [ -e "$EXAMPLES_DIR"/target/spark-examples*[0-9Tg].jar ]; then - # Use the JAR from the Maven build - # TODO: this also needs to become an assembly! - export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR"/target/spark-examples*[0-9Tg].jar` -fi if [[ -z $SPARK_EXAMPLES_JAR ]]; then echo "Failed to find Spark examples assembly in $FWDIR/examples/target" >&2 echo "You need to build Spark with sbt/sbt assembly before running this program" >&2 exit 1 fi + # Since the examples JAR ideally shouldn't include spark-core (that dependency should be # "provided"), also add our standard Spark classpath, built using compute-classpath.sh. CLASSPATH=`$FWDIR/bin/compute-classpath.sh` diff --git a/run-example.cmd b/bin/run-example.cmd index 5b2d048d6e..5b2d048d6e 100644 --- a/run-example.cmd +++ b/bin/run-example.cmd diff --git a/run-example2.cmd b/bin/run-example2.cmd index d4ad98d6e7..6861334cb0 100644 --- a/run-example2.cmd +++ b/bin/run-example2.cmd @@ -20,7 +20,7 @@ rem set SCALA_VERSION=2.10 rem Figure out where the Spark framework is installed -set FWDIR=%~dp0 +set FWDIR=%~dp0..\ rem Export this as SPARK_HOME set SPARK_HOME=%FWDIR% @@ -49,7 +49,7 @@ if "x%SPARK_EXAMPLES_JAR%"=="x" ( rem Compute Spark classpath using external script set DONT_PRINT_CLASSPATH=1 -call "%FWDIR%bin\compute-classpath.cmd" +call "%FWDIR%sbin\compute-classpath.cmd" set DONT_PRINT_CLASSPATH=0 set CLASSPATH=%SPARK_EXAMPLES_JAR%;%CLASSPATH% diff --git a/spark-class b/bin/spark-class index 1858ea6247..c4225a392d 100755 --- a/spark-class +++ b/bin/spark-class @@ -25,13 +25,13 @@ esac SCALA_VERSION=2.10 # Figure out where the Scala framework is installed -FWDIR="$(cd `dirname $0`; pwd)" +FWDIR="$(cd `dirname $0`/..; pwd)" # Export this as SPARK_HOME export SPARK_HOME="$FWDIR" # Load environment variables from conf/spark-env.sh, if it exists -if [ -e $FWDIR/conf/spark-env.sh ] ; then +if [ -e "$FWDIR/conf/spark-env.sh" ] ; then . $FWDIR/conf/spark-env.sh fi @@ -92,7 +92,7 @@ JAVA_OPTS="$OUR_JAVA_OPTS" JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH" JAVA_OPTS="$JAVA_OPTS -Xms$SPARK_MEM -Xmx$SPARK_MEM" # Load extra JAVA_OPTS from conf/java-opts, if it exists -if [ -e $FWDIR/conf/java-opts ] ; then +if [ -e "$FWDIR/conf/java-opts" ] ; then JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`" fi export JAVA_OPTS diff --git a/spark-class.cmd b/bin/spark-class.cmd index 19850db9e1..19850db9e1 100644 --- a/spark-class.cmd +++ b/bin/spark-class.cmd diff --git a/spark-class2.cmd b/bin/spark-class2.cmd index dc9dadf356..460e661476 100644 --- a/spark-class2.cmd +++ b/bin/spark-class2.cmd @@ -20,7 +20,7 @@ rem set SCALA_VERSION=2.10 rem Figure out where the Spark framework is installed -set FWDIR=%~dp0 +set FWDIR=%~dp0..\ rem Export this as SPARK_HOME set SPARK_HOME=%FWDIR% @@ -73,7 +73,7 @@ for %%d in ("%TOOLS_DIR%\target\scala-%SCALA_VERSION%\spark-tools*assembly*.jar" rem Compute classpath using external script set DONT_PRINT_CLASSPATH=1 -call "%FWDIR%bin\compute-classpath.cmd" +call "%FWDIR%sbin\compute-classpath.cmd" set DONT_PRINT_CLASSPATH=0 set CLASSPATH=%CLASSPATH%;%SPARK_TOOLS_JAR% diff --git a/spark-shell b/bin/spark-shell index d20af0fb39..e6885b51ef 100755 --- a/spark-shell +++ b/bin/spark-shell @@ -32,7 +32,7 @@ esac # Enter posix mode for bash set -o posix -FWDIR="`dirname $0`" +FWDIR="$(cd `dirname $0`/..; pwd)" for o in "$@"; do if [ "$1" = "-c" -o "$1" = "--cores" ]; then @@ -90,10 +90,10 @@ if $cygwin; then # "Backspace sends ^H" setting in "Keys" section of the Mintty options # (see https://github.com/sbt/sbt/issues/562). stty -icanon min 1 -echo > /dev/null 2>&1 - $FWDIR/spark-class -Djline.terminal=unix $OPTIONS org.apache.spark.repl.Main "$@" + $FWDIR/bin/spark-class -Djline.terminal=unix $OPTIONS org.apache.spark.repl.Main "$@" stty icanon echo > /dev/null 2>&1 else - $FWDIR/spark-class $OPTIONS org.apache.spark.repl.Main "$@" + $FWDIR/bin/spark-class $OPTIONS org.apache.spark.repl.Main "$@" fi # record the exit status lest it be overwritten: diff --git a/spark-shell.cmd b/bin/spark-shell.cmd index 3e52bf835e..23973e3e3d 100644 --- a/spark-shell.cmd +++ b/bin/spark-shell.cmd @@ -17,6 +17,7 @@ rem See the License for the specific language governing permissions and rem limitations under the License. rem -set FWDIR=%~dp0 +rem Find the path of sbin +set SBIN=%~dp0..\sbin\ -cmd /V /E /C %FWDIR%spark-class2.cmd org.apache.spark.repl.Main %* +cmd /V /E /C %SBIN%spark-class2.cmd org.apache.spark.repl.Main %* diff --git a/conf/log4j.properties.template b/conf/log4j.properties.template index d72dbadc39..17d1978dde 100644 --- a/conf/log4j.properties.template +++ b/conf/log4j.properties.template @@ -1,6 +1,7 @@ # Set everything to be logged to the console log4j.rootCategory=INFO, console log4j.appender.console=org.apache.log4j.ConsoleAppender +log4j.appender.console.target=System.err log4j.appender.console.layout=org.apache.log4j.PatternLayout log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n diff --git a/conf/spark-env.sh.template b/conf/spark-env.sh.template index 0a35ee7c79..e2071e2ade 100755 --- a/conf/spark-env.sh.template +++ b/conf/spark-env.sh.template @@ -18,4 +18,4 @@ # - SPARK_WORKER_MEMORY, to set how much memory to use (e.g. 1000m, 2g) # - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT # - SPARK_WORKER_INSTANCES, to set the number of worker processes per node - +# - SPARK_WORKER_DIR, to set the working directory of worker processes diff --git a/core/pom.xml b/core/pom.xml index aac0a9d11e..9e5a450d57 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -99,6 +99,11 @@ <artifactId>akka-slf4j_${scala.binary.version}</artifactId> </dependency> <dependency> + <groupId>${akka.group}</groupId> + <artifactId>akka-testkit_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> </dependency> @@ -166,6 +171,11 @@ <scope>test</scope> </dependency> <dependency> + <groupId>org.mockito</groupId> + <artifactId>mockito-all</artifactId> + <scope>test</scope> + </dependency> + <dependency> <groupId>org.scalacheck</groupId> <artifactId>scalacheck_${scala.binary.version}</artifactId> <scope>test</scope> diff --git a/core/src/main/java/org/apache/spark/network/netty/FileClient.java b/core/src/main/java/org/apache/spark/network/netty/FileClient.java index 46d61503bc..d2d778b756 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileClient.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileClient.java @@ -31,7 +31,8 @@ import java.util.concurrent.TimeUnit; class FileClient { - private Logger LOG = LoggerFactory.getLogger(this.getClass().getName()); + private static final Logger LOG = LoggerFactory.getLogger(FileClient.class.getName()); + private final FileClientHandler handler; private Channel channel = null; private Bootstrap bootstrap = null; @@ -39,7 +40,7 @@ class FileClient { private final int connectTimeout; private final int sendTimeout = 60; // 1 min - public FileClient(FileClientHandler handler, int connectTimeout) { + FileClient(FileClientHandler handler, int connectTimeout) { this.handler = handler; this.connectTimeout = connectTimeout; } diff --git a/core/src/main/java/org/apache/spark/network/netty/FileClientChannelInitializer.java b/core/src/main/java/org/apache/spark/network/netty/FileClientChannelInitializer.java index fb61be1c12..264cf97d02 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileClientChannelInitializer.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileClientChannelInitializer.java @@ -25,7 +25,7 @@ class FileClientChannelInitializer extends ChannelInitializer<SocketChannel> { private final FileClientHandler fhandler; - public FileClientChannelInitializer(FileClientHandler handler) { + FileClientChannelInitializer(FileClientHandler handler) { fhandler = handler; } diff --git a/core/src/main/java/org/apache/spark/network/netty/FileServer.java b/core/src/main/java/org/apache/spark/network/netty/FileServer.java index aea7534459..c93425e278 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileServer.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileServer.java @@ -33,15 +33,14 @@ import org.slf4j.LoggerFactory; */ class FileServer { - private Logger LOG = LoggerFactory.getLogger(this.getClass().getName()); + private static final Logger LOG = LoggerFactory.getLogger(FileServer.class.getName()); private EventLoopGroup bossGroup = null; private EventLoopGroup workerGroup = null; private ChannelFuture channelFuture = null; private int port = 0; - private Thread blockingThread = null; - public FileServer(PathResolver pResolver, int port) { + FileServer(PathResolver pResolver, int port) { InetSocketAddress addr = new InetSocketAddress(port); // Configure the server. @@ -70,7 +69,8 @@ class FileServer { * Start the file server asynchronously in a new thread. */ public void start() { - blockingThread = new Thread() { + Thread blockingThread = new Thread() { + @Override public void run() { try { channelFuture.channel().closeFuture().sync(); diff --git a/core/src/main/java/org/apache/spark/network/netty/FileServerChannelInitializer.java b/core/src/main/java/org/apache/spark/network/netty/FileServerChannelInitializer.java index 3f15ff898f..46efec8f8d 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileServerChannelInitializer.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileServerChannelInitializer.java @@ -25,9 +25,9 @@ import io.netty.handler.codec.string.StringDecoder; class FileServerChannelInitializer extends ChannelInitializer<SocketChannel> { - PathResolver pResolver; + private final PathResolver pResolver; - public FileServerChannelInitializer(PathResolver pResolver) { + FileServerChannelInitializer(PathResolver pResolver) { this.pResolver = pResolver; } diff --git a/core/src/main/java/org/apache/spark/network/netty/FileServerHandler.java b/core/src/main/java/org/apache/spark/network/netty/FileServerHandler.java index e2d9391b4c..3ac045f944 100644 --- a/core/src/main/java/org/apache/spark/network/netty/FileServerHandler.java +++ b/core/src/main/java/org/apache/spark/network/netty/FileServerHandler.java @@ -31,11 +31,11 @@ import org.slf4j.LoggerFactory; class FileServerHandler extends SimpleChannelInboundHandler<String> { - private Logger LOG = LoggerFactory.getLogger(this.getClass().getName()); + private static final Logger LOG = LoggerFactory.getLogger(FileServerHandler.class.getName()); private final PathResolver pResolver; - public FileServerHandler(PathResolver pResolver){ + FileServerHandler(PathResolver pResolver){ this.pResolver = pResolver; } @@ -61,7 +61,7 @@ class FileServerHandler extends SimpleChannelInboundHandler<String> { ctx.flush(); return; } - int len = new Long(length).intValue(); + int len = (int) length; ctx.write((new FileHeader(len, blockId)).buffer()); try { ctx.write(new DefaultFileRegion(new FileInputStream(file) diff --git a/core/src/main/java/org/apache/spark/network/netty/PathResolver.java b/core/src/main/java/org/apache/spark/network/netty/PathResolver.java index 9f7ced44cf..7ad8d03efb 100755 --- a/core/src/main/java/org/apache/spark/network/netty/PathResolver.java +++ b/core/src/main/java/org/apache/spark/network/netty/PathResolver.java @@ -1,26 +1,26 @@ -/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements. See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-package org.apache.spark.network.netty;
-
-import org.apache.spark.storage.BlockId;
-import org.apache.spark.storage.FileSegment;
-
-public interface PathResolver {
- /** Get the file segment in which the given block resides. */
- public FileSegment getBlockLocation(BlockId blockId);
-}
+/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.network.netty; + +import org.apache.spark.storage.BlockId; +import org.apache.spark.storage.FileSegment; + +public interface PathResolver { + /** Get the file segment in which the given block resides. */ + FileSegment getBlockLocation(BlockId blockId); +} diff --git a/core/src/main/resources/org/apache/spark/default-log4j.properties b/core/src/main/resources/org/apache/spark/log4j-defaults.properties index d72dbadc39..17d1978dde 100644 --- a/core/src/main/resources/org/apache/spark/default-log4j.properties +++ b/core/src/main/resources/org/apache/spark/log4j-defaults.properties @@ -1,6 +1,7 @@ # Set everything to be logged to the console log4j.rootCategory=INFO, console log4j.appender.console=org.apache.log4j.ConsoleAppender +log4j.appender.console.target=System.err log4j.appender.console.layout=org.apache.log4j.PatternLayout log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n diff --git a/core/src/main/scala/org/apache/spark/Logging.scala b/core/src/main/scala/org/apache/spark/Logging.scala index d519fc5a29..4a34989e50 100644 --- a/core/src/main/scala/org/apache/spark/Logging.scala +++ b/core/src/main/scala/org/apache/spark/Logging.scala @@ -104,13 +104,15 @@ trait Logging { // If Log4j doesn't seem initialized, load a default properties file val log4jInitialized = LogManager.getRootLogger.getAllAppenders.hasMoreElements if (!log4jInitialized) { - val defaultLogProps = "org/apache/spark/default-log4j.properties" + val defaultLogProps = "org/apache/spark/log4j-defaults.properties" val classLoader = this.getClass.getClassLoader Option(classLoader.getResource(defaultLogProps)) match { - case Some(url) => PropertyConfigurator.configure(url) - case None => System.err.println(s"Spark was unable to load $defaultLogProps") + case Some(url) => + PropertyConfigurator.configure(url) + log.info(s"Using Spark's default log4j profile: $defaultLogProps") + case None => + System.err.println(s"Spark was unable to load $defaultLogProps") } - log.info(s"Using Spark's default log4j profile: $defaultLogProps") } Logging.initialized = true diff --git a/core/src/main/scala/org/apache/spark/MapOutputTracker.scala b/core/src/main/scala/org/apache/spark/MapOutputTracker.scala index cdae167aef..77b8ca1cce 100644 --- a/core/src/main/scala/org/apache/spark/MapOutputTracker.scala +++ b/core/src/main/scala/org/apache/spark/MapOutputTracker.scala @@ -55,7 +55,7 @@ private[spark] class MapOutputTracker(conf: SparkConf) extends Logging { private val timeout = AkkaUtils.askTimeout(conf) // Set to the MapOutputTrackerActor living on the driver - var trackerActor: Either[ActorRef, ActorSelection] = _ + var trackerActor: ActorRef = _ protected val mapStatuses = new TimeStampedHashMap[Int, Array[MapStatus]] @@ -71,17 +71,7 @@ private[spark] class MapOutputTracker(conf: SparkConf) extends Logging { // throw a SparkException if this fails. private def askTracker(message: Any): Any = { try { - /* - The difference between ActorRef and ActorSelection is well explained here: - http://doc.akka.io/docs/akka/2.2.3/project/migration-guide-2.1.x-2.2.x.html#Use_actorSelection_instead_of_actorFor - In spark a map output tracker can be either started on Driver where it is created which - is an ActorRef or it can be on executor from where it is looked up which is an - actorSelection. - */ - val future = trackerActor match { - case Left(a: ActorRef) => a.ask(message)(timeout) - case Right(b: ActorSelection) => b.ask(message)(timeout) - } + val future = trackerActor.ask(message)(timeout) Await.result(future, timeout) } catch { case e: Exception => diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala index 31b0773bfe..9b043f06dd 100644 --- a/core/src/main/scala/org/apache/spark/Partitioner.scala +++ b/core/src/main/scala/org/apache/spark/Partitioner.scala @@ -61,7 +61,8 @@ object Partitioner { } /** - * A [[org.apache.spark.Partitioner]] that implements hash-based partitioning using Java's `Object.hashCode`. + * A [[org.apache.spark.Partitioner]] that implements hash-based partitioning using + * Java's `Object.hashCode`. * * Java arrays have hashCodes that are based on the arrays' identities rather than their contents, * so attempting to partition an RDD[Array[_]] or RDD[(Array[_], _)] using a HashPartitioner will @@ -84,8 +85,8 @@ class HashPartitioner(partitions: Int) extends Partitioner { } /** - * A [[org.apache.spark.Partitioner]] that partitions sortable records by range into roughly equal ranges. - * Determines the ranges by sampling the RDD passed in. + * A [[org.apache.spark.Partitioner]] that partitions sortable records by range into roughly + * equal ranges. The ranges are determined by sampling the content of the RDD passed in. */ class RangePartitioner[K <% Ordered[K]: ClassTag, V]( partitions: Int, diff --git a/core/src/main/scala/org/apache/spark/SparkConf.scala b/core/src/main/scala/org/apache/spark/SparkConf.scala index 98343e9532..2de32231e8 100644 --- a/core/src/main/scala/org/apache/spark/SparkConf.scala +++ b/core/src/main/scala/org/apache/spark/SparkConf.scala @@ -24,7 +24,7 @@ import com.typesafe.config.ConfigFactory * * @param loadDefaults whether to load values from the system properties and classpath */ -class SparkConf(loadDefaults: Boolean) extends Serializable with Cloneable { +class SparkConf(loadDefaults: Boolean) extends Serializable with Cloneable with Logging { /** Create a SparkConf that loads defaults from system properties and the classpath */ def this() = this(true) @@ -67,7 +67,8 @@ class SparkConf(loadDefaults: Boolean) extends Serializable with Cloneable { /** Set JAR files to distribute to the cluster. */ def setJars(jars: Seq[String]): SparkConf = { - set("spark.jars", jars.mkString(",")) + for (jar <- jars if (jar == null)) logWarning("null jar passed to SparkContext constructor") + set("spark.jars", jars.filter(_ != null).mkString(",")) } /** Set JAR files to distribute to the cluster. (Java-friendly version.) */ @@ -164,6 +165,11 @@ class SparkConf(loadDefaults: Boolean) extends Serializable with Cloneable { getOption(key).map(_.toDouble).getOrElse(defaultValue) } + /** Get a parameter as a boolean, falling back to a default if not set */ + def getBoolean(key: String, defaultValue: Boolean): Boolean = { + getOption(key).map(_.toBoolean).getOrElse(defaultValue) + } + /** Get all executor environment variables set on this SparkConf */ def getExecutorEnv: Seq[(String, String)] = { val prefix = "spark.executorEnv." @@ -171,6 +177,9 @@ class SparkConf(loadDefaults: Boolean) extends Serializable with Cloneable { .map{case (k, v) => (k.substring(prefix.length), v)} } + /** Get all akka conf variables set on this SparkConf */ + def getAkkaConf: Seq[(String, String)] = getAll.filter {case (k, v) => k.startsWith("akka.")} + /** Does the configuration contain a given parameter? */ def contains(key: String): Boolean = settings.contains(key) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 84bd0f7ffd..66c226e491 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -31,9 +31,9 @@ import scala.reflect.{ClassTag, classTag} import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.Path import org.apache.hadoop.io.{ArrayWritable, BooleanWritable, BytesWritable, DoubleWritable, -FloatWritable, IntWritable, LongWritable, NullWritable, Text, Writable} + FloatWritable, IntWritable, LongWritable, NullWritable, Text, Writable} import org.apache.hadoop.mapred.{FileInputFormat, InputFormat, JobConf, SequenceFileInputFormat, -TextInputFormat} + TextInputFormat} import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat, Job => NewHadoopJob} import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat => NewFileInputFormat} import org.apache.mesos.MesosNativeLibrary @@ -49,7 +49,7 @@ import org.apache.spark.scheduler.local.LocalBackend import org.apache.spark.storage.{BlockManagerSource, RDDInfo, StorageStatus, StorageUtils} import org.apache.spark.ui.SparkUI import org.apache.spark.util.{Utils, TimeStampedHashMap, MetadataCleaner, MetadataCleanerType, -ClosureCleaner} + ClosureCleaner} /** * Main entry point for Spark functionality. A SparkContext represents the connection to a Spark @@ -116,6 +116,10 @@ class SparkContext( throw new SparkException("An application must be set in your configuration") } + if (conf.getBoolean("spark.logConf", false)) { + logInfo("Spark configuration:\n" + conf.toDebugString) + } + // Set Spark driver host and port system properties conf.setIfMissing("spark.driver.host", Utils.localHostName()) conf.setIfMissing("spark.driver.port", "0") @@ -169,10 +173,16 @@ class SparkContext( // Environment variables to pass to our executors private[spark] val executorEnvs = HashMap[String, String]() // Note: SPARK_MEM is included for Mesos, but overwritten for standalone mode in ExecutorRunner - for (key <- Seq("SPARK_CLASSPATH", "SPARK_LIBRARY_PATH", "SPARK_JAVA_OPTS", "SPARK_TESTING"); + for (key <- Seq("SPARK_CLASSPATH", "SPARK_LIBRARY_PATH", "SPARK_JAVA_OPTS"); value <- Option(System.getenv(key))) { executorEnvs(key) = value } + // Convert java options to env vars as a work around + // since we can't set env vars directly in sbt. + for { (envKey, propKey) <- Seq(("SPARK_HOME", "spark.home"), ("SPARK_TESTING", "spark.testing")) + value <- Option(System.getenv(envKey)).orElse(Option(System.getProperty(propKey)))} { + executorEnvs(envKey) = value + } // Since memory can be set with a system property too, use that executorEnvs("SPARK_MEM") = executorMemory + "m" executorEnvs ++= conf.getExecutorEnv @@ -234,6 +244,10 @@ class SparkContext( localProperties.set(new Properties()) } + /** + * Set a local property that affects jobs submitted from this thread, such as the + * Spark fair scheduler pool. + */ def setLocalProperty(key: String, value: String) { if (localProperties.get() == null) { localProperties.set(new Properties()) @@ -245,6 +259,10 @@ class SparkContext( } } + /** + * Get a local property set in this thread, or null if it is missing. See + * [[org.apache.spark.SparkContext.setLocalProperty]]. + */ def getLocalProperty(key: String): String = Option(localProperties.get).map(_.getProperty(key)).getOrElse(null) @@ -255,7 +273,7 @@ class SparkContext( } /** - * Assigns a group id to all the jobs started by this thread until the group id is set to a + * Assigns a group ID to all the jobs started by this thread until the group ID is set to a * different value or cleared. * * Often, a unit of execution in an application consists of multiple Spark actions or jobs. @@ -278,7 +296,7 @@ class SparkContext( setLocalProperty(SparkContext.SPARK_JOB_GROUP_ID, groupId) } - /** Clear the job group id and its description. */ + /** Clear the current thread's job group ID and its description. */ def clearJobGroup() { setLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION, null) setLocalProperty(SparkContext.SPARK_JOB_GROUP_ID, null) @@ -507,15 +525,15 @@ class SparkContext( // Methods for creating shared variables /** - * Create an [[org.apache.spark.Accumulator]] variable of a given type, which tasks can "add" values - * to using the `+=` method. Only the driver can access the accumulator's `value`. + * Create an [[org.apache.spark.Accumulator]] variable of a given type, which tasks can "add" + * values to using the `+=` method. Only the driver can access the accumulator's `value`. */ def accumulator[T](initialValue: T)(implicit param: AccumulatorParam[T]) = new Accumulator(initialValue, param) /** - * Create an [[org.apache.spark.Accumulable]] shared variable, to which tasks can add values with `+=`. - * Only the driver can access the accumuable's `value`. + * Create an [[org.apache.spark.Accumulable]] shared variable, to which tasks can add values + * with `+=`. Only the driver can access the accumuable's `value`. * @tparam T accumulator type * @tparam R type that can be added to the accumulator */ @@ -528,14 +546,16 @@ class SparkContext( * Growable and TraversableOnce are the standard APIs that guarantee += and ++=, implemented by * standard mutable collections. So you can use this with mutable Map, Set, etc. */ - def accumulableCollection[R <% Growable[T] with TraversableOnce[T] with Serializable, T](initialValue: R) = { + def accumulableCollection[R <% Growable[T] with TraversableOnce[T] with Serializable, T] + (initialValue: R) = { val param = new GrowableAccumulableParam[R,T] new Accumulable(initialValue, param) } /** - * Broadcast a read-only variable to the cluster, returning a [[org.apache.spark.broadcast.Broadcast]] object for - * reading it in distributed functions. The variable will be sent to each cluster only once. + * Broadcast a read-only variable to the cluster, returning a + * [[org.apache.spark.broadcast.Broadcast]] object for reading it in distributed functions. + * The variable will be sent to each cluster only once. */ def broadcast[T](value: T) = env.broadcastManager.newBroadcast[T](value, isLocal) @@ -729,6 +749,26 @@ class SparkContext( } /** + * Support function for API backtraces. + */ + def setCallSite(site: String) { + setLocalProperty("externalCallSite", site) + } + + /** + * Support function for API backtraces. + */ + def clearCallSite() { + setLocalProperty("externalCallSite", null) + } + + private[spark] def getCallSite(): String = { + val callSite = getLocalProperty("externalCallSite") + if (callSite == null) return Utils.formatSparkCallSite + callSite + } + + /** * Run a function on a given set of partitions in an RDD and pass the results to the given * handler function. This is the main entry point for all actions in Spark. The allowLocal * flag specifies whether the scheduler can run the computation on the driver rather than @@ -740,7 +780,7 @@ class SparkContext( partitions: Seq[Int], allowLocal: Boolean, resultHandler: (Int, U) => Unit) { - val callSite = Utils.formatSparkCallSite + val callSite = getCallSite val cleanedFunc = clean(func) logInfo("Starting job: " + callSite) val start = System.nanoTime @@ -824,7 +864,7 @@ class SparkContext( func: (TaskContext, Iterator[T]) => U, evaluator: ApproximateEvaluator[U, R], timeout: Long): PartialResult[R] = { - val callSite = Utils.formatSparkCallSite + val callSite = getCallSite logInfo("Starting job: " + callSite) val start = System.nanoTime val result = dagScheduler.runApproximateJob(rdd, func, evaluator, callSite, timeout, @@ -844,7 +884,7 @@ class SparkContext( resultFunc: => R): SimpleFutureAction[R] = { val cleanF = clean(processPartition) - val callSite = Utils.formatSparkCallSite + val callSite = getCallSite val waiter = dagScheduler.submitJob( rdd, (context: TaskContext, iter: Iterator[T]) => cleanF(iter), @@ -980,7 +1020,8 @@ object SparkContext { implicit def stringToText(s: String) = new Text(s) - private implicit def arrayToArrayWritable[T <% Writable: ClassTag](arr: Traversable[T]): ArrayWritable = { + private implicit def arrayToArrayWritable[T <% Writable: ClassTag](arr: Traversable[T]) + : ArrayWritable = { def anyToWritable[U <% Writable](u: U): Writable = u new ArrayWritable(classTag[T].runtimeClass.asInstanceOf[Class[Writable]], @@ -1003,7 +1044,9 @@ object SparkContext { implicit def booleanWritableConverter() = simpleWritableConverter[Boolean, BooleanWritable](_.get) - implicit def bytesWritableConverter() = simpleWritableConverter[Array[Byte], BytesWritable](_.getBytes) + implicit def bytesWritableConverter() = { + simpleWritableConverter[Array[Byte], BytesWritable](_.getBytes) + } implicit def stringWritableConverter() = simpleWritableConverter[String, Text](_.toString) @@ -1019,7 +1062,8 @@ object SparkContext { if (uri != null) { val uriStr = uri.toString if (uriStr.startsWith("jar:file:")) { - // URI will be of the form "jar:file:/path/foo.jar!/package/cls.class", so pull out the /path/foo.jar + // URI will be of the form "jar:file:/path/foo.jar!/package/cls.class", + // so pull out the /path/foo.jar List(uriStr.substring("jar:file:".length, uriStr.indexOf('!'))) } else { Nil @@ -1173,7 +1217,7 @@ object SparkContext { case mesosUrl @ MESOS_REGEX(_) => MesosNativeLibrary.load() val scheduler = new TaskSchedulerImpl(sc) - val coarseGrained = sc.conf.get("spark.mesos.coarse", "false").toBoolean + val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", false) val url = mesosUrl.stripPrefix("mesos://") // strip scheme from raw Mesos URLs val backend = if (coarseGrained) { new CoarseMesosSchedulerBackend(scheduler, sc, url, appName) diff --git a/core/src/main/scala/org/apache/spark/SparkEnv.scala b/core/src/main/scala/org/apache/spark/SparkEnv.scala index 634a94f0a7..e093e2f162 100644 --- a/core/src/main/scala/org/apache/spark/SparkEnv.scala +++ b/core/src/main/scala/org/apache/spark/SparkEnv.scala @@ -17,11 +17,10 @@ package org.apache.spark -import collection.mutable -import serializer.Serializer +import scala.collection.mutable +import scala.concurrent.Await import akka.actor._ -import akka.remote.RemoteActorRefProvider import org.apache.spark.broadcast.BroadcastManager import org.apache.spark.metrics.MetricsSystem @@ -157,17 +156,18 @@ object SparkEnv extends Logging { conf.get("spark.closure.serializer", "org.apache.spark.serializer.JavaSerializer"), conf) - def registerOrLookup(name: String, newActor: => Actor): Either[ActorRef, ActorSelection] = { + def registerOrLookup(name: String, newActor: => Actor): ActorRef = { if (isDriver) { logInfo("Registering " + name) - Left(actorSystem.actorOf(Props(newActor), name = name)) + actorSystem.actorOf(Props(newActor), name = name) } else { val driverHost: String = conf.get("spark.driver.host", "localhost") - val driverPort: Int = conf.get("spark.driver.port", "7077").toInt + val driverPort: Int = conf.getInt("spark.driver.port", 7077) Utils.checkHost(driverHost, "Expected hostname") - val url = "akka.tcp://spark@%s:%s/user/%s".format(driverHost, driverPort, name) - logInfo("Connecting to " + name + ": " + url) - Right(actorSystem.actorSelection(url)) + val url = s"akka.tcp://spark@$driverHost:$driverPort/user/$name" + val timeout = AkkaUtils.lookupTimeout(conf) + logInfo(s"Connecting to $name: $url") + Await.result(actorSystem.actorSelection(url).resolveOne(timeout), timeout) } } diff --git a/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala b/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala index 103a1c2051..618d95015f 100644 --- a/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala +++ b/core/src/main/scala/org/apache/spark/SparkHadoopWriter.scala @@ -127,10 +127,6 @@ class SparkHadoopWriter(@transient jobConf: JobConf) cmtr.commitJob(getJobContext()) } - def cleanup() { - getOutputCommitter().cleanupJob(getJobContext()) - } - // ********* Private Functions ********* private def getOutputFormat(): OutputFormat[AnyRef,AnyRef] = { diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala index da30cf619a..b0dedc6f4e 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala @@ -207,13 +207,13 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, Jav * e.g. for the array * [1,10,20,50] the buckets are [1,10) [10,20) [20,50] * e.g 1<=x<10 , 10<=x<20, 20<=x<50 - * And on the input of 1 and 50 we would have a histogram of 1,0,0 - * + * And on the input of 1 and 50 we would have a histogram of 1,0,0 + * * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets * to true. * buckets must be sorted and not contain any duplicates. - * buckets array must be at least two elements + * buckets array must be at least two elements * All NaN entries are treated the same. If you have a NaN bucket it must be * the maximum value of the last position and all NaN entries will be counted * in that bucket. @@ -225,6 +225,12 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, Jav def histogram(buckets: Array[Double], evenBuckets: Boolean): Array[Long] = { srdd.histogram(buckets.map(_.toDouble), evenBuckets) } + + /** Assign a name to this RDD */ + def setName(name: String): JavaDoubleRDD = { + srdd.setName(name) + this + } } object JavaDoubleRDD { diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala index 55c87450ac..0fb7e195b3 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala @@ -647,6 +647,12 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)])(implicit val kClassTag: ClassTag[K def countApproxDistinctByKey(relativeSD: Double, numPartitions: Int): JavaRDD[(K, Long)] = { rdd.countApproxDistinctByKey(relativeSD, numPartitions) } + + /** Assign a name to this RDD */ + def setName(name: String): JavaPairRDD[K, V] = { + rdd.setName(name) + this + } } object JavaPairRDD { diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala index 037cd1c774..7d48ce01cf 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala @@ -127,6 +127,12 @@ JavaRDDLike[T, JavaRDD[T]] { wrapRDD(rdd.subtract(other, p)) override def toString = rdd.toString + + /** Assign a name to this RDD */ + def setName(name: String): JavaRDD[T] = { + rdd.setName(name) + this + } } object JavaRDD { diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala b/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala index 924d8af060..ebbbbd8806 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaRDDLike.scala @@ -245,6 +245,11 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable { } /** + * Return an array that contains all of the elements in this RDD. + */ + def toArray(): JList[T] = collect() + + /** * Return an array that contains all of the elements in a specific partition of this RDD. */ def collectPartitions(partitionIds: Array[Int]): Array[JList[T]] = { @@ -455,4 +460,5 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable { */ def countApproxDistinct(relativeSD: Double = 0.05): Long = rdd.countApproxDistinct(relativeSD) + def name(): String = rdd.name } diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala index 0680a065a3..7a6f044965 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala @@ -411,10 +411,82 @@ class JavaSparkContext(val sc: SparkContext) extends JavaSparkContextVarargsWork * changed at runtime. */ def getConf: SparkConf = sc.getConf + + /** + * Pass-through to SparkContext.setCallSite. For API support only. + */ + def setCallSite(site: String) { + sc.setCallSite(site) + } + + /** + * Pass-through to SparkContext.setCallSite. For API support only. + */ + def clearCallSite() { + sc.clearCallSite() + } + + /** + * Set a local property that affects jobs submitted from this thread, such as the + * Spark fair scheduler pool. + */ + def setLocalProperty(key: String, value: String): Unit = sc.setLocalProperty(key, value) + + /** + * Get a local property set in this thread, or null if it is missing. See + * [[org.apache.spark.api.java.JavaSparkContext.setLocalProperty]]. + */ + def getLocalProperty(key: String): String = sc.getLocalProperty(key) + + /** + * Assigns a group ID to all the jobs started by this thread until the group ID is set to a + * different value or cleared. + * + * Often, a unit of execution in an application consists of multiple Spark actions or jobs. + * Application programmers can use this method to group all those jobs together and give a + * group description. Once set, the Spark web UI will associate such jobs with this group. + * + * The application can also use [[org.apache.spark.api.java.JavaSparkContext.cancelJobGroup]] + * to cancel all running jobs in this group. For example, + * {{{ + * // In the main thread: + * sc.setJobGroup("some_job_to_cancel", "some job description"); + * rdd.map(...).count(); + * + * // In a separate thread: + * sc.cancelJobGroup("some_job_to_cancel"); + * }}} + */ + def setJobGroup(groupId: String, description: String): Unit = sc.setJobGroup(groupId, description) + + /** Clear the current thread's job group ID and its description. */ + def clearJobGroup(): Unit = sc.clearJobGroup() + + /** + * Cancel active jobs for the specified group. See + * [[org.apache.spark.api.java.JavaSparkContext.setJobGroup]] for more information. + */ + def cancelJobGroup(groupId: String): Unit = sc.cancelJobGroup(groupId) + + /** Cancel all jobs that have been scheduled or are running. */ + def cancelAllJobs(): Unit = sc.cancelAllJobs() } object JavaSparkContext { implicit def fromSparkContext(sc: SparkContext): JavaSparkContext = new JavaSparkContext(sc) implicit def toSparkContext(jsc: JavaSparkContext): SparkContext = jsc.sc + + /** + * Find the JAR from which a given class was loaded, to make it easy for users to pass + * their JARs to SparkContext. + */ + def jarOfClass(cls: Class[_]): Array[String] = SparkContext.jarOfClass(cls).toArray + + /** + * Find the JAR that contains the class of a particular object, to make it easy for users + * to pass their JARs to SparkContext. In most cases you can call jarOfObject(this) in + * your driver program. + */ + def jarOfObject(obj: AnyRef): Array[String] = SparkContext.jarOfObject(obj).toArray } diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala index 32cc70e8c9..40c519b5bd 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala @@ -41,7 +41,7 @@ private[spark] class PythonRDD[T: ClassTag]( accumulator: Accumulator[JList[Array[Byte]]]) extends RDD[Array[Byte]](parent) { - val bufferSize = conf.get("spark.buffer.size", "65536").toInt + val bufferSize = conf.getInt("spark.buffer.size", 65536) override def getPartitions = parent.partitions @@ -250,7 +250,7 @@ private class PythonAccumulatorParam(@transient serverHost: String, serverPort: Utils.checkHost(serverHost, "Expected hostname") - val bufferSize = SparkEnv.get.conf.get("spark.buffer.size", "65536").toInt + val bufferSize = SparkEnv.get.conf.getInt("spark.buffer.size", 65536) override def zero(value: JList[Array[Byte]]): JList[Array[Byte]] = new JArrayList diff --git a/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala b/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala index db596d5fcc..0eacda3d7d 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala @@ -92,8 +92,8 @@ private object HttpBroadcast extends Logging { def initialize(isDriver: Boolean, conf: SparkConf) { synchronized { if (!initialized) { - bufferSize = conf.get("spark.buffer.size", "65536").toInt - compress = conf.get("spark.broadcast.compress", "true").toBoolean + bufferSize = conf.getInt("spark.buffer.size", 65536) + compress = conf.getBoolean("spark.broadcast.compress", true) if (isDriver) { createServer(conf) conf.set("spark.httpBroadcast.uri", serverUri) diff --git a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala index 9530938278..fdf92eca4f 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala @@ -180,7 +180,7 @@ extends Logging { initialized = false } - lazy val BLOCK_SIZE = conf.get("spark.broadcast.blockSize", "4096").toInt * 1024 + lazy val BLOCK_SIZE = conf.getInt("spark.broadcast.blockSize", 4096) * 1024 def blockifyObject[T](obj: T): TorrentInfo = { val byteArray = Utils.serialize[T](obj) diff --git a/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala b/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala index 19d393a0db..e38459b883 100644 --- a/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala +++ b/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala @@ -19,7 +19,7 @@ package org.apache.spark.deploy private[spark] class ApplicationDescription( val name: String, - val maxCores: Int, /* Integer.MAX_VALUE denotes an unlimited number of cores */ + val maxCores: Option[Int], val memoryPerSlave: Int, val command: Command, val sparkHome: String, diff --git a/core/src/main/scala/org/apache/spark/deploy/Client.scala b/core/src/main/scala/org/apache/spark/deploy/Client.scala new file mode 100644 index 0000000000..e133893f6c --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/Client.scala @@ -0,0 +1,151 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy + +import scala.collection.JavaConversions._ +import scala.collection.mutable.Map +import scala.concurrent._ + +import akka.actor._ +import akka.pattern.ask +import org.apache.log4j.{Level, Logger} + +import org.apache.spark.{Logging, SparkConf} +import org.apache.spark.deploy.DeployMessages._ +import org.apache.spark.deploy.master.{DriverState, Master} +import org.apache.spark.util.{AkkaUtils, Utils} +import akka.actor.Actor.emptyBehavior +import akka.remote.{AssociationErrorEvent, DisassociatedEvent, RemotingLifecycleEvent} + +/** + * Proxy that relays messages to the driver. + */ +class ClientActor(driverArgs: ClientArguments, conf: SparkConf) extends Actor with Logging { + var masterActor: ActorSelection = _ + val timeout = AkkaUtils.askTimeout(conf) + + override def preStart() = { + masterActor = context.actorSelection(Master.toAkkaUrl(driverArgs.master)) + + context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent]) + + println(s"Sending ${driverArgs.cmd} command to ${driverArgs.master}") + + driverArgs.cmd match { + case "launch" => + // TODO: We could add an env variable here and intercept it in `sc.addJar` that would + // truncate filesystem paths similar to what YARN does. For now, we just require + // people call `addJar` assuming the jar is in the same directory. + val env = Map[String, String]() + System.getenv().foreach{case (k, v) => env(k) = v} + + val mainClass = "org.apache.spark.deploy.worker.DriverWrapper" + val command = new Command(mainClass, Seq("{{WORKER_URL}}", driverArgs.mainClass) ++ + driverArgs.driverOptions, env) + + val driverDescription = new DriverDescription( + driverArgs.jarUrl, + driverArgs.memory, + driverArgs.cores, + driverArgs.supervise, + command) + + masterActor ! RequestSubmitDriver(driverDescription) + + case "kill" => + val driverId = driverArgs.driverId + val killFuture = masterActor ! RequestKillDriver(driverId) + } + } + + /* Find out driver status then exit the JVM */ + def pollAndReportStatus(driverId: String) { + println(s"... waiting before polling master for driver state") + Thread.sleep(5000) + println("... polling master for driver state") + val statusFuture = (masterActor ? RequestDriverStatus(driverId))(timeout) + .mapTo[DriverStatusResponse] + val statusResponse = Await.result(statusFuture, timeout) + + statusResponse.found match { + case false => + println(s"ERROR: Cluster master did not recognize $driverId") + System.exit(-1) + case true => + println(s"State of $driverId is ${statusResponse.state.get}") + // Worker node, if present + (statusResponse.workerId, statusResponse.workerHostPort, statusResponse.state) match { + case (Some(id), Some(hostPort), Some(DriverState.RUNNING)) => + println(s"Driver running on $hostPort ($id)") + case _ => + } + // Exception, if present + statusResponse.exception.map { e => + println(s"Exception from cluster was: $e") + System.exit(-1) + } + System.exit(0) + } + } + + override def receive = { + + case SubmitDriverResponse(success, driverId, message) => + println(message) + if (success) pollAndReportStatus(driverId.get) else System.exit(-1) + + case KillDriverResponse(driverId, success, message) => + println(message) + if (success) pollAndReportStatus(driverId) else System.exit(-1) + + case DisassociatedEvent(_, remoteAddress, _) => + println(s"Error connecting to master ${driverArgs.master} ($remoteAddress), exiting.") + System.exit(-1) + + case AssociationErrorEvent(cause, _, remoteAddress, _) => + println(s"Error connecting to master ${driverArgs.master} ($remoteAddress), exiting.") + println(s"Cause was: $cause") + System.exit(-1) + } +} + +/** + * Executable utility for starting and terminating drivers inside of a standalone cluster. + */ +object Client { + def main(args: Array[String]) { + val conf = new SparkConf() + val driverArgs = new ClientArguments(args) + + if (!driverArgs.logLevel.isGreaterOrEqual(Level.WARN)) { + conf.set("spark.akka.logLifecycleEvents", "true") + } + conf.set("spark.akka.askTimeout", "10") + conf.set("akka.loglevel", driverArgs.logLevel.toString.replace("WARN", "WARNING")) + Logger.getRootLogger.setLevel(driverArgs.logLevel) + + // TODO: See if we can initialize akka so return messages are sent back using the same TCP + // flow. Else, this (sadly) requires the DriverClient be routable from the Master. + val (actorSystem, _) = AkkaUtils.createActorSystem( + "driverClient", Utils.localHostName(), 0, false, conf) + + actorSystem.actorOf(Props(classOf[ClientActor], driverArgs, conf)) + + actorSystem.awaitTermination() + } +} diff --git a/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala b/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala new file mode 100644 index 0000000000..db67c6d1bb --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala @@ -0,0 +1,117 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy + +import java.net.URL + +import scala.collection.mutable.ListBuffer + +import org.apache.log4j.Level + +/** + * Command-line parser for the driver client. + */ +private[spark] class ClientArguments(args: Array[String]) { + val defaultCores = 1 + val defaultMemory = 512 + + var cmd: String = "" // 'launch' or 'kill' + var logLevel = Level.WARN + + // launch parameters + var master: String = "" + var jarUrl: String = "" + var mainClass: String = "" + var supervise: Boolean = false + var memory: Int = defaultMemory + var cores: Int = defaultCores + private var _driverOptions = ListBuffer[String]() + def driverOptions = _driverOptions.toSeq + + // kill parameters + var driverId: String = "" + + parse(args.toList) + + def parse(args: List[String]): Unit = args match { + case ("--cores" | "-c") :: value :: tail => + cores = value.toInt + parse(tail) + + case ("--memory" | "-m") :: value :: tail => + memory = value.toInt + parse(tail) + + case ("--supervise" | "-s") :: tail => + supervise = true + parse(tail) + + case ("--help" | "-h") :: tail => + printUsageAndExit(0) + + case ("--verbose" | "-v") :: tail => + logLevel = Level.INFO + parse(tail) + + case "launch" :: _master :: _jarUrl :: _mainClass :: tail => + cmd = "launch" + + try { + new URL(_jarUrl) + } catch { + case e: Exception => + println(s"Jar url '${_jarUrl}' is not a valid URL.") + println(s"Jar must be in URL format (e.g. hdfs://XX, file://XX)") + printUsageAndExit(-1) + } + + jarUrl = _jarUrl + master = _master + mainClass = _mainClass + _driverOptions ++= tail + + case "kill" :: _master :: _driverId :: tail => + cmd = "kill" + master = _master + driverId = _driverId + + case _ => + printUsageAndExit(1) + } + + /** + * Print usage and exit JVM with the given exit code. + */ + def printUsageAndExit(exitCode: Int) { + // TODO: It wouldn't be too hard to allow users to submit their app and dependency jars + // separately similar to in the YARN client. + val usage = + s""" + |Usage: DriverClient [options] launch <active-master> <jar-url> <main-class> [driver options] + |Usage: DriverClient kill <active-master> <driver-id> + | + |Options: + | -c CORES, --cores CORES Number of cores to request (default: $defaultCores) + | -m MEMORY, --memory MEMORY Megabytes of memory to request (default: $defaultMemory) + | -s, --supervise Whether to restart the driver on failure + | -v, --verbose Print more debugging output + """.stripMargin + System.err.println(usage) + System.exit(exitCode) + } +} diff --git a/core/src/main/scala/org/apache/spark/deploy/DeployMessage.scala b/core/src/main/scala/org/apache/spark/deploy/DeployMessage.scala index 275331724a..5e824e1a67 100644 --- a/core/src/main/scala/org/apache/spark/deploy/DeployMessage.scala +++ b/core/src/main/scala/org/apache/spark/deploy/DeployMessage.scala @@ -20,12 +20,12 @@ package org.apache.spark.deploy import scala.collection.immutable.List import org.apache.spark.deploy.ExecutorState.ExecutorState -import org.apache.spark.deploy.master.{WorkerInfo, ApplicationInfo} +import org.apache.spark.deploy.master.{ApplicationInfo, DriverInfo, WorkerInfo} +import org.apache.spark.deploy.master.DriverState.DriverState import org.apache.spark.deploy.master.RecoveryState.MasterState -import org.apache.spark.deploy.worker.ExecutorRunner +import org.apache.spark.deploy.worker.{DriverRunner, ExecutorRunner} import org.apache.spark.util.Utils - private[deploy] sealed trait DeployMessage extends Serializable /** Contains messages sent between Scheduler actor nodes. */ @@ -54,7 +54,14 @@ private[deploy] object DeployMessages { exitStatus: Option[Int]) extends DeployMessage - case class WorkerSchedulerStateResponse(id: String, executors: List[ExecutorDescription]) + case class DriverStateChanged( + driverId: String, + state: DriverState, + exception: Option[Exception]) + extends DeployMessage + + case class WorkerSchedulerStateResponse(id: String, executors: List[ExecutorDescription], + driverIds: Seq[String]) case class Heartbeat(workerId: String) extends DeployMessage @@ -76,14 +83,18 @@ private[deploy] object DeployMessages { sparkHome: String) extends DeployMessage - // Client to Master + case class LaunchDriver(driverId: String, driverDesc: DriverDescription) extends DeployMessage + + case class KillDriver(driverId: String) extends DeployMessage + + // AppClient to Master case class RegisterApplication(appDescription: ApplicationDescription) extends DeployMessage case class MasterChangeAcknowledged(appId: String) - // Master to Client + // Master to AppClient case class RegisteredApplication(appId: String, masterUrl: String) extends DeployMessage @@ -97,11 +108,28 @@ private[deploy] object DeployMessages { case class ApplicationRemoved(message: String) - // Internal message in Client + // DriverClient <-> Master + + case class RequestSubmitDriver(driverDescription: DriverDescription) extends DeployMessage + + case class SubmitDriverResponse(success: Boolean, driverId: Option[String], message: String) + extends DeployMessage + + case class RequestKillDriver(driverId: String) extends DeployMessage + + case class KillDriverResponse(driverId: String, success: Boolean, message: String) + extends DeployMessage + + case class RequestDriverStatus(driverId: String) extends DeployMessage + + case class DriverStatusResponse(found: Boolean, state: Option[DriverState], + workerId: Option[String], workerHostPort: Option[String], exception: Option[Exception]) + + // Internal message in AppClient - case object StopClient + case object StopAppClient - // Master to Worker & Client + // Master to Worker & AppClient case class MasterChanged(masterUrl: String, masterWebUiUrl: String) @@ -113,6 +141,7 @@ private[deploy] object DeployMessages { case class MasterStateResponse(host: String, port: Int, workers: Array[WorkerInfo], activeApps: Array[ApplicationInfo], completedApps: Array[ApplicationInfo], + activeDrivers: Array[DriverInfo], completedDrivers: Array[DriverInfo], status: MasterState) { Utils.checkHost(host, "Required hostname") @@ -128,14 +157,15 @@ private[deploy] object DeployMessages { // Worker to WorkerWebUI case class WorkerStateResponse(host: String, port: Int, workerId: String, - executors: List[ExecutorRunner], finishedExecutors: List[ExecutorRunner], masterUrl: String, + executors: List[ExecutorRunner], finishedExecutors: List[ExecutorRunner], + drivers: List[DriverRunner], finishedDrivers: List[DriverRunner], masterUrl: String, cores: Int, memory: Int, coresUsed: Int, memoryUsed: Int, masterWebUiUrl: String) { Utils.checkHost(host, "Required hostname") assert (port > 0) } - // Actor System to Worker + // Liveness checks in various places case object SendHeartbeat } diff --git a/core/src/main/scala/org/apache/spark/deploy/DriverDescription.scala b/core/src/main/scala/org/apache/spark/deploy/DriverDescription.scala new file mode 100644 index 0000000000..58c95dc4f9 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/DriverDescription.scala @@ -0,0 +1,29 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy + +private[spark] class DriverDescription( + val jarUrl: String, + val mem: Int, + val cores: Int, + val supervise: Boolean, + val command: Command) + extends Serializable { + + override def toString: String = s"DriverDescription (${command.mainClass})" +} diff --git a/core/src/main/scala/org/apache/spark/deploy/client/Client.scala b/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala index 9bbd635ab9..1415e2f3d1 100644 --- a/core/src/main/scala/org/apache/spark/deploy/client/Client.scala +++ b/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala @@ -24,7 +24,8 @@ import scala.concurrent.duration._ import akka.actor._ import akka.pattern.ask -import akka.remote.{DisassociatedEvent, RemotingLifecycleEvent} +import akka.remote.{AssociationErrorEvent, DisassociatedEvent, RemotingLifecycleEvent} + import org.apache.spark.{Logging, SparkConf, SparkException} import org.apache.spark.deploy.{ApplicationDescription, ExecutorState} import org.apache.spark.deploy.DeployMessages._ @@ -32,16 +33,17 @@ import org.apache.spark.deploy.master.Master import org.apache.spark.util.AkkaUtils /** - * The main class used to talk to a Spark deploy cluster. Takes a master URL, an app description, - * and a listener for cluster events, and calls back the listener when various events occur. + * Interface allowing applications to speak with a Spark deploy cluster. Takes a master URL, + * an app description, and a listener for cluster events, and calls back the listener when various + * events occur. * * @param masterUrls Each url should look like spark://host:port. */ -private[spark] class Client( +private[spark] class AppClient( actorSystem: ActorSystem, masterUrls: Array[String], appDescription: ApplicationDescription, - listener: ClientListener, + listener: AppClientListener, conf: SparkConf) extends Logging { @@ -110,6 +112,12 @@ private[spark] class Client( } } + private def isPossibleMaster(remoteUrl: Address) = { + masterUrls.map(s => Master.toAkkaUrl(s)) + .map(u => AddressFromURIString(u).hostPort) + .contains(remoteUrl.hostPort) + } + override def receive = { case RegisteredApplication(appId_, masterUrl) => appId = appId_ @@ -145,7 +153,10 @@ private[spark] class Client( logWarning(s"Connection to $address failed; waiting for master to reconnect...") markDisconnected() - case StopClient => + case AssociationErrorEvent(cause, _, address, _) if isPossibleMaster(address) => + logWarning(s"Could not connect to $address: $cause") + + case StopAppClient => markDead() sender ! true context.stop(self) @@ -178,7 +189,7 @@ private[spark] class Client( if (actor != null) { try { val timeout = AkkaUtils.askTimeout(conf) - val future = actor.ask(StopClient)(timeout) + val future = actor.ask(StopAppClient)(timeout) Await.result(future, timeout) } catch { case e: TimeoutException => diff --git a/core/src/main/scala/org/apache/spark/deploy/client/ClientListener.scala b/core/src/main/scala/org/apache/spark/deploy/client/AppClientListener.scala index be7a11bd15..55d4ef1b31 100644 --- a/core/src/main/scala/org/apache/spark/deploy/client/ClientListener.scala +++ b/core/src/main/scala/org/apache/spark/deploy/client/AppClientListener.scala @@ -24,7 +24,7 @@ package org.apache.spark.deploy.client * * Users of this API should *not* block inside the callback methods. */ -private[spark] trait ClientListener { +private[spark] trait AppClientListener { def connected(appId: String): Unit /** Disconnection may be a temporary state, as we fail over to a new Master. */ diff --git a/core/src/main/scala/org/apache/spark/deploy/client/TestClient.scala b/core/src/main/scala/org/apache/spark/deploy/client/TestClient.scala index ef649fd80c..ffa909c26b 100644 --- a/core/src/main/scala/org/apache/spark/deploy/client/TestClient.scala +++ b/core/src/main/scala/org/apache/spark/deploy/client/TestClient.scala @@ -23,7 +23,7 @@ import org.apache.spark.deploy.{Command, ApplicationDescription} private[spark] object TestClient { - class TestListener extends ClientListener with Logging { + class TestListener extends AppClientListener with Logging { def connected(id: String) { logInfo("Connected to master, got app ID " + id) } @@ -48,10 +48,10 @@ private[spark] object TestClient { val (actorSystem, port) = AkkaUtils.createActorSystem("spark", Utils.localIpAddress, 0, conf = new SparkConf) val desc = new ApplicationDescription( - "TestClient", 1, 512, Command("spark.deploy.client.TestExecutor", Seq(), Map()), + "TestClient", Some(1), 512, Command("spark.deploy.client.TestExecutor", Seq(), Map()), "dummy-spark-home", "ignored") val listener = new TestListener - val client = new Client(actorSystem, Array(url), desc, listener, new SparkConf) + val client = new AppClient(actorSystem, Array(url), desc, listener, new SparkConf) client.start() actorSystem.awaitTermination() } diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala index 5150b7c7de..3e26379166 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ApplicationInfo.scala @@ -28,7 +28,8 @@ private[spark] class ApplicationInfo( val desc: ApplicationDescription, val submitDate: Date, val driver: ActorRef, - val appUiUrl: String) + val appUiUrl: String, + defaultCores: Int) extends Serializable { @transient var state: ApplicationState.Value = _ @@ -81,7 +82,9 @@ private[spark] class ApplicationInfo( } } - def coresLeft: Int = desc.maxCores - coresGranted + private val myMaxCores = desc.maxCores.getOrElse(defaultCores) + + def coresLeft: Int = myMaxCores - coresGranted private var _retryCount = 0 diff --git a/core/src/main/scala/org/apache/spark/deploy/master/DriverInfo.scala b/core/src/main/scala/org/apache/spark/deploy/master/DriverInfo.scala new file mode 100644 index 0000000000..33377931d6 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/master/DriverInfo.scala @@ -0,0 +1,36 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy.master + +import java.util.Date + +import org.apache.spark.deploy.DriverDescription + +private[spark] class DriverInfo( + val startTime: Long, + val id: String, + val desc: DriverDescription, + val submitDate: Date) + extends Serializable { + + @transient var state: DriverState.Value = DriverState.SUBMITTED + /* If we fail when launching the driver, the exception is stored here. */ + @transient var exception: Option[Exception] = None + /* Most recent worker assigned to this driver */ + @transient var worker: Option[WorkerInfo] = None +} diff --git a/core/src/main/scala/org/apache/spark/deploy/master/DriverState.scala b/core/src/main/scala/org/apache/spark/deploy/master/DriverState.scala new file mode 100644 index 0000000000..26a68bade3 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/master/DriverState.scala @@ -0,0 +1,33 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy.master + +private[spark] object DriverState extends Enumeration { + + type DriverState = Value + + // SUBMITTED: Submitted but not yet scheduled on a worker + // RUNNING: Has been allocated to a worker to run + // FINISHED: Previously ran and exited cleanly + // RELAUNCHING: Exited non-zero or due to worker failure, but has not yet started running again + // UNKNOWN: The state of the driver is temporarily not known due to master failure recovery + // KILLED: A user manually killed this driver + // FAILED: The driver exited non-zero and was not supervised + // ERROR: Unable to run or restart due to an unrecoverable error (e.g. missing jar file) + val SUBMITTED, RUNNING, FINISHED, RELAUNCHING, UNKNOWN, KILLED, FAILED, ERROR = Value +} diff --git a/core/src/main/scala/org/apache/spark/deploy/master/FileSystemPersistenceEngine.scala b/core/src/main/scala/org/apache/spark/deploy/master/FileSystemPersistenceEngine.scala index 043945a211..74bb9ebf1d 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/FileSystemPersistenceEngine.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/FileSystemPersistenceEngine.scala @@ -19,8 +19,6 @@ package org.apache.spark.deploy.master import java.io._ -import scala.Serializable - import akka.serialization.Serialization import org.apache.spark.Logging @@ -47,6 +45,15 @@ private[spark] class FileSystemPersistenceEngine( new File(dir + File.separator + "app_" + app.id).delete() } + override def addDriver(driver: DriverInfo) { + val driverFile = new File(dir + File.separator + "driver_" + driver.id) + serializeIntoFile(driverFile, driver) + } + + override def removeDriver(driver: DriverInfo) { + new File(dir + File.separator + "driver_" + driver.id).delete() + } + override def addWorker(worker: WorkerInfo) { val workerFile = new File(dir + File.separator + "worker_" + worker.id) serializeIntoFile(workerFile, worker) @@ -56,13 +63,15 @@ private[spark] class FileSystemPersistenceEngine( new File(dir + File.separator + "worker_" + worker.id).delete() } - override def readPersistedData(): (Seq[ApplicationInfo], Seq[WorkerInfo]) = { + override def readPersistedData(): (Seq[ApplicationInfo], Seq[DriverInfo], Seq[WorkerInfo]) = { val sortedFiles = new File(dir).listFiles().sortBy(_.getName) val appFiles = sortedFiles.filter(_.getName.startsWith("app_")) val apps = appFiles.map(deserializeFromFile[ApplicationInfo]) + val driverFiles = sortedFiles.filter(_.getName.startsWith("driver_")) + val drivers = driverFiles.map(deserializeFromFile[DriverInfo]) val workerFiles = sortedFiles.filter(_.getName.startsWith("worker_")) val workers = workerFiles.map(deserializeFromFile[WorkerInfo]) - (apps, workers) + (apps, drivers, workers) } private def serializeIntoFile(file: File, value: AnyRef) { diff --git a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala index 7b696cfcca..d9ea96afcf 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala @@ -23,19 +23,22 @@ import java.util.Date import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet} import scala.concurrent.Await import scala.concurrent.duration._ +import scala.util.Random import akka.actor._ import akka.pattern.ask import akka.remote.{DisassociatedEvent, RemotingLifecycleEvent} import akka.serialization.SerializationExtension -import org.apache.spark.{SparkConf, SparkContext, Logging, SparkException} -import org.apache.spark.deploy.{ApplicationDescription, ExecutorState} + +import org.apache.spark.{SparkConf, Logging, SparkException} +import org.apache.spark.deploy.{ApplicationDescription, DriverDescription, ExecutorState} import org.apache.spark.deploy.DeployMessages._ import org.apache.spark.deploy.master.MasterMessages._ import org.apache.spark.deploy.master.ui.MasterWebUI import org.apache.spark.metrics.MetricsSystem import org.apache.spark.util.{AkkaUtils, Utils} +import org.apache.spark.deploy.master.DriverState.DriverState private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Actor with Logging { import context.dispatcher // to use Akka's scheduler.schedule() @@ -43,13 +46,12 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act val conf = new SparkConf val DATE_FORMAT = new SimpleDateFormat("yyyyMMddHHmmss") // For application IDs - val WORKER_TIMEOUT = conf.get("spark.worker.timeout", "60").toLong * 1000 - val RETAINED_APPLICATIONS = conf.get("spark.deploy.retainedApplications", "200").toInt - val REAPER_ITERATIONS = conf.get("spark.dead.worker.persistence", "15").toInt + val WORKER_TIMEOUT = conf.getLong("spark.worker.timeout", 60) * 1000 + val RETAINED_APPLICATIONS = conf.getInt("spark.deploy.retainedApplications", 200) + val REAPER_ITERATIONS = conf.getInt("spark.dead.worker.persistence", 15) val RECOVERY_DIR = conf.get("spark.deploy.recoveryDirectory", "") val RECOVERY_MODE = conf.get("spark.deploy.recoveryMode", "NONE") - var nextAppNumber = 0 val workers = new HashSet[WorkerInfo] val idToWorker = new HashMap[String, WorkerInfo] val actorToWorker = new HashMap[ActorRef, WorkerInfo] @@ -59,9 +61,14 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act val idToApp = new HashMap[String, ApplicationInfo] val actorToApp = new HashMap[ActorRef, ApplicationInfo] val addressToApp = new HashMap[Address, ApplicationInfo] - val waitingApps = new ArrayBuffer[ApplicationInfo] val completedApps = new ArrayBuffer[ApplicationInfo] + var nextAppNumber = 0 + + val drivers = new HashSet[DriverInfo] + val completedDrivers = new ArrayBuffer[DriverInfo] + val waitingDrivers = new ArrayBuffer[DriverInfo] // Drivers currently spooled for scheduling + var nextDriverNumber = 0 Utils.checkHost(host, "Expected hostname") @@ -88,7 +95,13 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act // As a temporary workaround before better ways of configuring memory, we allow users to set // a flag that will perform round-robin scheduling across the nodes (spreading out each app // among all the nodes) instead of trying to consolidate each app onto a small # of nodes. - val spreadOutApps = conf.get("spark.deploy.spreadOut", "true").toBoolean + val spreadOutApps = conf.getBoolean("spark.deploy.spreadOut", true) + + // Default maxCores for applications that don't specify it (i.e. pass Int.MaxValue) + val defaultCores = conf.getInt("spark.deploy.defaultCores", Int.MaxValue) + if (defaultCores < 1) { + throw new SparkException("spark.deploy.defaultCores must be positive") + } override def preStart() { logInfo("Starting Spark master at " + masterUrl) @@ -136,14 +149,14 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act override def receive = { case ElectedLeader => { - val (storedApps, storedWorkers) = persistenceEngine.readPersistedData() - state = if (storedApps.isEmpty && storedWorkers.isEmpty) + val (storedApps, storedDrivers, storedWorkers) = persistenceEngine.readPersistedData() + state = if (storedApps.isEmpty && storedDrivers.isEmpty && storedWorkers.isEmpty) RecoveryState.ALIVE else RecoveryState.RECOVERING logInfo("I have been elected leader! New state: " + state) if (state == RecoveryState.RECOVERING) { - beginRecovery(storedApps, storedWorkers) + beginRecovery(storedApps, storedDrivers, storedWorkers) context.system.scheduler.scheduleOnce(WORKER_TIMEOUT millis) { completeRecovery() } } } @@ -170,6 +183,69 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act } } + case RequestSubmitDriver(description) => { + if (state != RecoveryState.ALIVE) { + val msg = s"Can only accept driver submissions in ALIVE state. Current state: $state." + sender ! SubmitDriverResponse(false, None, msg) + } else { + logInfo("Driver submitted " + description.command.mainClass) + val driver = createDriver(description) + persistenceEngine.addDriver(driver) + waitingDrivers += driver + drivers.add(driver) + schedule() + + // TODO: It might be good to instead have the submission client poll the master to determine + // the current status of the driver. For now it's simply "fire and forget". + + sender ! SubmitDriverResponse(true, Some(driver.id), + s"Driver successfully submitted as ${driver.id}") + } + } + + case RequestKillDriver(driverId) => { + if (state != RecoveryState.ALIVE) { + val msg = s"Can only kill drivers in ALIVE state. Current state: $state." + sender ! KillDriverResponse(driverId, success = false, msg) + } else { + logInfo("Asked to kill driver " + driverId) + val driver = drivers.find(_.id == driverId) + driver match { + case Some(d) => + if (waitingDrivers.contains(d)) { + waitingDrivers -= d + self ! DriverStateChanged(driverId, DriverState.KILLED, None) + } + else { + // We just notify the worker to kill the driver here. The final bookkeeping occurs + // on the return path when the worker submits a state change back to the master + // to notify it that the driver was successfully killed. + d.worker.foreach { w => + w.actor ! KillDriver(driverId) + } + } + // TODO: It would be nice for this to be a synchronous response + val msg = s"Kill request for $driverId submitted" + logInfo(msg) + sender ! KillDriverResponse(driverId, success = true, msg) + case None => + val msg = s"Driver $driverId has already finished or does not exist" + logWarning(msg) + sender ! KillDriverResponse(driverId, success = false, msg) + } + } + } + + case RequestDriverStatus(driverId) => { + (drivers ++ completedDrivers).find(_.id == driverId) match { + case Some(driver) => + sender ! DriverStatusResponse(found = true, Some(driver.state), + driver.worker.map(_.id), driver.worker.map(_.hostPort), driver.exception) + case None => + sender ! DriverStatusResponse(found = false, None, None, None, None) + } + } + case RegisterApplication(description) => { if (state == RecoveryState.STANDBY) { // ignore, don't send response @@ -212,6 +288,15 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act } } + case DriverStateChanged(driverId, state, exception) => { + state match { + case DriverState.ERROR | DriverState.FINISHED | DriverState.KILLED | DriverState.FAILED => + removeDriver(driverId, state, exception) + case _ => + throw new Exception(s"Received unexpected state update for driver $driverId: $state") + } + } + case Heartbeat(workerId) => { idToWorker.get(workerId) match { case Some(workerInfo) => @@ -233,7 +318,7 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act if (canCompleteRecovery) { completeRecovery() } } - case WorkerSchedulerStateResponse(workerId, executors) => { + case WorkerSchedulerStateResponse(workerId, executors, driverIds) => { idToWorker.get(workerId) match { case Some(worker) => logInfo("Worker has been re-registered: " + workerId) @@ -246,6 +331,14 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act worker.addExecutor(execInfo) execInfo.copyState(exec) } + + for (driverId <- driverIds) { + drivers.find(_.id == driverId).foreach { driver => + driver.worker = Some(worker) + driver.state = DriverState.RUNNING + worker.drivers(driverId) = driver + } + } case None => logWarning("Scheduler state from unknown worker: " + workerId) } @@ -263,7 +356,7 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act case RequestMasterState => { sender ! MasterStateResponse(host, port, workers.toArray, apps.toArray, completedApps.toArray, - state) + drivers.toArray, completedDrivers.toArray, state) } case CheckForWorkerTimeOut => { @@ -279,7 +372,8 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act workers.count(_.state == WorkerState.UNKNOWN) == 0 && apps.count(_.state == ApplicationState.UNKNOWN) == 0 - def beginRecovery(storedApps: Seq[ApplicationInfo], storedWorkers: Seq[WorkerInfo]) { + def beginRecovery(storedApps: Seq[ApplicationInfo], storedDrivers: Seq[DriverInfo], + storedWorkers: Seq[WorkerInfo]) { for (app <- storedApps) { logInfo("Trying to recover app: " + app.id) try { @@ -291,6 +385,12 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act } } + for (driver <- storedDrivers) { + // Here we just read in the list of drivers. Any drivers associated with now-lost workers + // will be re-launched when we detect that the worker is missing. + drivers += driver + } + for (worker <- storedWorkers) { logInfo("Trying to recover worker: " + worker.id) try { @@ -314,6 +414,18 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act workers.filter(_.state == WorkerState.UNKNOWN).foreach(removeWorker) apps.filter(_.state == ApplicationState.UNKNOWN).foreach(finishApplication) + // Reschedule drivers which were not claimed by any workers + drivers.filter(_.worker.isEmpty).foreach { d => + logWarning(s"Driver ${d.id} was not found after master recovery") + if (d.desc.supervise) { + logWarning(s"Re-launching ${d.id}") + relaunchDriver(d) + } else { + removeDriver(d.id, DriverState.ERROR, None) + logWarning(s"Did not re-launch ${d.id} because it was not supervised") + } + } + state = RecoveryState.ALIVE schedule() logInfo("Recovery complete - resuming operations!") @@ -334,6 +446,18 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act */ def schedule() { if (state != RecoveryState.ALIVE) { return } + + // First schedule drivers, they take strict precedence over applications + val shuffledWorkers = Random.shuffle(workers) // Randomization helps balance drivers + for (worker <- shuffledWorkers if worker.state == WorkerState.ALIVE) { + for (driver <- waitingDrivers) { + if (worker.memoryFree >= driver.desc.mem && worker.coresFree >= driver.desc.cores) { + launchDriver(worker, driver) + waitingDrivers -= driver + } + } + } + // Right now this is a very simple FIFO scheduler. We keep trying to fit in the first app // in the queue, then the second app, etc. if (spreadOutApps) { @@ -420,13 +544,30 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act exec.id, ExecutorState.LOST, Some("worker lost"), None) exec.application.removeExecutor(exec) } + for (driver <- worker.drivers.values) { + if (driver.desc.supervise) { + logInfo(s"Re-launching ${driver.id}") + relaunchDriver(driver) + } else { + logInfo(s"Not re-launching ${driver.id} because it was not supervised") + removeDriver(driver.id, DriverState.ERROR, None) + } + } persistenceEngine.removeWorker(worker) } + def relaunchDriver(driver: DriverInfo) { + driver.worker = None + driver.state = DriverState.RELAUNCHING + waitingDrivers += driver + schedule() + } + def createApplication(desc: ApplicationDescription, driver: ActorRef): ApplicationInfo = { val now = System.currentTimeMillis() val date = new Date(now) - new ApplicationInfo(now, newApplicationId(date), desc, date, driver, desc.appUiUrl) + new ApplicationInfo( + now, newApplicationId(date), desc, date, driver, desc.appUiUrl, defaultCores) } def registerApplication(app: ApplicationInfo): Unit = { @@ -501,6 +642,41 @@ private[spark] class Master(host: String, port: Int, webUiPort: Int) extends Act } } } + + def newDriverId(submitDate: Date): String = { + val appId = "driver-%s-%04d".format(DATE_FORMAT.format(submitDate), nextDriverNumber) + nextDriverNumber += 1 + appId + } + + def createDriver(desc: DriverDescription): DriverInfo = { + val now = System.currentTimeMillis() + val date = new Date(now) + new DriverInfo(now, newDriverId(date), desc, date) + } + + def launchDriver(worker: WorkerInfo, driver: DriverInfo) { + logInfo("Launching driver " + driver.id + " on worker " + worker.id) + worker.addDriver(driver) + driver.worker = Some(worker) + worker.actor ! LaunchDriver(driver.id, driver.desc) + driver.state = DriverState.RUNNING + } + + def removeDriver(driverId: String, finalState: DriverState, exception: Option[Exception]) { + drivers.find(d => d.id == driverId) match { + case Some(driver) => + logInfo(s"Removing driver: $driverId") + drivers -= driver + completedDrivers += driver + persistenceEngine.removeDriver(driver) + driver.state = finalState + driver.exception = exception + driver.worker.foreach(w => w.removeDriver(driver)) + case None => + logWarning(s"Asked to remove unknown driver: $driverId") + } + } } private[spark] object Master { diff --git a/core/src/main/scala/org/apache/spark/deploy/master/PersistenceEngine.scala b/core/src/main/scala/org/apache/spark/deploy/master/PersistenceEngine.scala index 94b986caf2..e3640ea4f7 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/PersistenceEngine.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/PersistenceEngine.scala @@ -35,11 +35,15 @@ private[spark] trait PersistenceEngine { def removeWorker(worker: WorkerInfo) + def addDriver(driver: DriverInfo) + + def removeDriver(driver: DriverInfo) + /** * Returns the persisted data sorted by their respective ids (which implies that they're * sorted by time of creation). */ - def readPersistedData(): (Seq[ApplicationInfo], Seq[WorkerInfo]) + def readPersistedData(): (Seq[ApplicationInfo], Seq[DriverInfo], Seq[WorkerInfo]) def close() {} } @@ -49,5 +53,8 @@ private[spark] class BlackHolePersistenceEngine extends PersistenceEngine { override def removeApplication(app: ApplicationInfo) {} override def addWorker(worker: WorkerInfo) {} override def removeWorker(worker: WorkerInfo) {} - override def readPersistedData() = (Nil, Nil) + override def addDriver(driver: DriverInfo) {} + override def removeDriver(driver: DriverInfo) {} + + override def readPersistedData() = (Nil, Nil, Nil) } diff --git a/core/src/main/scala/org/apache/spark/deploy/master/WorkerInfo.scala b/core/src/main/scala/org/apache/spark/deploy/master/WorkerInfo.scala index e05f587b58..c5fa9cf7d7 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/WorkerInfo.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/WorkerInfo.scala @@ -17,8 +17,10 @@ package org.apache.spark.deploy.master -import akka.actor.ActorRef import scala.collection.mutable + +import akka.actor.ActorRef + import org.apache.spark.util.Utils private[spark] class WorkerInfo( @@ -35,7 +37,8 @@ private[spark] class WorkerInfo( Utils.checkHost(host, "Expected hostname") assert (port > 0) - @transient var executors: mutable.HashMap[String, ExecutorInfo] = _ // fullId => info + @transient var executors: mutable.HashMap[String, ExecutorInfo] = _ // executorId => info + @transient var drivers: mutable.HashMap[String, DriverInfo] = _ // driverId => info @transient var state: WorkerState.Value = _ @transient var coresUsed: Int = _ @transient var memoryUsed: Int = _ @@ -54,6 +57,7 @@ private[spark] class WorkerInfo( private def init() { executors = new mutable.HashMap + drivers = new mutable.HashMap state = WorkerState.ALIVE coresUsed = 0 memoryUsed = 0 @@ -83,6 +87,18 @@ private[spark] class WorkerInfo( executors.values.exists(_.application == app) } + def addDriver(driver: DriverInfo) { + drivers(driver.id) = driver + memoryUsed += driver.desc.mem + coresUsed += driver.desc.cores + } + + def removeDriver(driver: DriverInfo) { + drivers -= driver.id + memoryUsed -= driver.desc.mem + coresUsed -= driver.desc.cores + } + def webUiAddress : String = { "http://" + this.publicAddress + ":" + this.webUiPort } diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ZooKeeperPersistenceEngine.scala b/core/src/main/scala/org/apache/spark/deploy/master/ZooKeeperPersistenceEngine.scala index 52000d4f9c..f24f49ea8a 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ZooKeeperPersistenceEngine.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ZooKeeperPersistenceEngine.scala @@ -49,6 +49,14 @@ class ZooKeeperPersistenceEngine(serialization: Serialization, conf: SparkConf) zk.delete(WORKING_DIR + "/app_" + app.id) } + override def addDriver(driver: DriverInfo) { + serializeIntoFile(WORKING_DIR + "/driver_" + driver.id, driver) + } + + override def removeDriver(driver: DriverInfo) { + zk.delete(WORKING_DIR + "/driver_" + driver.id) + } + override def addWorker(worker: WorkerInfo) { serializeIntoFile(WORKING_DIR + "/worker_" + worker.id, worker) } @@ -61,13 +69,15 @@ class ZooKeeperPersistenceEngine(serialization: Serialization, conf: SparkConf) zk.close() } - override def readPersistedData(): (Seq[ApplicationInfo], Seq[WorkerInfo]) = { + override def readPersistedData(): (Seq[ApplicationInfo], Seq[DriverInfo], Seq[WorkerInfo]) = { val sortedFiles = zk.getChildren(WORKING_DIR).toList.sorted val appFiles = sortedFiles.filter(_.startsWith("app_")) val apps = appFiles.map(deserializeFromFile[ApplicationInfo]) + val driverFiles = sortedFiles.filter(_.startsWith("driver_")) + val drivers = driverFiles.map(deserializeFromFile[DriverInfo]) val workerFiles = sortedFiles.filter(_.startsWith("worker_")) val workers = workerFiles.map(deserializeFromFile[WorkerInfo]) - (apps, workers) + (apps, drivers, workers) } private def serializeIntoFile(path: String, value: AnyRef) { diff --git a/core/src/main/scala/org/apache/spark/deploy/master/ui/IndexPage.scala b/core/src/main/scala/org/apache/spark/deploy/master/ui/IndexPage.scala index 4ef762892c..a9af8df552 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/ui/IndexPage.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/ui/IndexPage.scala @@ -18,6 +18,7 @@ package org.apache.spark.deploy.master.ui import scala.concurrent.Await +import scala.concurrent.duration._ import scala.xml.Node import akka.pattern.ask @@ -26,7 +27,7 @@ import net.liftweb.json.JsonAST.JValue import org.apache.spark.deploy.{DeployWebUI, JsonProtocol} import org.apache.spark.deploy.DeployMessages.{MasterStateResponse, RequestMasterState} -import org.apache.spark.deploy.master.{ApplicationInfo, WorkerInfo} +import org.apache.spark.deploy.master.{ApplicationInfo, DriverInfo, WorkerInfo} import org.apache.spark.ui.UIUtils import org.apache.spark.util.Utils @@ -56,6 +57,16 @@ private[spark] class IndexPage(parent: MasterWebUI) { val completedApps = state.completedApps.sortBy(_.endTime).reverse val completedAppsTable = UIUtils.listingTable(appHeaders, appRow, completedApps) + val driverHeaders = Seq("ID", "Submitted Time", "Worker", "State", "Cores", "Memory", "Main Class") + val activeDrivers = state.activeDrivers.sortBy(_.startTime).reverse + val activeDriversTable = UIUtils.listingTable(driverHeaders, driverRow, activeDrivers) + val completedDrivers = state.completedDrivers.sortBy(_.startTime).reverse + val completedDriversTable = UIUtils.listingTable(driverHeaders, driverRow, completedDrivers) + + // For now we only show driver information if the user has submitted drivers to the cluster. + // This is until we integrate the notion of drivers and applications in the UI. + def hasDrivers = activeDrivers.length > 0 || completedDrivers.length > 0 + val content = <div class="row-fluid"> <div class="span12"> @@ -70,6 +81,9 @@ private[spark] class IndexPage(parent: MasterWebUI) { <li><strong>Applications:</strong> {state.activeApps.size} Running, {state.completedApps.size} Completed </li> + <li><strong>Drivers:</strong> + {state.activeDrivers.size} Running, + {state.completedDrivers.size} Completed </li> </ul> </div> </div> @@ -84,17 +98,39 @@ private[spark] class IndexPage(parent: MasterWebUI) { <div class="row-fluid"> <div class="span12"> <h4> Running Applications </h4> - {activeAppsTable} </div> </div> + <div> + {if (hasDrivers) + <div class="row-fluid"> + <div class="span12"> + <h4> Running Drivers </h4> + {activeDriversTable} + </div> + </div> + } + </div> + <div class="row-fluid"> <div class="span12"> <h4> Completed Applications </h4> {completedAppsTable} </div> + </div> + + <div> + {if (hasDrivers) + <div class="row-fluid"> + <div class="span12"> + <h4> Completed Drivers </h4> + {completedDriversTable} + </div> + </div> + } </div>; + UIUtils.basicSparkPage(content, "Spark Master at " + state.uri) } @@ -134,4 +170,20 @@ private[spark] class IndexPage(parent: MasterWebUI) { <td>{DeployWebUI.formatDuration(app.duration)}</td> </tr> } + + def driverRow(driver: DriverInfo): Seq[Node] = { + <tr> + <td>{driver.id} </td> + <td>{driver.submitDate}</td> + <td>{driver.worker.map(w => <a href={w.webUiAddress}>{w.id.toString}</a>).getOrElse("None")}</td> + <td>{driver.state}</td> + <td sorttable_customkey={driver.desc.cores.toString}> + {driver.desc.cores} + </td> + <td sorttable_customkey={driver.desc.mem.toString}> + {Utils.megabytesToString(driver.desc.mem.toLong)} + </td> + <td>{driver.desc.command.arguments(1)}</td> + </tr> + } } diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala b/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala new file mode 100644 index 0000000000..7507bf8ad0 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala @@ -0,0 +1,63 @@ +package org.apache.spark.deploy.worker + +import java.io.{File, FileOutputStream, IOException, InputStream} +import java.lang.System._ + +import org.apache.spark.Logging +import org.apache.spark.deploy.Command +import org.apache.spark.util.Utils + +/** + ** Utilities for running commands with the spark classpath. + */ +object CommandUtils extends Logging { + private[spark] def buildCommandSeq(command: Command, memory: Int, sparkHome: String): Seq[String] = { + val runner = getEnv("JAVA_HOME", command).map(_ + "/bin/java").getOrElse("java") + + // SPARK-698: do not call the run.cmd script, as process.destroy() + // fails to kill a process tree on Windows + Seq(runner) ++ buildJavaOpts(command, memory, sparkHome) ++ Seq(command.mainClass) ++ + command.arguments + } + + private def getEnv(key: String, command: Command): Option[String] = + command.environment.get(key).orElse(Option(System.getenv(key))) + + /** + * Attention: this must always be aligned with the environment variables in the run scripts and + * the way the JAVA_OPTS are assembled there. + */ + def buildJavaOpts(command: Command, memory: Int, sparkHome: String): Seq[String] = { + val libraryOpts = getEnv("SPARK_LIBRARY_PATH", command) + .map(p => List("-Djava.library.path=" + p)) + .getOrElse(Nil) + val workerLocalOpts = Option(getenv("SPARK_JAVA_OPTS")).map(Utils.splitCommandString).getOrElse(Nil) + val userOpts = getEnv("SPARK_JAVA_OPTS", command).map(Utils.splitCommandString).getOrElse(Nil) + val memoryOpts = Seq(s"-Xms${memory}M", s"-Xmx${memory}M") + + // Figure out our classpath with the external compute-classpath script + val ext = if (System.getProperty("os.name").startsWith("Windows")) ".cmd" else ".sh" + val classPath = Utils.executeAndGetOutput( + Seq(sparkHome + "/bin/compute-classpath" + ext), + extraEnvironment=command.environment) + + Seq("-cp", classPath) ++ libraryOpts ++ workerLocalOpts ++ userOpts ++ memoryOpts + } + + /** Spawn a thread that will redirect a given stream to a file */ + def redirectStream(in: InputStream, file: File) { + val out = new FileOutputStream(file, true) + // TODO: It would be nice to add a shutdown hook here that explains why the output is + // terminating. Otherwise if the worker dies the executor logs will silently stop. + new Thread("redirect output to " + file) { + override def run() { + try { + Utils.copyStream(in, out, true) + } catch { + case e: IOException => + logInfo("Redirection to " + file + " closed: " + e.getMessage) + } + } + }.start() + } +} diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala b/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala new file mode 100644 index 0000000000..b4df1a0dd4 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala @@ -0,0 +1,234 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.deploy.worker + +import java.io._ + +import scala.collection.JavaConversions._ +import scala.collection.mutable.Map + +import akka.actor.ActorRef +import com.google.common.base.Charsets +import com.google.common.io.Files +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.{FileUtil, Path} + +import org.apache.spark.Logging +import org.apache.spark.deploy.{Command, DriverDescription} +import org.apache.spark.deploy.DeployMessages.DriverStateChanged +import org.apache.spark.deploy.master.DriverState +import org.apache.spark.deploy.master.DriverState.DriverState + +/** + * Manages the execution of one driver, including automatically restarting the driver on failure. + */ +private[spark] class DriverRunner( + val driverId: String, + val workDir: File, + val sparkHome: File, + val driverDesc: DriverDescription, + val worker: ActorRef, + val workerUrl: String) + extends Logging { + + @volatile var process: Option[Process] = None + @volatile var killed = false + + // Populated once finished + var finalState: Option[DriverState] = None + var finalException: Option[Exception] = None + var finalExitCode: Option[Int] = None + + // Decoupled for testing + private[deploy] def setClock(_clock: Clock) = clock = _clock + private[deploy] def setSleeper(_sleeper: Sleeper) = sleeper = _sleeper + private var clock = new Clock { + def currentTimeMillis(): Long = System.currentTimeMillis() + } + private var sleeper = new Sleeper { + def sleep(seconds: Int): Unit = (0 until seconds).takeWhile(f => {Thread.sleep(1000); !killed}) + } + + /** Starts a thread to run and manage the driver. */ + def start() = { + new Thread("DriverRunner for " + driverId) { + override def run() { + try { + val driverDir = createWorkingDirectory() + val localJarFilename = downloadUserJar(driverDir) + + // Make sure user application jar is on the classpath + // TODO: If we add ability to submit multiple jars they should also be added here + val env = Map(driverDesc.command.environment.toSeq: _*) + env("SPARK_CLASSPATH") = env.getOrElse("SPARK_CLASSPATH", "") + s":$localJarFilename" + val newCommand = Command(driverDesc.command.mainClass, + driverDesc.command.arguments.map(substituteVariables), env) + val command = CommandUtils.buildCommandSeq(newCommand, driverDesc.mem, + sparkHome.getAbsolutePath) + launchDriver(command, env, driverDir, driverDesc.supervise) + } + catch { + case e: Exception => finalException = Some(e) + } + + val state = + if (killed) { DriverState.KILLED } + else if (finalException.isDefined) { DriverState.ERROR } + else { + finalExitCode match { + case Some(0) => DriverState.FINISHED + case _ => DriverState.FAILED + } + } + + finalState = Some(state) + + worker ! DriverStateChanged(driverId, state, finalException) + } + }.start() + } + + /** Terminate this driver (or prevent it from ever starting if not yet started) */ + def kill() { + synchronized { + process.foreach(p => p.destroy()) + killed = true + } + } + + /** Replace variables in a command argument passed to us */ + private def substituteVariables(argument: String): String = argument match { + case "{{WORKER_URL}}" => workerUrl + case other => other + } + + /** + * Creates the working directory for this driver. + * Will throw an exception if there are errors preparing the directory. + */ + private def createWorkingDirectory(): File = { + val driverDir = new File(workDir, driverId) + if (!driverDir.exists() && !driverDir.mkdirs()) { + throw new IOException("Failed to create directory " + driverDir) + } + driverDir + } + + /** + * Download the user jar into the supplied directory and return its local path. + * Will throw an exception if there are errors downloading the jar. + */ + private def downloadUserJar(driverDir: File): String = { + + val jarPath = new Path(driverDesc.jarUrl) + + val emptyConf = new Configuration() + val jarFileSystem = jarPath.getFileSystem(emptyConf) + + val destPath = new File(driverDir.getAbsolutePath, jarPath.getName) + val jarFileName = jarPath.getName + val localJarFile = new File(driverDir, jarFileName) + val localJarFilename = localJarFile.getAbsolutePath + + if (!localJarFile.exists()) { // May already exist if running multiple workers on one node + logInfo(s"Copying user jar $jarPath to $destPath") + FileUtil.copy(jarFileSystem, jarPath, destPath, false, emptyConf) + } + + if (!localJarFile.exists()) { // Verify copy succeeded + throw new Exception(s"Did not see expected jar $jarFileName in $driverDir") + } + + localJarFilename + } + + private def launchDriver(command: Seq[String], envVars: Map[String, String], baseDir: File, + supervise: Boolean) { + val builder = new ProcessBuilder(command: _*).directory(baseDir) + envVars.map{ case(k,v) => builder.environment().put(k, v) } + + def initialize(process: Process) = { + // Redirect stdout and stderr to files + val stdout = new File(baseDir, "stdout") + CommandUtils.redirectStream(process.getInputStream, stdout) + + val stderr = new File(baseDir, "stderr") + val header = "Launch Command: %s\n%s\n\n".format( + command.mkString("\"", "\" \"", "\""), "=" * 40) + Files.append(header, stderr, Charsets.UTF_8) + CommandUtils.redirectStream(process.getErrorStream, stderr) + } + runCommandWithRetry(ProcessBuilderLike(builder), initialize, supervise) + } + + private[deploy] def runCommandWithRetry(command: ProcessBuilderLike, initialize: Process => Unit, + supervise: Boolean) { + // Time to wait between submission retries. + var waitSeconds = 1 + // A run of this many seconds resets the exponential back-off. + val successfulRunDuration = 5 + + var keepTrying = !killed + + while (keepTrying) { + logInfo("Launch Command: " + command.command.mkString("\"", "\" \"", "\"")) + + synchronized { + if (killed) { return } + process = Some(command.start()) + initialize(process.get) + } + + val processStart = clock.currentTimeMillis() + val exitCode = process.get.waitFor() + if (clock.currentTimeMillis() - processStart > successfulRunDuration * 1000) { + waitSeconds = 1 + } + + if (supervise && exitCode != 0 && !killed) { + logInfo(s"Command exited with status $exitCode, re-launching after $waitSeconds s.") + sleeper.sleep(waitSeconds) + waitSeconds = waitSeconds * 2 // exponential back-off + } + + keepTrying = supervise && exitCode != 0 && !killed + finalExitCode = Some(exitCode) + } + } +} + +private[deploy] trait Clock { + def currentTimeMillis(): Long +} + +private[deploy] trait Sleeper { + def sleep(seconds: Int) +} + +// Needed because ProcessBuilder is a final class and cannot be mocked +private[deploy] trait ProcessBuilderLike { + def start(): Process + def command: Seq[String] +} + +private[deploy] object ProcessBuilderLike { + def apply(processBuilder: ProcessBuilder) = new ProcessBuilderLike { + def start() = processBuilder.start() + def command = processBuilder.command() + } +} diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala b/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala new file mode 100644 index 0000000000..1640d5fee0 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala @@ -0,0 +1,31 @@ +package org.apache.spark.deploy.worker + +import akka.actor._ + +import org.apache.spark.SparkConf +import org.apache.spark.util.{AkkaUtils, Utils} + +/** + * Utility object for launching driver programs such that they share fate with the Worker process. + */ +object DriverWrapper { + def main(args: Array[String]) { + args.toList match { + case workerUrl :: mainClass :: extraArgs => + val (actorSystem, _) = AkkaUtils.createActorSystem("Driver", + Utils.localHostName(), 0, false, new SparkConf()) + actorSystem.actorOf(Props(classOf[WorkerWatcher], workerUrl), name = "workerWatcher") + + // Delegate to supplied main class + val clazz = Class.forName(args(1)) + val mainMethod = clazz.getMethod("main", classOf[Array[String]]) + mainMethod.invoke(null, extraArgs.toArray[String]) + + actorSystem.shutdown() + + case _ => + System.err.println("Usage: DriverWrapper <workerUrl> <driverMainClass> [options]") + System.exit(-1) + } + } +}
\ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala index fff9cb60c7..18885d7ca6 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala @@ -18,17 +18,15 @@ package org.apache.spark.deploy.worker import java.io._ -import java.lang.System.getenv import akka.actor.ActorRef import com.google.common.base.Charsets import com.google.common.io.Files -import org.apache.spark.{Logging} -import org.apache.spark.deploy.{ExecutorState, ApplicationDescription} +import org.apache.spark.Logging +import org.apache.spark.deploy.{ExecutorState, ApplicationDescription, Command} import org.apache.spark.deploy.DeployMessages.ExecutorStateChanged -import org.apache.spark.util.Utils /** * Manages the execution of one executor process. @@ -44,16 +42,17 @@ private[spark] class ExecutorRunner( val host: String, val sparkHome: File, val workDir: File, + val workerUrl: String, var state: ExecutorState.Value) extends Logging { val fullId = appId + "/" + execId var workerThread: Thread = null var process: Process = null - var shutdownHook: Thread = null - private def getAppEnv(key: String): Option[String] = - appDesc.command.environment.get(key).orElse(Option(getenv(key))) + // NOTE: This is now redundant with the automated shut-down enforced by the Executor. It might + // make sense to remove this in the future. + var shutdownHook: Thread = null def start() { workerThread = new Thread("ExecutorRunner for " + fullId) { @@ -92,55 +91,17 @@ private[spark] class ExecutorRunner( /** Replace variables such as {{EXECUTOR_ID}} and {{CORES}} in a command argument passed to us */ def substituteVariables(argument: String): String = argument match { + case "{{WORKER_URL}}" => workerUrl case "{{EXECUTOR_ID}}" => execId.toString case "{{HOSTNAME}}" => host case "{{CORES}}" => cores.toString case other => other } - def buildCommandSeq(): Seq[String] = { - val command = appDesc.command - val runner = getAppEnv("JAVA_HOME").map(_ + "/bin/java").getOrElse("java") - // SPARK-698: do not call the run.cmd script, as process.destroy() - // fails to kill a process tree on Windows - Seq(runner) ++ buildJavaOpts() ++ Seq(command.mainClass) ++ - (command.arguments ++ Seq(appId)).map(substituteVariables) - } - - /** - * Attention: this must always be aligned with the environment variables in the run scripts and - * the way the JAVA_OPTS are assembled there. - */ - def buildJavaOpts(): Seq[String] = { - val libraryOpts = getAppEnv("SPARK_LIBRARY_PATH") - .map(p => List("-Djava.library.path=" + p)) - .getOrElse(Nil) - val workerLocalOpts = Option(getenv("SPARK_JAVA_OPTS")).map(Utils.splitCommandString).getOrElse(Nil) - val userOpts = getAppEnv("SPARK_JAVA_OPTS").map(Utils.splitCommandString).getOrElse(Nil) - val memoryOpts = Seq("-Xms" + memory + "M", "-Xmx" + memory + "M") - - // Figure out our classpath with the external compute-classpath script - val ext = if (System.getProperty("os.name").startsWith("Windows")) ".cmd" else ".sh" - val classPath = Utils.executeAndGetOutput( - Seq(sparkHome + "/bin/compute-classpath" + ext), - extraEnvironment=appDesc.command.environment) - - Seq("-cp", classPath) ++ libraryOpts ++ workerLocalOpts ++ userOpts ++ memoryOpts - } - - /** Spawn a thread that will redirect a given stream to a file */ - def redirectStream(in: InputStream, file: File) { - val out = new FileOutputStream(file, true) - new Thread("redirect output to " + file) { - override def run() { - try { - Utils.copyStream(in, out, true) - } catch { - case e: IOException => - logInfo("Redirection to " + file + " closed: " + e.getMessage) - } - } - }.start() + def getCommandSeq = { + val command = Command(appDesc.command.mainClass, + appDesc.command.arguments.map(substituteVariables) ++ Seq(appId), appDesc.command.environment) + CommandUtils.buildCommandSeq(command, memory, sparkHome.getAbsolutePath) } /** @@ -155,7 +116,7 @@ private[spark] class ExecutorRunner( } // Launch the process - val command = buildCommandSeq() + val command = getCommandSeq logInfo("Launch command: " + command.mkString("\"", "\" \"", "\"")) val builder = new ProcessBuilder(command: _*).directory(executorDir) val env = builder.environment() @@ -172,11 +133,11 @@ private[spark] class ExecutorRunner( // Redirect its stdout and stderr to files val stdout = new File(executorDir, "stdout") - redirectStream(process.getInputStream, stdout) + CommandUtils.redirectStream(process.getInputStream, stdout) val stderr = new File(executorDir, "stderr") Files.write(header, stderr, Charsets.UTF_8) - redirectStream(process.getErrorStream, stderr) + CommandUtils.redirectStream(process.getErrorStream, stderr) // Wait for it to exit; this is actually a bad thing if it happens, because we expect to run // long-lived processes only. However, in the future, we might restart the executor a few diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala index fcaf4e92b1..5182dcbb2a 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala @@ -26,10 +26,12 @@ import scala.concurrent.duration._ import akka.actor._ import akka.remote.{DisassociatedEvent, RemotingLifecycleEvent} + import org.apache.spark.{Logging, SparkConf, SparkException} import org.apache.spark.deploy.{ExecutorDescription, ExecutorState} import org.apache.spark.deploy.DeployMessages._ -import org.apache.spark.deploy.master.Master +import org.apache.spark.deploy.master.{DriverState, Master} +import org.apache.spark.deploy.master.DriverState.DriverState import org.apache.spark.deploy.worker.ui.WorkerWebUI import org.apache.spark.metrics.MetricsSystem import org.apache.spark.util.{AkkaUtils, Utils} @@ -44,6 +46,8 @@ private[spark] class Worker( cores: Int, memory: Int, masterUrls: Array[String], + actorSystemName: String, + actorName: String, workDirPath: String = null, val conf: SparkConf) extends Actor with Logging { @@ -55,7 +59,7 @@ private[spark] class Worker( val DATE_FORMAT = new SimpleDateFormat("yyyyMMddHHmmss") // For worker and executor IDs // Send a heartbeat every (heartbeat timeout) / 4 milliseconds - val HEARTBEAT_MILLIS = conf.get("spark.worker.timeout", "60").toLong * 1000 / 4 + val HEARTBEAT_MILLIS = conf.getLong("spark.worker.timeout", 60) * 1000 / 4 val REGISTRATION_TIMEOUT = 20.seconds val REGISTRATION_RETRIES = 3 @@ -68,6 +72,7 @@ private[spark] class Worker( var masterAddress: Address = null var activeMasterUrl: String = "" var activeMasterWebUiUrl : String = "" + val akkaUrl = "akka.tcp://%s@%s:%s/user/%s".format(actorSystemName, host, port, actorName) @volatile var registered = false @volatile var connected = false val workerId = generateWorkerId() @@ -75,6 +80,9 @@ private[spark] class Worker( var workDir: File = null val executors = new HashMap[String, ExecutorRunner] val finishedExecutors = new HashMap[String, ExecutorRunner] + val drivers = new HashMap[String, DriverRunner] + val finishedDrivers = new HashMap[String, DriverRunner] + val publicAddress = { val envVar = System.getenv("SPARK_PUBLIC_DNS") if (envVar != null) envVar else host @@ -185,7 +193,10 @@ private[spark] class Worker( val execs = executors.values. map(e => new ExecutorDescription(e.appId, e.execId, e.cores, e.state)) - sender ! WorkerSchedulerStateResponse(workerId, execs.toList) + sender ! WorkerSchedulerStateResponse(workerId, execs.toList, drivers.keys.toSeq) + + case Heartbeat => + logInfo(s"Received heartbeat from driver ${sender.path}") case RegisterWorkerFailed(message) => if (!registered) { @@ -199,7 +210,7 @@ private[spark] class Worker( } else { logInfo("Asked to launch executor %s/%d for %s".format(appId, execId, appDesc.name)) val manager = new ExecutorRunner(appId, execId, appDesc, cores_, memory_, - self, workerId, host, new File(execSparkHome_), workDir, ExecutorState.RUNNING) + self, workerId, host, new File(execSparkHome_), workDir, akkaUrl, ExecutorState.RUNNING) executors(appId + "/" + execId) = manager manager.start() coresUsed += cores_ @@ -219,8 +230,8 @@ private[spark] class Worker( logInfo("Executor " + fullId + " finished with state " + state + message.map(" message " + _).getOrElse("") + exitStatus.map(" exitStatus " + _).getOrElse("")) - finishedExecutors(fullId) = executor executors -= fullId + finishedExecutors(fullId) = executor coresUsed -= executor.cores memoryUsed -= executor.memory } @@ -239,13 +250,52 @@ private[spark] class Worker( } } + case LaunchDriver(driverId, driverDesc) => { + logInfo(s"Asked to launch driver $driverId") + val driver = new DriverRunner(driverId, workDir, sparkHome, driverDesc, self, akkaUrl) + drivers(driverId) = driver + driver.start() + + coresUsed += driverDesc.cores + memoryUsed += driverDesc.mem + } + + case KillDriver(driverId) => { + logInfo(s"Asked to kill driver $driverId") + drivers.get(driverId) match { + case Some(runner) => + runner.kill() + case None => + logError(s"Asked to kill unknown driver $driverId") + } + } + + case DriverStateChanged(driverId, state, exception) => { + state match { + case DriverState.ERROR => + logWarning(s"Driver $driverId failed with unrecoverable exception: ${exception.get}") + case DriverState.FINISHED => + logInfo(s"Driver $driverId exited successfully") + case DriverState.KILLED => + logInfo(s"Driver $driverId was killed by user") + } + masterLock.synchronized { + master ! DriverStateChanged(driverId, state, exception) + } + val driver = drivers.remove(driverId).get + finishedDrivers(driverId) = driver + memoryUsed -= driver.driverDesc.mem + coresUsed -= driver.driverDesc.cores + } + case x: DisassociatedEvent if x.remoteAddress == masterAddress => logInfo(s"$x Disassociated !") masterDisconnected() case RequestWorkerState => { sender ! WorkerStateResponse(host, port, workerId, executors.values.toList, - finishedExecutors.values.toList, activeMasterUrl, cores, memory, + finishedExecutors.values.toList, drivers.values.toList, + finishedDrivers.values.toList, activeMasterUrl, cores, memory, coresUsed, memoryUsed, activeMasterWebUiUrl) } } @@ -282,10 +332,11 @@ private[spark] object Worker { // The LocalSparkCluster runs multiple local sparkWorkerX actor systems val conf = new SparkConf val systemName = "sparkWorker" + workerNumber.map(_.toString).getOrElse("") + val actorName = "Worker" val (actorSystem, boundPort) = AkkaUtils.createActorSystem(systemName, host, port, conf = conf) actorSystem.actorOf(Props(classOf[Worker], host, boundPort, webUiPort, cores, memory, - masterUrls, workDir, conf), name = "Worker") + masterUrls, systemName, actorName, workDir, conf), name = actorName) (actorSystem, boundPort) } diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/WorkerWatcher.scala b/core/src/main/scala/org/apache/spark/deploy/worker/WorkerWatcher.scala new file mode 100644 index 0000000000..0e0d0cd626 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/deploy/worker/WorkerWatcher.scala @@ -0,0 +1,55 @@ +package org.apache.spark.deploy.worker + +import akka.actor.{Actor, Address, AddressFromURIString} +import akka.remote.{AssociatedEvent, AssociationErrorEvent, AssociationEvent, DisassociatedEvent, RemotingLifecycleEvent} + +import org.apache.spark.Logging +import org.apache.spark.deploy.DeployMessages.SendHeartbeat + +/** + * Actor which connects to a worker process and terminates the JVM if the connection is severed. + * Provides fate sharing between a worker and its associated child processes. + */ +private[spark] class WorkerWatcher(workerUrl: String) extends Actor + with Logging { + override def preStart() { + context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent]) + + logInfo(s"Connecting to worker $workerUrl") + val worker = context.actorSelection(workerUrl) + worker ! SendHeartbeat // need to send a message here to initiate connection + } + + // Used to avoid shutting down JVM during tests + private[deploy] var isShutDown = false + private[deploy] def setTesting(testing: Boolean) = isTesting = testing + private var isTesting = false + + // Lets us filter events only from the worker's actor system + private val expectedHostPort = AddressFromURIString(workerUrl).hostPort + private def isWorker(address: Address) = address.hostPort == expectedHostPort + + def exitNonZero() = if (isTesting) isShutDown = true else System.exit(-1) + + override def receive = { + case AssociatedEvent(localAddress, remoteAddress, inbound) if isWorker(remoteAddress) => + logInfo(s"Successfully connected to $workerUrl") + + case AssociationErrorEvent(cause, localAddress, remoteAddress, inbound) + if isWorker(remoteAddress) => + // These logs may not be seen if the worker (and associated pipe) has died + logError(s"Could not initialize connection to worker $workerUrl. Exiting.") + logError(s"Error was: $cause") + exitNonZero() + + case DisassociatedEvent(localAddress, remoteAddress, inbound) if isWorker(remoteAddress) => + // This log message will never be seen + logError(s"Lost connection to worker actor $workerUrl. Exiting.") + exitNonZero() + + case e: AssociationEvent => + // pass through association events relating to other remote actor systems + + case e => logWarning(s"Received unexpected actor system event: $e") + } +}
\ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/ui/IndexPage.scala b/core/src/main/scala/org/apache/spark/deploy/worker/ui/IndexPage.scala index 0d59048313..925c6fb183 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/ui/IndexPage.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/ui/IndexPage.scala @@ -17,24 +17,20 @@ package org.apache.spark.deploy.worker.ui -import javax.servlet.http.HttpServletRequest - -import scala.xml.Node - -import scala.concurrent.duration._ import scala.concurrent.Await +import scala.xml.Node import akka.pattern.ask - +import javax.servlet.http.HttpServletRequest import net.liftweb.json.JsonAST.JValue import org.apache.spark.deploy.JsonProtocol import org.apache.spark.deploy.DeployMessages.{RequestWorkerState, WorkerStateResponse} -import org.apache.spark.deploy.worker.ExecutorRunner +import org.apache.spark.deploy.master.DriverState +import org.apache.spark.deploy.worker.{DriverRunner, ExecutorRunner} import org.apache.spark.ui.UIUtils import org.apache.spark.util.Utils - private[spark] class IndexPage(parent: WorkerWebUI) { val workerActor = parent.worker.self val worker = parent.worker @@ -56,6 +52,16 @@ private[spark] class IndexPage(parent: WorkerWebUI) { val finishedExecutorTable = UIUtils.listingTable(executorHeaders, executorRow, workerState.finishedExecutors) + val driverHeaders = Seq("DriverID", "Main Class", "State", "Cores", "Memory", "Logs", "Notes") + val runningDrivers = workerState.drivers.sortBy(_.driverId).reverse + val runningDriverTable = UIUtils.listingTable(driverHeaders, driverRow, runningDrivers) + val finishedDrivers = workerState.finishedDrivers.sortBy(_.driverId).reverse + def finishedDriverTable = UIUtils.listingTable(driverHeaders, driverRow, finishedDrivers) + + // For now we only show driver information if the user has submitted drivers to the cluster. + // This is until we integrate the notion of drivers and applications in the UI. + def hasDrivers = runningDrivers.length > 0 || finishedDrivers.length > 0 + val content = <div class="row-fluid"> <!-- Worker Details --> <div class="span12"> @@ -79,11 +85,33 @@ private[spark] class IndexPage(parent: WorkerWebUI) { </div> </div> + <div> + {if (hasDrivers) + <div class="row-fluid"> <!-- Running Drivers --> + <div class="span12"> + <h4> Running Drivers {workerState.drivers.size} </h4> + {runningDriverTable} + </div> + </div> + } + </div> + <div class="row-fluid"> <!-- Finished Executors --> <div class="span12"> <h4> Finished Executors </h4> {finishedExecutorTable} </div> + </div> + + <div> + {if (hasDrivers) + <div class="row-fluid"> <!-- Finished Drivers --> + <div class="span12"> + <h4> Finished Drivers </h4> + {finishedDriverTable} + </div> + </div> + } </div>; UIUtils.basicSparkPage(content, "Spark Worker at %s:%s".format( @@ -111,6 +139,27 @@ private[spark] class IndexPage(parent: WorkerWebUI) { .format(executor.appId, executor.execId)}>stderr</a> </td> </tr> + } + def driverRow(driver: DriverRunner): Seq[Node] = { + <tr> + <td>{driver.driverId}</td> + <td>{driver.driverDesc.command.arguments(1)}</td> + <td>{driver.finalState.getOrElse(DriverState.RUNNING)}</td> + <td sorttable_customkey={driver.driverDesc.cores.toString}> + {driver.driverDesc.cores.toString} + </td> + <td sorttable_customkey={driver.driverDesc.mem.toString}> + {Utils.megabytesToString(driver.driverDesc.mem)} + </td> + <td> + <a href={s"logPage?driverId=${driver.driverId}&logType=stdout"}>stdout</a> + <a href={s"logPage?driverId=${driver.driverId}&logType=stderr"}>stderr</a> + </td> + <td> + {driver.finalException.getOrElse("")} + </td> + </tr> + } } diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerWebUI.scala b/core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerWebUI.scala index c382034c99..8daa47b2b2 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerWebUI.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/ui/WorkerWebUI.scala @@ -69,30 +69,48 @@ class WorkerWebUI(val worker: Worker, val workDir: File, requestedPort: Option[I def log(request: HttpServletRequest): String = { val defaultBytes = 100 * 1024 - val appId = request.getParameter("appId") - val executorId = request.getParameter("executorId") + + val appId = Option(request.getParameter("appId")) + val executorId = Option(request.getParameter("executorId")) + val driverId = Option(request.getParameter("driverId")) val logType = request.getParameter("logType") val offset = Option(request.getParameter("offset")).map(_.toLong) val byteLength = Option(request.getParameter("byteLength")).map(_.toInt).getOrElse(defaultBytes) - val path = "%s/%s/%s/%s".format(workDir.getPath, appId, executorId, logType) + + val path = (appId, executorId, driverId) match { + case (Some(a), Some(e), None) => + s"${workDir.getPath}/$appId/$executorId/$logType" + case (None, None, Some(d)) => + s"${workDir.getPath}/$driverId/$logType" + case _ => + throw new Exception("Request must specify either application or driver identifiers") + } val (startByte, endByte) = getByteRange(path, offset, byteLength) val file = new File(path) val logLength = file.length - val pre = "==== Bytes %s-%s of %s of %s/%s/%s ====\n" - .format(startByte, endByte, logLength, appId, executorId, logType) + val pre = s"==== Bytes $startByte-$endByte of $logLength of $path ====\n" pre + Utils.offsetBytes(path, startByte, endByte) } def logPage(request: HttpServletRequest): Seq[scala.xml.Node] = { val defaultBytes = 100 * 1024 - val appId = request.getParameter("appId") - val executorId = request.getParameter("executorId") + val appId = Option(request.getParameter("appId")) + val executorId = Option(request.getParameter("executorId")) + val driverId = Option(request.getParameter("driverId")) val logType = request.getParameter("logType") val offset = Option(request.getParameter("offset")).map(_.toLong) val byteLength = Option(request.getParameter("byteLength")).map(_.toInt).getOrElse(defaultBytes) - val path = "%s/%s/%s/%s".format(workDir.getPath, appId, executorId, logType) + + val (path, params) = (appId, executorId, driverId) match { + case (Some(a), Some(e), None) => + (s"${workDir.getPath}/$a/$e/$logType", s"appId=$a&executorId=$e") + case (None, None, Some(d)) => + (s"${workDir.getPath}/$d/$logType", s"driverId=$d") + case _ => + throw new Exception("Request must specify either application or driver identifiers") + } val (startByte, endByte) = getByteRange(path, offset, byteLength) val file = new File(path) @@ -106,9 +124,8 @@ class WorkerWebUI(val worker: Worker, val workDir: File, requestedPort: Option[I val backButton = if (startByte > 0) { - <a href={"?appId=%s&executorId=%s&logType=%s&offset=%s&byteLength=%s" - .format(appId, executorId, logType, math.max(startByte-byteLength, 0), - byteLength)}> + <a href={"?%s&logType=%s&offset=%s&byteLength=%s" + .format(params, logType, math.max(startByte-byteLength, 0), byteLength)}> <button type="button" class="btn btn-default"> Previous {Utils.bytesToString(math.min(byteLength, startByte))} </button> @@ -122,8 +139,8 @@ class WorkerWebUI(val worker: Worker, val workDir: File, requestedPort: Option[I val nextButton = if (endByte < logLength) { - <a href={"?appId=%s&executorId=%s&logType=%s&offset=%s&byteLength=%s". - format(appId, executorId, logType, endByte, byteLength)}> + <a href={"?%s&logType=%s&offset=%s&byteLength=%s". + format(params, logType, endByte, byteLength)}> <button type="button" class="btn btn-default"> Next {Utils.bytesToString(math.min(byteLength, logLength-endByte))} </button> diff --git a/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala b/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala index 53a2b94a52..f9e43e0e94 100644 --- a/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala +++ b/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala @@ -24,8 +24,9 @@ import akka.remote._ import org.apache.spark.{SparkConf, SparkContext, Logging} import org.apache.spark.TaskState.TaskState +import org.apache.spark.deploy.worker.WorkerWatcher import org.apache.spark.scheduler.cluster.CoarseGrainedClusterMessages._ -import org.apache.spark.util.{Utils, AkkaUtils} +import org.apache.spark.util.{AkkaUtils, Utils} private[spark] class CoarseGrainedExecutorBackend( driverUrl: String, @@ -91,7 +92,8 @@ private[spark] class CoarseGrainedExecutorBackend( } private[spark] object CoarseGrainedExecutorBackend { - def run(driverUrl: String, executorId: String, hostname: String, cores: Int) { + def run(driverUrl: String, executorId: String, hostname: String, cores: Int, + workerUrl: Option[String]) { // Debug code Utils.checkHost(hostname) @@ -105,17 +107,24 @@ private[spark] object CoarseGrainedExecutorBackend { actorSystem.actorOf( Props(classOf[CoarseGrainedExecutorBackend], driverUrl, executorId, sparkHostPort, cores), name = "Executor") + workerUrl.foreach{ url => + actorSystem.actorOf(Props(classOf[WorkerWatcher], url), name = "WorkerWatcher") + } actorSystem.awaitTermination() } def main(args: Array[String]) { - if (args.length < 4) { - //the reason we allow the last appid argument is to make it easy to kill rogue executors - System.err.println( - "Usage: CoarseGrainedExecutorBackend <driverUrl> <executorId> <hostname> <cores> " + - "[<appid>]") - System.exit(1) + args.length match { + case x if x < 4 => + System.err.println( + // Worker url is used in spark standalone mode to enforce fate-sharing with worker + "Usage: CoarseGrainedExecutorBackend <driverUrl> <executorId> <hostname> " + + "<cores> [<workerUrl>]") + System.exit(1) + case 4 => + run(args(0), args(1), args(2), args(3).toInt, None) + case x if x > 4 => + run(args(0), args(1), args(2), args(3).toInt, Some(args(4))) } - run(args(0), args(1), args(2), args(3).toInt) } } diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala index 3c92c205ea..e51d274d33 100644 --- a/core/src/main/scala/org/apache/spark/executor/Executor.scala +++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala @@ -141,11 +141,6 @@ private[spark] class Executor( val tr = runningTasks.get(taskId) if (tr != null) { tr.kill() - // We remove the task also in the finally block in TaskRunner.run. - // The reason we need to remove it here is because killTask might be called before the task - // is even launched, and never reaching that finally block. ConcurrentHashMap's remove is - // idempotent. - runningTasks.remove(taskId) } } @@ -167,6 +162,8 @@ private[spark] class Executor( class TaskRunner(execBackend: ExecutorBackend, taskId: Long, serializedTask: ByteBuffer) extends Runnable { + object TaskKilledException extends Exception + @volatile private var killed = false @volatile private var task: Task[Any] = _ @@ -200,9 +197,11 @@ private[spark] class Executor( // If this task has been killed before we deserialized it, let's quit now. Otherwise, // continue executing the task. if (killed) { - logInfo("Executor killed task " + taskId) - execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled)) - return + // Throw an exception rather than returning, because returning within a try{} block + // causes a NonLocalReturnControl exception to be thrown. The NonLocalReturnControl + // exception will be caught by the catch block, leading to an incorrect ExceptionFailure + // for the task. + throw TaskKilledException } attemptedTask = Some(task) @@ -216,9 +215,7 @@ private[spark] class Executor( // If the task has been killed, let's fail it. if (task.killed) { - logInfo("Executor killed task " + taskId) - execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled)) - return + throw TaskKilledException } val resultSer = SparkEnv.get.serializer.newInstance() @@ -260,6 +257,11 @@ private[spark] class Executor( execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason)) } + case TaskKilledException => { + logInfo("Executor killed task " + taskId) + execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled)) + } + case t: Throwable => { val serviceTime = (System.currentTimeMillis() - taskStart).toInt val metrics = attemptedTask.flatMap(t => t.metrics) diff --git a/core/src/main/scala/org/apache/spark/io/CompressionCodec.scala b/core/src/main/scala/org/apache/spark/io/CompressionCodec.scala index a1e98845f6..5980177320 100644 --- a/core/src/main/scala/org/apache/spark/io/CompressionCodec.scala +++ b/core/src/main/scala/org/apache/spark/io/CompressionCodec.scala @@ -71,7 +71,7 @@ class LZFCompressionCodec(conf: SparkConf) extends CompressionCodec { class SnappyCompressionCodec(conf: SparkConf) extends CompressionCodec { override def compressedOutputStream(s: OutputStream): OutputStream = { - val blockSize = conf.get("spark.io.compression.snappy.block.size", "32768").toInt + val blockSize = conf.getInt("spark.io.compression.snappy.block.size", 32768) new SnappyOutputStream(s, blockSize) } diff --git a/core/src/main/scala/org/apache/spark/network/ConnectionManager.scala b/core/src/main/scala/org/apache/spark/network/ConnectionManager.scala index 46c40d0a2a..e6e01783c8 100644 --- a/core/src/main/scala/org/apache/spark/network/ConnectionManager.scala +++ b/core/src/main/scala/org/apache/spark/network/ConnectionManager.scala @@ -54,22 +54,22 @@ private[spark] class ConnectionManager(port: Int, conf: SparkConf) extends Loggi private val selector = SelectorProvider.provider.openSelector() private val handleMessageExecutor = new ThreadPoolExecutor( - conf.get("spark.core.connection.handler.threads.min", "20").toInt, - conf.get("spark.core.connection.handler.threads.max", "60").toInt, - conf.get("spark.core.connection.handler.threads.keepalive", "60").toInt, TimeUnit.SECONDS, + conf.getInt("spark.core.connection.handler.threads.min", 20), + conf.getInt("spark.core.connection.handler.threads.max", 60), + conf.getInt("spark.core.connection.handler.threads.keepalive", 60), TimeUnit.SECONDS, new LinkedBlockingDeque[Runnable]()) private val handleReadWriteExecutor = new ThreadPoolExecutor( - conf.get("spark.core.connection.io.threads.min", "4").toInt, - conf.get("spark.core.connection.io.threads.max", "32").toInt, - conf.get("spark.core.connection.io.threads.keepalive", "60").toInt, TimeUnit.SECONDS, + conf.getInt("spark.core.connection.io.threads.min", 4), + conf.getInt("spark.core.connection.io.threads.max", 32), + conf.getInt("spark.core.connection.io.threads.keepalive", 60), TimeUnit.SECONDS, new LinkedBlockingDeque[Runnable]()) // Use a different, yet smaller, thread pool - infrequently used with very short lived tasks : which should be executed asap private val handleConnectExecutor = new ThreadPoolExecutor( - conf.get("spark.core.connection.connect.threads.min", "1").toInt, - conf.get("spark.core.connection.connect.threads.max", "8").toInt, - conf.get("spark.core.connection.connect.threads.keepalive", "60").toInt, TimeUnit.SECONDS, + conf.getInt("spark.core.connection.connect.threads.min", 1), + conf.getInt("spark.core.connection.connect.threads.max", 8), + conf.getInt("spark.core.connection.connect.threads.keepalive", 60), TimeUnit.SECONDS, new LinkedBlockingDeque[Runnable]()) private val serverChannel = ServerSocketChannel.open() diff --git a/core/src/main/scala/org/apache/spark/network/netty/ShuffleCopier.scala b/core/src/main/scala/org/apache/spark/network/netty/ShuffleCopier.scala index b729eb11c5..d87157e12c 100644 --- a/core/src/main/scala/org/apache/spark/network/netty/ShuffleCopier.scala +++ b/core/src/main/scala/org/apache/spark/network/netty/ShuffleCopier.scala @@ -36,7 +36,7 @@ private[spark] class ShuffleCopier(conf: SparkConf) extends Logging { resultCollectCallback: (BlockId, Long, ByteBuf) => Unit) { val handler = new ShuffleCopier.ShuffleClientHandler(resultCollectCallback) - val connectTimeout = conf.get("spark.shuffle.netty.connect.timeout", "60000").toInt + val connectTimeout = conf.getInt("spark.shuffle.netty.connect.timeout", 60000) val fc = new FileClient(handler, connectTimeout) try { diff --git a/core/src/main/scala/org/apache/spark/rdd/CheckpointRDD.scala b/core/src/main/scala/org/apache/spark/rdd/CheckpointRDD.scala index 6d4f46125f..83109d1a6f 100644 --- a/core/src/main/scala/org/apache/spark/rdd/CheckpointRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/CheckpointRDD.scala @@ -97,7 +97,7 @@ private[spark] object CheckpointRDD extends Logging { throw new IOException("Checkpoint failed: temporary path " + tempOutputPath + " already exists") } - val bufferSize = env.conf.get("spark.buffer.size", "65536").toInt + val bufferSize = env.conf.getInt("spark.buffer.size", 65536) val fileOutputStream = if (blockSize < 0) { fs.create(tempOutputPath, false, bufferSize) @@ -131,7 +131,7 @@ private[spark] object CheckpointRDD extends Logging { ): Iterator[T] = { val env = SparkEnv.get val fs = path.getFileSystem(broadcastedConf.value.value) - val bufferSize = env.conf.get("spark.buffer.size", "65536").toInt + val bufferSize = env.conf.getInt("spark.buffer.size", 65536) val fileInputStream = fs.open(path, bufferSize) val serializer = env.serializer.newInstance() val deserializeStream = serializer.deserializeStream(fileInputStream) diff --git a/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala b/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala index 2662d48c84..73d15b9082 100644 --- a/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/NewHadoopRDD.scala @@ -76,7 +76,7 @@ class NewHadoopRDD[K, V]( val split = theSplit.asInstanceOf[NewHadoopPartition] logInfo("Input split: " + split.serializableHadoopSplit) val conf = confBroadcast.value.value - val attemptId = newTaskAttemptID(jobtrackerId, id, true, split.index, 0) + val attemptId = newTaskAttemptID(jobtrackerId, id, isMap = true, split.index, 0) val hadoopAttemptContext = newTaskAttemptContext(conf, attemptId) val format = inputFormatClass.newInstance if (format.isInstanceOf[Configurable]) { diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index 04a8d05988..c118ddfc01 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -18,35 +18,34 @@ package org.apache.spark.rdd import java.nio.ByteBuffer -import java.util.Date import java.text.SimpleDateFormat +import java.util.Date import java.util.{HashMap => JHashMap} -import scala.collection.{mutable, Map} +import scala.collection.Map +import scala.collection.mutable import scala.collection.mutable.ArrayBuffer import scala.collection.JavaConversions._ import scala.reflect.{ClassTag, classTag} -import org.apache.hadoop.mapred._ -import org.apache.hadoop.io.compress.CompressionCodec import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.Path import org.apache.hadoop.io.SequenceFile.CompressionType -import org.apache.hadoop.mapred.FileOutputFormat -import org.apache.hadoop.mapred.OutputFormat +import org.apache.hadoop.io.compress.CompressionCodec +import org.apache.hadoop.mapred.{FileOutputCommitter, FileOutputFormat, JobConf, OutputFormat} import org.apache.hadoop.mapreduce.{OutputFormat => NewOutputFormat} -import org.apache.hadoop.mapreduce.lib.output.{FileOutputFormat => NewFileOutputFormat} -import org.apache.hadoop.mapreduce.SparkHadoopMapReduceUtil import org.apache.hadoop.mapreduce.{Job => NewAPIHadoopJob} import org.apache.hadoop.mapreduce.{RecordWriter => NewRecordWriter} +import org.apache.hadoop.mapreduce.lib.output.{FileOutputFormat => NewFileOutputFormat} import com.clearspring.analytics.stream.cardinality.HyperLogLog +// SparkHadoopWriter and SparkHadoopMapReduceUtil are actually source files defined in Spark. +import org.apache.hadoop.mapred.SparkHadoopWriter +import org.apache.hadoop.mapreduce.SparkHadoopMapReduceUtil import org.apache.spark._ import org.apache.spark.SparkContext._ import org.apache.spark.partial.{BoundedDouble, PartialResult} -import org.apache.spark.Aggregator -import org.apache.spark.Partitioner import org.apache.spark.Partitioner.defaultPartitioner import org.apache.spark.util.SerializableHyperLogLog @@ -120,9 +119,9 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) } /** - * Merge the values for each key using an associative function and a neutral "zero value" which may - * be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for - * list concatenation, 0 for addition, or 1 for multiplication.). + * Merge the values for each key using an associative function and a neutral "zero value" which + * may be added to the result an arbitrary number of times, and must not change the result + * (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.). */ def foldByKey(zeroValue: V, partitioner: Partitioner)(func: (V, V) => V): RDD[(K, V)] = { // Serialize the zero value to a byte array so that we can get a new clone of it on each key @@ -138,18 +137,18 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) } /** - * Merge the values for each key using an associative function and a neutral "zero value" which may - * be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for - * list concatenation, 0 for addition, or 1 for multiplication.). + * Merge the values for each key using an associative function and a neutral "zero value" which + * may be added to the result an arbitrary number of times, and must not change the result + * (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.). */ def foldByKey(zeroValue: V, numPartitions: Int)(func: (V, V) => V): RDD[(K, V)] = { foldByKey(zeroValue, new HashPartitioner(numPartitions))(func) } /** - * Merge the values for each key using an associative function and a neutral "zero value" which may - * be added to the result an arbitrary number of times, and must not change the result (e.g., Nil for - * list concatenation, 0 for addition, or 1 for multiplication.). + * Merge the values for each key using an associative function and a neutral "zero value" which + * may be added to the result an arbitrary number of times, and must not change the result + * (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.). */ def foldByKey(zeroValue: V)(func: (V, V) => V): RDD[(K, V)] = { foldByKey(zeroValue, defaultPartitioner(self))(func) @@ -226,7 +225,7 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) } /** - * Return approximate number of distinct values for each key in this RDD. + * Return approximate number of distinct values for each key in this RDD. * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in * more accurate counts but increase the memory footprint and vise versa. HashPartitions the @@ -579,7 +578,8 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) */ def saveAsHadoopFile[F <: OutputFormat[K, V]]( path: String, codec: Class[_ <: CompressionCodec]) (implicit fm: ClassTag[F]) { - saveAsHadoopFile(path, getKeyClass, getValueClass, fm.runtimeClass.asInstanceOf[Class[F]], codec) + val runtimeClass = fm.runtimeClass + saveAsHadoopFile(path, getKeyClass, getValueClass, runtimeClass.asInstanceOf[Class[F]], codec) } /** @@ -599,7 +599,8 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) keyClass: Class[_], valueClass: Class[_], outputFormatClass: Class[_ <: NewOutputFormat[_, _]], - conf: Configuration = self.context.hadoopConfiguration) { + conf: Configuration = self.context.hadoopConfiguration) + { val job = new NewAPIHadoopJob(conf) job.setOutputKeyClass(keyClass) job.setOutputValueClass(valueClass) @@ -613,7 +614,8 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) // around by taking a mod. We expect that no task will be attempted 2 billion times. val attemptNumber = (context.attemptId % Int.MaxValue).toInt /* "reduce task" <split #> <attempt # = spark task #> */ - val attemptId = newTaskAttemptID(jobtrackerID, stageId, false, context.partitionId, attemptNumber) + val attemptId = newTaskAttemptID(jobtrackerID, stageId, isMap = false, context.partitionId, + attemptNumber) val hadoopContext = newTaskAttemptContext(wrappedConf.value, attemptId) val format = outputFormatClass.newInstance val committer = format.getOutputCommitter(hadoopContext) @@ -632,13 +634,12 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) * however we're only going to use this local OutputCommitter for * setupJob/commitJob, so we just use a dummy "map" task. */ - val jobAttemptId = newTaskAttemptID(jobtrackerID, stageId, true, 0, 0) + val jobAttemptId = newTaskAttemptID(jobtrackerID, stageId, isMap = true, 0, 0) val jobTaskContext = newTaskAttemptContext(wrappedConf.value, jobAttemptId) val jobCommitter = jobFormat.getOutputCommitter(jobTaskContext) jobCommitter.setupJob(jobTaskContext) val count = self.context.runJob(self, writeShard _).sum jobCommitter.commitJob(jobTaskContext) - jobCommitter.cleanupJob(jobTaskContext) } /** @@ -668,7 +669,9 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) codec: Option[Class[_ <: CompressionCodec]] = None) { conf.setOutputKeyClass(keyClass) conf.setOutputValueClass(valueClass) - // conf.setOutputFormat(outputFormatClass) // Doesn't work in Scala 2.9 due to what may be a generics bug + // Doesn't work in Scala 2.9 due to what may be a generics bug + // TODO: Should we uncomment this for Scala 2.10? + // conf.setOutputFormat(outputFormatClass) conf.set("mapred.output.format.class", outputFormatClass.getName) for (c <- codec) { conf.setCompressMapOutput(true) @@ -702,7 +705,8 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) throw new SparkException("Output value class not set") } - logInfo("Saving as hadoop file of type (" + keyClass.getSimpleName+ ", " + valueClass.getSimpleName+ ")") + logDebug("Saving as hadoop file of type (" + keyClass.getSimpleName + ", " + + valueClass.getSimpleName+ ")") val writer = new SparkHadoopWriter(conf) writer.preSetup() @@ -728,7 +732,6 @@ class PairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) self.context.runJob(self, writeToFile _) writer.commitJob() - writer.cleanup() } /** diff --git a/core/src/main/scala/org/apache/spark/rdd/PartitionerAwareUnionRDD.scala b/core/src/main/scala/org/apache/spark/rdd/PartitionerAwareUnionRDD.scala new file mode 100644 index 0000000000..4c625d062e --- /dev/null +++ b/core/src/main/scala/org/apache/spark/rdd/PartitionerAwareUnionRDD.scala @@ -0,0 +1,110 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.rdd + +import scala.reflect.ClassTag +import java.io.{ObjectOutputStream, IOException} +import org.apache.spark.{TaskContext, OneToOneDependency, SparkContext, Partition} + + +/** + * Class representing partitions of PartitionerAwareUnionRDD, which maintains the list of corresponding partitions + * of parent RDDs. + */ +private[spark] +class PartitionerAwareUnionRDDPartition( + @transient val rdds: Seq[RDD[_]], + val idx: Int + ) extends Partition { + var parents = rdds.map(_.partitions(idx)).toArray + + override val index = idx + override def hashCode(): Int = idx + + @throws(classOf[IOException]) + private def writeObject(oos: ObjectOutputStream) { + // Update the reference to parent partition at the time of task serialization + parents = rdds.map(_.partitions(index)).toArray + oos.defaultWriteObject() + } +} + +/** + * Class representing an RDD that can take multiple RDDs partitioned by the same partitioner and + * unify them into a single RDD while preserving the partitioner. So m RDDs with p partitions each + * will be unified to a single RDD with p partitions and the same partitioner. The preferred + * location for each partition of the unified RDD will be the most common preferred location + * of the corresponding partitions of the parent RDDs. For example, location of partition 0 + * of the unified RDD will be where most of partition 0 of the parent RDDs are located. + */ +private[spark] +class PartitionerAwareUnionRDD[T: ClassTag]( + sc: SparkContext, + var rdds: Seq[RDD[T]] + ) extends RDD[T](sc, rdds.map(x => new OneToOneDependency(x))) { + require(rdds.length > 0) + require(rdds.flatMap(_.partitioner).toSet.size == 1, + "Parent RDDs have different partitioners: " + rdds.flatMap(_.partitioner)) + + override val partitioner = rdds.head.partitioner + + override def getPartitions: Array[Partition] = { + val numPartitions = partitioner.get.numPartitions + (0 until numPartitions).map(index => { + new PartitionerAwareUnionRDDPartition(rdds, index) + }).toArray + } + + // Get the location where most of the partitions of parent RDDs are located + override def getPreferredLocations(s: Partition): Seq[String] = { + logDebug("Finding preferred location for " + this + ", partition " + s.index) + val parentPartitions = s.asInstanceOf[PartitionerAwareUnionRDDPartition].parents + val locations = rdds.zip(parentPartitions).flatMap { + case (rdd, part) => { + val parentLocations = currPrefLocs(rdd, part) + logDebug("Location of " + rdd + " partition " + part.index + " = " + parentLocations) + parentLocations + } + } + val location = if (locations.isEmpty) { + None + } else { + // Find the location that maximum number of parent partitions prefer + Some(locations.groupBy(x => x).maxBy(_._2.length)._1) + } + logDebug("Selected location for " + this + ", partition " + s.index + " = " + location) + location.toSeq + } + + override def compute(s: Partition, context: TaskContext): Iterator[T] = { + val parentPartitions = s.asInstanceOf[PartitionerAwareUnionRDDPartition].parents + rdds.zip(parentPartitions).iterator.flatMap { + case (rdd, p) => rdd.iterator(p, context) + } + } + + override def clearDependencies() { + super.clearDependencies() + rdds = null + } + + // Get the *current* preferred locations from the DAGScheduler (as opposed to the static ones) + private def currPrefLocs(rdd: RDD[_], part: Partition): Seq[String] = { + rdd.context.getPreferredLocs(rdd, part.index).map(tl => tl.host) + } +} diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 6a7b0f8a86..f9dc12eee3 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -23,7 +23,6 @@ import scala.collection.Map import scala.collection.JavaConversions.mapAsScalaMap import scala.collection.mutable.ArrayBuffer -import scala.collection.mutable.HashMap import scala.reflect.{classTag, ClassTag} import org.apache.hadoop.io.BytesWritable @@ -52,11 +51,13 @@ import org.apache.spark._ * partitioned collection of elements that can be operated on in parallel. This class contains the * basic operations available on all RDDs, such as `map`, `filter`, and `persist`. In addition, * [[org.apache.spark.rdd.PairRDDFunctions]] contains operations available only on RDDs of key-value - * pairs, such as `groupByKey` and `join`; [[org.apache.spark.rdd.DoubleRDDFunctions]] contains - * operations available only on RDDs of Doubles; and [[org.apache.spark.rdd.SequenceFileRDDFunctions]] - * contains operations available on RDDs that can be saved as SequenceFiles. These operations are - * automatically available on any RDD of the right type (e.g. RDD[(Int, Int)] through implicit - * conversions when you `import org.apache.spark.SparkContext._`. + * pairs, such as `groupByKey` and `join`; + * [[org.apache.spark.rdd.DoubleRDDFunctions]] contains operations available only on RDDs of + * Doubles; and + * [[org.apache.spark.rdd.SequenceFileRDDFunctions]] contains operations available on RDDs that + * can be saved as SequenceFiles. + * These operations are automatically available on any RDD of the right type (e.g. RDD[(Int, Int)] + * through implicit conversions when you `import org.apache.spark.SparkContext._`. * * Internally, each RDD is characterized by five main properties: * @@ -235,12 +236,9 @@ abstract class RDD[T: ClassTag]( /** * Compute an RDD partition or read it from a checkpoint if the RDD is checkpointing. */ - private[spark] def computeOrReadCheckpoint(split: Partition, context: TaskContext): Iterator[T] = { - if (isCheckpointed) { - firstParent[T].iterator(split, context) - } else { - compute(split, context) - } + private[spark] def computeOrReadCheckpoint(split: Partition, context: TaskContext): Iterator[T] = + { + if (isCheckpointed) firstParent[T].iterator(split, context) else compute(split, context) } // Transformations (return a new RDD) @@ -268,6 +266,9 @@ abstract class RDD[T: ClassTag]( def distinct(numPartitions: Int): RDD[T] = map(x => (x, null)).reduceByKey((x, y) => x, numPartitions).map(_._1) + /** + * Return a new RDD containing the distinct elements in this RDD. + */ def distinct(): RDD[T] = distinct(partitions.size) /** @@ -280,7 +281,7 @@ abstract class RDD[T: ClassTag]( * which can avoid performing a shuffle. */ def repartition(numPartitions: Int): RDD[T] = { - coalesce(numPartitions, true) + coalesce(numPartitions, shuffle = true) } /** @@ -646,7 +647,8 @@ abstract class RDD[T: ClassTag]( } /** - * Reduces the elements of this RDD using the specified commutative and associative binary operator. + * Reduces the elements of this RDD using the specified commutative and + * associative binary operator. */ def reduce(f: (T, T) => T): T = { val cleanF = sc.clean(f) @@ -953,7 +955,7 @@ abstract class RDD[T: ClassTag]( private var storageLevel: StorageLevel = StorageLevel.NONE /** Record user function generating this RDD. */ - @transient private[spark] val origin = Utils.formatSparkCallSite + @transient private[spark] val origin = sc.getCallSite() private[spark] def elementClassTag: ClassTag[T] = classTag[T] diff --git a/core/src/main/scala/org/apache/spark/rdd/RDDCheckpointData.scala b/core/src/main/scala/org/apache/spark/rdd/RDDCheckpointData.scala index 642dabaad5..bc688110f4 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDDCheckpointData.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDDCheckpointData.scala @@ -40,7 +40,7 @@ private[spark] object CheckpointState extends Enumeration { * manages the post-checkpoint state by providing the updated partitions, iterator and preferred locations * of the checkpointed RDD. */ -private[spark] class RDDCheckpointData[T: ClassTag](rdd: RDD[T]) +private[spark] class RDDCheckpointData[T: ClassTag](@transient rdd: RDD[T]) extends Logging with Serializable { import CheckpointState._ diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala index e22b1e53e8..c52d6175d2 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala @@ -31,7 +31,7 @@ import org.apache.spark.util.Utils private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedulerImpl) extends Logging { - private val THREADS = sparkEnv.conf.get("spark.resultGetter.threads", "4").toInt + private val THREADS = sparkEnv.conf.getInt("spark.resultGetter.threads", 4) private val getTaskResultExecutor = Utils.newDaemonFixedThreadPool( THREADS, "Result resolver thread") diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala index d94b706854..d4f74d3e18 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala @@ -51,15 +51,15 @@ private[spark] class TaskSchedulerImpl( isLocal: Boolean = false) extends TaskScheduler with Logging { - def this(sc: SparkContext) = this(sc, sc.conf.get("spark.task.maxFailures", "4").toInt) + def this(sc: SparkContext) = this(sc, sc.conf.getInt("spark.task.maxFailures", 4)) val conf = sc.conf // How often to check for speculative tasks - val SPECULATION_INTERVAL = conf.get("spark.speculation.interval", "100").toLong + val SPECULATION_INTERVAL = conf.getLong("spark.speculation.interval", 100) // Threshold above which we warn user initial TaskSet may be starved - val STARVATION_TIMEOUT = conf.get("spark.starvation.timeout", "15000").toLong + val STARVATION_TIMEOUT = conf.getLong("spark.starvation.timeout", 15000) // TaskSetManagers are not thread safe, so any access to one should be synchronized // on this class. @@ -125,7 +125,7 @@ private[spark] class TaskSchedulerImpl( override def start() { backend.start() - if (!isLocal && conf.get("spark.speculation", "false").toBoolean) { + if (!isLocal && conf.getBoolean("spark.speculation", false)) { logInfo("Starting speculative execution thread") import sc.env.actorSystem.dispatcher sc.env.actorSystem.scheduler.schedule(SPECULATION_INTERVAL milliseconds, @@ -285,7 +285,8 @@ private[spark] class TaskSchedulerImpl( } } case None => - logInfo("Ignoring update from TID " + tid + " because its task set is gone") + logInfo("Ignoring update with state %s from TID %s because its task set is gone" + .format(state, tid)) } } catch { case e: Exception => logError("Exception in statusUpdate", e) @@ -328,7 +329,7 @@ private[spark] class TaskSchedulerImpl( // Have each task set throw a SparkException with the error for ((taskSetId, manager) <- activeTaskSets) { try { - manager.error(message) + manager.abort(message) } catch { case e: Exception => logError("Exception in error callback", e) } diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala index 67ad99a4d7..a10e5397ad 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala @@ -57,11 +57,11 @@ private[spark] class TaskSetManager( val conf = sched.sc.conf // CPUs to request per task - val CPUS_PER_TASK = conf.get("spark.task.cpus", "1").toInt + val CPUS_PER_TASK = conf.getInt("spark.task.cpus", 1) // Quantile of tasks at which to start speculation - val SPECULATION_QUANTILE = conf.get("spark.speculation.quantile", "0.75").toDouble - val SPECULATION_MULTIPLIER = conf.get("spark.speculation.multiplier", "1.5").toDouble + val SPECULATION_QUANTILE = conf.getDouble("spark.speculation.quantile", 0.75) + val SPECULATION_MULTIPLIER = conf.getDouble("spark.speculation.multiplier", 1.5) // Serializer for closures and tasks. val env = SparkEnv.get @@ -116,7 +116,7 @@ private[spark] class TaskSetManager( // How frequently to reprint duplicate exceptions in full, in milliseconds val EXCEPTION_PRINT_INTERVAL = - conf.get("spark.logging.exceptionPrintInterval", "10000").toLong + conf.getLong("spark.logging.exceptionPrintInterval", 10000) // Map of recent exceptions (identified by string representation and top stack frame) to // duplicate count (how many times the same exception has appeared) and time the full exception @@ -548,11 +548,6 @@ private[spark] class TaskSetManager( } } - def error(message: String) { - // Save the error message - abort("Error: " + message) - } - def abort(message: String) { // TODO: Kill running tasks if we were not terminated due to a Mesos error sched.dagScheduler.taskSetFailed(taskSet, message) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala index 2f5bcafe40..8d596a76c2 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala @@ -63,7 +63,7 @@ class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, actorSystem: A context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent]) // Periodically revive offers to allow delay scheduling to work - val reviveInterval = conf.get("spark.scheduler.revive.interval", "1000").toLong + val reviveInterval = conf.getLong("spark.scheduler.revive.interval", 1000) import context.dispatcher context.system.scheduler.schedule(0.millis, reviveInterval.millis, self, ReviveOffers) } @@ -209,8 +209,7 @@ class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, actorSystem: A } override def defaultParallelism(): Int = { - conf.getOption("spark.default.parallelism").map(_.toInt).getOrElse( - math.max(totalCoreCount.get(), 2)) + conf.getInt("spark.default.parallelism", math.max(totalCoreCount.get(), 2)) } // Called by subclasses when notified of a lost worker diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SimrSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SimrSchedulerBackend.scala index b44d1e43c8..d99c76117c 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SimrSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SimrSchedulerBackend.scala @@ -33,7 +33,7 @@ private[spark] class SimrSchedulerBackend( val tmpPath = new Path(driverFilePath + "_tmp") val filePath = new Path(driverFilePath) - val maxCores = conf.get("spark.simr.executor.cores", "1").toInt + val maxCores = conf.getInt("spark.simr.executor.cores", 1) override def start() { super.start() diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala index 9858717d13..faa6e1ebe8 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala @@ -20,7 +20,7 @@ package org.apache.spark.scheduler.cluster import scala.collection.mutable.HashMap import org.apache.spark.{Logging, SparkContext} -import org.apache.spark.deploy.client.{Client, ClientListener} +import org.apache.spark.deploy.client.{AppClient, AppClientListener} import org.apache.spark.deploy.{Command, ApplicationDescription} import org.apache.spark.scheduler.{ExecutorExited, ExecutorLossReason, SlaveLost, TaskSchedulerImpl} import org.apache.spark.util.Utils @@ -31,14 +31,14 @@ private[spark] class SparkDeploySchedulerBackend( masters: Array[String], appName: String) extends CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem) - with ClientListener + with AppClientListener with Logging { - var client: Client = null + var client: AppClient = null var stopping = false var shutdownCallback : (SparkDeploySchedulerBackend) => Unit = _ - val maxCores = conf.get("spark.cores.max", Int.MaxValue.toString).toInt + val maxCores = conf.getOption("spark.cores.max").map(_.toInt) override def start() { super.start() @@ -47,14 +47,14 @@ private[spark] class SparkDeploySchedulerBackend( val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format( conf.get("spark.driver.host"), conf.get("spark.driver.port"), CoarseGrainedSchedulerBackend.ACTOR_NAME) - val args = Seq(driverUrl, "{{EXECUTOR_ID}}", "{{HOSTNAME}}", "{{CORES}}") + val args = Seq(driverUrl, "{{EXECUTOR_ID}}", "{{HOSTNAME}}", "{{CORES}}", "{{WORKER_URL}}") val command = Command( "org.apache.spark.executor.CoarseGrainedExecutorBackend", args, sc.executorEnvs) val sparkHome = sc.getSparkHome().getOrElse(null) val appDesc = new ApplicationDescription(appName, maxCores, sc.executorMemory, command, sparkHome, "http://" + sc.ui.appUIAddress) - client = new Client(sc.env.actorSystem, masters, appDesc, this, conf) + client = new AppClient(sc.env.actorSystem, masters, appDesc, this, conf) client.start() } diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala index 08811520cf..e16d60c54c 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala @@ -77,7 +77,7 @@ private[spark] class CoarseMesosSchedulerBackend( "Spark home is not set; set it through the spark.home system " + "property, the SPARK_HOME environment variable or the SparkContext constructor")) - val extraCoresPerSlave = conf.get("spark.mesos.extra.cores", "0").toInt + val extraCoresPerSlave = conf.getInt("spark.mesos.extra.cores", 0) var nextMesosTaskId = 0 @@ -127,7 +127,7 @@ private[spark] class CoarseMesosSchedulerBackend( CoarseGrainedSchedulerBackend.ACTOR_NAME) val uri = conf.get("spark.executor.uri", null) if (uri == null) { - val runScript = new File(sparkHome, "spark-class").getCanonicalPath + val runScript = new File(sparkHome, "./bin/spark-class").getCanonicalPath command.setValue( "\"%s\" org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d".format( runScript, driverUrl, offer.getSlaveId.getValue, offer.getHostname, numCores)) @@ -136,7 +136,7 @@ private[spark] class CoarseMesosSchedulerBackend( // glob the directory "correctly". val basename = uri.split('/').last.split('.').head command.setValue( - "cd %s*; ./spark-class org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d" + "cd %s*; ./bin/spark-class org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d" .format(basename, driverUrl, offer.getSlaveId.getValue, offer.getHostname, numCores)) command.addUris(CommandInfo.URI.newBuilder().setValue(uri)) } diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala index bb278fb155..b428c82a48 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala @@ -102,12 +102,12 @@ private[spark] class MesosSchedulerBackend( .setEnvironment(environment) val uri = sc.conf.get("spark.executor.uri", null) if (uri == null) { - command.setValue(new File(sparkHome, "spark-executor").getCanonicalPath) + command.setValue(new File(sparkHome, "/sbin/spark-executor").getCanonicalPath) } else { // Grab everything to the first '.'. We'll use that and '*' to // glob the directory "correctly". val basename = uri.split('/').last.split('.').head - command.setValue("cd %s*; ./spark-executor".format(basename)) + command.setValue("cd %s*; ./sbin/spark-executor".format(basename)) command.addUris(CommandInfo.URI.newBuilder().setValue(uri)) } val memory = Resource.newBuilder() @@ -340,5 +340,5 @@ private[spark] class MesosSchedulerBackend( } // TODO: query Mesos for number of cores - override def defaultParallelism() = sc.conf.get("spark.default.parallelism", "8").toInt + override def defaultParallelism() = sc.conf.getInt("spark.default.parallelism", 8) } diff --git a/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala b/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala index a24a3b04b8..c14cd47556 100644 --- a/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala +++ b/core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala @@ -36,7 +36,7 @@ import org.apache.spark.storage.{GetBlock, GotBlock, PutBlock} */ class KryoSerializer(conf: SparkConf) extends org.apache.spark.serializer.Serializer with Logging { private val bufferSize = { - conf.get("spark.kryoserializer.buffer.mb", "2").toInt * 1024 * 1024 + conf.getInt("spark.kryoserializer.buffer.mb", 2) * 1024 * 1024 } def newKryoOutput() = new KryoOutput(bufferSize) @@ -48,7 +48,7 @@ class KryoSerializer(conf: SparkConf) extends org.apache.spark.serializer.Serial // Allow disabling Kryo reference tracking if user knows their object graphs don't have loops. // Do this before we invoke the user registrator so the user registrator can override this. - kryo.setReferences(conf.get("spark.kryo.referenceTracking", "true").toBoolean) + kryo.setReferences(conf.getBoolean("spark.kryo.referenceTracking", true)) for (cls <- KryoSerializer.toRegister) kryo.register(cls) diff --git a/core/src/main/scala/org/apache/spark/serializer/Serializer.scala b/core/src/main/scala/org/apache/spark/serializer/Serializer.scala index 160cca4d6c..9a5e3cb77e 100644 --- a/core/src/main/scala/org/apache/spark/serializer/Serializer.scala +++ b/core/src/main/scala/org/apache/spark/serializer/Serializer.scala @@ -29,6 +29,9 @@ import org.apache.spark.util.{NextIterator, ByteBufferInputStream} * A serializer. Because some serialization libraries are not thread safe, this class is used to * create [[org.apache.spark.serializer.SerializerInstance]] objects that do the actual serialization and are * guaranteed to only be called from one thread at a time. + * + * Implementations of this trait should have a zero-arg constructor or a constructor that accepts a + * [[org.apache.spark.SparkConf]] as parameter. If both constructors are defined, the latter takes precedence. */ trait Serializer { def newInstance(): SerializerInstance diff --git a/core/src/main/scala/org/apache/spark/serializer/SerializerManager.scala b/core/src/main/scala/org/apache/spark/serializer/SerializerManager.scala index 22465272f3..36a37af4f8 100644 --- a/core/src/main/scala/org/apache/spark/serializer/SerializerManager.scala +++ b/core/src/main/scala/org/apache/spark/serializer/SerializerManager.scala @@ -27,6 +27,7 @@ import org.apache.spark.SparkConf * creating a new one. */ private[spark] class SerializerManager { + // TODO: Consider moving this into SparkConf itself to remove the global singleton. private val serializers = new ConcurrentHashMap[String, Serializer] private var _default: Serializer = _ @@ -53,8 +54,18 @@ private[spark] class SerializerManager { if (serializer == null) { val clsLoader = Thread.currentThread.getContextClassLoader val cls = Class.forName(clsName, true, clsLoader) - val constructor = cls.getConstructor(classOf[SparkConf]) - serializer = constructor.newInstance(conf).asInstanceOf[Serializer] + + // First try with the constructor that takes SparkConf. If we can't find one, + // use a no-arg constructor instead. + try { + val constructor = cls.getConstructor(classOf[SparkConf]) + serializer = constructor.newInstance(conf).asInstanceOf[Serializer] + } catch { + case _: NoSuchMethodException => + val constructor = cls.getConstructor() + serializer = constructor.newInstance().asInstanceOf[Serializer] + } + serializers.put(clsName, serializer) } serializer diff --git a/core/src/main/scala/org/apache/spark/storage/BlockFetcherIterator.scala b/core/src/main/scala/org/apache/spark/storage/BlockFetcherIterator.scala index 47478631a1..4fa2ab96d9 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockFetcherIterator.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockFetcherIterator.scala @@ -327,7 +327,7 @@ object BlockFetcherIterator { fetchRequestsSync.put(request) } - copiers = startCopiers(conf.get("spark.shuffle.copier.threads", "6").toInt) + copiers = startCopiers(conf.getInt("spark.shuffle.copier.threads", 6)) logInfo("Started " + fetchRequestsSync.size + " remote gets in " + Utils.getUsedTimeMs(startTime)) diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala index 6d2cda97b0..c56e2ca2df 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala @@ -58,8 +58,8 @@ private[spark] class BlockManager( // If we use Netty for shuffle, start a new Netty-based shuffle sender service. private val nettyPort: Int = { - val useNetty = conf.get("spark.shuffle.use.netty", "false").toBoolean - val nettyPortConfig = conf.get("spark.shuffle.sender.port", "0").toInt + val useNetty = conf.getBoolean("spark.shuffle.use.netty", false) + val nettyPortConfig = conf.getInt("spark.shuffle.sender.port", 0) if (useNetty) diskBlockManager.startShuffleBlockSender(nettyPortConfig) else 0 } @@ -72,14 +72,14 @@ private[spark] class BlockManager( // Max megabytes of data to keep in flight per reducer (to avoid over-allocating memory // for receiving shuffle outputs) val maxBytesInFlight = - conf.get("spark.reducer.maxMbInFlight", "48").toLong * 1024 * 1024 + conf.getLong("spark.reducer.maxMbInFlight", 48) * 1024 * 1024 // Whether to compress broadcast variables that are stored - val compressBroadcast = conf.get("spark.broadcast.compress", "true").toBoolean + val compressBroadcast = conf.getBoolean("spark.broadcast.compress", true) // Whether to compress shuffle output that are stored - val compressShuffle = conf.get("spark.shuffle.compress", "true").toBoolean + val compressShuffle = conf.getBoolean("spark.shuffle.compress", true) // Whether to compress RDD partitions that are stored serialized - val compressRdds = conf.get("spark.rdd.compress", "false").toBoolean + val compressRdds = conf.getBoolean("spark.rdd.compress", false) val heartBeatFrequency = BlockManager.getHeartBeatFrequency(conf) @@ -443,7 +443,7 @@ private[spark] class BlockManager( : BlockFetcherIterator = { val iter = - if (conf.get("spark.shuffle.use.netty", "false").toBoolean) { + if (conf.getBoolean("spark.shuffle.use.netty", false)) { new BlockFetcherIterator.NettyBlockFetcherIterator(this, blocksByAddress, serializer) } else { new BlockFetcherIterator.BasicBlockFetcherIterator(this, blocksByAddress, serializer) @@ -469,7 +469,7 @@ private[spark] class BlockManager( def getDiskWriter(blockId: BlockId, file: File, serializer: Serializer, bufferSize: Int) : BlockObjectWriter = { val compressStream: OutputStream => OutputStream = wrapForCompression(blockId, _) - val syncWrites = conf.get("spark.shuffle.sync", "false").toBoolean + val syncWrites = conf.getBoolean("spark.shuffle.sync", false) new DiskBlockObjectWriter(blockId, file, serializer, bufferSize, compressStream, syncWrites) } @@ -864,15 +864,15 @@ private[spark] object BlockManager extends Logging { val ID_GENERATOR = new IdGenerator def getMaxMemory(conf: SparkConf): Long = { - val memoryFraction = conf.get("spark.storage.memoryFraction", "0.66").toDouble + val memoryFraction = conf.getDouble("spark.storage.memoryFraction", 0.66) (Runtime.getRuntime.maxMemory * memoryFraction).toLong } def getHeartBeatFrequency(conf: SparkConf): Long = - conf.get("spark.storage.blockManagerTimeoutIntervalMs", "60000").toLong / 4 + conf.getLong("spark.storage.blockManagerTimeoutIntervalMs", 60000) / 4 def getDisableHeartBeatsForTesting(conf: SparkConf): Boolean = - conf.get("spark.test.disableBlockManagerHeartBeat", "false").toBoolean + conf.getBoolean("spark.test.disableBlockManagerHeartBeat", false) /** * Attempt to clean up a ByteBuffer if it is memory-mapped. This uses an *unsafe* Sun API that diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala index b5afe8cd23..c54e4f2664 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerMaster.scala @@ -28,11 +28,10 @@ import org.apache.spark.storage.BlockManagerMessages._ import org.apache.spark.util.AkkaUtils private[spark] -class BlockManagerMaster(var driverActor : Either[ActorRef, ActorSelection], - conf: SparkConf) extends Logging { +class BlockManagerMaster(var driverActor : ActorRef, conf: SparkConf) extends Logging { - val AKKA_RETRY_ATTEMPTS: Int = conf.get("spark.akka.num.retries", "3").toInt - val AKKA_RETRY_INTERVAL_MS: Int = conf.get("spark.akka.retry.wait", "3000").toInt + val AKKA_RETRY_ATTEMPTS: Int = conf.getInt("spark.akka.num.retries", 3) + val AKKA_RETRY_INTERVAL_MS: Int = conf.getInt("spark.akka.retry.wait", 3000) val DRIVER_AKKA_ACTOR_NAME = "BlockManagerMaster" @@ -159,10 +158,7 @@ class BlockManagerMaster(var driverActor : Either[ActorRef, ActorSelection], while (attempts < AKKA_RETRY_ATTEMPTS) { attempts += 1 try { - val future = driverActor match { - case Left(a: ActorRef) => a.ask(message)(timeout) - case Right(b: ActorSelection) => b.ask(message)(timeout) - } + val future = driverActor.ask(message)(timeout) val result = Await.result(future, timeout) if (result == null) { throw new SparkException("BlockManagerMaster returned null") diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterActor.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterActor.scala index 58452d9657..2c1a4e2f5d 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterActor.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerMasterActor.scala @@ -348,14 +348,19 @@ object BlockManagerMasterActor { if (storageLevel.isValid) { // isValid means it is either stored in-memory or on-disk. - _blocks.put(blockId, BlockStatus(storageLevel, memSize, diskSize)) + // But the memSize here indicates the data size in or dropped from memory, + // and the diskSize here indicates the data size in or dropped to disk. + // They can be both larger than 0, when a block is dropped from memory to disk. + // Therefore, a safe way to set BlockStatus is to set its info in accurate modes. if (storageLevel.useMemory) { + _blocks.put(blockId, BlockStatus(storageLevel, memSize, 0)) _remainingMem -= memSize logInfo("Added %s in memory on %s (size: %s, free: %s)".format( blockId, blockManagerId.hostPort, Utils.bytesToString(memSize), Utils.bytesToString(_remainingMem))) } if (storageLevel.useDisk) { + _blocks.put(blockId, BlockStatus(storageLevel, 0, diskSize)) logInfo("Added %s on disk on %s (size: %s)".format( blockId, blockManagerId.hostPort, Utils.bytesToString(diskSize))) } diff --git a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala index 55dcb3742c..edc1133172 100644 --- a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala @@ -38,7 +38,7 @@ private[spark] class DiskBlockManager(shuffleManager: ShuffleBlockManager, rootD extends PathResolver with Logging { private val MAX_DIR_CREATION_ATTEMPTS: Int = 10 - private val subDirsPerLocalDir = shuffleManager.conf.get("spark.diskStore.subDirectories", "64").toInt + private val subDirsPerLocalDir = shuffleManager.conf.getInt("spark.diskStore.subDirectories", 64) // Create one local directory for each path mentioned in spark.local.dir; then, inside this // directory, create multiple subdirectories that we will hash files into, in order to avoid diff --git a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala index 39dc7bb19a..e2b24298a5 100644 --- a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala @@ -64,9 +64,9 @@ class ShuffleBlockManager(blockManager: BlockManager) { // Turning off shuffle file consolidation causes all shuffle Blocks to get their own file. // TODO: Remove this once the shuffle file consolidation feature is stable. val consolidateShuffleFiles = - conf.get("spark.shuffle.consolidateFiles", "false").toBoolean + conf.getBoolean("spark.shuffle.consolidateFiles", false) - private val bufferSize = conf.get("spark.shuffle.file.buffer.kb", "100").toInt * 1024 + private val bufferSize = conf.getInt("spark.shuffle.file.buffer.kb", 100) * 1024 /** * Contains all the state related to a particular shuffle. This includes a pool of unused diff --git a/core/src/main/scala/org/apache/spark/storage/ThreadingTest.scala b/core/src/main/scala/org/apache/spark/storage/ThreadingTest.scala index dca98c6c05..729ba2c550 100644 --- a/core/src/main/scala/org/apache/spark/storage/ThreadingTest.scala +++ b/core/src/main/scala/org/apache/spark/storage/ThreadingTest.scala @@ -95,7 +95,7 @@ private[spark] object ThreadingTest { val conf = new SparkConf() val serializer = new KryoSerializer(conf) val blockManagerMaster = new BlockManagerMaster( - Left(actorSystem.actorOf(Props(new BlockManagerMasterActor(true, conf)))), conf) + actorSystem.actorOf(Props(new BlockManagerMasterActor(true, conf))), conf) val blockManager = new BlockManager( "<driver>", actorSystem, blockManagerMaster, serializer, 1024 * 1024, conf) val producers = (1 to numProducers).map(i => new ProducerThread(blockManager, i)) diff --git a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala index 58d47a201d..6ba15187d9 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala @@ -27,7 +27,7 @@ import org.apache.spark.scheduler.SchedulingMode /** * Continuously generates jobs that expose various features of the WebUI (internal testing tool). * - * Usage: ./run spark.ui.UIWorkloadGenerator [master] + * Usage: ./bin/spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR] */ private[spark] object UIWorkloadGenerator { @@ -36,7 +36,7 @@ private[spark] object UIWorkloadGenerator { def main(args: Array[String]) { if (args.length < 2) { - println("usage: ./spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]") + println("usage: ./bin/spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]") System.exit(1) } diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala index b7b87250b9..bcd2824450 100644 --- a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala +++ b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala @@ -33,7 +33,7 @@ import org.apache.spark.scheduler._ */ private[spark] class JobProgressListener(val sc: SparkContext) extends SparkListener { // How many stages to remember - val RETAINED_STAGES = sc.conf.get("spark.ui.retained_stages", "1000").toInt + val RETAINED_STAGES = sc.conf.getInt("spark.ui.retainedStages", 1000) val DEFAULT_POOL_NAME = "default" val stageIdToPool = new HashMap[Int, String]() diff --git a/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala b/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala index 362cea5e3e..761d378c7f 100644 --- a/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala +++ b/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala @@ -17,10 +17,13 @@ package org.apache.spark.util +import scala.collection.JavaConversions.mapAsJavaMap import scala.concurrent.duration.{Duration, FiniteDuration} import akka.actor.{ActorSystem, ExtendedActorSystem, IndestructibleActorSystem} import com.typesafe.config.ConfigFactory + +import org.apache.log4j.{Level, Logger} import org.apache.spark.SparkConf /** @@ -41,21 +44,29 @@ private[spark] object AkkaUtils { def createActorSystem(name: String, host: String, port: Int, indestructible: Boolean = false, conf: SparkConf): (ActorSystem, Int) = { - val akkaThreads = conf.get("spark.akka.threads", "4").toInt - val akkaBatchSize = conf.get("spark.akka.batchSize", "15").toInt + val akkaThreads = conf.getInt("spark.akka.threads", 4) + val akkaBatchSize = conf.getInt("spark.akka.batchSize", 15) + + val akkaTimeout = conf.getInt("spark.akka.timeout", 100) - val akkaTimeout = conf.get("spark.akka.timeout", "100").toInt + val akkaFrameSize = conf.getInt("spark.akka.frameSize", 10) + val akkaLogLifecycleEvents = conf.getBoolean("spark.akka.logLifecycleEvents", false) + val lifecycleEvents = if (akkaLogLifecycleEvents) "on" else "off" + if (!akkaLogLifecycleEvents) { + // As a workaround for Akka issue #3787, we coerce the "EndpointWriter" log to be silent. + // See: https://www.assembla.com/spaces/akka/tickets/3787#/ + Option(Logger.getLogger("akka.remote.EndpointWriter")).map(l => l.setLevel(Level.FATAL)) + } - val akkaFrameSize = conf.get("spark.akka.frameSize", "10").toInt - val lifecycleEvents = - if (conf.get("spark.akka.logLifecycleEvents", "false").toBoolean) "on" else "off" + val logAkkaConfig = if (conf.getBoolean("spark.akka.logAkkaConfig", false)) "on" else "off" - val akkaHeartBeatPauses = conf.get("spark.akka.heartbeat.pauses", "600").toInt + val akkaHeartBeatPauses = conf.getInt("spark.akka.heartbeat.pauses", 600) val akkaFailureDetector = - conf.get("spark.akka.failure-detector.threshold", "300.0").toDouble - val akkaHeartBeatInterval = conf.get("spark.akka.heartbeat.interval", "1000").toInt + conf.getDouble("spark.akka.failure-detector.threshold", 300.0) + val akkaHeartBeatInterval = conf.getInt("spark.akka.heartbeat.interval", 1000) - val akkaConf = ConfigFactory.parseString( + val akkaConf = ConfigFactory.parseMap(conf.getAkkaConf.toMap[String, String]).withFallback( + ConfigFactory.parseString( s""" |akka.daemonic = on |akka.loggers = [""akka.event.slf4j.Slf4jLogger""] @@ -73,8 +84,11 @@ private[spark] object AkkaUtils { |akka.remote.netty.tcp.maximum-frame-size = ${akkaFrameSize}MiB |akka.remote.netty.tcp.execution-pool-size = $akkaThreads |akka.actor.default-dispatcher.throughput = $akkaBatchSize + |akka.log-config-on-start = $logAkkaConfig |akka.remote.log-remote-lifecycle-events = $lifecycleEvents - """.stripMargin) + |akka.log-dead-letters = $lifecycleEvents + |akka.log-dead-letters-during-shutdown = $lifecycleEvents + """.stripMargin)) val actorSystem = if (indestructible) { IndestructibleActorSystem(name, akkaConf) @@ -89,6 +103,11 @@ private[spark] object AkkaUtils { /** Returns the default Spark timeout to use for Akka ask operations. */ def askTimeout(conf: SparkConf): FiniteDuration = { - Duration.create(conf.get("spark.akka.askTimeout", "30").toLong, "seconds") + Duration.create(conf.getLong("spark.akka.askTimeout", 30), "seconds") + } + + /** Returns the default Spark timeout to use for Akka remote actor lookup. */ + def lookupTimeout(conf: SparkConf): FiniteDuration = { + Duration.create(conf.get("spark.akka.lookupTimeout", "30").toLong, "seconds") } } diff --git a/core/src/main/scala/org/apache/spark/util/MetadataCleaner.scala b/core/src/main/scala/org/apache/spark/util/MetadataCleaner.scala index aa7f52cafb..3d1e90a352 100644 --- a/core/src/main/scala/org/apache/spark/util/MetadataCleaner.scala +++ b/core/src/main/scala/org/apache/spark/util/MetadataCleaner.scala @@ -74,7 +74,7 @@ object MetadataCleanerType extends Enumeration { // initialization of StreamingContext. It's okay for users trying to configure stuff themselves. object MetadataCleaner { def getDelaySeconds(conf: SparkConf) = { - conf.get("spark.cleaner.ttl", "3500").toInt + conf.getInt("spark.cleaner.ttl", 3500) } def getDelaySeconds(conf: SparkConf, cleanerType: MetadataCleanerType.MetadataCleanerType): Int = diff --git a/core/src/main/scala/org/apache/spark/util/XORShiftRandom.scala b/core/src/main/scala/org/apache/spark/util/XORShiftRandom.scala index e9907e6c85..08b31ac64f 100644 --- a/core/src/main/scala/org/apache/spark/util/XORShiftRandom.scala +++ b/core/src/main/scala/org/apache/spark/util/XORShiftRandom.scala @@ -91,4 +91,4 @@ private[spark] object XORShiftRandom { } -}
\ No newline at end of file +} diff --git a/core/src/test/resources/uncommons-maths-1.2.2.jar b/core/src/test/resources/uncommons-maths-1.2.2.jar Binary files differdeleted file mode 100644 index e126001c1c..0000000000 --- a/core/src/test/resources/uncommons-maths-1.2.2.jar +++ /dev/null diff --git a/core/src/test/scala/org/apache/spark/CheckpointSuite.scala b/core/src/test/scala/org/apache/spark/CheckpointSuite.scala index 70bfb81661..ec13b329b2 100644 --- a/core/src/test/scala/org/apache/spark/CheckpointSuite.scala +++ b/core/src/test/scala/org/apache/spark/CheckpointSuite.scala @@ -55,15 +55,15 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { } test("RDDs with one-to-one dependencies") { - testCheckpointing(_.map(x => x.toString)) - testCheckpointing(_.flatMap(x => 1 to x)) - testCheckpointing(_.filter(_ % 2 == 0)) - testCheckpointing(_.sample(false, 0.5, 0)) - testCheckpointing(_.glom()) - testCheckpointing(_.mapPartitions(_.map(_.toString))) - testCheckpointing(_.map(x => (x % 2, 1)).reduceByKey(_ + _).mapValues(_.toString)) - testCheckpointing(_.map(x => (x % 2, 1)).reduceByKey(_ + _).flatMapValues(x => 1 to x)) - testCheckpointing(_.pipe(Seq("cat"))) + testRDD(_.map(x => x.toString)) + testRDD(_.flatMap(x => 1 to x)) + testRDD(_.filter(_ % 2 == 0)) + testRDD(_.sample(false, 0.5, 0)) + testRDD(_.glom()) + testRDD(_.mapPartitions(_.map(_.toString))) + testRDD(_.map(x => (x % 2, 1)).reduceByKey(_ + _).mapValues(_.toString)) + testRDD(_.map(x => (x % 2, 1)).reduceByKey(_ + _).flatMapValues(x => 1 to x)) + testRDD(_.pipe(Seq("cat"))) } test("ParallelCollection") { @@ -95,7 +95,7 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { } test("ShuffledRDD") { - testCheckpointing(rdd => { + testRDD(rdd => { // Creating ShuffledRDD directly as PairRDDFunctions.combineByKey produces a MapPartitionedRDD new ShuffledRDD[Int, Int, (Int, Int)](rdd.map(x => (x % 2, 1)), partitioner) }) @@ -103,25 +103,17 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { test("UnionRDD") { def otherRDD = sc.makeRDD(1 to 10, 1) - - // Test whether the size of UnionRDDPartitions reduce in size after parent RDD is checkpointed. - // Current implementation of UnionRDD has transient reference to parent RDDs, - // so only the partitions will reduce in serialized size, not the RDD. - testCheckpointing(_.union(otherRDD), false, true) - testParentCheckpointing(_.union(otherRDD), false, true) + testRDD(_.union(otherRDD)) + testRDDPartitions(_.union(otherRDD)) } test("CartesianRDD") { def otherRDD = sc.makeRDD(1 to 10, 1) - testCheckpointing(new CartesianRDD(sc, _, otherRDD)) - - // Test whether size of CoalescedRDD reduce in size after parent RDD is checkpointed - // Current implementation of CoalescedRDDPartition has transient reference to parent RDD, - // so only the RDD will reduce in serialized size, not the partitions. - testParentCheckpointing(new CartesianRDD(sc, _, otherRDD), true, false) + testRDD(new CartesianRDD(sc, _, otherRDD)) + testRDDPartitions(new CartesianRDD(sc, _, otherRDD)) // Test that the CartesianRDD updates parent partitions (CartesianRDD.s1/s2) after - // the parent RDD has been checkpointed and parent partitions have been changed to HadoopPartitions. + // the parent RDD has been checkpointed and parent partitions have been changed. // Note that this test is very specific to the current implementation of CartesianRDD. val ones = sc.makeRDD(1 to 100, 10).map(x => x) ones.checkpoint() // checkpoint that MappedRDD @@ -132,23 +124,20 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { val splitAfterCheckpoint = serializeDeserialize(cartesian.partitions.head.asInstanceOf[CartesianPartition]) assert( - (splitAfterCheckpoint.s1 != splitBeforeCheckpoint.s1) && - (splitAfterCheckpoint.s2 != splitBeforeCheckpoint.s2), - "CartesianRDD.parents not updated after parent RDD checkpointed" + (splitAfterCheckpoint.s1.getClass != splitBeforeCheckpoint.s1.getClass) && + (splitAfterCheckpoint.s2.getClass != splitBeforeCheckpoint.s2.getClass), + "CartesianRDD.s1 and CartesianRDD.s2 not updated after parent RDD is checkpointed" ) } test("CoalescedRDD") { - testCheckpointing(_.coalesce(2)) + testRDD(_.coalesce(2)) + testRDDPartitions(_.coalesce(2)) - // Test whether size of CoalescedRDD reduce in size after parent RDD is checkpointed - // Current implementation of CoalescedRDDPartition has transient reference to parent RDD, - // so only the RDD will reduce in serialized size, not the partitions. - testParentCheckpointing(_.coalesce(2), true, false) - - // Test that the CoalescedRDDPartition updates parent partitions (CoalescedRDDPartition.parents) after - // the parent RDD has been checkpointed and parent partitions have been changed to HadoopPartitions. - // Note that this test is very specific to the current implementation of CoalescedRDDPartitions + // Test that the CoalescedRDDPartition updates parent partitions (CoalescedRDDPartition.parents) + // after the parent RDD has been checkpointed and parent partitions have been changed. + // Note that this test is very specific to the current implementation of + // CoalescedRDDPartitions. val ones = sc.makeRDD(1 to 100, 10).map(x => x) ones.checkpoint() // checkpoint that MappedRDD val coalesced = new CoalescedRDD(ones, 2) @@ -158,33 +147,78 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { val splitAfterCheckpoint = serializeDeserialize(coalesced.partitions.head.asInstanceOf[CoalescedRDDPartition]) assert( - splitAfterCheckpoint.parents.head != splitBeforeCheckpoint.parents.head, - "CoalescedRDDPartition.parents not updated after parent RDD checkpointed" + splitAfterCheckpoint.parents.head.getClass != splitBeforeCheckpoint.parents.head.getClass, + "CoalescedRDDPartition.parents not updated after parent RDD is checkpointed" ) } test("CoGroupedRDD") { - val longLineageRDD1 = generateLongLineageRDDForCoGroupedRDD() - testCheckpointing(rdd => { + val longLineageRDD1 = generateFatPairRDD() + testRDD(rdd => { CheckpointSuite.cogroup(longLineageRDD1, rdd.map(x => (x % 2, 1)), partitioner) - }, false, true) + }) - val longLineageRDD2 = generateLongLineageRDDForCoGroupedRDD() - testParentCheckpointing(rdd => { + val longLineageRDD2 = generateFatPairRDD() + testRDDPartitions(rdd => { CheckpointSuite.cogroup( longLineageRDD2, sc.makeRDD(1 to 2, 2).map(x => (x % 2, 1)), partitioner) - }, false, true) + }) } test("ZippedRDD") { - testCheckpointing( - rdd => new ZippedRDD(sc, rdd, rdd.map(x => x)), true, false) - - // Test whether size of ZippedRDD reduce in size after parent RDD is checkpointed - // Current implementation of ZippedRDDPartitions has transient references to parent RDDs, - // so only the RDD will reduce in serialized size, not the partitions. - testParentCheckpointing( - rdd => new ZippedRDD(sc, rdd, rdd.map(x => x)), true, false) + testRDD(rdd => new ZippedRDD(sc, rdd, rdd.map(x => x))) + testRDDPartitions(rdd => new ZippedRDD(sc, rdd, rdd.map(x => x))) + + // Test that the ZippedPartition updates parent partitions + // after the parent RDD has been checkpointed and parent partitions have been changed. + // Note that this test is very specific to the current implementation of ZippedRDD. + val rdd = generateFatRDD() + val zippedRDD = new ZippedRDD(sc, rdd, rdd.map(x => x)) + zippedRDD.rdd1.checkpoint() + zippedRDD.rdd2.checkpoint() + val partitionBeforeCheckpoint = + serializeDeserialize(zippedRDD.partitions.head.asInstanceOf[ZippedPartition[_, _]]) + zippedRDD.count() + val partitionAfterCheckpoint = + serializeDeserialize(zippedRDD.partitions.head.asInstanceOf[ZippedPartition[_, _]]) + assert( + partitionAfterCheckpoint.partition1.getClass != partitionBeforeCheckpoint.partition1.getClass && + partitionAfterCheckpoint.partition2.getClass != partitionBeforeCheckpoint.partition2.getClass, + "ZippedRDD.partition1 and ZippedRDD.partition2 not updated after parent RDD is checkpointed" + ) + } + + test("PartitionerAwareUnionRDD") { + testRDD(rdd => { + new PartitionerAwareUnionRDD[(Int, Int)](sc, Array( + generateFatPairRDD(), + rdd.map(x => (x % 2, 1)).reduceByKey(partitioner, _ + _) + )) + }) + + testRDDPartitions(rdd => { + new PartitionerAwareUnionRDD[(Int, Int)](sc, Array( + generateFatPairRDD(), + rdd.map(x => (x % 2, 1)).reduceByKey(partitioner, _ + _) + )) + }) + + // Test that the PartitionerAwareUnionRDD updates parent partitions + // (PartitionerAwareUnionRDD.parents) after the parent RDD has been checkpointed and parent + // partitions have been changed. Note that this test is very specific to the current + // implementation of PartitionerAwareUnionRDD. + val pairRDD = generateFatPairRDD() + pairRDD.checkpoint() + val unionRDD = new PartitionerAwareUnionRDD(sc, Array(pairRDD)) + val partitionBeforeCheckpoint = serializeDeserialize( + unionRDD.partitions.head.asInstanceOf[PartitionerAwareUnionRDDPartition]) + pairRDD.count() + val partitionAfterCheckpoint = serializeDeserialize( + unionRDD.partitions.head.asInstanceOf[PartitionerAwareUnionRDDPartition]) + assert( + partitionBeforeCheckpoint.parents.head.getClass != partitionAfterCheckpoint.parents.head.getClass, + "PartitionerAwareUnionRDDPartition.parents not updated after parent RDD is checkpointed" + ) } test("CheckpointRDD with zero partitions") { @@ -198,29 +232,32 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { } /** - * Test checkpointing of the final RDD generated by the given operation. By default, - * this method tests whether the size of serialized RDD has reduced after checkpointing or not. - * It can also test whether the size of serialized RDD partitions has reduced after checkpointing or - * not, but this is not done by default as usually the partitions do not refer to any RDD and - * therefore never store the lineage. + * Test checkpointing of the RDD generated by the given operation. It tests whether the + * serialized size of the RDD is reduce after checkpointing or not. This function should be called + * on all RDDs that have a parent RDD (i.e., do not call on ParallelCollection, BlockRDD, etc.). */ - def testCheckpointing[U: ClassTag]( - op: (RDD[Int]) => RDD[U], - testRDDSize: Boolean = true, - testRDDPartitionSize: Boolean = false - ) { + def testRDD[U: ClassTag](op: (RDD[Int]) => RDD[U]) { // Generate the final RDD using given RDD operation - val baseRDD = generateLongLineageRDD() + val baseRDD = generateFatRDD() val operatedRDD = op(baseRDD) val parentRDD = operatedRDD.dependencies.headOption.orNull val rddType = operatedRDD.getClass.getSimpleName val numPartitions = operatedRDD.partitions.length + // Force initialization of all the data structures in RDDs + // Without this, serializing the RDD will give a wrong estimate of the size of the RDD + initializeRdd(operatedRDD) + + val partitionsBeforeCheckpoint = operatedRDD.partitions + // Find serialized sizes before and after the checkpoint - val (rddSizeBeforeCheckpoint, splitSizeBeforeCheckpoint) = getSerializedSizes(operatedRDD) + logInfo("RDD after checkpoint: " + operatedRDD + "\n" + operatedRDD.toDebugString) + val (rddSizeBeforeCheckpoint, partitionSizeBeforeCheckpoint) = getSerializedSizes(operatedRDD) operatedRDD.checkpoint() val result = operatedRDD.collect() - val (rddSizeAfterCheckpoint, splitSizeAfterCheckpoint) = getSerializedSizes(operatedRDD) + operatedRDD.collect() // force re-initialization of post-checkpoint lazy variables + val (rddSizeAfterCheckpoint, partitionSizeAfterCheckpoint) = getSerializedSizes(operatedRDD) + logInfo("RDD after checkpoint: " + operatedRDD + "\n" + operatedRDD.toDebugString) // Test whether the checkpoint file has been created assert(sc.checkpointFile[U](operatedRDD.getCheckpointFile.get).collect() === result) @@ -228,6 +265,9 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { // Test whether dependencies have been changed from its earlier parent RDD assert(operatedRDD.dependencies.head.rdd != parentRDD) + // Test whether the partitions have been changed from its earlier partitions + assert(operatedRDD.partitions.toList != partitionsBeforeCheckpoint.toList) + // Test whether the partitions have been changed to the new Hadoop partitions assert(operatedRDD.partitions.toList === operatedRDD.checkpointData.get.getPartitions.toList) @@ -237,122 +277,72 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { // Test whether the data in the checkpointed RDD is same as original assert(operatedRDD.collect() === result) - // Test whether serialized size of the RDD has reduced. If the RDD - // does not have any dependency to another RDD (e.g., ParallelCollection, - // ShuffleRDD with ShuffleDependency), it may not reduce in size after checkpointing. - if (testRDDSize) { - logInfo("Size of " + rddType + - "[" + rddSizeBeforeCheckpoint + " --> " + rddSizeAfterCheckpoint + "]") - assert( - rddSizeAfterCheckpoint < rddSizeBeforeCheckpoint, - "Size of " + rddType + " did not reduce after checkpointing " + - "[" + rddSizeBeforeCheckpoint + " --> " + rddSizeAfterCheckpoint + "]" - ) - } + // Test whether serialized size of the RDD has reduced. + logInfo("Size of " + rddType + + " [" + rddSizeBeforeCheckpoint + " --> " + rddSizeAfterCheckpoint + "]") + assert( + rddSizeAfterCheckpoint < rddSizeBeforeCheckpoint, + "Size of " + rddType + " did not reduce after checkpointing " + + " [" + rddSizeBeforeCheckpoint + " --> " + rddSizeAfterCheckpoint + "]" + ) - // Test whether serialized size of the partitions has reduced. If the partitions - // do not have any non-transient reference to another RDD or another RDD's partitions, it - // does not refer to a lineage and therefore may not reduce in size after checkpointing. - // However, if the original partitions before checkpointing do refer to a parent RDD, the partitions - // must be forgotten after checkpointing (to remove all reference to parent RDDs) and - // replaced with the HadooPartitions of the checkpointed RDD. - if (testRDDPartitionSize) { - logInfo("Size of " + rddType + " partitions " - + "[" + splitSizeBeforeCheckpoint + " --> " + splitSizeAfterCheckpoint + "]") - assert( - splitSizeAfterCheckpoint < splitSizeBeforeCheckpoint, - "Size of " + rddType + " partitions did not reduce after checkpointing " + - "[" + splitSizeBeforeCheckpoint + " --> " + splitSizeAfterCheckpoint + "]" - ) - } } /** * Test whether checkpointing of the parent of the generated RDD also * truncates the lineage or not. Some RDDs like CoGroupedRDD hold on to its parent * RDDs partitions. So even if the parent RDD is checkpointed and its partitions changed, - * this RDD will remember the partitions and therefore potentially the whole lineage. + * the generated RDD will remember the partitions and therefore potentially the whole lineage. + * This function should be called only those RDD whose partitions refer to parent RDD's + * partitions (i.e., do not call it on simple RDD like MappedRDD). + * */ - def testParentCheckpointing[U: ClassTag]( - op: (RDD[Int]) => RDD[U], - testRDDSize: Boolean, - testRDDPartitionSize: Boolean - ) { + def testRDDPartitions[U: ClassTag](op: (RDD[Int]) => RDD[U]) { // Generate the final RDD using given RDD operation - val baseRDD = generateLongLineageRDD() + val baseRDD = generateFatRDD() val operatedRDD = op(baseRDD) - val parentRDD = operatedRDD.dependencies.head.rdd + val parentRDDs = operatedRDD.dependencies.map(_.rdd) val rddType = operatedRDD.getClass.getSimpleName - val parentRDDType = parentRDD.getClass.getSimpleName - // Get the partitions and dependencies of the parent in case they're lazily computed - parentRDD.dependencies - parentRDD.partitions + // Force initialization of all the data structures in RDDs + // Without this, serializing the RDD will give a wrong estimate of the size of the RDD + initializeRdd(operatedRDD) // Find serialized sizes before and after the checkpoint - val (rddSizeBeforeCheckpoint, splitSizeBeforeCheckpoint) = getSerializedSizes(operatedRDD) - parentRDD.checkpoint() // checkpoint the parent RDD, not the generated one - val result = operatedRDD.collect() - val (rddSizeAfterCheckpoint, splitSizeAfterCheckpoint) = getSerializedSizes(operatedRDD) + logInfo("RDD after checkpoint: " + operatedRDD + "\n" + operatedRDD.toDebugString) + val (rddSizeBeforeCheckpoint, partitionSizeBeforeCheckpoint) = getSerializedSizes(operatedRDD) + parentRDDs.foreach(_.checkpoint()) // checkpoint the parent RDD, not the generated one + val result = operatedRDD.collect() // force checkpointing + operatedRDD.collect() // force re-initialization of post-checkpoint lazy variables + val (rddSizeAfterCheckpoint, partitionSizeAfterCheckpoint) = getSerializedSizes(operatedRDD) + logInfo("RDD after checkpoint: " + operatedRDD + "\n" + operatedRDD.toDebugString) // Test whether the data in the checkpointed RDD is same as original assert(operatedRDD.collect() === result) - // Test whether serialized size of the RDD has reduced because of its parent being - // checkpointed. If this RDD or its parent RDD do not have any dependency - // to another RDD (e.g., ParallelCollection, ShuffleRDD with ShuffleDependency), it may - // not reduce in size after checkpointing. - if (testRDDSize) { - assert( - rddSizeAfterCheckpoint < rddSizeBeforeCheckpoint, - "Size of " + rddType + " did not reduce after checkpointing parent " + parentRDDType + - "[" + rddSizeBeforeCheckpoint + " --> " + rddSizeAfterCheckpoint + "]" - ) - } - - // Test whether serialized size of the partitions has reduced because of its parent being - // checkpointed. If the partitions do not have any non-transient reference to another RDD - // or another RDD's partitions, it does not refer to a lineage and therefore may not reduce - // in size after checkpointing. However, if the partitions do refer to the *partitions* of a parent - // RDD, then these partitions must update reference to the parent RDD partitions as the parent RDD's - // partitions must have changed after checkpointing. - if (testRDDPartitionSize) { - assert( - splitSizeAfterCheckpoint < splitSizeBeforeCheckpoint, - "Size of " + rddType + " partitions did not reduce after checkpointing parent " + parentRDDType + - "[" + splitSizeBeforeCheckpoint + " --> " + splitSizeAfterCheckpoint + "]" - ) - } - + // Test whether serialized size of the partitions has reduced + logInfo("Size of partitions of " + rddType + + " [" + partitionSizeBeforeCheckpoint + " --> " + partitionSizeAfterCheckpoint + "]") + assert( + partitionSizeAfterCheckpoint < partitionSizeBeforeCheckpoint, + "Size of " + rddType + " partitions did not reduce after checkpointing parent RDDs" + + " [" + partitionSizeBeforeCheckpoint + " --> " + partitionSizeAfterCheckpoint + "]" + ) } /** - * Generate an RDD with a long lineage of one-to-one dependencies. + * Generate an RDD such that both the RDD and its partitions have large size. */ - def generateLongLineageRDD(): RDD[Int] = { - var rdd = sc.makeRDD(1 to 100, 4) - for (i <- 1 to 50) { - rdd = rdd.map(x => x + 1) - } - rdd + def generateFatRDD(): RDD[Int] = { + new FatRDD(sc.makeRDD(1 to 100, 4)).map(x => x) } /** - * Generate an RDD with a long lineage specifically for CoGroupedRDD. - * A CoGroupedRDD can have a long lineage only one of its parents have a long lineage - * and narrow dependency with this RDD. This method generate such an RDD by a sequence - * of cogroups and mapValues which creates a long lineage of narrow dependencies. + * Generate an pair RDD (with partitioner) such that both the RDD and its partitions + * have large size. */ - def generateLongLineageRDDForCoGroupedRDD() = { - val add = (x: (Seq[Int], Seq[Int])) => (x._1 ++ x._2).reduce(_ + _) - - def ones: RDD[(Int, Int)] = sc.makeRDD(1 to 2, 2).map(x => (x % 2, 1)).reduceByKey(partitioner, _ + _) - - var cogrouped: RDD[(Int, (Seq[Int], Seq[Int]))] = ones.cogroup(ones) - for(i <- 1 to 10) { - cogrouped = cogrouped.mapValues(add).cogroup(ones) - } - cogrouped.mapValues(add) + def generateFatPairRDD() = { + new FatPairRDD(sc.makeRDD(1 to 100, 4), partitioner).mapValues(x => x) } /** @@ -360,8 +350,26 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { * upon checkpointing. Ignores the checkpointData field, which may grow when we checkpoint. */ def getSerializedSizes(rdd: RDD[_]): (Int, Int) = { - (Utils.serialize(rdd).length - Utils.serialize(rdd.checkpointData).length, - Utils.serialize(rdd.partitions).length) + val rddSize = Utils.serialize(rdd).size + val rddCpDataSize = Utils.serialize(rdd.checkpointData).size + val rddPartitionSize = Utils.serialize(rdd.partitions).size + val rddDependenciesSize = Utils.serialize(rdd.dependencies).size + + // Print detailed size, helps in debugging + logInfo("Serialized sizes of " + rdd + + ": RDD = " + rddSize + + ", RDD checkpoint data = " + rddCpDataSize + + ", RDD partitions = " + rddPartitionSize + + ", RDD dependencies = " + rddDependenciesSize + ) + // this makes sure that serializing the RDD's checkpoint data does not + // serialize the whole RDD as well + assert( + rddSize > rddCpDataSize, + "RDD's checkpoint data (" + rddCpDataSize + ") is equal or larger than the " + + "whole RDD with checkpoint data (" + rddSize + ")" + ) + (rddSize - rddCpDataSize, rddPartitionSize) } /** @@ -373,8 +381,49 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { val bytes = Utils.serialize(obj) Utils.deserialize[T](bytes) } + + /** + * Recursively force the initialization of the all members of an RDD and it parents. + */ + def initializeRdd(rdd: RDD[_]) { + rdd.partitions // forces the + rdd.dependencies.map(_.rdd).foreach(initializeRdd(_)) + } } +/** RDD partition that has large serialized size. */ +class FatPartition(val partition: Partition) extends Partition { + val bigData = new Array[Byte](10000) + def index: Int = partition.index +} + +/** RDD that has large serialized size. */ +class FatRDD(parent: RDD[Int]) extends RDD[Int](parent) { + val bigData = new Array[Byte](100000) + + protected def getPartitions: Array[Partition] = { + parent.partitions.map(p => new FatPartition(p)) + } + + def compute(split: Partition, context: TaskContext): Iterator[Int] = { + parent.compute(split.asInstanceOf[FatPartition].partition, context) + } +} + +/** Pair RDD that has large serialized size. */ +class FatPairRDD(parent: RDD[Int], _partitioner: Partitioner) extends RDD[(Int, Int)](parent) { + val bigData = new Array[Byte](100000) + + protected def getPartitions: Array[Partition] = { + parent.partitions.map(p => new FatPartition(p)) + } + + @transient override val partitioner = Some(_partitioner) + + def compute(split: Partition, context: TaskContext): Iterator[(Int, Int)] = { + parent.compute(split.asInstanceOf[FatPartition].partition, context).map(x => (x, x)) + } +} object CheckpointSuite { // This is a custom cogroup function that does not use mapValues like diff --git a/core/src/test/scala/org/apache/spark/DriverSuite.scala b/core/src/test/scala/org/apache/spark/DriverSuite.scala index 6d1695eae7..fb89537258 100644 --- a/core/src/test/scala/org/apache/spark/DriverSuite.scala +++ b/core/src/test/scala/org/apache/spark/DriverSuite.scala @@ -30,13 +30,15 @@ import org.apache.spark.util.Utils class DriverSuite extends FunSuite with Timeouts { test("driver should exit after finishing") { - assert(System.getenv("SPARK_HOME") != null) + val sparkHome = sys.env.get("SPARK_HOME").orElse(sys.props.get("spark.home")).get // Regression test for SPARK-530: "Spark driver process doesn't exit after finishing" val masters = Table(("master"), ("local"), ("local-cluster[2,1,512]")) forAll(masters) { (master: String) => failAfter(60 seconds) { - Utils.execute(Seq("./spark-class", "org.apache.spark.DriverWithoutCleanup", master), - new File(System.getenv("SPARK_HOME"))) + Utils.executeAndGetOutput( + Seq("./bin/spark-class", "org.apache.spark.DriverWithoutCleanup", master), + new File(sparkHome), + Map("SPARK_TESTING" -> "1", "SPARK_HOME" -> sparkHome)) } } } diff --git a/core/src/test/scala/org/apache/spark/FileServerSuite.scala b/core/src/test/scala/org/apache/spark/FileServerSuite.scala index c210dd5c3b..a2eb9a4e84 100644 --- a/core/src/test/scala/org/apache/spark/FileServerSuite.scala +++ b/core/src/test/scala/org/apache/spark/FileServerSuite.scala @@ -17,33 +17,49 @@ package org.apache.spark +import java.io._ +import java.util.jar.{JarEntry, JarOutputStream} + +import SparkContext._ import com.google.common.io.Files import org.scalatest.FunSuite -import java.io.{File, PrintWriter, FileReader, BufferedReader} -import SparkContext._ class FileServerSuite extends FunSuite with LocalSparkContext { @transient var tmpFile: File = _ - @transient var testJarFile: File = _ - - override def beforeEach() { - super.beforeEach() - // Create a sample text file - val tmpdir = new File(Files.createTempDir(), "test") - tmpdir.mkdir() - tmpFile = new File(tmpdir, "FileServerSuite.txt") - val pw = new PrintWriter(tmpFile) + @transient var tmpJarUrl: String = _ + + override def beforeAll() { + super.beforeAll() + val tmpDir = new File(Files.createTempDir(), "test") + tmpDir.mkdir() + + val textFile = new File(tmpDir, "FileServerSuite.txt") + val pw = new PrintWriter(textFile) pw.println("100") pw.close() - } + + val jarFile = new File(tmpDir, "test.jar") + val jarStream = new FileOutputStream(jarFile) + val jar = new JarOutputStream(jarStream, new java.util.jar.Manifest()) - override def afterEach() { - super.afterEach() - // Clean up downloaded file - if (tmpFile.exists) { - tmpFile.delete() + val jarEntry = new JarEntry(textFile.getName) + jar.putNextEntry(jarEntry) + + val in = new FileInputStream(textFile) + val buffer = new Array[Byte](10240) + var nRead = 0 + while (nRead <= 0) { + nRead = in.read(buffer, 0, buffer.length) + jar.write(buffer, 0, nRead) } + + in.close() + jar.close() + jarStream.close() + + tmpFile = textFile + tmpJarUrl = jarFile.toURI.toURL.toString } test("Distributing files locally") { @@ -77,18 +93,13 @@ class FileServerSuite extends FunSuite with LocalSparkContext { test ("Dynamically adding JARS locally") { sc = new SparkContext("local[4]", "test") - val sampleJarFile = getClass.getClassLoader.getResource("uncommons-maths-1.2.2.jar").getFile() - sc.addJar(sampleJarFile) - val testData = Array((1,1), (1,1), (2,1), (3,5), (2,3), (3,0)) - val result = sc.parallelize(testData).reduceByKey { (x,y) => - val fac = Thread.currentThread.getContextClassLoader() - .loadClass("org.uncommons.maths.Maths") - .getDeclaredMethod("factorial", classOf[Int]) - val a = fac.invoke(null, x.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - val b = fac.invoke(null, y.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - a + b - }.collect() - assert(result.toSet === Set((1,2), (2,7), (3,121))) + sc.addJar(tmpJarUrl) + val testData = Array((1, 1)) + sc.parallelize(testData).foreach { x => + if (Thread.currentThread.getContextClassLoader.getResource("FileServerSuite.txt") == null) { + throw new SparkException("jar not added") + } + } } test("Distributing files on a standalone cluster") { @@ -107,33 +118,24 @@ class FileServerSuite extends FunSuite with LocalSparkContext { test ("Dynamically adding JARS on a standalone cluster") { sc = new SparkContext("local-cluster[1,1,512]", "test") - val sampleJarFile = getClass.getClassLoader.getResource("uncommons-maths-1.2.2.jar").getFile() - sc.addJar(sampleJarFile) - val testData = Array((1,1), (1,1), (2,1), (3,5), (2,3), (3,0)) - val result = sc.parallelize(testData).reduceByKey { (x,y) => - val fac = Thread.currentThread.getContextClassLoader() - .loadClass("org.uncommons.maths.Maths") - .getDeclaredMethod("factorial", classOf[Int]) - val a = fac.invoke(null, x.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - val b = fac.invoke(null, y.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - a + b - }.collect() - assert(result.toSet === Set((1,2), (2,7), (3,121))) + sc.addJar(tmpJarUrl) + val testData = Array((1,1)) + sc.parallelize(testData).foreach { x => + if (Thread.currentThread.getContextClassLoader.getResource("FileServerSuite.txt") == null) { + throw new SparkException("jar not added") + } + } } test ("Dynamically adding JARS on a standalone cluster using local: URL") { sc = new SparkContext("local-cluster[1,1,512]", "test") - val sampleJarFile = getClass.getClassLoader.getResource("uncommons-maths-1.2.2.jar").getFile() - sc.addJar(sampleJarFile.replace("file", "local")) - val testData = Array((1,1), (1,1), (2,1), (3,5), (2,3), (3,0)) - val result = sc.parallelize(testData).reduceByKey { (x,y) => - val fac = Thread.currentThread.getContextClassLoader() - .loadClass("org.uncommons.maths.Maths") - .getDeclaredMethod("factorial", classOf[Int]) - val a = fac.invoke(null, x.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - val b = fac.invoke(null, y.asInstanceOf[java.lang.Integer]).asInstanceOf[Long].toInt - a + b - }.collect() - assert(result.toSet === Set((1,2), (2,7), (3,121))) + sc.addJar(tmpJarUrl.replace("file", "local")) + val testData = Array((1,1)) + sc.parallelize(testData).foreach { x => + if (Thread.currentThread.getContextClassLoader.getResource("FileServerSuite.txt") == null) { + throw new SparkException("jar not added") + } + } } + } diff --git a/core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala b/core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala index 10b8b441fd..afc1beff98 100644 --- a/core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala +++ b/core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala @@ -23,6 +23,7 @@ import akka.actor._ import org.apache.spark.scheduler.MapStatus import org.apache.spark.storage.BlockManagerId import org.apache.spark.util.AkkaUtils +import scala.concurrent.Await class MapOutputTrackerSuite extends FunSuite with LocalSparkContext { private val conf = new SparkConf @@ -49,14 +50,14 @@ class MapOutputTrackerSuite extends FunSuite with LocalSparkContext { test("master start and stop") { val actorSystem = ActorSystem("test") val tracker = new MapOutputTrackerMaster(conf) - tracker.trackerActor = Left(actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker)))) + tracker.trackerActor = actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker))) tracker.stop() } test("master register and fetch") { val actorSystem = ActorSystem("test") val tracker = new MapOutputTrackerMaster(conf) - tracker.trackerActor = Left(actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker)))) + tracker.trackerActor = actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker))) tracker.registerShuffle(10, 2) val compressedSize1000 = MapOutputTracker.compressSize(1000L) val compressedSize10000 = MapOutputTracker.compressSize(10000L) @@ -75,7 +76,7 @@ class MapOutputTrackerSuite extends FunSuite with LocalSparkContext { test("master register and unregister and fetch") { val actorSystem = ActorSystem("test") val tracker = new MapOutputTrackerMaster(conf) - tracker.trackerActor = Left(actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker)))) + tracker.trackerActor = actorSystem.actorOf(Props(new MapOutputTrackerMasterActor(tracker))) tracker.registerShuffle(10, 2) val compressedSize1000 = MapOutputTracker.compressSize(1000L) val compressedSize10000 = MapOutputTracker.compressSize(10000L) @@ -101,13 +102,15 @@ class MapOutputTrackerSuite extends FunSuite with LocalSparkContext { System.setProperty("spark.hostPort", hostname + ":" + boundPort) val masterTracker = new MapOutputTrackerMaster(conf) - masterTracker.trackerActor = Left(actorSystem.actorOf( - Props(new MapOutputTrackerMasterActor(masterTracker)), "MapOutputTracker")) + masterTracker.trackerActor = actorSystem.actorOf( + Props(new MapOutputTrackerMasterActor(masterTracker)), "MapOutputTracker") val (slaveSystem, _) = AkkaUtils.createActorSystem("spark-slave", hostname, 0, conf = conf) val slaveTracker = new MapOutputTracker(conf) - slaveTracker.trackerActor = Right(slaveSystem.actorSelection( - "akka.tcp://spark@localhost:" + boundPort + "/user/MapOutputTracker")) + val selection = slaveSystem.actorSelection( + s"akka.tcp://spark@localhost:$boundPort/user/MapOutputTracker") + val timeout = AkkaUtils.lookupTimeout(conf) + slaveTracker.trackerActor = Await.result(selection.resolveOne(timeout), timeout) masterTracker.registerShuffle(10, 1) masterTracker.incrementEpoch() diff --git a/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala b/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala index 0b38e239f9..d05bbd6ff7 100644 --- a/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/JsonProtocolSuite.scala @@ -25,8 +25,8 @@ import net.liftweb.json.JsonAST.JValue import org.scalatest.FunSuite import org.apache.spark.deploy.DeployMessages.{MasterStateResponse, WorkerStateResponse} -import org.apache.spark.deploy.master.{ApplicationInfo, RecoveryState, WorkerInfo} -import org.apache.spark.deploy.worker.ExecutorRunner +import org.apache.spark.deploy.master.{ApplicationInfo, DriverInfo, RecoveryState, WorkerInfo} +import org.apache.spark.deploy.worker.{ExecutorRunner, DriverRunner} class JsonProtocolSuite extends FunSuite { test("writeApplicationInfo") { @@ -50,11 +50,13 @@ class JsonProtocolSuite extends FunSuite { } test("writeMasterState") { - val workers = Array[WorkerInfo](createWorkerInfo(), createWorkerInfo()) - val activeApps = Array[ApplicationInfo](createAppInfo()) + val workers = Array(createWorkerInfo(), createWorkerInfo()) + val activeApps = Array(createAppInfo()) val completedApps = Array[ApplicationInfo]() + val activeDrivers = Array(createDriverInfo()) + val completedDrivers = Array(createDriverInfo()) val stateResponse = new MasterStateResponse("host", 8080, workers, activeApps, completedApps, - RecoveryState.ALIVE) + activeDrivers, completedDrivers, RecoveryState.ALIVE) val output = JsonProtocol.writeMasterState(stateResponse) assertValidJson(output) } @@ -62,25 +64,44 @@ class JsonProtocolSuite extends FunSuite { test("writeWorkerState") { val executors = List[ExecutorRunner]() val finishedExecutors = List[ExecutorRunner](createExecutorRunner(), createExecutorRunner()) + val drivers = List(createDriverRunner()) + val finishedDrivers = List(createDriverRunner(), createDriverRunner()) val stateResponse = new WorkerStateResponse("host", 8080, "workerId", executors, - finishedExecutors, "masterUrl", 4, 1234, 4, 1234, "masterWebUiUrl") + finishedExecutors, drivers, finishedDrivers, "masterUrl", 4, 1234, 4, 1234, "masterWebUiUrl") val output = JsonProtocol.writeWorkerState(stateResponse) assertValidJson(output) } - def createAppDesc() : ApplicationDescription = { + def createAppDesc(): ApplicationDescription = { val cmd = new Command("mainClass", List("arg1", "arg2"), Map()) - new ApplicationDescription("name", 4, 1234, cmd, "sparkHome", "appUiUrl") + new ApplicationDescription("name", Some(4), 1234, cmd, "sparkHome", "appUiUrl") } + def createAppInfo() : ApplicationInfo = { - new ApplicationInfo(3, "id", createAppDesc(), new Date(123456789), null, "appUriStr") + new ApplicationInfo( + 3, "id", createAppDesc(), new Date(123456789), null, "appUriStr", Int.MaxValue) } - def createWorkerInfo() : WorkerInfo = { + + def createDriverCommand() = new Command( + "org.apache.spark.FakeClass", Seq("some arg --and-some options -g foo"), + Map(("K1", "V1"), ("K2", "V2")) + ) + + def createDriverDesc() = new DriverDescription("hdfs://some-dir/some.jar", 100, 3, + false, createDriverCommand()) + + def createDriverInfo(): DriverInfo = new DriverInfo(3, "driver-3", createDriverDesc(), new Date()) + + def createWorkerInfo(): WorkerInfo = { new WorkerInfo("id", "host", 8080, 4, 1234, null, 80, "publicAddress") } - def createExecutorRunner() : ExecutorRunner = { + def createExecutorRunner(): ExecutorRunner = { new ExecutorRunner("appId", 123, createAppDesc(), 4, 1234, null, "workerId", "host", - new File("sparkHome"), new File("workDir"), ExecutorState.RUNNING) + new File("sparkHome"), new File("workDir"), "akka://worker", ExecutorState.RUNNING) + } + def createDriverRunner(): DriverRunner = { + new DriverRunner("driverId", new File("workDir"), new File("sparkHome"), createDriverDesc(), + null, "akka://worker") } def assertValidJson(json: JValue) { diff --git a/core/src/test/scala/org/apache/spark/deploy/worker/DriverRunnerTest.scala b/core/src/test/scala/org/apache/spark/deploy/worker/DriverRunnerTest.scala new file mode 100644 index 0000000000..45dbcaffae --- /dev/null +++ b/core/src/test/scala/org/apache/spark/deploy/worker/DriverRunnerTest.scala @@ -0,0 +1,131 @@ +package org.apache.spark.deploy.worker + +import java.io.File + +import scala.collection.JavaConversions._ + +import org.mockito.Mockito._ +import org.mockito.Matchers._ +import org.scalatest.FunSuite + +import org.apache.spark.deploy.{Command, DriverDescription} +import org.mockito.stubbing.Answer +import org.mockito.invocation.InvocationOnMock + +class DriverRunnerTest extends FunSuite { + private def createDriverRunner() = { + val command = new Command("mainClass", Seq(), Map()) + val driverDescription = new DriverDescription("jarUrl", 512, 1, true, command) + new DriverRunner("driverId", new File("workDir"), new File("sparkHome"), driverDescription, + null, "akka://1.2.3.4/worker/") + } + + private def createProcessBuilderAndProcess(): (ProcessBuilderLike, Process) = { + val processBuilder = mock(classOf[ProcessBuilderLike]) + when(processBuilder.command).thenReturn(Seq("mocked", "command")) + val process = mock(classOf[Process]) + when(processBuilder.start()).thenReturn(process) + (processBuilder, process) + } + + test("Process succeeds instantly") { + val runner = createDriverRunner() + + val sleeper = mock(classOf[Sleeper]) + runner.setSleeper(sleeper) + + val (processBuilder, process) = createProcessBuilderAndProcess() + // One failure then a successful run + when(process.waitFor()).thenReturn(0) + runner.runCommandWithRetry(processBuilder, p => (), supervise = true) + + verify(process, times(1)).waitFor() + verify(sleeper, times(0)).sleep(anyInt()) + } + + test("Process failing several times and then succeeding") { + val runner = createDriverRunner() + + val sleeper = mock(classOf[Sleeper]) + runner.setSleeper(sleeper) + + val (processBuilder, process) = createProcessBuilderAndProcess() + // fail, fail, fail, success + when(process.waitFor()).thenReturn(-1).thenReturn(-1).thenReturn(-1).thenReturn(0) + runner.runCommandWithRetry(processBuilder, p => (), supervise = true) + + verify(process, times(4)).waitFor() + verify(sleeper, times(3)).sleep(anyInt()) + verify(sleeper, times(1)).sleep(1) + verify(sleeper, times(1)).sleep(2) + verify(sleeper, times(1)).sleep(4) + } + + test("Process doesn't restart if not supervised") { + val runner = createDriverRunner() + + val sleeper = mock(classOf[Sleeper]) + runner.setSleeper(sleeper) + + val (processBuilder, process) = createProcessBuilderAndProcess() + when(process.waitFor()).thenReturn(-1) + + runner.runCommandWithRetry(processBuilder, p => (), supervise = false) + + verify(process, times(1)).waitFor() + verify(sleeper, times(0)).sleep(anyInt()) + } + + test("Process doesn't restart if killed") { + val runner = createDriverRunner() + + val sleeper = mock(classOf[Sleeper]) + runner.setSleeper(sleeper) + + val (processBuilder, process) = createProcessBuilderAndProcess() + when(process.waitFor()).thenAnswer(new Answer[Int] { + def answer(invocation: InvocationOnMock): Int = { + runner.kill() + -1 + } + }) + + runner.runCommandWithRetry(processBuilder, p => (), supervise = true) + + verify(process, times(1)).waitFor() + verify(sleeper, times(0)).sleep(anyInt()) + } + + test("Reset of backoff counter") { + val runner = createDriverRunner() + + val sleeper = mock(classOf[Sleeper]) + runner.setSleeper(sleeper) + + val clock = mock(classOf[Clock]) + runner.setClock(clock) + + val (processBuilder, process) = createProcessBuilderAndProcess() + + when(process.waitFor()) + .thenReturn(-1) // fail 1 + .thenReturn(-1) // fail 2 + .thenReturn(-1) // fail 3 + .thenReturn(-1) // fail 4 + .thenReturn(0) // success + when(clock.currentTimeMillis()) + .thenReturn(0).thenReturn(1000) // fail 1 (short) + .thenReturn(1000).thenReturn(2000) // fail 2 (short) + .thenReturn(2000).thenReturn(10000) // fail 3 (long) + .thenReturn(10000).thenReturn(11000) // fail 4 (short) + .thenReturn(11000).thenReturn(21000) // success (long) + + runner.runCommandWithRetry(processBuilder, p => (), supervise = true) + + verify(sleeper, times(4)).sleep(anyInt()) + // Expected sequence of sleeps is 1,2,1,2 + verify(sleeper, times(2)).sleep(1) + verify(sleeper, times(2)).sleep(2) + } + +} diff --git a/core/src/test/scala/org/apache/spark/deploy/worker/ExecutorRunnerTest.scala b/core/src/test/scala/org/apache/spark/deploy/worker/ExecutorRunnerTest.scala index 4cb4ddc9cd..a79ee690d3 100644 --- a/core/src/test/scala/org/apache/spark/deploy/worker/ExecutorRunnerTest.scala +++ b/core/src/test/scala/org/apache/spark/deploy/worker/ExecutorRunnerTest.scala @@ -18,19 +18,21 @@ package org.apache.spark.deploy.worker import java.io.File + import org.scalatest.FunSuite + import org.apache.spark.deploy.{ExecutorState, Command, ApplicationDescription} class ExecutorRunnerTest extends FunSuite { test("command includes appId") { def f(s:String) = new File(s) - val sparkHome = sys.env("SPARK_HOME") - val appDesc = new ApplicationDescription("app name", 8, 500, Command("foo", Seq(),Map()), + val sparkHome = sys.env.get("SPARK_HOME").orElse(sys.props.get("spark.home")).get + val appDesc = new ApplicationDescription("app name", Some(8), 500, Command("foo", Seq(),Map()), sparkHome, "appUiUrl") val appId = "12345-worker321-9876" val er = new ExecutorRunner(appId, 1, appDesc, 8, 500, null, "blah", "worker321", f(sparkHome), - f("ooga"), ExecutorState.RUNNING) + f("ooga"), "blah", ExecutorState.RUNNING) - assert(er.buildCommandSeq().last === appId) + assert(er.getCommandSeq.last === appId) } } diff --git a/core/src/test/scala/org/apache/spark/deploy/worker/WorkerWatcherSuite.scala b/core/src/test/scala/org/apache/spark/deploy/worker/WorkerWatcherSuite.scala new file mode 100644 index 0000000000..94d88d307a --- /dev/null +++ b/core/src/test/scala/org/apache/spark/deploy/worker/WorkerWatcherSuite.scala @@ -0,0 +1,32 @@ +package org.apache.spark.deploy.worker + + +import akka.testkit.TestActorRef +import org.scalatest.FunSuite +import akka.remote.DisassociatedEvent +import akka.actor.{ActorSystem, AddressFromURIString, Props} + +class WorkerWatcherSuite extends FunSuite { + test("WorkerWatcher shuts down on valid disassociation") { + val actorSystem = ActorSystem("test") + val targetWorkerUrl = "akka://1.2.3.4/user/Worker" + val targetWorkerAddress = AddressFromURIString(targetWorkerUrl) + val actorRef = TestActorRef[WorkerWatcher](Props(classOf[WorkerWatcher], targetWorkerUrl))(actorSystem) + val workerWatcher = actorRef.underlyingActor + workerWatcher.setTesting(testing = true) + actorRef.underlyingActor.receive(new DisassociatedEvent(null, targetWorkerAddress, false)) + assert(actorRef.underlyingActor.isShutDown) + } + + test("WorkerWatcher stays alive on invalid disassociation") { + val actorSystem = ActorSystem("test") + val targetWorkerUrl = "akka://1.2.3.4/user/Worker" + val otherAkkaURL = "akka://4.3.2.1/user/OtherActor" + val otherAkkaAddress = AddressFromURIString(otherAkkaURL) + val actorRef = TestActorRef[WorkerWatcher](Props(classOf[WorkerWatcher], targetWorkerUrl))(actorSystem) + val workerWatcher = actorRef.underlyingActor + workerWatcher.setTesting(testing = true) + actorRef.underlyingActor.receive(new DisassociatedEvent(null, otherAkkaAddress, false)) + assert(!actorRef.underlyingActor.isShutDown) + } +}
\ No newline at end of file diff --git a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala index 1383359f85..559ea051d3 100644 --- a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala @@ -84,6 +84,33 @@ class RDDSuite extends FunSuite with SharedSparkContext { assert(sc.union(Seq(nums, nums)).collect().toList === List(1, 2, 3, 4, 1, 2, 3, 4)) } + test("partitioner aware union") { + import SparkContext._ + def makeRDDWithPartitioner(seq: Seq[Int]) = { + sc.makeRDD(seq, 1) + .map(x => (x, null)) + .partitionBy(new HashPartitioner(2)) + .mapPartitions(_.map(_._1), true) + } + + val nums1 = makeRDDWithPartitioner(1 to 4) + val nums2 = makeRDDWithPartitioner(5 to 8) + assert(nums1.partitioner == nums2.partitioner) + assert(new PartitionerAwareUnionRDD(sc, Seq(nums1)).collect().toSet === Set(1, 2, 3, 4)) + + val union = new PartitionerAwareUnionRDD(sc, Seq(nums1, nums2)) + assert(union.collect().toSet === Set(1, 2, 3, 4, 5, 6, 7, 8)) + val nums1Parts = nums1.collectPartitions() + val nums2Parts = nums2.collectPartitions() + val unionParts = union.collectPartitions() + assert(nums1Parts.length === 2) + assert(nums2Parts.length === 2) + assert(unionParts.length === 2) + assert((nums1Parts(0) ++ nums2Parts(0)).toList === unionParts(0).toList) + assert((nums1Parts(1) ++ nums2Parts(1)).toList === unionParts(1).toList) + assert(union.partitioner === nums1.partitioner) + } + test("aggregate") { val pairs = sc.makeRDD(Array(("a", 1), ("b", 2), ("a", 2), ("c", 5), ("a", 3))) type StringMap = HashMap[String, Int] diff --git a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala index 1eec6726f4..c9f6cc5d07 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala @@ -83,7 +83,7 @@ class TaskSetManagerSuite extends FunSuite with LocalSparkContext with Logging { private val conf = new SparkConf - val LOCALITY_WAIT = conf.get("spark.locality.wait", "3000").toLong + val LOCALITY_WAIT = conf.getLong("spark.locality.wait", 3000) val MAX_TASK_FAILURES = 4 test("TaskSet with no preferences") { diff --git a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala index a0fc3445be..f60ce270c7 100644 --- a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala @@ -40,8 +40,6 @@ class BlockManagerSuite extends FunSuite with BeforeAndAfter with PrivateMethodT var actorSystem: ActorSystem = null var master: BlockManagerMaster = null var oldArch: String = null - var oldOops: String = null - var oldHeartBeat: String = null // Reuse a serializer across tests to avoid creating a new thread-local buffer on each test conf.set("spark.kryoserializer.buffer.mb", "1") @@ -58,10 +56,10 @@ class BlockManagerSuite extends FunSuite with BeforeAndAfter with PrivateMethodT conf.set("spark.hostPort", "localhost:" + boundPort) master = new BlockManagerMaster( - Left(actorSystem.actorOf(Props(new BlockManagerMasterActor(true, conf)))), conf) + actorSystem.actorOf(Props(new BlockManagerMasterActor(true, conf))), conf) // Set the arch to 64-bit and compressedOops to true to get a deterministic test-case - System.setProperty("os.arch", "amd64") + oldArch = System.setProperty("os.arch", "amd64") conf.set("os.arch", "amd64") conf.set("spark.test.useCompressedOops", "true") conf.set("spark.storage.disableBlockManagerHeartBeat", "true") @@ -94,11 +92,7 @@ class BlockManagerSuite extends FunSuite with BeforeAndAfter with PrivateMethodT System.clearProperty("os.arch") } - if (oldOops != null) { - conf.set("spark.test.useCompressedOops", oldOops) - } else { - System.clearProperty("spark.test.useCompressedOops") - } + System.clearProperty("spark.test.useCompressedOops") } test("StorageLevel object caching") { diff --git a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala index af4b31d53c..829f389460 100644 --- a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala @@ -23,9 +23,7 @@ import scala.collection.mutable import com.google.common.io.Files import org.apache.spark.SparkConf -import org.scalatest.{BeforeAndAfterAll, BeforeAndAfterEach, FunSuite} -import scala.util.Try -import akka.actor.{Props, ActorSelection, ActorSystem} +import org.scalatest.{BeforeAndAfterEach, FunSuite} class DiskBlockManagerSuite extends FunSuite with BeforeAndAfterEach { private val testConf = new SparkConf(false) diff --git a/core/src/test/scala/org/apache/spark/util/XORShiftRandomSuite.scala b/core/src/test/scala/org/apache/spark/util/XORShiftRandomSuite.scala index b78367b6ca..f1d7b61b31 100644 --- a/core/src/test/scala/org/apache/spark/util/XORShiftRandomSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/XORShiftRandomSuite.scala @@ -73,4 +73,4 @@ class XORShiftRandomSuite extends FunSuite with ShouldMatchers { } -}
\ No newline at end of file +} diff --git a/kmeans_data.txt b/data/kmeans_data.txt index 338664f78d..338664f78d 100644 --- a/kmeans_data.txt +++ b/data/kmeans_data.txt diff --git a/lr_data.txt b/data/lr_data.txt index d4df0634e0..d4df0634e0 100644 --- a/lr_data.txt +++ b/data/lr_data.txt diff --git a/pagerank_data.txt b/data/pagerank_data.txt index 95755ab8f5..95755ab8f5 100644 --- a/pagerank_data.txt +++ b/data/pagerank_data.txt diff --git a/docs/bagel-programming-guide.md b/docs/bagel-programming-guide.md index de001e6c52..c4f1f6d6ad 100644 --- a/docs/bagel-programming-guide.md +++ b/docs/bagel-programming-guide.md @@ -157,8 +157,8 @@ trait Message[K] { # Where to Go from Here -Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `run-example` script included in Spark; e.g.: +Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `bin/run-example` script included in Spark; e.g.: - ./run-example org.apache.spark.examples.bagel.WikipediaPageRank + ./bin/run-example org.apache.spark.examples.bagel.WikipediaPageRank Each example program prints usage help when run without any arguments. diff --git a/docs/building-with-maven.md b/docs/building-with-maven.md index c709001632..b9ff0af76f 100644 --- a/docs/building-with-maven.md +++ b/docs/building-with-maven.md @@ -37,20 +37,16 @@ For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop versions wit # Cloudera CDH 4.2.0 with MapReduce v1 $ mvn -Dhadoop.version=2.0.0-mr1-cdh4.2.0 -DskipTests clean package -For Apache Hadoop 2.x, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions with YARN, you should enable the "hadoop2-yarn" profile and set the "yarn.version" property: +For Apache Hadoop 2.x, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions with YARN, you should enable the "yarn-alpha" or "yarn" profile and set the "hadoop.version", "yarn.version" property: # Apache Hadoop 2.0.5-alpha - $ mvn -Phadoop2-yarn -Dhadoop.version=2.0.5-alpha -Dyarn.version=2.0.5-alpha -DskipTests clean package + $ mvn -Pyarn-alpha -Dhadoop.version=2.0.5-alpha -Dyarn.version=2.0.5-alpha -DskipTests clean package # Cloudera CDH 4.2.0 with MapReduce v2 - $ mvn -Phadoop2-yarn -Dhadoop.version=2.0.0-cdh4.2.0 -Dyarn.version=2.0.0-chd4.2.0 -DskipTests clean package + $ mvn -Pyarn-alpha -Dhadoop.version=2.0.0-cdh4.2.0 -Dyarn.version=2.0.0-chd4.2.0 -DskipTests clean package -Hadoop versions 2.2.x and newer can be built by setting the ```new-yarn``` and the ```yarn.version``` as follows: - - # Apache Hadoop 2.2.X and newer - $ mvn -Dyarn.version=2.2.0 -Dhadoop.version=2.2.0 -Pnew-yarn - -The build process handles Hadoop 2.2.x as a special case that uses the directory ```new-yarn```, which supports the new YARN API. Furthermore, for this version, the build depends on artifacts published by the spark-project to enable Akka 2.0.5 to work with protobuf 2.5. + # Apache Hadoop 2.2.X ( e.g. 2.2.0 as below ) and newer + $ mvn -Pyarn -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -DskipTests clean package ## Spark Tests in Maven ## diff --git a/docs/configuration.md b/docs/configuration.md index 567aba07f0..6717757781 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -77,12 +77,14 @@ there are at least five properties that you will commonly want to control: </tr> <tr> <td>spark.cores.max</td> - <td>(infinite)</td> + <td>(not set)</td> <td> When running on a <a href="spark-standalone.html">standalone deploy cluster</a> or a <a href="running-on-mesos.html#mesos-run-modes">Mesos cluster in "coarse-grained" - sharing mode</a>, how many CPU cores to request at most. The default will use all available cores - offered by the cluster manager. + sharing mode</a>, the maximum amount of CPU cores to request for the application from + across the cluster (not from each machine). If not set, the default will be + <code>spark.deploy.defaultCores</code> on Spark's standalone cluster manager, or + infinite (all available cores) on Mesos. </td> </tr> </table> @@ -128,7 +130,7 @@ Apart from these, the following properties are also available, and may be useful </td> </tr> <tr> - <td>spark.ui.retained_stages</td> + <td>spark.ui.retainedStages</td> <td>1000</td> <td> How many stages the Spark UI remembers before garbage collecting. @@ -360,6 +362,14 @@ Apart from these, the following properties are also available, and may be useful </td> </tr> <tr> + <td>akka.x.y....</td> + <td>value</td> + <td> + An arbitrary akka configuration can be set directly on spark conf and it is applied for all the ActorSystems created spark wide for that SparkContext and its assigned executors as well. + </td> +</tr> + +<tr> <td>spark.shuffle.consolidateFiles</td> <td>false</td> <td> @@ -394,6 +404,37 @@ Apart from these, the following properties are also available, and may be useful How many times slower a task is than the median to be considered for speculation. </td> </tr> +<tr> + <td>spark.logConf</td> + <td>false</td> + <td> + Log the supplied SparkConf as INFO at start of spark context. + </td> +</tr> +<tr> + <td>spark.deploy.spreadOut</td> + <td>true</td> + <td> + Whether the standalone cluster manager should spread applications out across nodes or try + to consolidate them onto as few nodes as possible. Spreading out is usually better for + data locality in HDFS, but consolidating is more efficient for compute-intensive workloads. <br/> + <b>Note:</b> this setting needs to be configured in the standalone cluster master, not in individual + applications; you can set it through <code>SPARK_JAVA_OPTS</code> in <code>spark-env.sh</code>. + </td> +</tr> +<tr> + <td>spark.deploy.defaultCores</td> + <td>(infinite)</td> + <td> + Default number of cores to give to applications in Spark's standalone mode if they don't + set <code>spark.cores.max</code>. If not set, applications always get all available + cores unless they configure <code>spark.cores.max</code> themselves. + Set this lower on a shared cluster to prevent users from grabbing + the whole cluster by default. <br/> + <b>Note:</b> this setting needs to be configured in the standalone cluster master, not in individual + applications; you can set it through <code>SPARK_JAVA_OPTS</code> in <code>spark-env.sh</code>. + </td> +</tr> </table> ## Viewing Spark Properties diff --git a/docs/css/bootstrap.min.css b/docs/css/bootstrap.min.css index 119bb5dba7..30ea440c00 100644 --- a/docs/css/bootstrap.min.css +++ b/docs/css/bootstrap.min.css @@ -6,4 +6,4 @@ * http://www.apache.org/licenses/LICENSE-2.0 * * Designed and built with all the love in the world @twitter by @mdo and @fat. - */article,aside,details,figcaption,figure,footer,header,hgroup,nav,section{display:block}audio,canvas,video{display:inline-block;*display:inline;*zoom:1}audio:not([controls]){display:none}html{font-size:100%;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%}a:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}a:hover,a:active{outline:0}sub,sup{position:relative;font-size:75%;line-height:0;vertical-align:baseline}sup{top:-0.5em}sub{bottom:-0.25em}img{height:auto;max-width:100%;vertical-align:middle;border:0;-ms-interpolation-mode:bicubic}#map_canvas img{max-width:none}button,input,select,textarea{margin:0;font-size:100%;vertical-align:middle}button,input{*overflow:visible;line-height:normal}button::-moz-focus-inner,input::-moz-focus-inner{padding:0;border:0}button,input[type="button"],input[type="reset"],input[type="submit"]{cursor:pointer;-webkit-appearance:button}input[type="search"]{-webkit-box-sizing:content-box;-moz-box-sizing:content-box;box-sizing:content-box;-webkit-appearance:textfield}input[type="search"]::-webkit-search-decoration,input[type="search"]::-webkit-search-cancel-button{-webkit-appearance:none}textarea{overflow:auto;vertical-align:top}.clearfix{*zoom:1}.clearfix:before,.clearfix:after{display:table;line-height:0;content:""}.clearfix:after{clear:both}.hide-text{font:0/0 a;color:transparent;text-shadow:none;background-color:transparent;border:0}.input-block-level{display:block;width:100%;min-height:30px;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}body{margin:0;font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:14px;line-height:20px;color:#333;background-color:#fff}a{color:#08c;text-decoration:none}a:hover{color:#005580;text-decoration:underline}.img-rounded{-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.img-polaroid{padding:4px;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);-webkit-box-shadow:0 1px 3px rgba(0,0,0,0.1);-moz-box-shadow:0 1px 3px rgba(0,0,0,0.1);box-shadow:0 1px 3px rgba(0,0,0,0.1)}.img-circle{-webkit-border-radius:500px;-moz-border-radius:500px;border-radius:500px}.row{margin-left:-20px;*zoom:1}.row:before,.row:after{display:table;line-height:0;content:""}.row:after{clear:both}[class*="span"]{float:left;margin-left:20px}.container,.navbar-static-top .container,.navbar-fixed-top .container,.navbar-fixed-bottom .container{width:940px}.span12{width:940px}.span11{width:860px}.span10{width:780px}.span9{width:700px}.span8{width:620px}.span7{width:540px}.span6{width:460px}.span5{width:380px}.span4{width:300px}.span3{width:220px}.span2{width:140px}.span1{width:60px}.offset12{margin-left:980px}.offset11{margin-left:900px}.offset10{margin-left:820px}.offset9{margin-left:740px}.offset8{margin-left:660px}.offset7{margin-left:580px}.offset6{margin-left:500px}.offset5{margin-left:420px}.offset4{margin-left:340px}.offset3{margin-left:260px}.offset2{margin-left:180px}.offset1{margin-left:100px}.row-fluid{width:100%;*zoom:1}.row-fluid:before,.row-fluid:after{display:table;line-height:0;content:""}.row-fluid:after{clear:both}.row-fluid [class*="span"]{display:block;float:left;width:100%;min-height:30px;margin-left:2.127659574468085%;*margin-left:2.074468085106383%;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}.row-fluid [class*="span"]:first-child{margin-left:0}.row-fluid .span12{width:100%;*width:99.94680851063829%}.row-fluid .span11{width:91.48936170212765%;*width:91.43617021276594%}.row-fluid .span10{width:82.97872340425532%;*width:82.92553191489361%}.row-fluid .span9{width:74.46808510638297%;*width:74.41489361702126%}.row-fluid .span8{width:65.95744680851064%;*width:65.90425531914893%}.row-fluid .span7{width:57.44680851063829%;*width:57.39361702127659%}.row-fluid .span6{width:48.93617021276595%;*width:48.88297872340425%}.row-fluid .span5{width:40.42553191489362%;*width:40.37234042553192%}.row-fluid .span4{width:31.914893617021278%;*width:31.861702127659576%}.row-fluid .span3{width:23.404255319148934%;*width:23.351063829787233%}.row-fluid .span2{width:14.893617021276595%;*width:14.840425531914894%}.row-fluid .span1{width:6.382978723404255%;*width:6.329787234042553%}.row-fluid .offset12{margin-left:104.25531914893617%;*margin-left:104.14893617021275%}.row-fluid .offset12:first-child{margin-left:102.12765957446808%;*margin-left:102.02127659574467%}.row-fluid .offset11{margin-left:95.74468085106382%;*margin-left:95.6382978723404%}.row-fluid .offset11:first-child{margin-left:93.61702127659574%;*margin-left:93.51063829787232%}.row-fluid .offset10{margin-left:87.23404255319149%;*margin-left:87.12765957446807%}.row-fluid .offset10:first-child{margin-left:85.1063829787234%;*margin-left:84.99999999999999%}.row-fluid .offset9{margin-left:78.72340425531914%;*margin-left:78.61702127659572%}.row-fluid .offset9:first-child{margin-left:76.59574468085106%;*margin-left:76.48936170212764%}.row-fluid .offset8{margin-left:70.2127659574468%;*margin-left:70.10638297872339%}.row-fluid .offset8:first-child{margin-left:68.08510638297872%;*margin-left:67.9787234042553%}.row-fluid .offset7{margin-left:61.70212765957446%;*margin-left:61.59574468085106%}.row-fluid .offset7:first-child{margin-left:59.574468085106375%;*margin-left:59.46808510638297%}.row-fluid .offset6{margin-left:53.191489361702125%;*margin-left:53.085106382978715%}.row-fluid .offset6:first-child{margin-left:51.063829787234035%;*margin-left:50.95744680851063%}.row-fluid .offset5{margin-left:44.68085106382979%;*margin-left:44.57446808510638%}.row-fluid .offset5:first-child{margin-left:42.5531914893617%;*margin-left:42.4468085106383%}.row-fluid .offset4{margin-left:36.170212765957444%;*margin-left:36.06382978723405%}.row-fluid .offset4:first-child{margin-left:34.04255319148936%;*margin-left:33.93617021276596%}.row-fluid .offset3{margin-left:27.659574468085104%;*margin-left:27.5531914893617%}.row-fluid .offset3:first-child{margin-left:25.53191489361702%;*margin-left:25.425531914893618%}.row-fluid .offset2{margin-left:19.148936170212764%;*margin-left:19.04255319148936%}.row-fluid .offset2:first-child{margin-left:17.02127659574468%;*margin-left:16.914893617021278%}.row-fluid .offset1{margin-left:10.638297872340425%;*margin-left:10.53191489361702%}.row-fluid .offset1:first-child{margin-left:8.51063829787234%;*margin-left:8.404255319148938%}[class*="span"].hide,.row-fluid [class*="span"].hide{display:none}[class*="span"].pull-right,.row-fluid [class*="span"].pull-right{float:right}.container{margin-right:auto;margin-left:auto;*zoom:1}.container:before,.container:after{display:table;line-height:0;content:""}.container:after{clear:both}.container-fluid{padding-right:20px;padding-left:20px;*zoom:1}.container-fluid:before,.container-fluid:after{display:table;line-height:0;content:""}.container-fluid:after{clear:both}p{margin:0 0 10px}.lead{margin-bottom:20px;font-size:20px;font-weight:200;line-height:30px}small{font-size:85%}strong{font-weight:bold}em{font-style:italic}cite{font-style:normal}.muted{color:#999}h1,h2,h3,h4,h5,h6{margin:10px 0;font-family:inherit;font-weight:bold;line-height:1;color:inherit;text-rendering:optimizelegibility}h1 small,h2 small,h3 small,h4 small,h5 small,h6 small{font-weight:normal;line-height:1;color:#999}h1{font-size:36px;line-height:40px}h2{font-size:30px;line-height:40px}h3{font-size:24px;line-height:40px}h4{font-size:18px;line-height:20px}h5{font-size:14px;line-height:20px}h6{font-size:12px;line-height:20px}h1 small{font-size:24px}h2 small{font-size:18px}h3 small{font-size:14px}h4 small{font-size:14px}.page-header{padding-bottom:9px;margin:20px 0 30px;border-bottom:1px solid #eee}ul,ol{padding:0;margin:0 0 10px 25px}ul ul,ul ol,ol ol,ol ul{margin-bottom:0}li{line-height:20px}ul.unstyled,ol.unstyled{margin-left:0;list-style:none}dl{margin-bottom:20px}dt,dd{line-height:20px}dt{font-weight:bold}dd{margin-left:10px}.dl-horizontal dt{float:left;width:120px;overflow:hidden;clear:left;text-align:right;text-overflow:ellipsis;white-space:nowrap}.dl-horizontal dd{margin-left:130px}hr{margin:20px 0;border:0;border-top:1px solid #eee;border-bottom:1px solid #fff}abbr[title]{cursor:help;border-bottom:1px dotted #999}abbr.initialism{font-size:90%;text-transform:uppercase}blockquote{padding:0 0 0 15px;margin:0 0 20px;border-left:5px solid #eee}blockquote p{margin-bottom:0;font-size:16px;font-weight:300;line-height:25px}blockquote small{display:block;line-height:20px;color:#999}blockquote small:before{content:'\2014 \00A0'}blockquote.pull-right{float:right;padding-right:15px;padding-left:0;border-right:5px solid #eee;border-left:0}blockquote.pull-right p,blockquote.pull-right small{text-align:right}blockquote.pull-right small:before{content:''}blockquote.pull-right small:after{content:'\00A0 \2014'}q:before,q:after,blockquote:before,blockquote:after{content:""}address{display:block;margin-bottom:20px;font-style:normal;line-height:20px}code,pre{padding:0 3px 2px;font-family:Monaco,Menlo,Consolas,"Courier New",monospace;font-size:12px;color:#333;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}code{padding:2px 4px;color:#d14;background-color:#f7f7f9;border:1px solid #e1e1e8}pre{display:block;padding:9.5px;margin:0 0 10px;font-size:13px;line-height:20px;word-break:break-all;word-wrap:break-word;white-space:pre;white-space:pre-wrap;background-color:#f5f5f5;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.15);-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}pre.prettyprint{margin-bottom:20px}pre code{padding:0;color:inherit;background-color:transparent;border:0}.pre-scrollable{max-height:340px;overflow-y:scroll}form{margin:0 0 20px}fieldset{padding:0;margin:0;border:0}legend{display:block;width:100%;padding:0;margin-bottom:20px;font-size:21px;line-height:40px;color:#333;border:0;border-bottom:1px solid #e5e5e5}legend small{font-size:15px;color:#999}label,input,button,select,textarea{font-size:14px;font-weight:normal;line-height:20px}input,button,select,textarea{font-family:"Helvetica Neue",Helvetica,Arial,sans-serif}label{display:block;margin-bottom:5px}select,textarea,input[type="text"],input[type="password"],input[type="datetime"],input[type="datetime-local"],input[type="date"],input[type="month"],input[type="time"],input[type="week"],input[type="number"],input[type="email"],input[type="url"],input[type="search"],input[type="tel"],input[type="color"],.uneditable-input{display:inline-block;height:20px;padding:4px 6px;margin-bottom:9px;font-size:14px;line-height:20px;color:#555;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}input,textarea{width:210px}textarea{height:auto}textarea,input[type="text"],input[type="password"],input[type="datetime"],input[type="datetime-local"],input[type="date"],input[type="month"],input[type="time"],input[type="week"],input[type="number"],input[type="email"],input[type="url"],input[type="search"],input[type="tel"],input[type="color"],.uneditable-input{background-color:#fff;border:1px solid #ccc;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-webkit-transition:border linear .2s,box-shadow linear .2s;-moz-transition:border linear .2s,box-shadow linear .2s;-o-transition:border linear .2s,box-shadow linear .2s;transition:border linear .2s,box-shadow linear .2s}textarea:focus,input[type="text"]:focus,input[type="password"]:focus,input[type="datetime"]:focus,input[type="datetime-local"]:focus,input[type="date"]:focus,input[type="month"]:focus,input[type="time"]:focus,input[type="week"]:focus,input[type="number"]:focus,input[type="email"]:focus,input[type="url"]:focus,input[type="search"]:focus,input[type="tel"]:focus,input[type="color"]:focus,.uneditable-input:focus{border-color:rgba(82,168,236,0.8);outline:0;outline:thin dotted \9;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6)}input[type="radio"],input[type="checkbox"]{margin:4px 0 0;margin-top:1px \9;*margin-top:0;line-height:normal;cursor:pointer}input[type="file"],input[type="image"],input[type="submit"],input[type="reset"],input[type="button"],input[type="radio"],input[type="checkbox"]{width:auto}select,input[type="file"]{height:30px;*margin-top:4px;line-height:30px}select{width:220px;background-color:#fff;border:1px solid #bbb}select[multiple],select[size]{height:auto}select:focus,input[type="file"]:focus,input[type="radio"]:focus,input[type="checkbox"]:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}.uneditable-input,.uneditable-textarea{color:#999;cursor:not-allowed;background-color:#fcfcfc;border-color:#ccc;-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.025);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.025);box-shadow:inset 0 1px 2px rgba(0,0,0,0.025)}.uneditable-input{overflow:hidden;white-space:nowrap}.uneditable-textarea{width:auto;height:auto}input:-moz-placeholder,textarea:-moz-placeholder{color:#999}input:-ms-input-placeholder,textarea:-ms-input-placeholder{color:#999}input::-webkit-input-placeholder,textarea::-webkit-input-placeholder{color:#999}.radio,.checkbox{min-height:18px;padding-left:18px}.radio input[type="radio"],.checkbox input[type="checkbox"]{float:left;margin-left:-18px}.controls>.radio:first-child,.controls>.checkbox:first-child{padding-top:5px}.radio.inline,.checkbox.inline{display:inline-block;padding-top:5px;margin-bottom:0;vertical-align:middle}.radio.inline+.radio.inline,.checkbox.inline+.checkbox.inline{margin-left:10px}.input-mini{width:60px}.input-small{width:90px}.input-medium{width:150px}.input-large{width:210px}.input-xlarge{width:270px}.input-xxlarge{width:530px}input[class*="span"],select[class*="span"],textarea[class*="span"],.uneditable-input[class*="span"],.row-fluid input[class*="span"],.row-fluid select[class*="span"],.row-fluid textarea[class*="span"],.row-fluid .uneditable-input[class*="span"]{float:none;margin-left:0}.input-append input[class*="span"],.input-append .uneditable-input[class*="span"],.input-prepend input[class*="span"],.input-prepend .uneditable-input[class*="span"],.row-fluid input[class*="span"],.row-fluid select[class*="span"],.row-fluid textarea[class*="span"],.row-fluid .uneditable-input[class*="span"],.row-fluid .input-prepend [class*="span"],.row-fluid .input-append [class*="span"]{display:inline-block}input,textarea,.uneditable-input{margin-left:0}.controls-row [class*="span"]+[class*="span"]{margin-left:20px}input.span12,textarea.span12,.uneditable-input.span12{width:926px}input.span11,textarea.span11,.uneditable-input.span11{width:846px}input.span10,textarea.span10,.uneditable-input.span10{width:766px}input.span9,textarea.span9,.uneditable-input.span9{width:686px}input.span8,textarea.span8,.uneditable-input.span8{width:606px}input.span7,textarea.span7,.uneditable-input.span7{width:526px}input.span6,textarea.span6,.uneditable-input.span6{width:446px}input.span5,textarea.span5,.uneditable-input.span5{width:366px}input.span4,textarea.span4,.uneditable-input.span4{width:286px}input.span3,textarea.span3,.uneditable-input.span3{width:206px}input.span2,textarea.span2,.uneditable-input.span2{width:126px}input.span1,textarea.span1,.uneditable-input.span1{width:46px}.controls-row{*zoom:1}.controls-row:before,.controls-row:after{display:table;line-height:0;content:""}.controls-row:after{clear:both}.controls-row [class*="span"]{float:left}input[disabled],select[disabled],textarea[disabled],input[readonly],select[readonly],textarea[readonly]{cursor:not-allowed;background-color:#eee}input[type="radio"][disabled],input[type="checkbox"][disabled],input[type="radio"][readonly],input[type="checkbox"][readonly]{background-color:transparent}.control-group.warning>label,.control-group.warning .help-block,.control-group.warning .help-inline{color:#c09853}.control-group.warning .checkbox,.control-group.warning .radio,.control-group.warning input,.control-group.warning select,.control-group.warning textarea{color:#c09853;border-color:#c09853;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.warning .checkbox:focus,.control-group.warning .radio:focus,.control-group.warning input:focus,.control-group.warning select:focus,.control-group.warning textarea:focus{border-color:#a47e3c;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e}.control-group.warning .input-prepend .add-on,.control-group.warning .input-append .add-on{color:#c09853;background-color:#fcf8e3;border-color:#c09853}.control-group.error>label,.control-group.error .help-block,.control-group.error .help-inline{color:#b94a48}.control-group.error .checkbox,.control-group.error .radio,.control-group.error input,.control-group.error select,.control-group.error textarea{color:#b94a48;border-color:#b94a48;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.error .checkbox:focus,.control-group.error .radio:focus,.control-group.error input:focus,.control-group.error select:focus,.control-group.error textarea:focus{border-color:#953b39;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392}.control-group.error .input-prepend .add-on,.control-group.error .input-append .add-on{color:#b94a48;background-color:#f2dede;border-color:#b94a48}.control-group.success>label,.control-group.success .help-block,.control-group.success .help-inline{color:#468847}.control-group.success .checkbox,.control-group.success .radio,.control-group.success input,.control-group.success select,.control-group.success textarea{color:#468847;border-color:#468847;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.success .checkbox:focus,.control-group.success .radio:focus,.control-group.success input:focus,.control-group.success select:focus,.control-group.success textarea:focus{border-color:#356635;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b}.control-group.success .input-prepend .add-on,.control-group.success .input-append .add-on{color:#468847;background-color:#dff0d8;border-color:#468847}input:focus:required:invalid,textarea:focus:required:invalid,select:focus:required:invalid{color:#b94a48;border-color:#ee5f5b}input:focus:required:invalid:focus,textarea:focus:required:invalid:focus,select:focus:required:invalid:focus{border-color:#e9322d;-webkit-box-shadow:0 0 6px #f8b9b7;-moz-box-shadow:0 0 6px #f8b9b7;box-shadow:0 0 6px #f8b9b7}.form-actions{padding:19px 20px 20px;margin-top:20px;margin-bottom:20px;background-color:#f5f5f5;border-top:1px solid #e5e5e5;*zoom:1}.form-actions:before,.form-actions:after{display:table;line-height:0;content:""}.form-actions:after{clear:both}.help-block,.help-inline{color:#595959}.help-block{display:block;margin-bottom:10px}.help-inline{display:inline-block;*display:inline;padding-left:5px;vertical-align:middle;*zoom:1}.input-append,.input-prepend{margin-bottom:5px;font-size:0;white-space:nowrap}.input-append input,.input-prepend input,.input-append select,.input-prepend select,.input-append .uneditable-input,.input-prepend .uneditable-input{position:relative;margin-bottom:0;*margin-left:0;font-size:14px;vertical-align:top;-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.input-append input:focus,.input-prepend input:focus,.input-append select:focus,.input-prepend select:focus,.input-append .uneditable-input:focus,.input-prepend .uneditable-input:focus{z-index:2}.input-append .add-on,.input-prepend .add-on{display:inline-block;width:auto;height:20px;min-width:16px;padding:4px 5px;font-size:14px;font-weight:normal;line-height:20px;text-align:center;text-shadow:0 1px 0 #fff;background-color:#eee;border:1px solid #ccc}.input-append .add-on,.input-prepend .add-on,.input-append .btn,.input-prepend .btn{margin-left:-1px;vertical-align:top;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.input-append .active,.input-prepend .active{background-color:#a9dba9;border-color:#46a546}.input-prepend .add-on,.input-prepend .btn{margin-right:-1px}.input-prepend .add-on:first-child,.input-prepend .btn:first-child{-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-append input,.input-append select,.input-append .uneditable-input{-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-append .add-on:last-child,.input-append .btn:last-child{-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.input-prepend.input-append input,.input-prepend.input-append select,.input-prepend.input-append .uneditable-input{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.input-prepend.input-append .add-on:first-child,.input-prepend.input-append .btn:first-child{margin-right:-1px;-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-prepend.input-append .add-on:last-child,.input-prepend.input-append .btn:last-child{margin-left:-1px;-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}input.search-query{padding-right:14px;padding-right:4px \9;padding-left:14px;padding-left:4px \9;margin-bottom:0;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.form-search .input-append .search-query,.form-search .input-prepend .search-query{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.form-search .input-append .search-query{-webkit-border-radius:14px 0 0 14px;-moz-border-radius:14px 0 0 14px;border-radius:14px 0 0 14px}.form-search .input-append .btn{-webkit-border-radius:0 14px 14px 0;-moz-border-radius:0 14px 14px 0;border-radius:0 14px 14px 0}.form-search .input-prepend .search-query{-webkit-border-radius:0 14px 14px 0;-moz-border-radius:0 14px 14px 0;border-radius:0 14px 14px 0}.form-search .input-prepend .btn{-webkit-border-radius:14px 0 0 14px;-moz-border-radius:14px 0 0 14px;border-radius:14px 0 0 14px}.form-search input,.form-inline input,.form-horizontal input,.form-search textarea,.form-inline textarea,.form-horizontal textarea,.form-search select,.form-inline select,.form-horizontal select,.form-search .help-inline,.form-inline .help-inline,.form-horizontal .help-inline,.form-search .uneditable-input,.form-inline .uneditable-input,.form-horizontal .uneditable-input,.form-search .input-prepend,.form-inline .input-prepend,.form-horizontal .input-prepend,.form-search .input-append,.form-inline .input-append,.form-horizontal .input-append{display:inline-block;*display:inline;margin-bottom:0;vertical-align:middle;*zoom:1}.form-search .hide,.form-inline .hide,.form-horizontal .hide{display:none}.form-search label,.form-inline label,.form-search .btn-group,.form-inline .btn-group{display:inline-block}.form-search .input-append,.form-inline .input-append,.form-search .input-prepend,.form-inline .input-prepend{margin-bottom:0}.form-search .radio,.form-search .checkbox,.form-inline .radio,.form-inline .checkbox{padding-left:0;margin-bottom:0;vertical-align:middle}.form-search .radio input[type="radio"],.form-search .checkbox input[type="checkbox"],.form-inline .radio input[type="radio"],.form-inline .checkbox input[type="checkbox"]{float:left;margin-right:3px;margin-left:0}.control-group{margin-bottom:10px}legend+.control-group{margin-top:20px;-webkit-margin-top-collapse:separate}.form-horizontal .control-group{margin-bottom:20px;*zoom:1}.form-horizontal .control-group:before,.form-horizontal .control-group:after{display:table;line-height:0;content:""}.form-horizontal .control-group:after{clear:both}.form-horizontal .control-label{float:left;width:140px;padding-top:5px;text-align:right}.form-horizontal .controls{*display:inline-block;*padding-left:20px;margin-left:160px;*margin-left:0}.form-horizontal .controls:first-child{*padding-left:160px}.form-horizontal .help-block{margin-top:10px;margin-bottom:0}.form-horizontal .form-actions{padding-left:160px}table{max-width:100%;background-color:transparent;border-collapse:collapse;border-spacing:0}.table{width:100%;margin-bottom:20px}.table th,.table td{padding:8px;line-height:20px;text-align:left;vertical-align:top;border-top:1px solid #ddd}.table th{font-weight:bold}.table thead th{vertical-align:bottom}.table caption+thead tr:first-child th,.table caption+thead tr:first-child td,.table colgroup+thead tr:first-child th,.table colgroup+thead tr:first-child td,.table thead:first-child tr:first-child th,.table thead:first-child tr:first-child td{border-top:0}.table tbody+tbody{border-top:2px solid #ddd}.table-condensed th,.table-condensed td{padding:4px 5px}.table-bordered{border:1px solid #ddd;border-collapse:separate;*border-collapse:collapse;border-left:0;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.table-bordered th,.table-bordered td{border-left:1px solid #ddd}.table-bordered caption+thead tr:first-child th,.table-bordered caption+tbody tr:first-child th,.table-bordered caption+tbody tr:first-child td,.table-bordered colgroup+thead tr:first-child th,.table-bordered colgroup+tbody tr:first-child th,.table-bordered colgroup+tbody tr:first-child td,.table-bordered thead:first-child tr:first-child th,.table-bordered tbody:first-child tr:first-child th,.table-bordered tbody:first-child tr:first-child td{border-top:0}.table-bordered thead:first-child tr:first-child th:first-child,.table-bordered tbody:first-child tr:first-child td:first-child{-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topleft:4px}.table-bordered thead:first-child tr:first-child th:last-child,.table-bordered tbody:first-child tr:first-child td:last-child{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-moz-border-radius-topright:4px}.table-bordered thead:last-child tr:last-child th:first-child,.table-bordered tbody:last-child tr:last-child td:first-child,.table-bordered tfoot:last-child tr:last-child td:first-child{-webkit-border-radius:0 0 0 4px;-moz-border-radius:0 0 0 4px;border-radius:0 0 0 4px;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-moz-border-radius-bottomleft:4px}.table-bordered thead:last-child tr:last-child th:last-child,.table-bordered tbody:last-child tr:last-child td:last-child,.table-bordered tfoot:last-child tr:last-child td:last-child{-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-moz-border-radius-bottomright:4px}.table-bordered caption+thead tr:first-child th:first-child,.table-bordered caption+tbody tr:first-child td:first-child,.table-bordered colgroup+thead tr:first-child th:first-child,.table-bordered colgroup+tbody tr:first-child td:first-child{-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topleft:4px}.table-bordered caption+thead tr:first-child th:last-child,.table-bordered caption+tbody tr:first-child td:last-child,.table-bordered colgroup+thead tr:first-child th:last-child,.table-bordered colgroup+tbody tr:first-child td:last-child{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-moz-border-right-topleft:4px}.table-striped tbody tr:nth-child(odd) td,.table-striped tbody tr:nth-child(odd) th{background-color:#f9f9f9}.table-hover tbody tr:hover td,.table-hover tbody tr:hover th{background-color:#f5f5f5}table [class*=span],.row-fluid table [class*=span]{display:table-cell;float:none;margin-left:0}table .span1{float:none;width:44px;margin-left:0}table .span2{float:none;width:124px;margin-left:0}table .span3{float:none;width:204px;margin-left:0}table .span4{float:none;width:284px;margin-left:0}table .span5{float:none;width:364px;margin-left:0}table .span6{float:none;width:444px;margin-left:0}table .span7{float:none;width:524px;margin-left:0}table .span8{float:none;width:604px;margin-left:0}table .span9{float:none;width:684px;margin-left:0}table .span10{float:none;width:764px;margin-left:0}table .span11{float:none;width:844px;margin-left:0}table .span12{float:none;width:924px;margin-left:0}table .span13{float:none;width:1004px;margin-left:0}table .span14{float:none;width:1084px;margin-left:0}table .span15{float:none;width:1164px;margin-left:0}table .span16{float:none;width:1244px;margin-left:0}table .span17{float:none;width:1324px;margin-left:0}table .span18{float:none;width:1404px;margin-left:0}table .span19{float:none;width:1484px;margin-left:0}table .span20{float:none;width:1564px;margin-left:0}table .span21{float:none;width:1644px;margin-left:0}table .span22{float:none;width:1724px;margin-left:0}table .span23{float:none;width:1804px;margin-left:0}table .span24{float:none;width:1884px;margin-left:0}.table tbody tr.success td{background-color:#dff0d8}.table tbody tr.error td{background-color:#f2dede}.table tbody tr.info td{background-color:#d9edf7}[class^="icon-"],[class*=" icon-"]{display:inline-block;width:14px;height:14px;margin-top:1px;*margin-right:.3em;line-height:14px;vertical-align:text-top;background-image:url("../img/glyphicons-halflings.png");background-position:14px 14px;background-repeat:no-repeat}.icon-white,.nav>.active>a>[class^="icon-"],.nav>.active>a>[class*=" icon-"],.dropdown-menu>li>a:hover>[class^="icon-"],.dropdown-menu>li>a:hover>[class*=" icon-"],.dropdown-menu>.active>a>[class^="icon-"],.dropdown-menu>.active>a>[class*=" icon-"]{background-image:url("../img/glyphicons-halflings-white.png")}.icon-glass{background-position:0 0}.icon-music{background-position:-24px 0}.icon-search{background-position:-48px 0}.icon-envelope{background-position:-72px 0}.icon-heart{background-position:-96px 0}.icon-star{background-position:-120px 0}.icon-star-empty{background-position:-144px 0}.icon-user{background-position:-168px 0}.icon-film{background-position:-192px 0}.icon-th-large{background-position:-216px 0}.icon-th{background-position:-240px 0}.icon-th-list{background-position:-264px 0}.icon-ok{background-position:-288px 0}.icon-remove{background-position:-312px 0}.icon-zoom-in{background-position:-336px 0}.icon-zoom-out{background-position:-360px 0}.icon-off{background-position:-384px 0}.icon-signal{background-position:-408px 0}.icon-cog{background-position:-432px 0}.icon-trash{background-position:-456px 0}.icon-home{background-position:0 -24px}.icon-file{background-position:-24px -24px}.icon-time{background-position:-48px -24px}.icon-road{background-position:-72px -24px}.icon-download-alt{background-position:-96px -24px}.icon-download{background-position:-120px -24px}.icon-upload{background-position:-144px -24px}.icon-inbox{background-position:-168px -24px}.icon-play-circle{background-position:-192px -24px}.icon-repeat{background-position:-216px -24px}.icon-refresh{background-position:-240px -24px}.icon-list-alt{background-position:-264px -24px}.icon-lock{background-position:-287px -24px}.icon-flag{background-position:-312px -24px}.icon-headphones{background-position:-336px -24px}.icon-volume-off{background-position:-360px -24px}.icon-volume-down{background-position:-384px -24px}.icon-volume-up{background-position:-408px -24px}.icon-qrcode{background-position:-432px -24px}.icon-barcode{background-position:-456px -24px}.icon-tag{background-position:0 -48px}.icon-tags{background-position:-25px -48px}.icon-book{background-position:-48px -48px}.icon-bookmark{background-position:-72px -48px}.icon-print{background-position:-96px -48px}.icon-camera{background-position:-120px -48px}.icon-font{background-position:-144px -48px}.icon-bold{background-position:-167px -48px}.icon-italic{background-position:-192px -48px}.icon-text-height{background-position:-216px -48px}.icon-text-width{background-position:-240px -48px}.icon-align-left{background-position:-264px -48px}.icon-align-center{background-position:-288px -48px}.icon-align-right{background-position:-312px -48px}.icon-align-justify{background-position:-336px -48px}.icon-list{background-position:-360px -48px}.icon-indent-left{background-position:-384px -48px}.icon-indent-right{background-position:-408px -48px}.icon-facetime-video{background-position:-432px -48px}.icon-picture{background-position:-456px -48px}.icon-pencil{background-position:0 -72px}.icon-map-marker{background-position:-24px -72px}.icon-adjust{background-position:-48px -72px}.icon-tint{background-position:-72px -72px}.icon-edit{background-position:-96px -72px}.icon-share{background-position:-120px -72px}.icon-check{background-position:-144px -72px}.icon-move{background-position:-168px -72px}.icon-step-backward{background-position:-192px -72px}.icon-fast-backward{background-position:-216px -72px}.icon-backward{background-position:-240px -72px}.icon-play{background-position:-264px -72px}.icon-pause{background-position:-288px -72px}.icon-stop{background-position:-312px -72px}.icon-forward{background-position:-336px -72px}.icon-fast-forward{background-position:-360px -72px}.icon-step-forward{background-position:-384px -72px}.icon-eject{background-position:-408px -72px}.icon-chevron-left{background-position:-432px -72px}.icon-chevron-right{background-position:-456px -72px}.icon-plus-sign{background-position:0 -96px}.icon-minus-sign{background-position:-24px -96px}.icon-remove-sign{background-position:-48px -96px}.icon-ok-sign{background-position:-72px -96px}.icon-question-sign{background-position:-96px -96px}.icon-info-sign{background-position:-120px -96px}.icon-screenshot{background-position:-144px -96px}.icon-remove-circle{background-position:-168px -96px}.icon-ok-circle{background-position:-192px -96px}.icon-ban-circle{background-position:-216px -96px}.icon-arrow-left{background-position:-240px -96px}.icon-arrow-right{background-position:-264px -96px}.icon-arrow-up{background-position:-289px -96px}.icon-arrow-down{background-position:-312px -96px}.icon-share-alt{background-position:-336px -96px}.icon-resize-full{background-position:-360px -96px}.icon-resize-small{background-position:-384px -96px}.icon-plus{background-position:-408px -96px}.icon-minus{background-position:-433px -96px}.icon-asterisk{background-position:-456px -96px}.icon-exclamation-sign{background-position:0 -120px}.icon-gift{background-position:-24px -120px}.icon-leaf{background-position:-48px -120px}.icon-fire{background-position:-72px -120px}.icon-eye-open{background-position:-96px -120px}.icon-eye-close{background-position:-120px -120px}.icon-warning-sign{background-position:-144px -120px}.icon-plane{background-position:-168px -120px}.icon-calendar{background-position:-192px -120px}.icon-random{width:16px;background-position:-216px -120px}.icon-comment{background-position:-240px -120px}.icon-magnet{background-position:-264px -120px}.icon-chevron-up{background-position:-288px -120px}.icon-chevron-down{background-position:-313px -119px}.icon-retweet{background-position:-336px -120px}.icon-shopping-cart{background-position:-360px -120px}.icon-folder-close{background-position:-384px -120px}.icon-folder-open{width:16px;background-position:-408px -120px}.icon-resize-vertical{background-position:-432px -119px}.icon-resize-horizontal{background-position:-456px -118px}.icon-hdd{background-position:0 -144px}.icon-bullhorn{background-position:-24px -144px}.icon-bell{background-position:-48px -144px}.icon-certificate{background-position:-72px -144px}.icon-thumbs-up{background-position:-96px -144px}.icon-thumbs-down{background-position:-120px -144px}.icon-hand-right{background-position:-144px -144px}.icon-hand-left{background-position:-168px -144px}.icon-hand-up{background-position:-192px -144px}.icon-hand-down{background-position:-216px -144px}.icon-circle-arrow-right{background-position:-240px -144px}.icon-circle-arrow-left{background-position:-264px -144px}.icon-circle-arrow-up{background-position:-288px -144px}.icon-circle-arrow-down{background-position:-312px -144px}.icon-globe{background-position:-336px -144px}.icon-wrench{background-position:-360px -144px}.icon-tasks{background-position:-384px -144px}.icon-filter{background-position:-408px -144px}.icon-briefcase{background-position:-432px -144px}.icon-fullscreen{background-position:-456px -144px}.dropup,.dropdown{position:relative}.dropdown-toggle{*margin-bottom:-3px}.dropdown-toggle:active,.open .dropdown-toggle{outline:0}.caret{display:inline-block;width:0;height:0;vertical-align:top;border-top:4px solid #000;border-right:4px solid transparent;border-left:4px solid transparent;content:""}.dropdown .caret{margin-top:8px;margin-left:2px}.dropdown-menu{position:absolute;top:100%;left:0;z-index:1000;display:none;float:left;min-width:160px;padding:5px 0;margin:2px 0 0;list-style:none;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);*border-right-width:2px;*border-bottom-width:2px;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 5px 10px rgba(0,0,0,0.2);-moz-box-shadow:0 5px 10px rgba(0,0,0,0.2);box-shadow:0 5px 10px rgba(0,0,0,0.2);-webkit-background-clip:padding-box;-moz-background-clip:padding;background-clip:padding-box}.dropdown-menu.pull-right{right:0;left:auto}.dropdown-menu .divider{*width:100%;height:1px;margin:9px 1px;*margin:-5px 0 5px;overflow:hidden;background-color:#e5e5e5;border-bottom:1px solid #fff}.dropdown-menu a{display:block;padding:3px 20px;clear:both;font-weight:normal;line-height:20px;color:#333;white-space:nowrap}.dropdown-menu li>a:hover,.dropdown-menu li>a:focus,.dropdown-submenu:hover>a{color:#fff;text-decoration:none;background-color:#0088cc;background-color:#0088cc;background-image:-moz-linear-gradient(top,#0088cc,#0087b3);background-image:-webkit-gradient(linear,0 0,0 100%,from(#0088cc),to(#0087b3));background-image:-webkit-linear-gradient(top,#0088cc,#0087b3);background-image:-o-linear-gradient(top,#0088cc,#0087b3);background-image:linear-gradient(to bottom,#0088cc,#0087b3);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0087b3',GradientType=0)}.dropdown-menu .active>a,.dropdown-menu .active>a:hover{color:#fff;text-decoration:none;background-color:#0088cc;background-color:#0081c2;background-image:linear-gradient(to bottom,#0088cc,#0087b3);background-image:-moz-linear-gradient(top,#0088cc,#0087b3);background-image:-webkit-gradient(linear,0 0,0 100%,from(#0088cc),to(#0087b3));background-image:-webkit-linear-gradient(top,#0088cc,#0087b3);background-image:-o-linear-gradient(top,#0088cc,#0087b3);background-repeat:repeat-x;outline:0;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0087b3',GradientType=0)}.dropdown-menu .disabled>a,.dropdown-menu .disabled>a:hover{color:#999}.dropdown-menu .disabled>a:hover{text-decoration:none;cursor:default;background-color:transparent}.open{*z-index:1000}.open>.dropdown-menu{display:block}.pull-right>.dropdown-menu{right:0;left:auto}.dropup .caret,.navbar-fixed-bottom .dropdown .caret{border-top:0;border-bottom:4px solid #000;content:"\2191"}.dropup .dropdown-menu,.navbar-fixed-bottom .dropdown .dropdown-menu{top:auto;bottom:100%;margin-bottom:1px}.dropdown-submenu{position:relative}.dropdown-submenu>.dropdown-menu{top:0;left:100%;margin-top:-6px;margin-left:-1px;-webkit-border-radius:0 6px 6px 6px;-moz-border-radius:0 6px 6px 6px;border-radius:0 6px 6px 6px}.dropdown-submenu:hover .dropdown-menu{display:block}.dropdown-submenu>a:after{display:block;float:right;width:0;height:0;margin-top:5px;margin-right:-10px;border-color:transparent;border-left-color:#ccc;border-style:solid;border-width:5px 0 5px 5px;content:" "}.dropdown-submenu:hover>a:after{border-left-color:#fff}.dropdown .dropdown-menu .nav-header{padding-right:20px;padding-left:20px}.typeahead{margin-top:2px;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.well{min-height:20px;padding:19px;margin-bottom:20px;background-color:#f5f5f5;border:1px solid #e3e3e3;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.05);box-shadow:inset 0 1px 1px rgba(0,0,0,0.05)}.well blockquote{border-color:#ddd;border-color:rgba(0,0,0,0.15)}.well-large{padding:24px;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.well-small{padding:9px;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}.fade{opacity:0;-webkit-transition:opacity .15s linear;-moz-transition:opacity .15s linear;-o-transition:opacity .15s linear;transition:opacity .15s linear}.fade.in{opacity:1}.collapse{position:relative;height:0;overflow:hidden;overflow:visible \9;-webkit-transition:height .35s ease;-moz-transition:height .35s ease;-o-transition:height .35s ease;transition:height .35s ease}.collapse.in{height:auto}.close{float:right;font-size:20px;font-weight:bold;line-height:20px;color:#000;text-shadow:0 1px 0 #fff;opacity:.2;filter:alpha(opacity=20)}.close:hover{color:#000;text-decoration:none;cursor:pointer;opacity:.4;filter:alpha(opacity=40)}button.close{padding:0;cursor:pointer;background:transparent;border:0;-webkit-appearance:none}.btn{display:inline-block;*display:inline;padding:4px 14px;margin-bottom:0;*margin-left:.3em;font-size:14px;line-height:20px;*line-height:20px;color:#333;text-align:center;text-shadow:0 1px 1px rgba(255,255,255,0.75);vertical-align:middle;cursor:pointer;background-color:#f5f5f5;*background-color:#e6e6e6;background-image:-webkit-gradient(linear,0 0,0 100%,from(#fff),to(#e6e6e6));background-image:-webkit-linear-gradient(top,#fff,#e6e6e6);background-image:-o-linear-gradient(top,#fff,#e6e6e6);background-image:linear-gradient(to bottom,#fff,#e6e6e6);background-image:-moz-linear-gradient(top,#fff,#e6e6e6);background-repeat:repeat-x;border:1px solid #bbb;*border:0;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);border-color:#e6e6e6 #e6e6e6 #bfbfbf;border-bottom-color:#a2a2a2;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffffffff',endColorstr='#ffe6e6e6',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false);*zoom:1;-webkit-box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05)}.btn:hover,.btn:active,.btn.active,.btn.disabled,.btn[disabled]{color:#333;background-color:#e6e6e6;*background-color:#d9d9d9}.btn:active,.btn.active{background-color:#ccc \9}.btn:first-child{*margin-left:0}.btn:hover{color:#333;text-decoration:none;background-color:#e6e6e6;*background-color:#d9d9d9;background-position:0 -15px;-webkit-transition:background-position .1s linear;-moz-transition:background-position .1s linear;-o-transition:background-position .1s linear;transition:background-position .1s linear}.btn:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}.btn.active,.btn:active{background-color:#e6e6e6;background-color:#d9d9d9 \9;background-image:none;outline:0;-webkit-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05)}.btn.disabled,.btn[disabled]{cursor:default;background-color:#e6e6e6;background-image:none;opacity:.65;filter:alpha(opacity=65);-webkit-box-shadow:none;-moz-box-shadow:none;box-shadow:none}.btn-large{padding:9px 14px;font-size:16px;line-height:normal;-webkit-border-radius:5px;-moz-border-radius:5px;border-radius:5px}.btn-large [class^="icon-"]{margin-top:2px}.btn-small{padding:3px 9px;font-size:12px;line-height:18px}.btn-small [class^="icon-"]{margin-top:0}.btn-mini{padding:2px 6px;font-size:11px;line-height:16px}.btn-block{display:block;width:100%;padding-right:0;padding-left:0;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}.btn-block+.btn-block{margin-top:5px}.btn-primary.active,.btn-warning.active,.btn-danger.active,.btn-success.active,.btn-info.active,.btn-inverse.active{color:rgba(255,255,255,0.75)}.btn{border-color:#c5c5c5;border-color:rgba(0,0,0,0.15) rgba(0,0,0,0.15) rgba(0,0,0,0.25)}.btn-primary{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#006dcc;*background-color:#04c;background-image:-webkit-gradient(linear,0 0,0 100%,from(#08c),to(#04c));background-image:-webkit-linear-gradient(top,#08c,#04c);background-image:-o-linear-gradient(top,#08c,#04c);background-image:linear-gradient(to bottom,#08c,#04c);background-image:-moz-linear-gradient(top,#08c,#04c);background-repeat:repeat-x;border-color:#04c #04c #002a80;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0044cc',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-primary:hover,.btn-primary:active,.btn-primary.active,.btn-primary.disabled,.btn-primary[disabled]{color:#fff;background-color:#04c;*background-color:#003bb3}.btn-primary:active,.btn-primary.active{background-color:#039 \9}.btn-warning{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#faa732;*background-color:#f89406;background-image:-webkit-gradient(linear,0 0,0 100%,from(#fbb450),to(#f89406));background-image:-webkit-linear-gradient(top,#fbb450,#f89406);background-image:-o-linear-gradient(top,#fbb450,#f89406);background-image:linear-gradient(to bottom,#fbb450,#f89406);background-image:-moz-linear-gradient(top,#fbb450,#f89406);background-repeat:repeat-x;border-color:#f89406 #f89406 #ad6704;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fffbb450',endColorstr='#fff89406',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-warning:hover,.btn-warning:active,.btn-warning.active,.btn-warning.disabled,.btn-warning[disabled]{color:#fff;background-color:#f89406;*background-color:#df8505}.btn-warning:active,.btn-warning.active{background-color:#c67605 \9}.btn-danger{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#da4f49;*background-color:#bd362f;background-image:-webkit-gradient(linear,0 0,0 100%,from(#ee5f5b),to(#bd362f));background-image:-webkit-linear-gradient(top,#ee5f5b,#bd362f);background-image:-o-linear-gradient(top,#ee5f5b,#bd362f);background-image:linear-gradient(to bottom,#ee5f5b,#bd362f);background-image:-moz-linear-gradient(top,#ee5f5b,#bd362f);background-repeat:repeat-x;border-color:#bd362f #bd362f #802420;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffee5f5b',endColorstr='#ffbd362f',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-danger:hover,.btn-danger:active,.btn-danger.active,.btn-danger.disabled,.btn-danger[disabled]{color:#fff;background-color:#bd362f;*background-color:#a9302a}.btn-danger:active,.btn-danger.active{background-color:#942a25 \9}.btn-success{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#5bb75b;*background-color:#51a351;background-image:-webkit-gradient(linear,0 0,0 100%,from(#62c462),to(#51a351));background-image:-webkit-linear-gradient(top,#62c462,#51a351);background-image:-o-linear-gradient(top,#62c462,#51a351);background-image:linear-gradient(to bottom,#62c462,#51a351);background-image:-moz-linear-gradient(top,#62c462,#51a351);background-repeat:repeat-x;border-color:#51a351 #51a351 #387038;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff62c462',endColorstr='#ff51a351',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-success:hover,.btn-success:active,.btn-success.active,.btn-success.disabled,.btn-success[disabled]{color:#fff;background-color:#51a351;*background-color:#499249}.btn-success:active,.btn-success.active{background-color:#408140 \9}.btn-info{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#49afcd;*background-color:#2f96b4;background-image:-webkit-gradient(linear,0 0,0 100%,from(#5bc0de),to(#2f96b4));background-image:-webkit-linear-gradient(top,#5bc0de,#2f96b4);background-image:-o-linear-gradient(top,#5bc0de,#2f96b4);background-image:linear-gradient(to bottom,#5bc0de,#2f96b4);background-image:-moz-linear-gradient(top,#5bc0de,#2f96b4);background-repeat:repeat-x;border-color:#2f96b4 #2f96b4 #1f6377;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff5bc0de',endColorstr='#ff2f96b4',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-info:hover,.btn-info:active,.btn-info.active,.btn-info.disabled,.btn-info[disabled]{color:#fff;background-color:#2f96b4;*background-color:#2a85a0}.btn-info:active,.btn-info.active{background-color:#24748c \9}.btn-inverse{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#363636;*background-color:#222;background-image:-webkit-gradient(linear,0 0,0 100%,from(#444),to(#222));background-image:-webkit-linear-gradient(top,#444,#222);background-image:-o-linear-gradient(top,#444,#222);background-image:linear-gradient(to bottom,#444,#222);background-image:-moz-linear-gradient(top,#444,#222);background-repeat:repeat-x;border-color:#222 #222 #000;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff444444',endColorstr='#ff222222',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-inverse:hover,.btn-inverse:active,.btn-inverse.active,.btn-inverse.disabled,.btn-inverse[disabled]{color:#fff;background-color:#222;*background-color:#151515}.btn-inverse:active,.btn-inverse.active{background-color:#080808 \9}button.btn,input[type="submit"].btn{*padding-top:3px;*padding-bottom:3px}button.btn::-moz-focus-inner,input[type="submit"].btn::-moz-focus-inner{padding:0;border:0}button.btn.btn-large,input[type="submit"].btn.btn-large{*padding-top:7px;*padding-bottom:7px}button.btn.btn-small,input[type="submit"].btn.btn-small{*padding-top:3px;*padding-bottom:3px}button.btn.btn-mini,input[type="submit"].btn.btn-mini{*padding-top:1px;*padding-bottom:1px}.btn-link,.btn-link:active{background-color:transparent;background-image:none;-webkit-box-shadow:none;-moz-box-shadow:none;box-shadow:none}.btn-link{color:#08c;cursor:pointer;border-color:transparent;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-link:hover{color:#005580;text-decoration:underline;background-color:transparent}.btn-group{position:relative;*margin-left:.3em;font-size:0;white-space:nowrap}.btn-group:first-child{*margin-left:0}.btn-group+.btn-group{margin-left:5px}.btn-toolbar{margin-top:10px;margin-bottom:10px;font-size:0}.btn-toolbar .btn-group{display:inline-block;*display:inline;*zoom:1}.btn-toolbar .btn+.btn,.btn-toolbar .btn-group+.btn,.btn-toolbar .btn+.btn-group{margin-left:5px}.btn-group>.btn{position:relative;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-group>.btn+.btn{margin-left:-1px}.btn-group>.btn,.btn-group>.dropdown-menu{font-size:14px}.btn-group>.btn-mini{font-size:11px}.btn-group>.btn-small{font-size:12px}.btn-group>.btn-large{font-size:16px}.btn-group>.btn:first-child{margin-left:0;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-bottomleft:4px;-moz-border-radius-topleft:4px}.btn-group>.btn:last-child,.btn-group>.dropdown-toggle{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-moz-border-radius-topright:4px;-moz-border-radius-bottomright:4px}.btn-group>.btn.large:first-child{margin-left:0;-webkit-border-bottom-left-radius:6px;border-bottom-left-radius:6px;-webkit-border-top-left-radius:6px;border-top-left-radius:6px;-moz-border-radius-bottomleft:6px;-moz-border-radius-topleft:6px}.btn-group>.btn.large:last-child,.btn-group>.large.dropdown-toggle{-webkit-border-top-right-radius:6px;border-top-right-radius:6px;-webkit-border-bottom-right-radius:6px;border-bottom-right-radius:6px;-moz-border-radius-topright:6px;-moz-border-radius-bottomright:6px}.btn-group>.btn:hover,.btn-group>.btn:focus,.btn-group>.btn:active,.btn-group>.btn.active{z-index:2}.btn-group .dropdown-toggle:active,.btn-group.open .dropdown-toggle{outline:0}.btn-group>.btn+.dropdown-toggle{*padding-top:5px;padding-right:8px;*padding-bottom:5px;padding-left:8px;-webkit-box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05)}.btn-group>.btn-mini+.dropdown-toggle{*padding-top:2px;padding-right:5px;*padding-bottom:2px;padding-left:5px}.btn-group>.btn-small+.dropdown-toggle{*padding-top:5px;*padding-bottom:4px}.btn-group>.btn-large+.dropdown-toggle{*padding-top:7px;padding-right:12px;*padding-bottom:7px;padding-left:12px}.btn-group.open .dropdown-toggle{background-image:none;-webkit-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05)}.btn-group.open .btn.dropdown-toggle{background-color:#e6e6e6}.btn-group.open .btn-primary.dropdown-toggle{background-color:#04c}.btn-group.open .btn-warning.dropdown-toggle{background-color:#f89406}.btn-group.open .btn-danger.dropdown-toggle{background-color:#bd362f}.btn-group.open .btn-success.dropdown-toggle{background-color:#51a351}.btn-group.open .btn-info.dropdown-toggle{background-color:#2f96b4}.btn-group.open .btn-inverse.dropdown-toggle{background-color:#222}.btn .caret{margin-top:8px;margin-left:0}.btn-mini .caret,.btn-small .caret,.btn-large .caret{margin-top:6px}.btn-large .caret{border-top-width:5px;border-right-width:5px;border-left-width:5px}.dropup .btn-large .caret{border-top:0;border-bottom:5px solid #000}.btn-primary .caret,.btn-warning .caret,.btn-danger .caret,.btn-info .caret,.btn-success .caret,.btn-inverse .caret{border-top-color:#fff;border-bottom-color:#fff}.btn-group-vertical{display:inline-block;*display:inline;*zoom:1}.btn-group-vertical .btn{display:block;float:none;width:100%;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-group-vertical .btn+.btn{margin-top:-1px;margin-left:0}.btn-group-vertical .btn:first-child{-webkit-border-radius:4px 4px 0 0;-moz-border-radius:4px 4px 0 0;border-radius:4px 4px 0 0}.btn-group-vertical .btn:last-child{-webkit-border-radius:0 0 4px 4px;-moz-border-radius:0 0 4px 4px;border-radius:0 0 4px 4px}.btn-group-vertical .btn-large:first-child{-webkit-border-radius:6px 6px 0 0;-moz-border-radius:6px 6px 0 0;border-radius:6px 6px 0 0}.btn-group-vertical .btn-large:last-child{-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px}.alert{padding:8px 35px 8px 14px;margin-bottom:20px;color:#c09853;text-shadow:0 1px 0 rgba(255,255,255,0.5);background-color:#fcf8e3;border:1px solid #fbeed5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.alert h4{margin:0}.alert .close{position:relative;top:-2px;right:-21px;line-height:20px}.alert-success{color:#468847;background-color:#dff0d8;border-color:#d6e9c6}.alert-danger,.alert-error{color:#b94a48;background-color:#f2dede;border-color:#eed3d7}.alert-info{color:#3a87ad;background-color:#d9edf7;border-color:#bce8f1}.alert-block{padding-top:14px;padding-bottom:14px}.alert-block>p,.alert-block>ul{margin-bottom:0}.alert-block p+p{margin-top:5px}.nav{margin-bottom:20px;margin-left:0;list-style:none}.nav>li>a{display:block}.nav>li>a:hover{text-decoration:none;background-color:#eee}.nav>.pull-right{float:right}.nav-header{display:block;padding:3px 15px;font-size:11px;font-weight:bold;line-height:20px;color:#999;text-shadow:0 1px 0 rgba(255,255,255,0.5);text-transform:uppercase}.nav li+.nav-header{margin-top:9px}.nav-list{padding-right:15px;padding-left:15px;margin-bottom:0}.nav-list>li>a,.nav-list .nav-header{margin-right:-15px;margin-left:-15px;text-shadow:0 1px 0 rgba(255,255,255,0.5)}.nav-list>li>a{padding:3px 15px}.nav-list>.active>a,.nav-list>.active>a:hover{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.2);background-color:#08c}.nav-list [class^="icon-"]{margin-right:2px}.nav-list .divider{*width:100%;height:1px;margin:9px 1px;*margin:-5px 0 5px;overflow:hidden;background-color:#e5e5e5;border-bottom:1px solid #fff}.nav-tabs,.nav-pills{*zoom:1}.nav-tabs:before,.nav-pills:before,.nav-tabs:after,.nav-pills:after{display:table;line-height:0;content:""}.nav-tabs:after,.nav-pills:after{clear:both}.nav-tabs>li,.nav-pills>li{float:left}.nav-tabs>li>a,.nav-pills>li>a{padding-right:12px;padding-left:12px;margin-right:2px;line-height:14px}.nav-tabs{border-bottom:1px solid #ddd}.nav-tabs>li{margin-bottom:-1px}.nav-tabs>li>a{padding-top:8px;padding-bottom:8px;line-height:20px;border:1px solid transparent;-webkit-border-radius:4px 4px 0 0;-moz-border-radius:4px 4px 0 0;border-radius:4px 4px 0 0}.nav-tabs>li>a:hover{border-color:#eee #eee #ddd}.nav-tabs>.active>a,.nav-tabs>.active>a:hover{color:#555;cursor:default;background-color:#fff;border:1px solid #ddd;border-bottom-color:transparent}.nav-pills>li>a{padding-top:8px;padding-bottom:8px;margin-top:2px;margin-bottom:2px;-webkit-border-radius:5px;-moz-border-radius:5px;border-radius:5px}.nav-pills>.active>a,.nav-pills>.active>a:hover{color:#fff;background-color:#08c}.nav-stacked>li{float:none}.nav-stacked>li>a{margin-right:0}.nav-tabs.nav-stacked{border-bottom:0}.nav-tabs.nav-stacked>li>a{border:1px solid #ddd;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.nav-tabs.nav-stacked>li:first-child>a{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topright:4px;-moz-border-radius-topleft:4px}.nav-tabs.nav-stacked>li:last-child>a{-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-moz-border-radius-bottomright:4px;-moz-border-radius-bottomleft:4px}.nav-tabs.nav-stacked>li>a:hover{z-index:2;border-color:#ddd}.nav-pills.nav-stacked>li>a{margin-bottom:3px}.nav-pills.nav-stacked>li:last-child>a{margin-bottom:1px}.nav-tabs .dropdown-menu{-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px}.nav-pills .dropdown-menu{-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.nav .dropdown-toggle .caret{margin-top:6px;border-top-color:#08c;border-bottom-color:#08c}.nav .dropdown-toggle:hover .caret{border-top-color:#005580;border-bottom-color:#005580}.nav-tabs .dropdown-toggle .caret{margin-top:8px}.nav .active .dropdown-toggle .caret{border-top-color:#fff;border-bottom-color:#fff}.nav-tabs .active .dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.nav>.dropdown.active>a:hover{cursor:pointer}.nav-tabs .open .dropdown-toggle,.nav-pills .open .dropdown-toggle,.nav>li.dropdown.open.active>a:hover{color:#fff;background-color:#999;border-color:#999}.nav li.dropdown.open .caret,.nav li.dropdown.open.active .caret,.nav li.dropdown.open a:hover .caret{border-top-color:#fff;border-bottom-color:#fff;opacity:1;filter:alpha(opacity=100)}.tabs-stacked .open>a:hover{border-color:#999}.tabbable{*zoom:1}.tabbable:before,.tabbable:after{display:table;line-height:0;content:""}.tabbable:after{clear:both}.tab-content{overflow:auto}.tabs-below>.nav-tabs,.tabs-right>.nav-tabs,.tabs-left>.nav-tabs{border-bottom:0}.tab-content>.tab-pane,.pill-content>.pill-pane{display:none}.tab-content>.active,.pill-content>.active{display:block}.tabs-below>.nav-tabs{border-top:1px solid #ddd}.tabs-below>.nav-tabs>li{margin-top:-1px;margin-bottom:0}.tabs-below>.nav-tabs>li>a{-webkit-border-radius:0 0 4px 4px;-moz-border-radius:0 0 4px 4px;border-radius:0 0 4px 4px}.tabs-below>.nav-tabs>li>a:hover{border-top-color:#ddd;border-bottom-color:transparent}.tabs-below>.nav-tabs>.active>a,.tabs-below>.nav-tabs>.active>a:hover{border-color:transparent #ddd #ddd #ddd}.tabs-left>.nav-tabs>li,.tabs-right>.nav-tabs>li{float:none}.tabs-left>.nav-tabs>li>a,.tabs-right>.nav-tabs>li>a{min-width:74px;margin-right:0;margin-bottom:3px}.tabs-left>.nav-tabs{float:left;margin-right:19px;border-right:1px solid #ddd}.tabs-left>.nav-tabs>li>a{margin-right:-1px;-webkit-border-radius:4px 0 0 4px;-moz-border-radius:4px 0 0 4px;border-radius:4px 0 0 4px}.tabs-left>.nav-tabs>li>a:hover{border-color:#eee #ddd #eee #eee}.tabs-left>.nav-tabs .active>a,.tabs-left>.nav-tabs .active>a:hover{border-color:#ddd transparent #ddd #ddd;*border-right-color:#fff}.tabs-right>.nav-tabs{float:right;margin-left:19px;border-left:1px solid #ddd}.tabs-right>.nav-tabs>li>a{margin-left:-1px;-webkit-border-radius:0 4px 4px 0;-moz-border-radius:0 4px 4px 0;border-radius:0 4px 4px 0}.tabs-right>.nav-tabs>li>a:hover{border-color:#eee #eee #eee #ddd}.tabs-right>.nav-tabs .active>a,.tabs-right>.nav-tabs .active>a:hover{border-color:#ddd #ddd #ddd transparent;*border-left-color:#fff}.nav>.disabled>a{color:#999}.nav>.disabled>a:hover{text-decoration:none;cursor:default;background-color:transparent}.navbar{*position:relative;*z-index:2;margin-bottom:20px;overflow:visible;color:#555}.navbar-inner{min-height:40px;padding-right:20px;padding-left:20px;background-color:#fafafa;background-image:-moz-linear-gradient(top,#fff,#feecda);background-image:-webkit-gradient(linear,0 0,0 100%,from(#fff),to(#feecda));background-image:-webkit-linear-gradient(top,#fff,#feecda);background-image:-o-linear-gradient(top,#fff,#feecda);background-image:linear-gradient(to bottom,#fff,#feecda);background-repeat:repeat-x;border:1px solid #d4d4d4;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffffffff',endColorstr='#fffeecda',GradientType=0);-webkit-box-shadow:0 1px 4px rgba(0,0,0,0.065);-moz-box-shadow:0 1px 4px rgba(0,0,0,0.065);box-shadow:0 1px 4px rgba(0,0,0,0.065)}.navbar .container{width:auto}.nav-collapse.collapse{height:auto}.navbar .brand{display:block;float:left;padding:10px 20px 10px;margin-left:-20px;font-size:20px;font-weight:200;color:#555;text-shadow:0 1px 0 #fff}.navbar .brand:hover{text-decoration:none}.navbar-text{margin-bottom:0;line-height:40px}.navbar-link{color:#555}.navbar-link:hover{color:#333}.navbar .divider-vertical{height:40px;margin:0 9px;border-right:1px solid #fff;border-left:1px solid #f2f2f2}.navbar .btn,.navbar .btn-group{margin-top:6px}.navbar .btn-group .btn{margin:0}.navbar-form{margin-bottom:0;*zoom:1}.navbar-form:before,.navbar-form:after{display:table;line-height:0;content:""}.navbar-form:after{clear:both}.navbar-form input,.navbar-form select,.navbar-form .radio,.navbar-form .checkbox{margin-top:5px}.navbar-form input,.navbar-form select,.navbar-form .btn{display:inline-block;margin-bottom:0}.navbar-form input[type="image"],.navbar-form input[type="checkbox"],.navbar-form input[type="radio"]{margin-top:3px}.navbar-form .input-append,.navbar-form .input-prepend{margin-top:6px;white-space:nowrap}.navbar-form .input-append input,.navbar-form .input-prepend input{margin-top:0}.navbar-search{position:relative;float:left;margin-top:5px;margin-bottom:0}.navbar-search .search-query{padding:4px 14px;margin-bottom:0;font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:13px;font-weight:normal;line-height:1;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.navbar-static-top{position:static;width:100%;margin-bottom:0}.navbar-static-top .navbar-inner{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.navbar-fixed-top,.navbar-fixed-bottom{position:fixed;right:0;left:0;z-index:1030;margin-bottom:0}.navbar-fixed-top .navbar-inner,.navbar-fixed-bottom .navbar-inner,.navbar-static-top .navbar-inner{border:0}.navbar-fixed-top .navbar-inner,.navbar-fixed-bottom .navbar-inner{padding-right:0;padding-left:0;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.navbar-static-top .container,.navbar-fixed-top .container,.navbar-fixed-bottom .container{width:940px}.navbar-fixed-top{top:0}.navbar-fixed-top .navbar-inner,.navbar-static-top .navbar-inner{-webkit-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1);box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1)}.navbar-fixed-bottom{bottom:0}.navbar-fixed-bottom .navbar-inner{-webkit-box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1);box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1)}.navbar .nav{position:relative;left:0;display:block;float:left;margin:0 10px 0 0}.navbar .nav.pull-right{float:right}.navbar .nav>li{float:left}.navbar .nav>li>a{float:none;padding:10px 15px 10px;color:#555;text-decoration:none;text-shadow:0 1px 0 #fff}.navbar .nav .dropdown-toggle .caret{margin-top:8px}.navbar .nav>li>a:focus,.navbar .nav>li>a:hover{color:#333;text-decoration:none;background-color:transparent}.navbar .nav>.active>a,.navbar .nav>.active>a:hover,.navbar .nav>.active>a:focus{color:#555;text-decoration:none;background-color:#e5e5e5;-webkit-box-shadow:inset 0 3px 8px rgba(0,0,0,0.125);-moz-box-shadow:inset 0 3px 8px rgba(0,0,0,0.125);box-shadow:inset 0 3px 8px rgba(0,0,0,0.125)}.navbar .btn-navbar{display:none;float:right;padding:7px 10px;margin-right:5px;margin-left:5px;color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#ededed;*background-color:#e5e5e5;background-image:-webkit-gradient(linear,0 0,0 100%,from(#f2f2f2),to(#e5e5e5));background-image:-webkit-linear-gradient(top,#f2f2f2,#e5e5e5);background-image:-o-linear-gradient(top,#f2f2f2,#e5e5e5);background-image:linear-gradient(to bottom,#f2f2f2,#e5e5e5);background-image:-moz-linear-gradient(top,#f2f2f2,#e5e5e5);background-repeat:repeat-x;border-color:#e5e5e5 #e5e5e5 #bfbfbf;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fff2f2f2',endColorstr='#ffe5e5e5',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false);-webkit-box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075);-moz-box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075);box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075)}.navbar .btn-navbar:hover,.navbar .btn-navbar:active,.navbar .btn-navbar.active,.navbar .btn-navbar.disabled,.navbar .btn-navbar[disabled]{color:#fff;background-color:#e5e5e5;*background-color:#d9d9d9}.navbar .btn-navbar:active,.navbar .btn-navbar.active{background-color:#ccc \9}.navbar .btn-navbar .icon-bar{display:block;width:18px;height:2px;background-color:#f5f5f5;-webkit-border-radius:1px;-moz-border-radius:1px;border-radius:1px;-webkit-box-shadow:0 1px 0 rgba(0,0,0,0.25);-moz-box-shadow:0 1px 0 rgba(0,0,0,0.25);box-shadow:0 1px 0 rgba(0,0,0,0.25)}.btn-navbar .icon-bar+.icon-bar{margin-top:3px}.navbar .nav>li>.dropdown-menu:before{position:absolute;top:-7px;left:9px;display:inline-block;border-right:7px solid transparent;border-bottom:7px solid #ccc;border-left:7px solid transparent;border-bottom-color:rgba(0,0,0,0.2);content:''}.navbar .nav>li>.dropdown-menu:after{position:absolute;top:-6px;left:10px;display:inline-block;border-right:6px solid transparent;border-bottom:6px solid #fff;border-left:6px solid transparent;content:''}.navbar-fixed-bottom .nav>li>.dropdown-menu:before{top:auto;bottom:-7px;border-top:7px solid #ccc;border-bottom:0;border-top-color:rgba(0,0,0,0.2)}.navbar-fixed-bottom .nav>li>.dropdown-menu:after{top:auto;bottom:-6px;border-top:6px solid #fff;border-bottom:0}.navbar .nav li.dropdown.open>.dropdown-toggle,.navbar .nav li.dropdown.active>.dropdown-toggle,.navbar .nav li.dropdown.open.active>.dropdown-toggle{color:#555;background-color:#e5e5e5}.navbar .nav li.dropdown>.dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.navbar .nav li.dropdown.open>.dropdown-toggle .caret,.navbar .nav li.dropdown.active>.dropdown-toggle .caret,.navbar .nav li.dropdown.open.active>.dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.navbar .pull-right>li>.dropdown-menu,.navbar .nav>li>.dropdown-menu.pull-right{right:0;left:auto}.navbar .pull-right>li>.dropdown-menu:before,.navbar .nav>li>.dropdown-menu.pull-right:before{right:12px;left:auto}.navbar .pull-right>li>.dropdown-menu:after,.navbar .nav>li>.dropdown-menu.pull-right:after{right:13px;left:auto}.navbar .pull-right>li>.dropdown-menu .dropdown-menu,.navbar .nav>li>.dropdown-menu.pull-right .dropdown-menu{right:100%;left:auto;margin-right:-1px;margin-left:0;-webkit-border-radius:6px 0 6px 6px;-moz-border-radius:6px 0 6px 6px;border-radius:6px 0 6px 6px}.navbar-inverse{color:#999}.navbar-inverse .navbar-inner{background-color:#1b1b1b;background-image:-moz-linear-gradient(top,#222,#111);background-image:-webkit-gradient(linear,0 0,0 100%,from(#222),to(#111));background-image:-webkit-linear-gradient(top,#222,#111);background-image:-o-linear-gradient(top,#222,#111);background-image:linear-gradient(to bottom,#222,#111);background-repeat:repeat-x;border-color:#252525;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff222222',endColorstr='#ff111111',GradientType=0)}.navbar-inverse .brand,.navbar-inverse .nav>li>a{color:#999;text-shadow:0 -1px 0 rgba(0,0,0,0.25)}.navbar-inverse .brand:hover,.navbar-inverse .nav>li>a:hover{color:#fff}.navbar-inverse .nav>li>a:focus,.navbar-inverse .nav>li>a:hover{color:#fff;background-color:transparent}.navbar-inverse .nav .active>a,.navbar-inverse .nav .active>a:hover,.navbar-inverse .nav .active>a:focus{color:#fff;background-color:#111}.navbar-inverse .navbar-link{color:#999}.navbar-inverse .navbar-link:hover{color:#fff}.navbar-inverse .divider-vertical{border-right-color:#222;border-left-color:#111}.navbar-inverse .nav li.dropdown.open>.dropdown-toggle,.navbar-inverse .nav li.dropdown.active>.dropdown-toggle,.navbar-inverse .nav li.dropdown.open.active>.dropdown-toggle{color:#fff;background-color:#111}.navbar-inverse .nav li.dropdown>.dropdown-toggle .caret{border-top-color:#999;border-bottom-color:#999}.navbar-inverse .nav li.dropdown.open>.dropdown-toggle .caret,.navbar-inverse .nav li.dropdown.active>.dropdown-toggle .caret,.navbar-inverse .nav li.dropdown.open.active>.dropdown-toggle .caret{border-top-color:#fff;border-bottom-color:#fff}.navbar-inverse .navbar-search .search-query{color:#fff;background-color:#515151;border-color:#111;-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);-webkit-transition:none;-moz-transition:none;-o-transition:none;transition:none}.navbar-inverse .navbar-search .search-query:-moz-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query:-ms-input-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query::-webkit-input-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query:focus,.navbar-inverse .navbar-search .search-query.focused{padding:5px 15px;color:#333;text-shadow:0 1px 0 #fff;background-color:#fff;border:0;outline:0;-webkit-box-shadow:0 0 3px rgba(0,0,0,0.15);-moz-box-shadow:0 0 3px rgba(0,0,0,0.15);box-shadow:0 0 3px rgba(0,0,0,0.15)}.navbar-inverse .btn-navbar{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#0e0e0e;*background-color:#040404;background-image:-webkit-gradient(linear,0 0,0 100%,from(#151515),to(#040404));background-image:-webkit-linear-gradient(top,#151515,#040404);background-image:-o-linear-gradient(top,#151515,#040404);background-image:linear-gradient(to bottom,#151515,#040404);background-image:-moz-linear-gradient(top,#151515,#040404);background-repeat:repeat-x;border-color:#040404 #040404 #000;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff151515',endColorstr='#ff040404',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.navbar-inverse .btn-navbar:hover,.navbar-inverse .btn-navbar:active,.navbar-inverse .btn-navbar.active,.navbar-inverse .btn-navbar.disabled,.navbar-inverse .btn-navbar[disabled]{color:#fff;background-color:#040404;*background-color:#000}.navbar-inverse .btn-navbar:active,.navbar-inverse .btn-navbar.active{background-color:#000 \9}.breadcrumb{padding:8px 15px;margin:0 0 20px;list-style:none;background-color:#f5f5f5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.breadcrumb li{display:inline-block;*display:inline;text-shadow:0 1px 0 #fff;*zoom:1}.breadcrumb .divider{padding:0 5px;color:#ccc}.breadcrumb .active{color:#999}.pagination{height:40px;margin:20px 0}.pagination ul{display:inline-block;*display:inline;margin-bottom:0;margin-left:0;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px;*zoom:1;-webkit-box-shadow:0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:0 1px 2px rgba(0,0,0,0.05);box-shadow:0 1px 2px rgba(0,0,0,0.05)}.pagination li{display:inline}.pagination a,.pagination span{float:left;padding:0 14px;line-height:38px;text-decoration:none;background-color:#fff;border:1px solid #ddd;border-left-width:0}.pagination a:hover,.pagination .active a,.pagination .active span{background-color:#f5f5f5}.pagination .active a,.pagination .active span{color:#999;cursor:default}.pagination .disabled span,.pagination .disabled a,.pagination .disabled a:hover{color:#999;cursor:default;background-color:transparent}.pagination li:first-child a,.pagination li:first-child span{border-left-width:1px;-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.pagination li:last-child a,.pagination li:last-child span{-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.pagination-centered{text-align:center}.pagination-right{text-align:right}.pager{margin:20px 0;text-align:center;list-style:none;*zoom:1}.pager:before,.pager:after{display:table;line-height:0;content:""}.pager:after{clear:both}.pager li{display:inline}.pager a{display:inline-block;padding:5px 14px;background-color:#fff;border:1px solid #ddd;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.pager a:hover{text-decoration:none;background-color:#f5f5f5}.pager .next a{float:right}.pager .previous a{float:left}.pager .disabled a,.pager .disabled a:hover{color:#999;cursor:default;background-color:#fff}.modal-open .dropdown-menu{z-index:2050}.modal-open .dropdown.open{*z-index:2050}.modal-open .popover{z-index:2060}.modal-open .tooltip{z-index:2080}.modal-backdrop{position:fixed;top:0;right:0;bottom:0;left:0;z-index:1040;background-color:#000}.modal-backdrop.fade{opacity:0}.modal-backdrop,.modal-backdrop.fade.in{opacity:.8;filter:alpha(opacity=80)}.modal{position:fixed;top:50%;left:50%;z-index:1050;width:560px;margin:-250px 0 0 -280px;overflow:auto;background-color:#fff;border:1px solid #999;border:1px solid rgba(0,0,0,0.3);*border:1px solid #999;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 3px 7px rgba(0,0,0,0.3);-moz-box-shadow:0 3px 7px rgba(0,0,0,0.3);box-shadow:0 3px 7px rgba(0,0,0,0.3);-webkit-background-clip:padding-box;-moz-background-clip:padding-box;background-clip:padding-box}.modal.fade{top:-25%;-webkit-transition:opacity .3s linear,top .3s ease-out;-moz-transition:opacity .3s linear,top .3s ease-out;-o-transition:opacity .3s linear,top .3s ease-out;transition:opacity .3s linear,top .3s ease-out}.modal.fade.in{top:50%}.modal-header{padding:9px 15px;border-bottom:1px solid #eee}.modal-header .close{margin-top:2px}.modal-header h3{margin:0;line-height:30px}.modal-body{max-height:400px;padding:15px;overflow-y:auto}.modal-form{margin-bottom:0}.modal-footer{padding:14px 15px 15px;margin-bottom:0;text-align:right;background-color:#f5f5f5;border-top:1px solid #ddd;-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px;*zoom:1;-webkit-box-shadow:inset 0 1px 0 #fff;-moz-box-shadow:inset 0 1px 0 #fff;box-shadow:inset 0 1px 0 #fff}.modal-footer:before,.modal-footer:after{display:table;line-height:0;content:""}.modal-footer:after{clear:both}.modal-footer .btn+.btn{margin-bottom:0;margin-left:5px}.modal-footer .btn-group .btn+.btn{margin-left:-1px}.tooltip{position:absolute;z-index:1030;display:block;padding:5px;font-size:11px;opacity:0;filter:alpha(opacity=0);visibility:visible}.tooltip.in{opacity:.8;filter:alpha(opacity=80)}.tooltip.top{margin-top:-3px}.tooltip.right{margin-left:3px}.tooltip.bottom{margin-top:3px}.tooltip.left{margin-left:-3px}.tooltip-inner{max-width:200px;padding:3px 8px;color:#fff;text-align:center;text-decoration:none;background-color:#000;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.tooltip-arrow{position:absolute;width:0;height:0;border-color:transparent;border-style:solid}.tooltip.top .tooltip-arrow{bottom:0;left:50%;margin-left:-5px;border-top-color:#000;border-width:5px 5px 0}.tooltip.right .tooltip-arrow{top:50%;left:0;margin-top:-5px;border-right-color:#000;border-width:5px 5px 5px 0}.tooltip.left .tooltip-arrow{top:50%;right:0;margin-top:-5px;border-left-color:#000;border-width:5px 0 5px 5px}.tooltip.bottom .tooltip-arrow{top:0;left:50%;margin-left:-5px;border-bottom-color:#000;border-width:0 5px 5px}.popover{position:absolute;top:0;left:0;z-index:1010;display:none;width:236px;padding:1px;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 5px 10px rgba(0,0,0,0.2);-moz-box-shadow:0 5px 10px rgba(0,0,0,0.2);box-shadow:0 5px 10px rgba(0,0,0,0.2);-webkit-background-clip:padding-box;-moz-background-clip:padding;background-clip:padding-box}.popover.top{margin-bottom:10px}.popover.right{margin-left:10px}.popover.bottom{margin-top:10px}.popover.left{margin-right:10px}.popover-title{padding:8px 14px;margin:0;font-size:14px;font-weight:normal;line-height:18px;background-color:#f7f7f7;border-bottom:1px solid #ebebeb;-webkit-border-radius:5px 5px 0 0;-moz-border-radius:5px 5px 0 0;border-radius:5px 5px 0 0}.popover-content{padding:9px 14px}.popover-content p,.popover-content ul,.popover-content ol{margin-bottom:0}.popover .arrow,.popover .arrow:after{position:absolute;display:inline-block;width:0;height:0;border-color:transparent;border-style:solid}.popover .arrow:after{z-index:-1;content:""}.popover.top .arrow{bottom:-10px;left:50%;margin-left:-10px;border-top-color:#fff;border-width:10px 10px 0}.popover.top .arrow:after{bottom:-1px;left:-11px;border-top-color:rgba(0,0,0,0.25);border-width:11px 11px 0}.popover.right .arrow{top:50%;left:-10px;margin-top:-10px;border-right-color:#fff;border-width:10px 10px 10px 0}.popover.right .arrow:after{bottom:-11px;left:-1px;border-right-color:rgba(0,0,0,0.25);border-width:11px 11px 11px 0}.popover.bottom .arrow{top:-10px;left:50%;margin-left:-10px;border-bottom-color:#fff;border-width:0 10px 10px}.popover.bottom .arrow:after{top:-1px;left:-11px;border-bottom-color:rgba(0,0,0,0.25);border-width:0 11px 11px}.popover.left .arrow{top:50%;right:-10px;margin-top:-10px;border-left-color:#fff;border-width:10px 0 10px 10px}.popover.left .arrow:after{right:-1px;bottom:-11px;border-left-color:rgba(0,0,0,0.25);border-width:11px 0 11px 11px}.thumbnails{margin-left:-20px;list-style:none;*zoom:1}.thumbnails:before,.thumbnails:after{display:table;line-height:0;content:""}.thumbnails:after{clear:both}.row-fluid .thumbnails{margin-left:0}.thumbnails>li{float:left;margin-bottom:20px;margin-left:20px}.thumbnail{display:block;padding:4px;line-height:20px;border:1px solid #ddd;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;-webkit-box-shadow:0 1px 3px rgba(0,0,0,0.055);-moz-box-shadow:0 1px 3px rgba(0,0,0,0.055);box-shadow:0 1px 3px rgba(0,0,0,0.055);-webkit-transition:all .2s ease-in-out;-moz-transition:all .2s ease-in-out;-o-transition:all .2s ease-in-out;transition:all .2s ease-in-out}a.thumbnail:hover{border-color:#08c;-webkit-box-shadow:0 1px 4px rgba(0,105,214,0.25);-moz-box-shadow:0 1px 4px rgba(0,105,214,0.25);box-shadow:0 1px 4px rgba(0,105,214,0.25)}.thumbnail>img{display:block;max-width:100%;margin-right:auto;margin-left:auto}.thumbnail .caption{padding:9px;color:#555}.label,.badge{font-size:11.844px;font-weight:bold;line-height:14px;color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);white-space:nowrap;vertical-align:baseline;background-color:#999}.label{padding:1px 4px 2px;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}.badge{padding:1px 9px 2px;-webkit-border-radius:9px;-moz-border-radius:9px;border-radius:9px}a.label:hover,a.badge:hover{color:#fff;text-decoration:none;cursor:pointer}.label-important,.badge-important{background-color:#b94a48}.label-important[href],.badge-important[href]{background-color:#953b39}.label-warning,.badge-warning{background-color:#f89406}.label-warning[href],.badge-warning[href]{background-color:#c67605}.label-success,.badge-success{background-color:#468847}.label-success[href],.badge-success[href]{background-color:#356635}.label-info,.badge-info{background-color:#3a87ad}.label-info[href],.badge-info[href]{background-color:#2d6987}.label-inverse,.badge-inverse{background-color:#333}.label-inverse[href],.badge-inverse[href]{background-color:#1a1a1a}.btn .label,.btn .badge{position:relative;top:-1px}.btn-mini .label,.btn-mini .badge{top:0}@-webkit-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-moz-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-ms-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-o-keyframes progress-bar-stripes{from{background-position:0 0}to{background-position:40px 0}}@keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}.progress{height:20px;margin-bottom:20px;overflow:hidden;background-color:#f7f7f7;background-image:-moz-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:-webkit-gradient(linear,0 0,0 100%,from(#f5f5f5),to(#f9f9f9));background-image:-webkit-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:-o-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:linear-gradient(to bottom,#f5f5f5,#f9f9f9);background-repeat:repeat-x;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fff5f5f5',endColorstr='#fff9f9f9',GradientType=0);-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1);box-shadow:inset 0 1px 2px rgba(0,0,0,0.1)}.progress .bar{float:left;width:0;height:100%;font-size:12px;color:#fff;text-align:center;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#0e90d2;background-image:-moz-linear-gradient(top,#149bdf,#0480be);background-image:-webkit-gradient(linear,0 0,0 100%,from(#149bdf),to(#0480be));background-image:-webkit-linear-gradient(top,#149bdf,#0480be);background-image:-o-linear-gradient(top,#149bdf,#0480be);background-image:linear-gradient(to bottom,#149bdf,#0480be);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff149bdf',endColorstr='#ff0480be',GradientType=0);-webkit-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);-moz-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box;-webkit-transition:width .6s ease;-moz-transition:width .6s ease;-o-transition:width .6s ease;transition:width .6s ease}.progress .bar+.bar{-webkit-box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15);-moz-box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15);box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15)}.progress-striped .bar{background-color:#149bdf;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);-webkit-background-size:40px 40px;-moz-background-size:40px 40px;-o-background-size:40px 40px;background-size:40px 40px}.progress.active .bar{-webkit-animation:progress-bar-stripes 2s linear infinite;-moz-animation:progress-bar-stripes 2s linear infinite;-ms-animation:progress-bar-stripes 2s linear infinite;-o-animation:progress-bar-stripes 2s linear infinite;animation:progress-bar-stripes 2s linear infinite}.progress-danger .bar,.progress .bar-danger{background-color:#dd514c;background-image:-moz-linear-gradient(top,#ee5f5b,#c43c35);background-image:-webkit-gradient(linear,0 0,0 100%,from(#ee5f5b),to(#c43c35));background-image:-webkit-linear-gradient(top,#ee5f5b,#c43c35);background-image:-o-linear-gradient(top,#ee5f5b,#c43c35);background-image:linear-gradient(to bottom,#ee5f5b,#c43c35);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffee5f5b',endColorstr='#ffc43c35',GradientType=0)}.progress-danger.progress-striped .bar,.progress-striped .bar-danger{background-color:#ee5f5b;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-success .bar,.progress .bar-success{background-color:#5eb95e;background-image:-moz-linear-gradient(top,#62c462,#57a957);background-image:-webkit-gradient(linear,0 0,0 100%,from(#62c462),to(#57a957));background-image:-webkit-linear-gradient(top,#62c462,#57a957);background-image:-o-linear-gradient(top,#62c462,#57a957);background-image:linear-gradient(to bottom,#62c462,#57a957);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff62c462',endColorstr='#ff57a957',GradientType=0)}.progress-success.progress-striped .bar,.progress-striped .bar-success{background-color:#62c462;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-info .bar,.progress .bar-info{background-color:#4bb1cf;background-image:-moz-linear-gradient(top,#5bc0de,#339bb9);background-image:-webkit-gradient(linear,0 0,0 100%,from(#5bc0de),to(#339bb9));background-image:-webkit-linear-gradient(top,#5bc0de,#339bb9);background-image:-o-linear-gradient(top,#5bc0de,#339bb9);background-image:linear-gradient(to bottom,#5bc0de,#339bb9);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff5bc0de',endColorstr='#ff339bb9',GradientType=0)}.progress-info.progress-striped .bar,.progress-striped .bar-info{background-color:#5bc0de;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-warning .bar,.progress .bar-warning{background-color:#faa732;background-image:-moz-linear-gradient(top,#fbb450,#f89406);background-image:-webkit-gradient(linear,0 0,0 100%,from(#fbb450),to(#f89406));background-image:-webkit-linear-gradient(top,#fbb450,#f89406);background-image:-o-linear-gradient(top,#fbb450,#f89406);background-image:linear-gradient(to bottom,#fbb450,#f89406);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fffbb450',endColorstr='#fff89406',GradientType=0)}.progress-warning.progress-striped .bar,.progress-striped .bar-warning{background-color:#fbb450;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.accordion{margin-bottom:20px}.accordion-group{margin-bottom:2px;border:1px solid #e5e5e5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.accordion-heading{border-bottom:0}.accordion-heading .accordion-toggle{display:block;padding:8px 15px}.accordion-toggle{cursor:pointer}.accordion-inner{padding:9px 15px;border-top:1px solid #e5e5e5}.carousel{position:relative;margin-bottom:20px;line-height:1}.carousel-inner{position:relative;width:100%;overflow:hidden}.carousel .item{position:relative;display:none;-webkit-transition:.6s ease-in-out left;-moz-transition:.6s ease-in-out left;-o-transition:.6s ease-in-out left;transition:.6s ease-in-out left}.carousel .item>img{display:block;line-height:1}.carousel .active,.carousel .next,.carousel .prev{display:block}.carousel .active{left:0}.carousel .next,.carousel .prev{position:absolute;top:0;width:100%}.carousel .next{left:100%}.carousel .prev{left:-100%}.carousel .next.left,.carousel .prev.right{left:0}.carousel .active.left{left:-100%}.carousel .active.right{left:100%}.carousel-control{position:absolute;top:40%;left:15px;width:40px;height:40px;margin-top:-20px;font-size:60px;font-weight:100;line-height:30px;color:#fff;text-align:center;background:#222;border:3px solid #fff;-webkit-border-radius:23px;-moz-border-radius:23px;border-radius:23px;opacity:.5;filter:alpha(opacity=50)}.carousel-control.right{right:15px;left:auto}.carousel-control:hover{color:#fff;text-decoration:none;opacity:.9;filter:alpha(opacity=90)}.carousel-caption{position:absolute;right:0;bottom:0;left:0;padding:15px;background:#333;background:rgba(0,0,0,0.75)}.carousel-caption h4,.carousel-caption p{line-height:20px;color:#fff}.carousel-caption h4{margin:0 0 5px}.carousel-caption p{margin-bottom:0}.hero-unit{padding:60px;margin-bottom:30px;background-color:#eee;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.hero-unit h1{margin-bottom:0;font-size:60px;line-height:1;letter-spacing:-1px;color:inherit}.hero-unit p{font-size:18px;font-weight:200;line-height:30px;color:inherit}.pull-right{float:right}.pull-left{float:left}.hide{display:none}.show{display:block}.invisible{visibility:hidden}.affix{position:fixed} + */article,aside,details,figcaption,figure,footer,header,hgroup,nav,section{display:block}audio,canvas,video{display:inline-block;*display:inline;*zoom:1}audio:not([controls]){display:none}html{font-size:100%;-webkit-text-size-adjust:100%;-ms-text-size-adjust:100%}a:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}a:hover,a:active{outline:0}sub,sup{position:relative;font-size:75%;line-height:0;vertical-align:baseline}sup{top:-0.5em}sub{bottom:-0.25em}img{height:auto;max-width:100%;vertical-align:middle;border:0;-ms-interpolation-mode:bicubic}#map_canvas img{max-width:none}button,input,select,textarea{margin:0;font-size:100%;vertical-align:middle}button,input{*overflow:visible;line-height:normal}button::-moz-focus-inner,input::-moz-focus-inner{padding:0;border:0}button,input[type="button"],input[type="reset"],input[type="submit"]{cursor:pointer;-webkit-appearance:button}input[type="search"]{-webkit-box-sizing:content-box;-moz-box-sizing:content-box;box-sizing:content-box;-webkit-appearance:textfield}input[type="search"]::-webkit-search-decoration,input[type="search"]::-webkit-search-cancel-button{-webkit-appearance:none}textarea{overflow:auto;vertical-align:top}.clearfix{*zoom:1}.clearfix:before,.clearfix:after{display:table;line-height:0;content:""}.clearfix:after{clear:both}.hide-text{font:0/0 a;color:transparent;text-shadow:none;background-color:transparent;border:0}.input-block-level{display:block;width:100%;min-height:30px;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}body{margin:0;font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:14px;line-height:20px;color:#333;background-color:#fff}a{color:#08c;text-decoration:none}a:hover{color:#005580;text-decoration:underline}.img-rounded{-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.img-polaroid{padding:4px;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);-webkit-box-shadow:0 1px 3px rgba(0,0,0,0.1);-moz-box-shadow:0 1px 3px rgba(0,0,0,0.1);box-shadow:0 1px 3px rgba(0,0,0,0.1)}.img-circle{-webkit-border-radius:500px;-moz-border-radius:500px;border-radius:500px}.row{margin-left:-20px;*zoom:1}.row:before,.row:after{display:table;line-height:0;content:""}.row:after{clear:both}[class*="span"]{float:left;margin-left:20px}.container,.navbar-static-top .container,.navbar-fixed-top .container,.navbar-fixed-bottom .container{width:940px}.span12{width:940px}.span11{width:860px}.span10{width:780px}.span9{width:700px}.span8{width:620px}.span7{width:540px}.span6{width:460px}.span5{width:380px}.span4{width:300px}.span3{width:220px}.span2{width:140px}.span1{width:60px}.offset12{margin-left:980px}.offset11{margin-left:900px}.offset10{margin-left:820px}.offset9{margin-left:740px}.offset8{margin-left:660px}.offset7{margin-left:580px}.offset6{margin-left:500px}.offset5{margin-left:420px}.offset4{margin-left:340px}.offset3{margin-left:260px}.offset2{margin-left:180px}.offset1{margin-left:100px}.row-fluid{width:100%;*zoom:1}.row-fluid:before,.row-fluid:after{display:table;line-height:0;content:""}.row-fluid:after{clear:both}.row-fluid [class*="span"]{display:block;float:left;width:100%;min-height:30px;margin-left:2.127659574468085%;*margin-left:2.074468085106383%;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}.row-fluid [class*="span"]:first-child{margin-left:0}.row-fluid .span12{width:100%;*width:99.94680851063829%}.row-fluid .span11{width:91.48936170212765%;*width:91.43617021276594%}.row-fluid .span10{width:82.97872340425532%;*width:82.92553191489361%}.row-fluid .span9{width:74.46808510638297%;*width:74.41489361702126%}.row-fluid .span8{width:65.95744680851064%;*width:65.90425531914893%}.row-fluid .span7{width:57.44680851063829%;*width:57.39361702127659%}.row-fluid .span6{width:48.93617021276595%;*width:48.88297872340425%}.row-fluid .span5{width:40.42553191489362%;*width:40.37234042553192%}.row-fluid .span4{width:31.914893617021278%;*width:31.861702127659576%}.row-fluid .span3{width:23.404255319148934%;*width:23.351063829787233%}.row-fluid .span2{width:14.893617021276595%;*width:14.840425531914894%}.row-fluid .span1{width:6.382978723404255%;*width:6.329787234042553%}.row-fluid .offset12{margin-left:104.25531914893617%;*margin-left:104.14893617021275%}.row-fluid .offset12:first-child{margin-left:102.12765957446808%;*margin-left:102.02127659574467%}.row-fluid .offset11{margin-left:95.74468085106382%;*margin-left:95.6382978723404%}.row-fluid .offset11:first-child{margin-left:93.61702127659574%;*margin-left:93.51063829787232%}.row-fluid .offset10{margin-left:87.23404255319149%;*margin-left:87.12765957446807%}.row-fluid .offset10:first-child{margin-left:85.1063829787234%;*margin-left:84.99999999999999%}.row-fluid .offset9{margin-left:78.72340425531914%;*margin-left:78.61702127659572%}.row-fluid .offset9:first-child{margin-left:76.59574468085106%;*margin-left:76.48936170212764%}.row-fluid .offset8{margin-left:70.2127659574468%;*margin-left:70.10638297872339%}.row-fluid .offset8:first-child{margin-left:68.08510638297872%;*margin-left:67.9787234042553%}.row-fluid .offset7{margin-left:61.70212765957446%;*margin-left:61.59574468085106%}.row-fluid .offset7:first-child{margin-left:59.574468085106375%;*margin-left:59.46808510638297%}.row-fluid .offset6{margin-left:53.191489361702125%;*margin-left:53.085106382978715%}.row-fluid .offset6:first-child{margin-left:51.063829787234035%;*margin-left:50.95744680851063%}.row-fluid .offset5{margin-left:44.68085106382979%;*margin-left:44.57446808510638%}.row-fluid .offset5:first-child{margin-left:42.5531914893617%;*margin-left:42.4468085106383%}.row-fluid .offset4{margin-left:36.170212765957444%;*margin-left:36.06382978723405%}.row-fluid .offset4:first-child{margin-left:34.04255319148936%;*margin-left:33.93617021276596%}.row-fluid .offset3{margin-left:27.659574468085104%;*margin-left:27.5531914893617%}.row-fluid .offset3:first-child{margin-left:25.53191489361702%;*margin-left:25.425531914893618%}.row-fluid .offset2{margin-left:19.148936170212764%;*margin-left:19.04255319148936%}.row-fluid .offset2:first-child{margin-left:17.02127659574468%;*margin-left:16.914893617021278%}.row-fluid .offset1{margin-left:10.638297872340425%;*margin-left:10.53191489361702%}.row-fluid .offset1:first-child{margin-left:8.51063829787234%;*margin-left:8.404255319148938%}[class*="span"].hide,.row-fluid [class*="span"].hide{display:none}[class*="span"].pull-right,.row-fluid [class*="span"].pull-right{float:right}.container{margin-right:auto;margin-left:auto;*zoom:1}.container:before,.container:after{display:table;line-height:0;content:""}.container:after{clear:both}.container-fluid{padding-right:20px;padding-left:20px;*zoom:1}.container-fluid:before,.container-fluid:after{display:table;line-height:0;content:""}.container-fluid:after{clear:both}p{margin:0 0 10px}.lead{margin-bottom:20px;font-size:20px;font-weight:200;line-height:30px}small{font-size:85%}strong{font-weight:bold}em{font-style:italic}cite{font-style:normal}.muted{color:#999}h1,h2,h3,h4,h5,h6{margin:10px 0;font-family:inherit;font-weight:bold;line-height:1;color:inherit;text-rendering:optimizelegibility}h1 small,h2 small,h3 small,h4 small,h5 small,h6 small{font-weight:normal;line-height:1;color:#999}h1{font-size:36px;line-height:40px}h2{font-size:30px;line-height:40px}h3{font-size:24px;line-height:40px}h4{font-size:18px;line-height:20px}h5{font-size:14px;line-height:20px}h6{font-size:12px;line-height:20px}h1 small{font-size:24px}h2 small{font-size:18px}h3 small{font-size:14px}h4 small{font-size:14px}.page-header{padding-bottom:9px;margin:20px 0 30px;border-bottom:1px solid #eee}ul,ol{padding:0;margin:0 0 10px 25px}ul ul,ul ol,ol ol,ol ul{margin-bottom:0}li{line-height:20px}ul.unstyled,ol.unstyled{margin-left:0;list-style:none}dl{margin-bottom:20px}dt,dd{line-height:20px}dt{font-weight:bold}dd{margin-left:10px}.dl-horizontal dt{float:left;width:120px;overflow:hidden;clear:left;text-align:right;text-overflow:ellipsis;white-space:nowrap}.dl-horizontal dd{margin-left:130px}hr{margin:20px 0;border:0;border-top:1px solid #eee;border-bottom:1px solid #fff}abbr[title]{cursor:help;border-bottom:1px dotted #999}abbr.initialism{font-size:90%;text-transform:uppercase}blockquote{padding:0 0 0 15px;margin:0 0 20px;border-left:5px solid #eee}blockquote p{margin-bottom:0;font-size:16px;font-weight:300;line-height:25px}blockquote small{display:block;line-height:20px;color:#999}blockquote small:before{content:'\2014 \00A0'}blockquote.pull-right{float:right;padding-right:15px;padding-left:0;border-right:5px solid #eee;border-left:0}blockquote.pull-right p,blockquote.pull-right small{text-align:right}blockquote.pull-right small:before{content:''}blockquote.pull-right small:after{content:'\00A0 \2014'}q:before,q:after,blockquote:before,blockquote:after{content:""}address{display:block;margin-bottom:20px;font-style:normal;line-height:20px}code,pre{padding:0 3px 2px;font-family:Monaco,Menlo,Consolas,"Courier New",monospace;font-size:12px;color:#333;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}code{padding:2px 4px;color:#d14;background-color:#f7f7f9;border:1px solid #e1e1e8}pre{display:block;padding:9.5px;margin:0 0 10px;font-size:13px;line-height:20px;word-break:break-all;word-wrap:break-word;white-space:pre;white-space:pre-wrap;background-color:#f5f5f5;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.15);-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}pre.prettyprint{margin-bottom:20px}pre code{padding:0;color:inherit;background-color:transparent;border:0}.pre-scrollable{max-height:340px;overflow-y:scroll}form{margin:0 0 20px}fieldset{padding:0;margin:0;border:0}legend{display:block;width:100%;padding:0;margin-bottom:20px;font-size:21px;line-height:40px;color:#333;border:0;border-bottom:1px solid #e5e5e5}legend small{font-size:15px;color:#999}label,input,button,select,textarea{font-size:14px;font-weight:normal;line-height:20px}input,button,select,textarea{font-family:"Helvetica Neue",Helvetica,Arial,sans-serif}label{display:block;margin-bottom:5px}select,textarea,input[type="text"],input[type="password"],input[type="datetime"],input[type="datetime-local"],input[type="date"],input[type="month"],input[type="time"],input[type="week"],input[type="number"],input[type="email"],input[type="url"],input[type="search"],input[type="tel"],input[type="color"],.uneditable-input{display:inline-block;height:20px;padding:4px 6px;margin-bottom:9px;font-size:14px;line-height:20px;color:#555;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}input,textarea{width:210px}textarea{height:auto}textarea,input[type="text"],input[type="password"],input[type="datetime"],input[type="datetime-local"],input[type="date"],input[type="month"],input[type="time"],input[type="week"],input[type="number"],input[type="email"],input[type="url"],input[type="search"],input[type="tel"],input[type="color"],.uneditable-input{background-color:#fff;border:1px solid #ccc;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-webkit-transition:border linear .2s,box-shadow linear .2s;-moz-transition:border linear .2s,box-shadow linear .2s;-o-transition:border linear .2s,box-shadow linear .2s;transition:border linear .2s,box-shadow linear .2s}textarea:focus,input[type="text"]:focus,input[type="password"]:focus,input[type="datetime"]:focus,input[type="datetime-local"]:focus,input[type="date"]:focus,input[type="month"]:focus,input[type="time"]:focus,input[type="week"]:focus,input[type="number"]:focus,input[type="email"]:focus,input[type="url"]:focus,input[type="search"]:focus,input[type="tel"]:focus,input[type="color"]:focus,.uneditable-input:focus{border-color:rgba(82,168,236,0.8);outline:0;outline:thin dotted \9;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 8px rgba(82,168,236,0.6)}input[type="radio"],input[type="checkbox"]{margin:4px 0 0;margin-top:1px \9;*margin-top:0;line-height:normal;cursor:pointer}input[type="file"],input[type="image"],input[type="submit"],input[type="reset"],input[type="button"],input[type="radio"],input[type="checkbox"]{width:auto}select,input[type="file"]{height:30px;*margin-top:4px;line-height:30px}select{width:220px;background-color:#fff;border:1px solid #bbb}select[multiple],select[size]{height:auto}select:focus,input[type="file"]:focus,input[type="radio"]:focus,input[type="checkbox"]:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}.uneditable-input,.uneditable-textarea{color:#999;cursor:not-allowed;background-color:#fcfcfc;border-color:#ccc;-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.025);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.025);box-shadow:inset 0 1px 2px rgba(0,0,0,0.025)}.uneditable-input{overflow:hidden;white-space:nowrap}.uneditable-textarea{width:auto;height:auto}input:-moz-placeholder,textarea:-moz-placeholder{color:#999}input:-ms-input-placeholder,textarea:-ms-input-placeholder{color:#999}input::-webkit-input-placeholder,textarea::-webkit-input-placeholder{color:#999}.radio,.checkbox{min-height:18px;padding-left:18px}.radio input[type="radio"],.checkbox input[type="checkbox"]{float:left;margin-left:-18px}.controls>.radio:first-child,.controls>.checkbox:first-child{padding-top:5px}.radio.inline,.checkbox.inline{display:inline-block;padding-top:5px;margin-bottom:0;vertical-align:middle}.radio.inline+.radio.inline,.checkbox.inline+.checkbox.inline{margin-left:10px}.input-mini{width:60px}.input-small{width:90px}.input-medium{width:150px}.input-large{width:210px}.input-xlarge{width:270px}.input-xxlarge{width:530px}input[class*="span"],select[class*="span"],textarea[class*="span"],.uneditable-input[class*="span"],.row-fluid input[class*="span"],.row-fluid select[class*="span"],.row-fluid textarea[class*="span"],.row-fluid .uneditable-input[class*="span"]{float:none;margin-left:0}.input-append input[class*="span"],.input-append .uneditable-input[class*="span"],.input-prepend input[class*="span"],.input-prepend .uneditable-input[class*="span"],.row-fluid input[class*="span"],.row-fluid select[class*="span"],.row-fluid textarea[class*="span"],.row-fluid .uneditable-input[class*="span"],.row-fluid .input-prepend [class*="span"],.row-fluid .input-append [class*="span"]{display:inline-block}input,textarea,.uneditable-input{margin-left:0}.controls-row [class*="span"]+[class*="span"]{margin-left:20px}input.span12,textarea.span12,.uneditable-input.span12{width:926px}input.span11,textarea.span11,.uneditable-input.span11{width:846px}input.span10,textarea.span10,.uneditable-input.span10{width:766px}input.span9,textarea.span9,.uneditable-input.span9{width:686px}input.span8,textarea.span8,.uneditable-input.span8{width:606px}input.span7,textarea.span7,.uneditable-input.span7{width:526px}input.span6,textarea.span6,.uneditable-input.span6{width:446px}input.span5,textarea.span5,.uneditable-input.span5{width:366px}input.span4,textarea.span4,.uneditable-input.span4{width:286px}input.span3,textarea.span3,.uneditable-input.span3{width:206px}input.span2,textarea.span2,.uneditable-input.span2{width:126px}input.span1,textarea.span1,.uneditable-input.span1{width:46px}.controls-row{*zoom:1}.controls-row:before,.controls-row:after{display:table;line-height:0;content:""}.controls-row:after{clear:both}.controls-row [class*="span"]{float:left}input[disabled],select[disabled],textarea[disabled],input[readonly],select[readonly],textarea[readonly]{cursor:not-allowed;background-color:#eee}input[type="radio"][disabled],input[type="checkbox"][disabled],input[type="radio"][readonly],input[type="checkbox"][readonly]{background-color:transparent}.control-group.warning>label,.control-group.warning .help-block,.control-group.warning .help-inline{color:#c09853}.control-group.warning .checkbox,.control-group.warning .radio,.control-group.warning input,.control-group.warning select,.control-group.warning textarea{color:#c09853;border-color:#c09853;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.warning .checkbox:focus,.control-group.warning .radio:focus,.control-group.warning input:focus,.control-group.warning select:focus,.control-group.warning textarea:focus{border-color:#a47e3c;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #dbc59e}.control-group.warning .input-prepend .add-on,.control-group.warning .input-append .add-on{color:#c09853;background-color:#fcf8e3;border-color:#c09853}.control-group.error>label,.control-group.error .help-block,.control-group.error .help-inline{color:#b94a48}.control-group.error .checkbox,.control-group.error .radio,.control-group.error input,.control-group.error select,.control-group.error textarea{color:#b94a48;border-color:#b94a48;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.error .checkbox:focus,.control-group.error .radio:focus,.control-group.error input:focus,.control-group.error select:focus,.control-group.error textarea:focus{border-color:#953b39;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #d59392}.control-group.error .input-prepend .add-on,.control-group.error .input-append .add-on{color:#b94a48;background-color:#f2dede;border-color:#b94a48}.control-group.success>label,.control-group.success .help-block,.control-group.success .help-inline{color:#468847}.control-group.success .checkbox,.control-group.success .radio,.control-group.success input,.control-group.success select,.control-group.success textarea{color:#468847;border-color:#468847;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075);box-shadow:inset 0 1px 1px rgba(0,0,0,0.075)}.control-group.success .checkbox:focus,.control-group.success .radio:focus,.control-group.success input:focus,.control-group.success select:focus,.control-group.success textarea:focus{border-color:#356635;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b;-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b;box-shadow:inset 0 1px 1px rgba(0,0,0,0.075),0 0 6px #7aba7b}.control-group.success .input-prepend .add-on,.control-group.success .input-append .add-on{color:#468847;background-color:#dff0d8;border-color:#468847}input:focus:required:invalid,textarea:focus:required:invalid,select:focus:required:invalid{color:#b94a48;border-color:#ee5f5b}input:focus:required:invalid:focus,textarea:focus:required:invalid:focus,select:focus:required:invalid:focus{border-color:#e9322d;-webkit-box-shadow:0 0 6px #f8b9b7;-moz-box-shadow:0 0 6px #f8b9b7;box-shadow:0 0 6px #f8b9b7}.form-actions{padding:19px 20px 20px;margin-top:20px;margin-bottom:20px;background-color:#f5f5f5;border-top:1px solid #e5e5e5;*zoom:1}.form-actions:before,.form-actions:after{display:table;line-height:0;content:""}.form-actions:after{clear:both}.help-block,.help-inline{color:#595959}.help-block{display:block;margin-bottom:10px}.help-inline{display:inline-block;*display:inline;padding-left:5px;vertical-align:middle;*zoom:1}.input-append,.input-prepend{margin-bottom:5px;font-size:0;white-space:nowrap}.input-append input,.input-prepend input,.input-append select,.input-prepend select,.input-append .uneditable-input,.input-prepend .uneditable-input{position:relative;margin-bottom:0;*margin-left:0;font-size:14px;vertical-align:top;-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.input-append input:focus,.input-prepend input:focus,.input-append select:focus,.input-prepend select:focus,.input-append .uneditable-input:focus,.input-prepend .uneditable-input:focus{z-index:2}.input-append .add-on,.input-prepend .add-on{display:inline-block;width:auto;height:20px;min-width:16px;padding:4px 5px;font-size:14px;font-weight:normal;line-height:20px;text-align:center;text-shadow:0 1px 0 #fff;background-color:#eee;border:1px solid #ccc}.input-append .add-on,.input-prepend .add-on,.input-append .btn,.input-prepend .btn{margin-left:-1px;vertical-align:top;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.input-append .active,.input-prepend .active{background-color:#a9dba9;border-color:#46a546}.input-prepend .add-on,.input-prepend .btn{margin-right:-1px}.input-prepend .add-on:first-child,.input-prepend .btn:first-child{-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-append input,.input-append select,.input-append .uneditable-input{-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-append .add-on:last-child,.input-append .btn:last-child{-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.input-prepend.input-append input,.input-prepend.input-append select,.input-prepend.input-append .uneditable-input{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.input-prepend.input-append .add-on:first-child,.input-prepend.input-append .btn:first-child{margin-right:-1px;-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.input-prepend.input-append .add-on:last-child,.input-prepend.input-append .btn:last-child{margin-left:-1px;-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}input.search-query{padding-right:14px;padding-right:4px \9;padding-left:14px;padding-left:4px \9;margin-bottom:0;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.form-search .input-append .search-query,.form-search .input-prepend .search-query{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.form-search .input-append .search-query{-webkit-border-radius:14px 0 0 14px;-moz-border-radius:14px 0 0 14px;border-radius:14px 0 0 14px}.form-search .input-append .btn{-webkit-border-radius:0 14px 14px 0;-moz-border-radius:0 14px 14px 0;border-radius:0 14px 14px 0}.form-search .input-prepend .search-query{-webkit-border-radius:0 14px 14px 0;-moz-border-radius:0 14px 14px 0;border-radius:0 14px 14px 0}.form-search .input-prepend .btn{-webkit-border-radius:14px 0 0 14px;-moz-border-radius:14px 0 0 14px;border-radius:14px 0 0 14px}.form-search input,.form-inline input,.form-horizontal input,.form-search textarea,.form-inline textarea,.form-horizontal textarea,.form-search select,.form-inline select,.form-horizontal select,.form-search .help-inline,.form-inline .help-inline,.form-horizontal .help-inline,.form-search .uneditable-input,.form-inline .uneditable-input,.form-horizontal .uneditable-input,.form-search .input-prepend,.form-inline .input-prepend,.form-horizontal .input-prepend,.form-search .input-append,.form-inline .input-append,.form-horizontal .input-append{display:inline-block;*display:inline;margin-bottom:0;vertical-align:middle;*zoom:1}.form-search .hide,.form-inline .hide,.form-horizontal .hide{display:none}.form-search label,.form-inline label,.form-search .btn-group,.form-inline .btn-group{display:inline-block}.form-search .input-append,.form-inline .input-append,.form-search .input-prepend,.form-inline .input-prepend{margin-bottom:0}.form-search .radio,.form-search .checkbox,.form-inline .radio,.form-inline .checkbox{padding-left:0;margin-bottom:0;vertical-align:middle}.form-search .radio input[type="radio"],.form-search .checkbox input[type="checkbox"],.form-inline .radio input[type="radio"],.form-inline .checkbox input[type="checkbox"]{float:left;margin-right:3px;margin-left:0}.control-group{margin-bottom:10px}legend+.control-group{margin-top:20px;-webkit-margin-top-collapse:separate}.form-horizontal .control-group{margin-bottom:20px;*zoom:1}.form-horizontal .control-group:before,.form-horizontal .control-group:after{display:table;line-height:0;content:""}.form-horizontal .control-group:after{clear:both}.form-horizontal .control-label{float:left;width:140px;padding-top:5px;text-align:right}.form-horizontal .controls{*display:inline-block;*padding-left:20px;margin-left:160px;*margin-left:0}.form-horizontal .controls:first-child{*padding-left:160px}.form-horizontal .help-block{margin-top:10px;margin-bottom:0}.form-horizontal .form-actions{padding-left:160px}table{max-width:100%;background-color:transparent;border-collapse:collapse;border-spacing:0}.table{width:100%;margin-bottom:20px}.table th,.table td{padding:8px;line-height:20px;text-align:left;vertical-align:top;border-top:1px solid #ddd}.table th{font-weight:bold}.table thead th{vertical-align:bottom}.table caption+thead tr:first-child th,.table caption+thead tr:first-child td,.table colgroup+thead tr:first-child th,.table colgroup+thead tr:first-child td,.table thead:first-child tr:first-child th,.table thead:first-child tr:first-child td{border-top:0}.table tbody+tbody{border-top:2px solid #ddd}.table-condensed th,.table-condensed td{padding:4px 5px}.table-bordered{border:1px solid #ddd;border-collapse:separate;*border-collapse:collapse;border-left:0;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.table-bordered th,.table-bordered td{border-left:1px solid #ddd}.table-bordered caption+thead tr:first-child th,.table-bordered caption+tbody tr:first-child th,.table-bordered caption+tbody tr:first-child td,.table-bordered colgroup+thead tr:first-child th,.table-bordered colgroup+tbody tr:first-child th,.table-bordered colgroup+tbody tr:first-child td,.table-bordered thead:first-child tr:first-child th,.table-bordered tbody:first-child tr:first-child th,.table-bordered tbody:first-child tr:first-child td{border-top:0}.table-bordered thead:first-child tr:first-child th:first-child,.table-bordered tbody:first-child tr:first-child td:first-child{-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topleft:4px}.table-bordered thead:first-child tr:first-child th:last-child,.table-bordered tbody:first-child tr:first-child td:last-child{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-moz-border-radius-topright:4px}.table-bordered thead:last-child tr:last-child th:first-child,.table-bordered tbody:last-child tr:last-child td:first-child,.table-bordered tfoot:last-child tr:last-child td:first-child{-webkit-border-radius:0 0 0 4px;-moz-border-radius:0 0 0 4px;border-radius:0 0 0 4px;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-moz-border-radius-bottomleft:4px}.table-bordered thead:last-child tr:last-child th:last-child,.table-bordered tbody:last-child tr:last-child td:last-child,.table-bordered tfoot:last-child tr:last-child td:last-child{-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-moz-border-radius-bottomright:4px}.table-bordered caption+thead tr:first-child th:first-child,.table-bordered caption+tbody tr:first-child td:first-child,.table-bordered colgroup+thead tr:first-child th:first-child,.table-bordered colgroup+tbody tr:first-child td:first-child{-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topleft:4px}.table-bordered caption+thead tr:first-child th:last-child,.table-bordered caption+tbody tr:first-child td:last-child,.table-bordered colgroup+thead tr:first-child th:last-child,.table-bordered colgroup+tbody tr:first-child td:last-child{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-moz-border-right-topleft:4px}.table-striped tbody tr:nth-child(odd) td,.table-striped tbody tr:nth-child(odd) th{background-color:#f9f9f9}.table-hover tbody tr:hover td,.table-hover tbody tr:hover th{background-color:#f5f5f5}table [class*=span],.row-fluid table [class*=span]{display:table-cell;float:none;margin-left:0}table .span1{float:none;width:44px;margin-left:0}table .span2{float:none;width:124px;margin-left:0}table .span3{float:none;width:204px;margin-left:0}table .span4{float:none;width:284px;margin-left:0}table .span5{float:none;width:364px;margin-left:0}table .span6{float:none;width:444px;margin-left:0}table .span7{float:none;width:524px;margin-left:0}table .span8{float:none;width:604px;margin-left:0}table .span9{float:none;width:684px;margin-left:0}table .span10{float:none;width:764px;margin-left:0}table .span11{float:none;width:844px;margin-left:0}table .span12{float:none;width:924px;margin-left:0}table .span13{float:none;width:1004px;margin-left:0}table .span14{float:none;width:1084px;margin-left:0}table .span15{float:none;width:1164px;margin-left:0}table .span16{float:none;width:1244px;margin-left:0}table .span17{float:none;width:1324px;margin-left:0}table .span18{float:none;width:1404px;margin-left:0}table .span19{float:none;width:1484px;margin-left:0}table .span20{float:none;width:1564px;margin-left:0}table .span21{float:none;width:1644px;margin-left:0}table .span22{float:none;width:1724px;margin-left:0}table .span23{float:none;width:1804px;margin-left:0}table .span24{float:none;width:1884px;margin-left:0}.table tbody tr.success td{background-color:#dff0d8}.table tbody tr.error td{background-color:#f2dede}.table tbody tr.info td{background-color:#d9edf7}[class^="icon-"],[class*=" icon-"]{display:inline-block;width:14px;height:14px;margin-top:1px;*margin-right:.3em;line-height:14px;vertical-align:text-top;background-image:url("../img/glyphicons-halflings.png");background-position:14px 14px;background-repeat:no-repeat}.icon-white,.nav>.active>a>[class^="icon-"],.nav>.active>a>[class*=" icon-"],.dropdown-menu>li>a:hover>[class^="icon-"],.dropdown-menu>li>a:hover>[class*=" icon-"],.dropdown-menu>.active>a>[class^="icon-"],.dropdown-menu>.active>a>[class*=" icon-"]{background-image:url("../img/glyphicons-halflings-white.png")}.icon-glass{background-position:0 0}.icon-music{background-position:-24px 0}.icon-search{background-position:-48px 0}.icon-envelope{background-position:-72px 0}.icon-heart{background-position:-96px 0}.icon-star{background-position:-120px 0}.icon-star-empty{background-position:-144px 0}.icon-user{background-position:-168px 0}.icon-film{background-position:-192px 0}.icon-th-large{background-position:-216px 0}.icon-th{background-position:-240px 0}.icon-th-list{background-position:-264px 0}.icon-ok{background-position:-288px 0}.icon-remove{background-position:-312px 0}.icon-zoom-in{background-position:-336px 0}.icon-zoom-out{background-position:-360px 0}.icon-off{background-position:-384px 0}.icon-signal{background-position:-408px 0}.icon-cog{background-position:-432px 0}.icon-trash{background-position:-456px 0}.icon-home{background-position:0 -24px}.icon-file{background-position:-24px -24px}.icon-time{background-position:-48px -24px}.icon-road{background-position:-72px -24px}.icon-download-alt{background-position:-96px -24px}.icon-download{background-position:-120px -24px}.icon-upload{background-position:-144px -24px}.icon-inbox{background-position:-168px -24px}.icon-play-circle{background-position:-192px -24px}.icon-repeat{background-position:-216px -24px}.icon-refresh{background-position:-240px -24px}.icon-list-alt{background-position:-264px -24px}.icon-lock{background-position:-287px -24px}.icon-flag{background-position:-312px -24px}.icon-headphones{background-position:-336px -24px}.icon-volume-off{background-position:-360px -24px}.icon-volume-down{background-position:-384px -24px}.icon-volume-up{background-position:-408px -24px}.icon-qrcode{background-position:-432px -24px}.icon-barcode{background-position:-456px -24px}.icon-tag{background-position:0 -48px}.icon-tags{background-position:-25px -48px}.icon-book{background-position:-48px -48px}.icon-bookmark{background-position:-72px -48px}.icon-print{background-position:-96px -48px}.icon-camera{background-position:-120px -48px}.icon-font{background-position:-144px -48px}.icon-bold{background-position:-167px -48px}.icon-italic{background-position:-192px -48px}.icon-text-height{background-position:-216px -48px}.icon-text-width{background-position:-240px -48px}.icon-align-left{background-position:-264px -48px}.icon-align-center{background-position:-288px -48px}.icon-align-right{background-position:-312px -48px}.icon-align-justify{background-position:-336px -48px}.icon-list{background-position:-360px -48px}.icon-indent-left{background-position:-384px -48px}.icon-indent-right{background-position:-408px -48px}.icon-facetime-video{background-position:-432px -48px}.icon-picture{background-position:-456px -48px}.icon-pencil{background-position:0 -72px}.icon-map-marker{background-position:-24px -72px}.icon-adjust{background-position:-48px -72px}.icon-tint{background-position:-72px -72px}.icon-edit{background-position:-96px -72px}.icon-share{background-position:-120px -72px}.icon-check{background-position:-144px -72px}.icon-move{background-position:-168px -72px}.icon-step-backward{background-position:-192px -72px}.icon-fast-backward{background-position:-216px -72px}.icon-backward{background-position:-240px -72px}.icon-play{background-position:-264px -72px}.icon-pause{background-position:-288px -72px}.icon-stop{background-position:-312px -72px}.icon-forward{background-position:-336px -72px}.icon-fast-forward{background-position:-360px -72px}.icon-step-forward{background-position:-384px -72px}.icon-eject{background-position:-408px -72px}.icon-chevron-left{background-position:-432px -72px}.icon-chevron-right{background-position:-456px -72px}.icon-plus-sign{background-position:0 -96px}.icon-minus-sign{background-position:-24px -96px}.icon-remove-sign{background-position:-48px -96px}.icon-ok-sign{background-position:-72px -96px}.icon-question-sign{background-position:-96px -96px}.icon-info-sign{background-position:-120px -96px}.icon-screenshot{background-position:-144px -96px}.icon-remove-circle{background-position:-168px -96px}.icon-ok-circle{background-position:-192px -96px}.icon-ban-circle{background-position:-216px -96px}.icon-arrow-left{background-position:-240px -96px}.icon-arrow-right{background-position:-264px -96px}.icon-arrow-up{background-position:-289px -96px}.icon-arrow-down{background-position:-312px -96px}.icon-share-alt{background-position:-336px -96px}.icon-resize-full{background-position:-360px -96px}.icon-resize-small{background-position:-384px -96px}.icon-plus{background-position:-408px -96px}.icon-minus{background-position:-433px -96px}.icon-asterisk{background-position:-456px -96px}.icon-exclamation-sign{background-position:0 -120px}.icon-gift{background-position:-24px -120px}.icon-leaf{background-position:-48px -120px}.icon-fire{background-position:-72px -120px}.icon-eye-open{background-position:-96px -120px}.icon-eye-close{background-position:-120px -120px}.icon-warning-sign{background-position:-144px -120px}.icon-plane{background-position:-168px -120px}.icon-calendar{background-position:-192px -120px}.icon-random{width:16px;background-position:-216px -120px}.icon-comment{background-position:-240px -120px}.icon-magnet{background-position:-264px -120px}.icon-chevron-up{background-position:-288px -120px}.icon-chevron-down{background-position:-313px -119px}.icon-retweet{background-position:-336px -120px}.icon-shopping-cart{background-position:-360px -120px}.icon-folder-close{background-position:-384px -120px}.icon-folder-open{width:16px;background-position:-408px -120px}.icon-resize-vertical{background-position:-432px -119px}.icon-resize-horizontal{background-position:-456px -118px}.icon-hdd{background-position:0 -144px}.icon-bullhorn{background-position:-24px -144px}.icon-bell{background-position:-48px -144px}.icon-certificate{background-position:-72px -144px}.icon-thumbs-up{background-position:-96px -144px}.icon-thumbs-down{background-position:-120px -144px}.icon-hand-right{background-position:-144px -144px}.icon-hand-left{background-position:-168px -144px}.icon-hand-up{background-position:-192px -144px}.icon-hand-down{background-position:-216px -144px}.icon-circle-arrow-right{background-position:-240px -144px}.icon-circle-arrow-left{background-position:-264px -144px}.icon-circle-arrow-up{background-position:-288px -144px}.icon-circle-arrow-down{background-position:-312px -144px}.icon-globe{background-position:-336px -144px}.icon-wrench{background-position:-360px -144px}.icon-tasks{background-position:-384px -144px}.icon-filter{background-position:-408px -144px}.icon-briefcase{background-position:-432px -144px}.icon-fullscreen{background-position:-456px -144px}.dropup,.dropdown{position:relative}.dropdown-toggle{*margin-bottom:-3px}.dropdown-toggle:active,.open .dropdown-toggle{outline:0}.caret{display:inline-block;width:0;height:0;vertical-align:top;border-top:4px solid #000;border-right:4px solid transparent;border-left:4px solid transparent;content:""}.dropdown .caret{margin-top:8px;margin-left:2px}.dropdown-menu{position:absolute;top:100%;left:0;z-index:1000;display:none;float:left;min-width:160px;padding:5px 0;margin:2px 0 0;list-style:none;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);*border-right-width:2px;*border-bottom-width:2px;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 5px 10px rgba(0,0,0,0.2);-moz-box-shadow:0 5px 10px rgba(0,0,0,0.2);box-shadow:0 5px 10px rgba(0,0,0,0.2);-webkit-background-clip:padding-box;-moz-background-clip:padding;background-clip:padding-box}.dropdown-menu.pull-right{right:0;left:auto}.dropdown-menu .divider{*width:100%;height:1px;margin:9px 1px;*margin:-5px 0 5px;overflow:hidden;background-color:#e5e5e5;border-bottom:1px solid #fff}.dropdown-menu a{display:block;padding:3px 20px;clear:both;font-weight:normal;line-height:20px;color:#333;white-space:nowrap}.dropdown-menu li>a:hover,.dropdown-menu li>a:focus,.dropdown-submenu:hover>a{color:#fff;text-decoration:none;background-color:#0088cc;background-color:#0088cc;background-image:-moz-linear-gradient(top,#0088cc,#0087b3);background-image:-webkit-gradient(linear,0 0,0 100%,from(#0088cc),to(#0087b3));background-image:-webkit-linear-gradient(top,#0088cc,#0087b3);background-image:-o-linear-gradient(top,#0088cc,#0087b3);background-image:linear-gradient(to bottom,#0088cc,#0087b3);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0087b3',GradientType=0)}.dropdown-menu .active>a,.dropdown-menu .active>a:hover{color:#fff;text-decoration:none;background-color:#0088cc;background-color:#0081c2;background-image:linear-gradient(to bottom,#0088cc,#0087b3);background-image:-moz-linear-gradient(top,#0088cc,#0087b3);background-image:-webkit-gradient(linear,0 0,0 100%,from(#0088cc),to(#0087b3));background-image:-webkit-linear-gradient(top,#0088cc,#0087b3);background-image:-o-linear-gradient(top,#0088cc,#0087b3);background-repeat:repeat-x;outline:0;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0087b3',GradientType=0)}.dropdown-menu .disabled>a,.dropdown-menu .disabled>a:hover{color:#999}.dropdown-menu .disabled>a:hover{text-decoration:none;cursor:default;background-color:transparent}.open{*z-index:1000}.open>.dropdown-menu{display:block}.pull-right>.dropdown-menu{right:0;left:auto}.dropup .caret,.navbar-fixed-bottom .dropdown .caret{border-top:0;border-bottom:4px solid #000;content:"\2191"}.dropup .dropdown-menu,.navbar-fixed-bottom .dropdown .dropdown-menu{top:auto;bottom:100%;margin-bottom:1px}.dropdown-submenu{position:relative}.dropdown-submenu>.dropdown-menu{top:0;left:100%;margin-top:-6px;margin-left:-1px;-webkit-border-radius:0 6px 6px 6px;-moz-border-radius:0 6px 6px 6px;border-radius:0 6px 6px 6px}.dropdown-submenu:hover .dropdown-menu{display:block}.dropdown-submenu>a:after{display:block;float:right;width:0;height:0;margin-top:5px;margin-right:-10px;border-color:transparent;border-left-color:#ccc;border-style:solid;border-width:5px 0 5px 5px;content:" "}.dropdown-submenu:hover>a:after{border-left-color:#fff}.dropdown .dropdown-menu .nav-header{padding-right:20px;padding-left:20px}.typeahead{margin-top:2px;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.well{min-height:20px;padding:19px;margin-bottom:20px;background-color:#f5f5f5;border:1px solid #e3e3e3;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;-webkit-box-shadow:inset 0 1px 1px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 1px 1px rgba(0,0,0,0.05);box-shadow:inset 0 1px 1px rgba(0,0,0,0.05)}.well blockquote{border-color:#ddd;border-color:rgba(0,0,0,0.15)}.well-large{padding:24px;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.well-small{padding:9px;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}.fade{opacity:0;-webkit-transition:opacity .15s linear;-moz-transition:opacity .15s linear;-o-transition:opacity .15s linear;transition:opacity .15s linear}.fade.in{opacity:1}.collapse{position:relative;height:0;overflow:hidden;overflow:visible \9;-webkit-transition:height .35s ease;-moz-transition:height .35s ease;-o-transition:height .35s ease;transition:height .35s ease}.collapse.in{height:auto}.close{float:right;font-size:20px;font-weight:bold;line-height:20px;color:#000;text-shadow:0 1px 0 #fff;opacity:.2;filter:alpha(opacity=20)}.close:hover{color:#000;text-decoration:none;cursor:pointer;opacity:.4;filter:alpha(opacity=40)}button.close{padding:0;cursor:pointer;background:transparent;border:0;-webkit-appearance:none}.btn{display:inline-block;*display:inline;padding:4px 14px;margin-bottom:0;*margin-left:.3em;font-size:14px;line-height:20px;*line-height:20px;color:#333;text-align:center;text-shadow:0 1px 1px rgba(255,255,255,0.75);vertical-align:middle;cursor:pointer;background-color:#f5f5f5;*background-color:#e6e6e6;background-image:-webkit-gradient(linear,0 0,0 100%,from(#fff),to(#e6e6e6));background-image:-webkit-linear-gradient(top,#fff,#e6e6e6);background-image:-o-linear-gradient(top,#fff,#e6e6e6);background-image:linear-gradient(to bottom,#fff,#e6e6e6);background-image:-moz-linear-gradient(top,#fff,#e6e6e6);background-repeat:repeat-x;border:1px solid #bbb;*border:0;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);border-color:#e6e6e6 #e6e6e6 #bfbfbf;border-bottom-color:#a2a2a2;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffffffff',endColorstr='#ffe6e6e6',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false);*zoom:1;-webkit-box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05)}.btn:hover,.btn:active,.btn.active,.btn.disabled,.btn[disabled]{color:#333;background-color:#e6e6e6;*background-color:#d9d9d9}.btn:active,.btn.active{background-color:#ccc \9}.btn:first-child{*margin-left:0}.btn:hover{color:#333;text-decoration:none;background-color:#e6e6e6;*background-color:#d9d9d9;background-position:0 -15px;-webkit-transition:background-position .1s linear;-moz-transition:background-position .1s linear;-o-transition:background-position .1s linear;transition:background-position .1s linear}.btn:focus{outline:thin dotted #333;outline:5px auto -webkit-focus-ring-color;outline-offset:-2px}.btn.active,.btn:active{background-color:#e6e6e6;background-color:#d9d9d9 \9;background-image:none;outline:0;-webkit-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05)}.btn.disabled,.btn[disabled]{cursor:default;background-color:#e6e6e6;background-image:none;opacity:.65;filter:alpha(opacity=65);-webkit-box-shadow:none;-moz-box-shadow:none;box-shadow:none}.btn-large{padding:9px 14px;font-size:16px;line-height:normal;-webkit-border-radius:5px;-moz-border-radius:5px;border-radius:5px}.btn-large [class^="icon-"]{margin-top:2px}.btn-small{padding:3px 9px;font-size:12px;line-height:18px}.btn-small [class^="icon-"]{margin-top:0}.btn-mini{padding:2px 6px;font-size:11px;line-height:16px}.btn-block{display:block;width:100%;padding-right:0;padding-left:0;-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box}.btn-block+.btn-block{margin-top:5px}.btn-primary.active,.btn-warning.active,.btn-danger.active,.btn-success.active,.btn-info.active,.btn-inverse.active{color:rgba(255,255,255,0.75)}.btn{border-color:#c5c5c5;border-color:rgba(0,0,0,0.15) rgba(0,0,0,0.15) rgba(0,0,0,0.25)}.btn-primary{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#006dcc;*background-color:#04c;background-image:-webkit-gradient(linear,0 0,0 100%,from(#08c),to(#04c));background-image:-webkit-linear-gradient(top,#08c,#04c);background-image:-o-linear-gradient(top,#08c,#04c);background-image:linear-gradient(to bottom,#08c,#04c);background-image:-moz-linear-gradient(top,#08c,#04c);background-repeat:repeat-x;border-color:#04c #04c #002a80;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff0088cc',endColorstr='#ff0044cc',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-primary:hover,.btn-primary:active,.btn-primary.active,.btn-primary.disabled,.btn-primary[disabled]{color:#fff;background-color:#04c;*background-color:#003bb3}.btn-primary:active,.btn-primary.active{background-color:#039 \9}.btn-warning{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#faa732;*background-color:#f89406;background-image:-webkit-gradient(linear,0 0,0 100%,from(#fbb450),to(#f89406));background-image:-webkit-linear-gradient(top,#fbb450,#f89406);background-image:-o-linear-gradient(top,#fbb450,#f89406);background-image:linear-gradient(to bottom,#fbb450,#f89406);background-image:-moz-linear-gradient(top,#fbb450,#f89406);background-repeat:repeat-x;border-color:#f89406 #f89406 #ad6704;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fffbb450',endColorstr='#fff89406',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-warning:hover,.btn-warning:active,.btn-warning.active,.btn-warning.disabled,.btn-warning[disabled]{color:#fff;background-color:#f89406;*background-color:#df8505}.btn-warning:active,.btn-warning.active{background-color:#c67605 \9}.btn-danger{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#da4f49;*background-color:#bd362f;background-image:-webkit-gradient(linear,0 0,0 100%,from(#ee5f5b),to(#bd362f));background-image:-webkit-linear-gradient(top,#ee5f5b,#bd362f);background-image:-o-linear-gradient(top,#ee5f5b,#bd362f);background-image:linear-gradient(to bottom,#ee5f5b,#bd362f);background-image:-moz-linear-gradient(top,#ee5f5b,#bd362f);background-repeat:repeat-x;border-color:#bd362f #bd362f #802420;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffee5f5b',endColorstr='#ffbd362f',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-danger:hover,.btn-danger:active,.btn-danger.active,.btn-danger.disabled,.btn-danger[disabled]{color:#fff;background-color:#bd362f;*background-color:#a9302a}.btn-danger:active,.btn-danger.active{background-color:#942a25 \9}.btn-success{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#5bb75b;*background-color:#51a351;background-image:-webkit-gradient(linear,0 0,0 100%,from(#62c462),to(#51a351));background-image:-webkit-linear-gradient(top,#62c462,#51a351);background-image:-o-linear-gradient(top,#62c462,#51a351);background-image:linear-gradient(to bottom,#62c462,#51a351);background-image:-moz-linear-gradient(top,#62c462,#51a351);background-repeat:repeat-x;border-color:#51a351 #51a351 #387038;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff62c462',endColorstr='#ff51a351',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-success:hover,.btn-success:active,.btn-success.active,.btn-success.disabled,.btn-success[disabled]{color:#fff;background-color:#51a351;*background-color:#499249}.btn-success:active,.btn-success.active{background-color:#408140 \9}.btn-info{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#49afcd;*background-color:#2f96b4;background-image:-webkit-gradient(linear,0 0,0 100%,from(#5bc0de),to(#2f96b4));background-image:-webkit-linear-gradient(top,#5bc0de,#2f96b4);background-image:-o-linear-gradient(top,#5bc0de,#2f96b4);background-image:linear-gradient(to bottom,#5bc0de,#2f96b4);background-image:-moz-linear-gradient(top,#5bc0de,#2f96b4);background-repeat:repeat-x;border-color:#2f96b4 #2f96b4 #1f6377;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff5bc0de',endColorstr='#ff2f96b4',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-info:hover,.btn-info:active,.btn-info.active,.btn-info.disabled,.btn-info[disabled]{color:#fff;background-color:#2f96b4;*background-color:#2a85a0}.btn-info:active,.btn-info.active{background-color:#24748c \9}.btn-inverse{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#363636;*background-color:#222;background-image:-webkit-gradient(linear,0 0,0 100%,from(#444),to(#222));background-image:-webkit-linear-gradient(top,#444,#222);background-image:-o-linear-gradient(top,#444,#222);background-image:linear-gradient(to bottom,#444,#222);background-image:-moz-linear-gradient(top,#444,#222);background-repeat:repeat-x;border-color:#222 #222 #000;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff444444',endColorstr='#ff222222',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.btn-inverse:hover,.btn-inverse:active,.btn-inverse.active,.btn-inverse.disabled,.btn-inverse[disabled]{color:#fff;background-color:#222;*background-color:#151515}.btn-inverse:active,.btn-inverse.active{background-color:#080808 \9}button.btn,input[type="submit"].btn{*padding-top:3px;*padding-bottom:3px}button.btn::-moz-focus-inner,input[type="submit"].btn::-moz-focus-inner{padding:0;border:0}button.btn.btn-large,input[type="submit"].btn.btn-large{*padding-top:7px;*padding-bottom:7px}button.btn.btn-small,input[type="submit"].btn.btn-small{*padding-top:3px;*padding-bottom:3px}button.btn.btn-mini,input[type="submit"].btn.btn-mini{*padding-top:1px;*padding-bottom:1px}.btn-link,.btn-link:active{background-color:transparent;background-image:none;-webkit-box-shadow:none;-moz-box-shadow:none;box-shadow:none}.btn-link{color:#08c;cursor:pointer;border-color:transparent;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-link:hover{color:#005580;text-decoration:underline;background-color:transparent}.btn-group{position:relative;*margin-left:.3em;font-size:0;white-space:nowrap}.btn-group:first-child{*margin-left:0}.btn-group+.btn-group{margin-left:5px}.btn-toolbar{margin-top:10px;margin-bottom:10px;font-size:0}.btn-toolbar .btn-group{display:inline-block;*display:inline;*zoom:1}.btn-toolbar .btn+.btn,.btn-toolbar .btn-group+.btn,.btn-toolbar .btn+.btn-group{margin-left:5px}.btn-group>.btn{position:relative;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-group>.btn+.btn{margin-left:-1px}.btn-group>.btn,.btn-group>.dropdown-menu{font-size:14px}.btn-group>.btn-mini{font-size:11px}.btn-group>.btn-small{font-size:12px}.btn-group>.btn-large{font-size:16px}.btn-group>.btn:first-child{margin-left:0;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-bottomleft:4px;-moz-border-radius-topleft:4px}.btn-group>.btn:last-child,.btn-group>.dropdown-toggle{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-moz-border-radius-topright:4px;-moz-border-radius-bottomright:4px}.btn-group>.btn.large:first-child{margin-left:0;-webkit-border-bottom-left-radius:6px;border-bottom-left-radius:6px;-webkit-border-top-left-radius:6px;border-top-left-radius:6px;-moz-border-radius-bottomleft:6px;-moz-border-radius-topleft:6px}.btn-group>.btn.large:last-child,.btn-group>.large.dropdown-toggle{-webkit-border-top-right-radius:6px;border-top-right-radius:6px;-webkit-border-bottom-right-radius:6px;border-bottom-right-radius:6px;-moz-border-radius-topright:6px;-moz-border-radius-bottomright:6px}.btn-group>.btn:hover,.btn-group>.btn:focus,.btn-group>.btn:active,.btn-group>.btn.active{z-index:2}.btn-group .dropdown-toggle:active,.btn-group.open .dropdown-toggle{outline:0}.btn-group>.btn+.dropdown-toggle{*padding-top:5px;padding-right:8px;*padding-bottom:5px;padding-left:8px;-webkit-box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 1px 0 0 rgba(255,255,255,0.125),inset 0 1px 0 rgba(255,255,255,0.2),0 1px 2px rgba(0,0,0,0.05)}.btn-group>.btn-mini+.dropdown-toggle{*padding-top:2px;padding-right:5px;*padding-bottom:2px;padding-left:5px}.btn-group>.btn-small+.dropdown-toggle{*padding-top:5px;*padding-bottom:4px}.btn-group>.btn-large+.dropdown-toggle{*padding-top:7px;padding-right:12px;*padding-bottom:7px;padding-left:12px}.btn-group.open .dropdown-toggle{background-image:none;-webkit-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05);box-shadow:inset 0 2px 4px rgba(0,0,0,0.15),0 1px 2px rgba(0,0,0,0.05)}.btn-group.open .btn.dropdown-toggle{background-color:#e6e6e6}.btn-group.open .btn-primary.dropdown-toggle{background-color:#04c}.btn-group.open .btn-warning.dropdown-toggle{background-color:#f89406}.btn-group.open .btn-danger.dropdown-toggle{background-color:#bd362f}.btn-group.open .btn-success.dropdown-toggle{background-color:#51a351}.btn-group.open .btn-info.dropdown-toggle{background-color:#2f96b4}.btn-group.open .btn-inverse.dropdown-toggle{background-color:#222}.btn .caret{margin-top:8px;margin-left:0}.btn-mini .caret,.btn-small .caret,.btn-large .caret{margin-top:6px}.btn-large .caret{border-top-width:5px;border-right-width:5px;border-left-width:5px}.dropup .btn-large .caret{border-top:0;border-bottom:5px solid #000}.btn-primary .caret,.btn-warning .caret,.btn-danger .caret,.btn-info .caret,.btn-success .caret,.btn-inverse .caret{border-top-color:#fff;border-bottom-color:#fff}.btn-group-vertical{display:inline-block;*display:inline;*zoom:1}.btn-group-vertical .btn{display:block;float:none;width:100%;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.btn-group-vertical .btn+.btn{margin-top:-1px;margin-left:0}.btn-group-vertical .btn:first-child{-webkit-border-radius:4px 4px 0 0;-moz-border-radius:4px 4px 0 0;border-radius:4px 4px 0 0}.btn-group-vertical .btn:last-child{-webkit-border-radius:0 0 4px 4px;-moz-border-radius:0 0 4px 4px;border-radius:0 0 4px 4px}.btn-group-vertical .btn-large:first-child{-webkit-border-radius:6px 6px 0 0;-moz-border-radius:6px 6px 0 0;border-radius:6px 6px 0 0}.btn-group-vertical .btn-large:last-child{-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px}.alert{padding:8px 35px 8px 14px;margin-bottom:20px;color:#c09853;text-shadow:0 1px 0 rgba(255,255,255,0.5);background-color:#fcf8e3;border:1px solid #fbeed5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.alert h4{margin:0}.alert .close{position:relative;top:-2px;right:-21px;line-height:20px}.alert-success{color:#468847;background-color:#dff0d8;border-color:#d6e9c6}.alert-danger,.alert-error{color:#b94a48;background-color:#f2dede;border-color:#eed3d7}.alert-info{color:#3a87ad;background-color:#d9edf7;border-color:#bce8f1}.alert-block{padding-top:14px;padding-bottom:14px}.alert-block>p,.alert-block>ul{margin-bottom:0}.alert-block p+p{margin-top:5px}.nav{margin-bottom:20px;margin-left:0;list-style:none}.nav>li>a{display:block}.nav>li>a:hover{text-decoration:none;background-color:#eee}.nav>.pull-right{float:right}.nav-header{display:block;padding:3px 15px;font-size:11px;font-weight:bold;line-height:20px;color:#999;text-shadow:0 1px 0 rgba(255,255,255,0.5);text-transform:uppercase}.nav li+.nav-header{margin-top:9px}.nav-list{padding-right:15px;padding-left:15px;margin-bottom:0}.nav-list>li>a,.nav-list .nav-header{margin-right:-15px;margin-left:-15px;text-shadow:0 1px 0 rgba(255,255,255,0.5)}.nav-list>li>a{padding:3px 15px}.nav-list>.active>a,.nav-list>.active>a:hover{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.2);background-color:#08c}.nav-list [class^="icon-"]{margin-right:2px}.nav-list .divider{*width:100%;height:1px;margin:9px 1px;*margin:-5px 0 5px;overflow:hidden;background-color:#e5e5e5;border-bottom:1px solid #fff}.nav-tabs,.nav-pills{*zoom:1}.nav-tabs:before,.nav-pills:before,.nav-tabs:after,.nav-pills:after{display:table;line-height:0;content:""}.nav-tabs:after,.nav-pills:after{clear:both}.nav-tabs>li,.nav-pills>li{float:left}.nav-tabs>li>a,.nav-pills>li>a{padding-right:12px;padding-left:12px;margin-right:2px;line-height:14px}.nav-tabs{border-bottom:1px solid #ddd}.nav-tabs>li{margin-bottom:-1px}.nav-tabs>li>a{padding-top:8px;padding-bottom:8px;line-height:20px;border:1px solid transparent;-webkit-border-radius:4px 4px 0 0;-moz-border-radius:4px 4px 0 0;border-radius:4px 4px 0 0}.nav-tabs>li>a:hover{border-color:#eee #eee #ddd}.nav-tabs>.active>a,.nav-tabs>.active>a:hover{color:#555;cursor:default;background-color:#fff;border:1px solid #ddd;border-bottom-color:transparent}.nav-pills>li>a{padding-top:8px;padding-bottom:8px;margin-top:2px;margin-bottom:2px;-webkit-border-radius:5px;-moz-border-radius:5px;border-radius:5px}.nav-pills>.active>a,.nav-pills>.active>a:hover{color:#fff;background-color:#08c}.nav-stacked>li{float:none}.nav-stacked>li>a{margin-right:0}.nav-tabs.nav-stacked{border-bottom:0}.nav-tabs.nav-stacked>li>a{border:1px solid #ddd;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.nav-tabs.nav-stacked>li:first-child>a{-webkit-border-top-right-radius:4px;border-top-right-radius:4px;-webkit-border-top-left-radius:4px;border-top-left-radius:4px;-moz-border-radius-topright:4px;-moz-border-radius-topleft:4px}.nav-tabs.nav-stacked>li:last-child>a{-webkit-border-bottom-right-radius:4px;border-bottom-right-radius:4px;-webkit-border-bottom-left-radius:4px;border-bottom-left-radius:4px;-moz-border-radius-bottomright:4px;-moz-border-radius-bottomleft:4px}.nav-tabs.nav-stacked>li>a:hover{z-index:2;border-color:#ddd}.nav-pills.nav-stacked>li>a{margin-bottom:3px}.nav-pills.nav-stacked>li:last-child>a{margin-bottom:1px}.nav-tabs .dropdown-menu{-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px}.nav-pills .dropdown-menu{-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.nav .dropdown-toggle .caret{margin-top:6px;border-top-color:#08c;border-bottom-color:#08c}.nav .dropdown-toggle:hover .caret{border-top-color:#005580;border-bottom-color:#005580}.nav-tabs .dropdown-toggle .caret{margin-top:8px}.nav .active .dropdown-toggle .caret{border-top-color:#fff;border-bottom-color:#fff}.nav-tabs .active .dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.nav>.dropdown.active>a:hover{cursor:pointer}.nav-tabs .open .dropdown-toggle,.nav-pills .open .dropdown-toggle,.nav>li.dropdown.open.active>a:hover{color:#fff;background-color:#999;border-color:#999}.nav li.dropdown.open .caret,.nav li.dropdown.open.active .caret,.nav li.dropdown.open a:hover .caret{border-top-color:#fff;border-bottom-color:#fff;opacity:1;filter:alpha(opacity=100)}.tabs-stacked .open>a:hover{border-color:#999}.tabbable{*zoom:1}.tabbable:before,.tabbable:after{display:table;line-height:0;content:""}.tabbable:after{clear:both}.tab-content{overflow:auto}.tabs-below>.nav-tabs,.tabs-right>.nav-tabs,.tabs-left>.nav-tabs{border-bottom:0}.tab-content>.tab-pane,.pill-content>.pill-pane{display:none}.tab-content>.active,.pill-content>.active{display:block}.tabs-below>.nav-tabs{border-top:1px solid #ddd}.tabs-below>.nav-tabs>li{margin-top:-1px;margin-bottom:0}.tabs-below>.nav-tabs>li>a{-webkit-border-radius:0 0 4px 4px;-moz-border-radius:0 0 4px 4px;border-radius:0 0 4px 4px}.tabs-below>.nav-tabs>li>a:hover{border-top-color:#ddd;border-bottom-color:transparent}.tabs-below>.nav-tabs>.active>a,.tabs-below>.nav-tabs>.active>a:hover{border-color:transparent #ddd #ddd #ddd}.tabs-left>.nav-tabs>li,.tabs-right>.nav-tabs>li{float:none}.tabs-left>.nav-tabs>li>a,.tabs-right>.nav-tabs>li>a{min-width:74px;margin-right:0;margin-bottom:3px}.tabs-left>.nav-tabs{float:left;margin-right:19px;border-right:1px solid #ddd}.tabs-left>.nav-tabs>li>a{margin-right:-1px;-webkit-border-radius:4px 0 0 4px;-moz-border-radius:4px 0 0 4px;border-radius:4px 0 0 4px}.tabs-left>.nav-tabs>li>a:hover{border-color:#eee #ddd #eee #eee}.tabs-left>.nav-tabs .active>a,.tabs-left>.nav-tabs .active>a:hover{border-color:#ddd transparent #ddd #ddd;*border-right-color:#fff}.tabs-right>.nav-tabs{float:right;margin-left:19px;border-left:1px solid #ddd}.tabs-right>.nav-tabs>li>a{margin-left:-1px;-webkit-border-radius:0 4px 4px 0;-moz-border-radius:0 4px 4px 0;border-radius:0 4px 4px 0}.tabs-right>.nav-tabs>li>a:hover{border-color:#eee #eee #eee #ddd}.tabs-right>.nav-tabs .active>a,.tabs-right>.nav-tabs .active>a:hover{border-color:#ddd #ddd #ddd transparent;*border-left-color:#fff}.nav>.disabled>a{color:#999}.nav>.disabled>a:hover{text-decoration:none;cursor:default;background-color:transparent}.navbar{*position:relative;*z-index:2;margin-bottom:20px;overflow:visible;color:#555}.navbar-inner{min-height:40px;padding-right:20px;padding-left:20px;background-color:#fafafa;background-image:-moz-linear-gradient(top,#fff,#feead8);background-image:-webkit-gradient(linear,0 0,0 100%,from(#fff),to(#feead8));background-image:-webkit-linear-gradient(top,#fff,#feead8);background-image:-o-linear-gradient(top,#fff,#feead8);background-image:linear-gradient(to bottom,#fff,#feead8);background-repeat:repeat-x;border:1px solid #d4d4d4;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffffffff',endColorstr='#fffeead8',GradientType=0);-webkit-box-shadow:0 1px 4px rgba(0,0,0,0.065);-moz-box-shadow:0 1px 4px rgba(0,0,0,0.065);box-shadow:0 1px 4px rgba(0,0,0,0.065)}.navbar .container{width:auto}.nav-collapse.collapse{height:auto}.navbar .brand{display:block;float:left;padding:10px 20px 10px;margin-left:-20px;font-size:20px;font-weight:200;color:#555;text-shadow:0 1px 0 #fff}.navbar .brand:hover{text-decoration:none}.navbar-text{margin-bottom:0;line-height:40px}.navbar-link{color:#555}.navbar-link:hover{color:#333}.navbar .divider-vertical{height:40px;margin:0 9px;border-right:1px solid #fff;border-left:1px solid #f2f2f2}.navbar .btn,.navbar .btn-group{margin-top:6px}.navbar .btn-group .btn{margin:0}.navbar-form{margin-bottom:0;*zoom:1}.navbar-form:before,.navbar-form:after{display:table;line-height:0;content:""}.navbar-form:after{clear:both}.navbar-form input,.navbar-form select,.navbar-form .radio,.navbar-form .checkbox{margin-top:5px}.navbar-form input,.navbar-form select,.navbar-form .btn{display:inline-block;margin-bottom:0}.navbar-form input[type="image"],.navbar-form input[type="checkbox"],.navbar-form input[type="radio"]{margin-top:3px}.navbar-form .input-append,.navbar-form .input-prepend{margin-top:6px;white-space:nowrap}.navbar-form .input-append input,.navbar-form .input-prepend input{margin-top:0}.navbar-search{position:relative;float:left;margin-top:5px;margin-bottom:0}.navbar-search .search-query{padding:4px 14px;margin-bottom:0;font-family:"Helvetica Neue",Helvetica,Arial,sans-serif;font-size:13px;font-weight:normal;line-height:1;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.navbar-static-top{position:static;width:100%;margin-bottom:0}.navbar-static-top .navbar-inner{-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.navbar-fixed-top,.navbar-fixed-bottom{position:fixed;right:0;left:0;z-index:1030;margin-bottom:0}.navbar-fixed-top .navbar-inner,.navbar-fixed-bottom .navbar-inner,.navbar-static-top .navbar-inner{border:0}.navbar-fixed-top .navbar-inner,.navbar-fixed-bottom .navbar-inner{padding-right:0;padding-left:0;-webkit-border-radius:0;-moz-border-radius:0;border-radius:0}.navbar-static-top .container,.navbar-fixed-top .container,.navbar-fixed-bottom .container{width:940px}.navbar-fixed-top{top:0}.navbar-fixed-top .navbar-inner,.navbar-static-top .navbar-inner{-webkit-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1);box-shadow:inset 0 -1px 0 rgba(0,0,0,0.1),0 1px 10px rgba(0,0,0,0.1)}.navbar-fixed-bottom{bottom:0}.navbar-fixed-bottom .navbar-inner{-webkit-box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1);box-shadow:inset 0 1px 0 rgba(0,0,0,0.1),0 -1px 10px rgba(0,0,0,0.1)}.navbar .nav{position:relative;left:0;display:block;float:left;margin:0 10px 0 0}.navbar .nav.pull-right{float:right}.navbar .nav>li{float:left}.navbar .nav>li>a{float:none;padding:10px 15px 10px;color:#555;text-decoration:none;text-shadow:0 1px 0 #fff}.navbar .nav .dropdown-toggle .caret{margin-top:8px}.navbar .nav>li>a:focus,.navbar .nav>li>a:hover{color:#333;text-decoration:none;background-color:transparent}.navbar .nav>.active>a,.navbar .nav>.active>a:hover,.navbar .nav>.active>a:focus{color:#555;text-decoration:none;background-color:#e5e5e5;-webkit-box-shadow:inset 0 3px 8px rgba(0,0,0,0.125);-moz-box-shadow:inset 0 3px 8px rgba(0,0,0,0.125);box-shadow:inset 0 3px 8px rgba(0,0,0,0.125)}.navbar .btn-navbar{display:none;float:right;padding:7px 10px;margin-right:5px;margin-left:5px;color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#ededed;*background-color:#e5e5e5;background-image:-webkit-gradient(linear,0 0,0 100%,from(#f2f2f2),to(#e5e5e5));background-image:-webkit-linear-gradient(top,#f2f2f2,#e5e5e5);background-image:-o-linear-gradient(top,#f2f2f2,#e5e5e5);background-image:linear-gradient(to bottom,#f2f2f2,#e5e5e5);background-image:-moz-linear-gradient(top,#f2f2f2,#e5e5e5);background-repeat:repeat-x;border-color:#e5e5e5 #e5e5e5 #bfbfbf;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fff2f2f2',endColorstr='#ffe5e5e5',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false);-webkit-box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075);-moz-box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075);box-shadow:inset 0 1px 0 rgba(255,255,255,0.1),0 1px 0 rgba(255,255,255,0.075)}.navbar .btn-navbar:hover,.navbar .btn-navbar:active,.navbar .btn-navbar.active,.navbar .btn-navbar.disabled,.navbar .btn-navbar[disabled]{color:#fff;background-color:#e5e5e5;*background-color:#d9d9d9}.navbar .btn-navbar:active,.navbar .btn-navbar.active{background-color:#ccc \9}.navbar .btn-navbar .icon-bar{display:block;width:18px;height:2px;background-color:#f5f5f5;-webkit-border-radius:1px;-moz-border-radius:1px;border-radius:1px;-webkit-box-shadow:0 1px 0 rgba(0,0,0,0.25);-moz-box-shadow:0 1px 0 rgba(0,0,0,0.25);box-shadow:0 1px 0 rgba(0,0,0,0.25)}.btn-navbar .icon-bar+.icon-bar{margin-top:3px}.navbar .nav>li>.dropdown-menu:before{position:absolute;top:-7px;left:9px;display:inline-block;border-right:7px solid transparent;border-bottom:7px solid #ccc;border-left:7px solid transparent;border-bottom-color:rgba(0,0,0,0.2);content:''}.navbar .nav>li>.dropdown-menu:after{position:absolute;top:-6px;left:10px;display:inline-block;border-right:6px solid transparent;border-bottom:6px solid #fff;border-left:6px solid transparent;content:''}.navbar-fixed-bottom .nav>li>.dropdown-menu:before{top:auto;bottom:-7px;border-top:7px solid #ccc;border-bottom:0;border-top-color:rgba(0,0,0,0.2)}.navbar-fixed-bottom .nav>li>.dropdown-menu:after{top:auto;bottom:-6px;border-top:6px solid #fff;border-bottom:0}.navbar .nav li.dropdown.open>.dropdown-toggle,.navbar .nav li.dropdown.active>.dropdown-toggle,.navbar .nav li.dropdown.open.active>.dropdown-toggle{color:#555;background-color:#e5e5e5}.navbar .nav li.dropdown>.dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.navbar .nav li.dropdown.open>.dropdown-toggle .caret,.navbar .nav li.dropdown.active>.dropdown-toggle .caret,.navbar .nav li.dropdown.open.active>.dropdown-toggle .caret{border-top-color:#555;border-bottom-color:#555}.navbar .pull-right>li>.dropdown-menu,.navbar .nav>li>.dropdown-menu.pull-right{right:0;left:auto}.navbar .pull-right>li>.dropdown-menu:before,.navbar .nav>li>.dropdown-menu.pull-right:before{right:12px;left:auto}.navbar .pull-right>li>.dropdown-menu:after,.navbar .nav>li>.dropdown-menu.pull-right:after{right:13px;left:auto}.navbar .pull-right>li>.dropdown-menu .dropdown-menu,.navbar .nav>li>.dropdown-menu.pull-right .dropdown-menu{right:100%;left:auto;margin-right:-1px;margin-left:0;-webkit-border-radius:6px 0 6px 6px;-moz-border-radius:6px 0 6px 6px;border-radius:6px 0 6px 6px}.navbar-inverse{color:#999}.navbar-inverse .navbar-inner{background-color:#1b1b1b;background-image:-moz-linear-gradient(top,#222,#111);background-image:-webkit-gradient(linear,0 0,0 100%,from(#222),to(#111));background-image:-webkit-linear-gradient(top,#222,#111);background-image:-o-linear-gradient(top,#222,#111);background-image:linear-gradient(to bottom,#222,#111);background-repeat:repeat-x;border-color:#252525;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff222222',endColorstr='#ff111111',GradientType=0)}.navbar-inverse .brand,.navbar-inverse .nav>li>a{color:#999;text-shadow:0 -1px 0 rgba(0,0,0,0.25)}.navbar-inverse .brand:hover,.navbar-inverse .nav>li>a:hover{color:#fff}.navbar-inverse .nav>li>a:focus,.navbar-inverse .nav>li>a:hover{color:#fff;background-color:transparent}.navbar-inverse .nav .active>a,.navbar-inverse .nav .active>a:hover,.navbar-inverse .nav .active>a:focus{color:#fff;background-color:#111}.navbar-inverse .navbar-link{color:#999}.navbar-inverse .navbar-link:hover{color:#fff}.navbar-inverse .divider-vertical{border-right-color:#222;border-left-color:#111}.navbar-inverse .nav li.dropdown.open>.dropdown-toggle,.navbar-inverse .nav li.dropdown.active>.dropdown-toggle,.navbar-inverse .nav li.dropdown.open.active>.dropdown-toggle{color:#fff;background-color:#111}.navbar-inverse .nav li.dropdown>.dropdown-toggle .caret{border-top-color:#999;border-bottom-color:#999}.navbar-inverse .nav li.dropdown.open>.dropdown-toggle .caret,.navbar-inverse .nav li.dropdown.active>.dropdown-toggle .caret,.navbar-inverse .nav li.dropdown.open.active>.dropdown-toggle .caret{border-top-color:#fff;border-bottom-color:#fff}.navbar-inverse .navbar-search .search-query{color:#fff;background-color:#515151;border-color:#111;-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);box-shadow:inset 0 1px 2px rgba(0,0,0,0.1),0 1px 0 rgba(255,255,255,0.15);-webkit-transition:none;-moz-transition:none;-o-transition:none;transition:none}.navbar-inverse .navbar-search .search-query:-moz-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query:-ms-input-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query::-webkit-input-placeholder{color:#ccc}.navbar-inverse .navbar-search .search-query:focus,.navbar-inverse .navbar-search .search-query.focused{padding:5px 15px;color:#333;text-shadow:0 1px 0 #fff;background-color:#fff;border:0;outline:0;-webkit-box-shadow:0 0 3px rgba(0,0,0,0.15);-moz-box-shadow:0 0 3px rgba(0,0,0,0.15);box-shadow:0 0 3px rgba(0,0,0,0.15)}.navbar-inverse .btn-navbar{color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#0e0e0e;*background-color:#040404;background-image:-webkit-gradient(linear,0 0,0 100%,from(#151515),to(#040404));background-image:-webkit-linear-gradient(top,#151515,#040404);background-image:-o-linear-gradient(top,#151515,#040404);background-image:linear-gradient(to bottom,#151515,#040404);background-image:-moz-linear-gradient(top,#151515,#040404);background-repeat:repeat-x;border-color:#040404 #040404 #000;border-color:rgba(0,0,0,0.1) rgba(0,0,0,0.1) rgba(0,0,0,0.25);filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff151515',endColorstr='#ff040404',GradientType=0);filter:progid:dximagetransform.microsoft.gradient(enabled=false)}.navbar-inverse .btn-navbar:hover,.navbar-inverse .btn-navbar:active,.navbar-inverse .btn-navbar.active,.navbar-inverse .btn-navbar.disabled,.navbar-inverse .btn-navbar[disabled]{color:#fff;background-color:#040404;*background-color:#000}.navbar-inverse .btn-navbar:active,.navbar-inverse .btn-navbar.active{background-color:#000 \9}.breadcrumb{padding:8px 15px;margin:0 0 20px;list-style:none;background-color:#f5f5f5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.breadcrumb li{display:inline-block;*display:inline;text-shadow:0 1px 0 #fff;*zoom:1}.breadcrumb .divider{padding:0 5px;color:#ccc}.breadcrumb .active{color:#999}.pagination{height:40px;margin:20px 0}.pagination ul{display:inline-block;*display:inline;margin-bottom:0;margin-left:0;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px;*zoom:1;-webkit-box-shadow:0 1px 2px rgba(0,0,0,0.05);-moz-box-shadow:0 1px 2px rgba(0,0,0,0.05);box-shadow:0 1px 2px rgba(0,0,0,0.05)}.pagination li{display:inline}.pagination a,.pagination span{float:left;padding:0 14px;line-height:38px;text-decoration:none;background-color:#fff;border:1px solid #ddd;border-left-width:0}.pagination a:hover,.pagination .active a,.pagination .active span{background-color:#f5f5f5}.pagination .active a,.pagination .active span{color:#999;cursor:default}.pagination .disabled span,.pagination .disabled a,.pagination .disabled a:hover{color:#999;cursor:default;background-color:transparent}.pagination li:first-child a,.pagination li:first-child span{border-left-width:1px;-webkit-border-radius:3px 0 0 3px;-moz-border-radius:3px 0 0 3px;border-radius:3px 0 0 3px}.pagination li:last-child a,.pagination li:last-child span{-webkit-border-radius:0 3px 3px 0;-moz-border-radius:0 3px 3px 0;border-radius:0 3px 3px 0}.pagination-centered{text-align:center}.pagination-right{text-align:right}.pager{margin:20px 0;text-align:center;list-style:none;*zoom:1}.pager:before,.pager:after{display:table;line-height:0;content:""}.pager:after{clear:both}.pager li{display:inline}.pager a{display:inline-block;padding:5px 14px;background-color:#fff;border:1px solid #ddd;-webkit-border-radius:15px;-moz-border-radius:15px;border-radius:15px}.pager a:hover{text-decoration:none;background-color:#f5f5f5}.pager .next a{float:right}.pager .previous a{float:left}.pager .disabled a,.pager .disabled a:hover{color:#999;cursor:default;background-color:#fff}.modal-open .dropdown-menu{z-index:2050}.modal-open .dropdown.open{*z-index:2050}.modal-open .popover{z-index:2060}.modal-open .tooltip{z-index:2080}.modal-backdrop{position:fixed;top:0;right:0;bottom:0;left:0;z-index:1040;background-color:#000}.modal-backdrop.fade{opacity:0}.modal-backdrop,.modal-backdrop.fade.in{opacity:.8;filter:alpha(opacity=80)}.modal{position:fixed;top:50%;left:50%;z-index:1050;width:560px;margin:-250px 0 0 -280px;overflow:auto;background-color:#fff;border:1px solid #999;border:1px solid rgba(0,0,0,0.3);*border:1px solid #999;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 3px 7px rgba(0,0,0,0.3);-moz-box-shadow:0 3px 7px rgba(0,0,0,0.3);box-shadow:0 3px 7px rgba(0,0,0,0.3);-webkit-background-clip:padding-box;-moz-background-clip:padding-box;background-clip:padding-box}.modal.fade{top:-25%;-webkit-transition:opacity .3s linear,top .3s ease-out;-moz-transition:opacity .3s linear,top .3s ease-out;-o-transition:opacity .3s linear,top .3s ease-out;transition:opacity .3s linear,top .3s ease-out}.modal.fade.in{top:50%}.modal-header{padding:9px 15px;border-bottom:1px solid #eee}.modal-header .close{margin-top:2px}.modal-header h3{margin:0;line-height:30px}.modal-body{max-height:400px;padding:15px;overflow-y:auto}.modal-form{margin-bottom:0}.modal-footer{padding:14px 15px 15px;margin-bottom:0;text-align:right;background-color:#f5f5f5;border-top:1px solid #ddd;-webkit-border-radius:0 0 6px 6px;-moz-border-radius:0 0 6px 6px;border-radius:0 0 6px 6px;*zoom:1;-webkit-box-shadow:inset 0 1px 0 #fff;-moz-box-shadow:inset 0 1px 0 #fff;box-shadow:inset 0 1px 0 #fff}.modal-footer:before,.modal-footer:after{display:table;line-height:0;content:""}.modal-footer:after{clear:both}.modal-footer .btn+.btn{margin-bottom:0;margin-left:5px}.modal-footer .btn-group .btn+.btn{margin-left:-1px}.tooltip{position:absolute;z-index:1030;display:block;padding:5px;font-size:11px;opacity:0;filter:alpha(opacity=0);visibility:visible}.tooltip.in{opacity:.8;filter:alpha(opacity=80)}.tooltip.top{margin-top:-3px}.tooltip.right{margin-left:3px}.tooltip.bottom{margin-top:3px}.tooltip.left{margin-left:-3px}.tooltip-inner{max-width:200px;padding:3px 8px;color:#fff;text-align:center;text-decoration:none;background-color:#000;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.tooltip-arrow{position:absolute;width:0;height:0;border-color:transparent;border-style:solid}.tooltip.top .tooltip-arrow{bottom:0;left:50%;margin-left:-5px;border-top-color:#000;border-width:5px 5px 0}.tooltip.right .tooltip-arrow{top:50%;left:0;margin-top:-5px;border-right-color:#000;border-width:5px 5px 5px 0}.tooltip.left .tooltip-arrow{top:50%;right:0;margin-top:-5px;border-left-color:#000;border-width:5px 0 5px 5px}.tooltip.bottom .tooltip-arrow{top:0;left:50%;margin-left:-5px;border-bottom-color:#000;border-width:0 5px 5px}.popover{position:absolute;top:0;left:0;z-index:1010;display:none;width:236px;padding:1px;background-color:#fff;border:1px solid #ccc;border:1px solid rgba(0,0,0,0.2);-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px;-webkit-box-shadow:0 5px 10px rgba(0,0,0,0.2);-moz-box-shadow:0 5px 10px rgba(0,0,0,0.2);box-shadow:0 5px 10px rgba(0,0,0,0.2);-webkit-background-clip:padding-box;-moz-background-clip:padding;background-clip:padding-box}.popover.top{margin-bottom:10px}.popover.right{margin-left:10px}.popover.bottom{margin-top:10px}.popover.left{margin-right:10px}.popover-title{padding:8px 14px;margin:0;font-size:14px;font-weight:normal;line-height:18px;background-color:#f7f7f7;border-bottom:1px solid #ebebeb;-webkit-border-radius:5px 5px 0 0;-moz-border-radius:5px 5px 0 0;border-radius:5px 5px 0 0}.popover-content{padding:9px 14px}.popover-content p,.popover-content ul,.popover-content ol{margin-bottom:0}.popover .arrow,.popover .arrow:after{position:absolute;display:inline-block;width:0;height:0;border-color:transparent;border-style:solid}.popover .arrow:after{z-index:-1;content:""}.popover.top .arrow{bottom:-10px;left:50%;margin-left:-10px;border-top-color:#fff;border-width:10px 10px 0}.popover.top .arrow:after{bottom:-1px;left:-11px;border-top-color:rgba(0,0,0,0.25);border-width:11px 11px 0}.popover.right .arrow{top:50%;left:-10px;margin-top:-10px;border-right-color:#fff;border-width:10px 10px 10px 0}.popover.right .arrow:after{bottom:-11px;left:-1px;border-right-color:rgba(0,0,0,0.25);border-width:11px 11px 11px 0}.popover.bottom .arrow{top:-10px;left:50%;margin-left:-10px;border-bottom-color:#fff;border-width:0 10px 10px}.popover.bottom .arrow:after{top:-1px;left:-11px;border-bottom-color:rgba(0,0,0,0.25);border-width:0 11px 11px}.popover.left .arrow{top:50%;right:-10px;margin-top:-10px;border-left-color:#fff;border-width:10px 0 10px 10px}.popover.left .arrow:after{right:-1px;bottom:-11px;border-left-color:rgba(0,0,0,0.25);border-width:11px 0 11px 11px}.thumbnails{margin-left:-20px;list-style:none;*zoom:1}.thumbnails:before,.thumbnails:after{display:table;line-height:0;content:""}.thumbnails:after{clear:both}.row-fluid .thumbnails{margin-left:0}.thumbnails>li{float:left;margin-bottom:20px;margin-left:20px}.thumbnail{display:block;padding:4px;line-height:20px;border:1px solid #ddd;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;-webkit-box-shadow:0 1px 3px rgba(0,0,0,0.055);-moz-box-shadow:0 1px 3px rgba(0,0,0,0.055);box-shadow:0 1px 3px rgba(0,0,0,0.055);-webkit-transition:all .2s ease-in-out;-moz-transition:all .2s ease-in-out;-o-transition:all .2s ease-in-out;transition:all .2s ease-in-out}a.thumbnail:hover{border-color:#08c;-webkit-box-shadow:0 1px 4px rgba(0,105,214,0.25);-moz-box-shadow:0 1px 4px rgba(0,105,214,0.25);box-shadow:0 1px 4px rgba(0,105,214,0.25)}.thumbnail>img{display:block;max-width:100%;margin-right:auto;margin-left:auto}.thumbnail .caption{padding:9px;color:#555}.label,.badge{font-size:11.844px;font-weight:bold;line-height:14px;color:#fff;text-shadow:0 -1px 0 rgba(0,0,0,0.25);white-space:nowrap;vertical-align:baseline;background-color:#999}.label{padding:1px 4px 2px;-webkit-border-radius:3px;-moz-border-radius:3px;border-radius:3px}.badge{padding:1px 9px 2px;-webkit-border-radius:9px;-moz-border-radius:9px;border-radius:9px}a.label:hover,a.badge:hover{color:#fff;text-decoration:none;cursor:pointer}.label-important,.badge-important{background-color:#b94a48}.label-important[href],.badge-important[href]{background-color:#953b39}.label-warning,.badge-warning{background-color:#f89406}.label-warning[href],.badge-warning[href]{background-color:#c67605}.label-success,.badge-success{background-color:#468847}.label-success[href],.badge-success[href]{background-color:#356635}.label-info,.badge-info{background-color:#3a87ad}.label-info[href],.badge-info[href]{background-color:#2d6987}.label-inverse,.badge-inverse{background-color:#333}.label-inverse[href],.badge-inverse[href]{background-color:#1a1a1a}.btn .label,.btn .badge{position:relative;top:-1px}.btn-mini .label,.btn-mini .badge{top:0}@-webkit-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-moz-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-ms-keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}@-o-keyframes progress-bar-stripes{from{background-position:0 0}to{background-position:40px 0}}@keyframes progress-bar-stripes{from{background-position:40px 0}to{background-position:0 0}}.progress{height:20px;margin-bottom:20px;overflow:hidden;background-color:#f7f7f7;background-image:-moz-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:-webkit-gradient(linear,0 0,0 100%,from(#f5f5f5),to(#f9f9f9));background-image:-webkit-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:-o-linear-gradient(top,#f5f5f5,#f9f9f9);background-image:linear-gradient(to bottom,#f5f5f5,#f9f9f9);background-repeat:repeat-x;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fff5f5f5',endColorstr='#fff9f9f9',GradientType=0);-webkit-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1);-moz-box-shadow:inset 0 1px 2px rgba(0,0,0,0.1);box-shadow:inset 0 1px 2px rgba(0,0,0,0.1)}.progress .bar{float:left;width:0;height:100%;font-size:12px;color:#fff;text-align:center;text-shadow:0 -1px 0 rgba(0,0,0,0.25);background-color:#0e90d2;background-image:-moz-linear-gradient(top,#149bdf,#0480be);background-image:-webkit-gradient(linear,0 0,0 100%,from(#149bdf),to(#0480be));background-image:-webkit-linear-gradient(top,#149bdf,#0480be);background-image:-o-linear-gradient(top,#149bdf,#0480be);background-image:linear-gradient(to bottom,#149bdf,#0480be);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff149bdf',endColorstr='#ff0480be',GradientType=0);-webkit-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);-moz-box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);box-shadow:inset 0 -1px 0 rgba(0,0,0,0.15);-webkit-box-sizing:border-box;-moz-box-sizing:border-box;box-sizing:border-box;-webkit-transition:width .6s ease;-moz-transition:width .6s ease;-o-transition:width .6s ease;transition:width .6s ease}.progress .bar+.bar{-webkit-box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15);-moz-box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15);box-shadow:inset 1px 0 0 rgba(0,0,0,0.15),inset 0 -1px 0 rgba(0,0,0,0.15)}.progress-striped .bar{background-color:#149bdf;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);-webkit-background-size:40px 40px;-moz-background-size:40px 40px;-o-background-size:40px 40px;background-size:40px 40px}.progress.active .bar{-webkit-animation:progress-bar-stripes 2s linear infinite;-moz-animation:progress-bar-stripes 2s linear infinite;-ms-animation:progress-bar-stripes 2s linear infinite;-o-animation:progress-bar-stripes 2s linear infinite;animation:progress-bar-stripes 2s linear infinite}.progress-danger .bar,.progress .bar-danger{background-color:#dd514c;background-image:-moz-linear-gradient(top,#ee5f5b,#c43c35);background-image:-webkit-gradient(linear,0 0,0 100%,from(#ee5f5b),to(#c43c35));background-image:-webkit-linear-gradient(top,#ee5f5b,#c43c35);background-image:-o-linear-gradient(top,#ee5f5b,#c43c35);background-image:linear-gradient(to bottom,#ee5f5b,#c43c35);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ffee5f5b',endColorstr='#ffc43c35',GradientType=0)}.progress-danger.progress-striped .bar,.progress-striped .bar-danger{background-color:#ee5f5b;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-success .bar,.progress .bar-success{background-color:#5eb95e;background-image:-moz-linear-gradient(top,#62c462,#57a957);background-image:-webkit-gradient(linear,0 0,0 100%,from(#62c462),to(#57a957));background-image:-webkit-linear-gradient(top,#62c462,#57a957);background-image:-o-linear-gradient(top,#62c462,#57a957);background-image:linear-gradient(to bottom,#62c462,#57a957);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff62c462',endColorstr='#ff57a957',GradientType=0)}.progress-success.progress-striped .bar,.progress-striped .bar-success{background-color:#62c462;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-info .bar,.progress .bar-info{background-color:#4bb1cf;background-image:-moz-linear-gradient(top,#5bc0de,#339bb9);background-image:-webkit-gradient(linear,0 0,0 100%,from(#5bc0de),to(#339bb9));background-image:-webkit-linear-gradient(top,#5bc0de,#339bb9);background-image:-o-linear-gradient(top,#5bc0de,#339bb9);background-image:linear-gradient(to bottom,#5bc0de,#339bb9);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#ff5bc0de',endColorstr='#ff339bb9',GradientType=0)}.progress-info.progress-striped .bar,.progress-striped .bar-info{background-color:#5bc0de;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.progress-warning .bar,.progress .bar-warning{background-color:#faa732;background-image:-moz-linear-gradient(top,#fbb450,#f89406);background-image:-webkit-gradient(linear,0 0,0 100%,from(#fbb450),to(#f89406));background-image:-webkit-linear-gradient(top,#fbb450,#f89406);background-image:-o-linear-gradient(top,#fbb450,#f89406);background-image:linear-gradient(to bottom,#fbb450,#f89406);background-repeat:repeat-x;filter:progid:dximagetransform.microsoft.gradient(startColorstr='#fffbb450',endColorstr='#fff89406',GradientType=0)}.progress-warning.progress-striped .bar,.progress-striped .bar-warning{background-color:#fbb450;background-image:-webkit-gradient(linear,0 100%,100% 0,color-stop(0.25,rgba(255,255,255,0.15)),color-stop(0.25,transparent),color-stop(0.5,transparent),color-stop(0.5,rgba(255,255,255,0.15)),color-stop(0.75,rgba(255,255,255,0.15)),color-stop(0.75,transparent),to(transparent));background-image:-webkit-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-moz-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:-o-linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent);background-image:linear-gradient(45deg,rgba(255,255,255,0.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,0.15) 50%,rgba(255,255,255,0.15) 75%,transparent 75%,transparent)}.accordion{margin-bottom:20px}.accordion-group{margin-bottom:2px;border:1px solid #e5e5e5;-webkit-border-radius:4px;-moz-border-radius:4px;border-radius:4px}.accordion-heading{border-bottom:0}.accordion-heading .accordion-toggle{display:block;padding:8px 15px}.accordion-toggle{cursor:pointer}.accordion-inner{padding:9px 15px;border-top:1px solid #e5e5e5}.carousel{position:relative;margin-bottom:20px;line-height:1}.carousel-inner{position:relative;width:100%;overflow:hidden}.carousel .item{position:relative;display:none;-webkit-transition:.6s ease-in-out left;-moz-transition:.6s ease-in-out left;-o-transition:.6s ease-in-out left;transition:.6s ease-in-out left}.carousel .item>img{display:block;line-height:1}.carousel .active,.carousel .next,.carousel .prev{display:block}.carousel .active{left:0}.carousel .next,.carousel .prev{position:absolute;top:0;width:100%}.carousel .next{left:100%}.carousel .prev{left:-100%}.carousel .next.left,.carousel .prev.right{left:0}.carousel .active.left{left:-100%}.carousel .active.right{left:100%}.carousel-control{position:absolute;top:40%;left:15px;width:40px;height:40px;margin-top:-20px;font-size:60px;font-weight:100;line-height:30px;color:#fff;text-align:center;background:#222;border:3px solid #fff;-webkit-border-radius:23px;-moz-border-radius:23px;border-radius:23px;opacity:.5;filter:alpha(opacity=50)}.carousel-control.right{right:15px;left:auto}.carousel-control:hover{color:#fff;text-decoration:none;opacity:.9;filter:alpha(opacity=90)}.carousel-caption{position:absolute;right:0;bottom:0;left:0;padding:15px;background:#333;background:rgba(0,0,0,0.75)}.carousel-caption h4,.carousel-caption p{line-height:20px;color:#fff}.carousel-caption h4{margin:0 0 5px}.carousel-caption p{margin-bottom:0}.hero-unit{padding:60px;margin-bottom:30px;background-color:#eee;-webkit-border-radius:6px;-moz-border-radius:6px;border-radius:6px}.hero-unit h1{margin-bottom:0;font-size:60px;line-height:1;letter-spacing:-1px;color:inherit}.hero-unit p{font-size:18px;font-weight:200;line-height:30px;color:inherit}.pull-right{float:right}.pull-left{float:left}.hide{display:none}.show{display:block}.invisible{visibility:hidden}.affix{position:fixed} diff --git a/docs/index.md b/docs/index.md index d3ac696d1e..86d574daaa 100644 --- a/docs/index.md +++ b/docs/index.md @@ -24,9 +24,9 @@ For its Scala API, Spark {{site.SPARK_VERSION}} depends on Scala {{site.SCALA_VE # Running the Examples and Shell Spark comes with several sample programs in the `examples` directory. -To run one of the samples, use `./run-example <class> <params>` in the top-level Spark directory -(the `run-example` script sets up the appropriate paths and launches that program). -For example, try `./run-example org.apache.spark.examples.SparkPi local`. +To run one of the samples, use `./bin/run-example <class> <params>` in the top-level Spark directory +(the `bin/run-example` script sets up the appropriate paths and launches that program). +For example, try `./bin/run-example org.apache.spark.examples.SparkPi local`. Each example prints usage help when run with no parameters. Note that all of the sample programs take a `<master>` parameter specifying the cluster URL @@ -34,8 +34,8 @@ to connect to. This can be a [URL for a distributed cluster](scala-programming-g or `local` to run locally with one thread, or `local[N]` to run locally with N threads. You should start by using `local` for testing. -Finally, you can run Spark interactively through modified versions of the Scala shell (`./spark-shell`) or -Python interpreter (`./pyspark`). These are a great way to learn the framework. +Finally, you can run Spark interactively through modified versions of the Scala shell (`./bin/spark-shell`) or +Python interpreter (`./bin/pyspark`). These are a great way to learn the framework. # Launching on a Cluster diff --git a/docs/java-programming-guide.md b/docs/java-programming-guide.md index 53085cc671..07732fa122 100644 --- a/docs/java-programming-guide.md +++ b/docs/java-programming-guide.md @@ -190,9 +190,9 @@ We hope to generate documentation with Java-style syntax in the future. Spark includes several sample programs using the Java API in [`examples/src/main/java`](https://github.com/apache/incubator-spark/tree/master/examples/src/main/java/org/apache/spark/examples). You can run them by passing the class name to the -`run-example` script included in Spark; for example: +`bin/run-example` script included in Spark; for example: - ./run-example org.apache.spark.examples.JavaWordCount + ./bin/run-example org.apache.spark.examples.JavaWordCount Each example program prints usage help when run without any arguments. diff --git a/docs/job-scheduling.md b/docs/job-scheduling.md index 5951155fe3..df2faa5e41 100644 --- a/docs/job-scheduling.md +++ b/docs/job-scheduling.md @@ -32,9 +32,8 @@ Resource allocation can be configured as follows, based on the cluster type: * **Standalone mode:** By default, applications submitted to the standalone mode cluster will run in FIFO (first-in-first-out) order, and each application will try to use all available nodes. You can limit - the number of nodes an application uses by setting the `spark.cores.max` configuration property in it. This - will allow multiple users/applications to run concurrently. For example, you might launch a long-running - server that uses 10 cores, and allow users to launch shells that use 20 cores each. + the number of nodes an application uses by setting the `spark.cores.max` configuration property in it, + or change the default for applications that don't set this setting through `spark.deploy.defaultCores`. Finally, in addition to controlling cores, each application's `spark.executor.memory` setting controls its memory use. * **Mesos:** To use static partitioning on Mesos, set the `spark.mesos.coarse` configuration property to `true`, diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 44e6c8f58b..21d0464852 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -3,6 +3,9 @@ layout: global title: Machine Learning Library (MLlib) --- +* Table of contents +{:toc} + MLlib is a Spark implementation of some common machine learning (ML) functionality, as well associated tests and data generators. MLlib currently supports four common types of machine learning problem settings, @@ -39,57 +42,6 @@ underlying gradient descent primitive (described parameter (*regParam*) along with various parameters associated with gradient descent (*stepSize*, *numIterations*, *miniBatchFraction*). -The following code snippet illustrates how to load a sample dataset, execute a -training algorithm on this training data using a static method in the algorithm -object, and make predictions with the resulting model to compute the training -error. - -{% highlight scala %} -import org.apache.spark.SparkContext -import org.apache.spark.mllib.classification.SVMWithSGD -import org.apache.spark.mllib.regression.LabeledPoint - -// Load and parse the data file -val data = sc.textFile("mllib/data/sample_svm_data.txt") -val parsedData = data.map { line => - val parts = line.split(' ') - LabeledPoint(parts(0).toDouble, parts.tail.map(x => x.toDouble).toArray) -} - -// Run training algorithm -val numIterations = 20 -val model = SVMWithSGD.train(parsedData, numIterations) - -// Evaluate model on training examples and compute training error -val labelAndPreds = parsedData.map { point => - val prediction = model.predict(point.features) - (point.label, prediction) -} -val trainErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / parsedData.count -println("trainError = " + trainErr) -{% endhighlight %} - -The `SVMWithSGD.train()` method by default performs L2 regularization with the -regularization parameter set to 1.0. If we want to configure this algorithm, we -can customize `SVMWithSGD` further by creating a new object directly and -calling setter methods. All other MLlib algorithms support customization in -this way as well. For example, the following code produces an L1 regularized -variant of SVMs with regularization parameter set to 0.1, and runs the training -algorithm for 200 iterations. - -{% highlight scala %} -import org.apache.spark.mllib.optimization.L1Updater - -val svmAlg = new SVMWithSGD() -svmAlg.optimizer.setNumIterations(200) - .setRegParam(0.1) - .setUpdater(new L1Updater) -val modelL1 = svmAlg.run(parsedData) -{% endhighlight %} - -Both of the code snippets above can be executed in `spark-shell` to generate a -classifier for the provided dataset. - Available algorithms for binary classification: * [SVMWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.SVMWithSGD) @@ -121,14 +73,14 @@ of entities with one another based on some notion of similarity. Clustering is often used for exploratory analysis and/or as a component of a hierarchical supervised learning pipeline (in which distinct classifiers or regression models are trained for each cluster). MLlib supports -[k-means](http://en.wikipedia.org/wiki/K-means_clustering) clustering, arguably -the most commonly used clustering approach that clusters the data points into -*k* clusters. The MLlib implementation includes a parallelized +[k-means](http://en.wikipedia.org/wiki/K-means_clustering) clustering, one of +the most commonly used clustering algorithms that clusters the data points into +predfined number of clusters. The MLlib implementation includes a parallelized variant of the [k-means++](http://en.wikipedia.org/wiki/K-means%2B%2B) method called [kmeans||](http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf). The implementation in MLlib has the following parameters: -* *k* is the number of clusters. +* *k* is the number of desired clusters. * *maxIterations* is the maximum number of iterations to run. * *initializationMode* specifies either random initialization or initialization via k-means\|\|. @@ -169,7 +121,7 @@ the entries in the user-item matrix as *explicit* preferences given by the user It is common in many real-world use cases to only have access to *implicit feedback* (e.g. views, clicks, purchases, likes, shares etc.). The approach used in MLlib to deal with such data is taken from -[Collaborative Filtering for Implicit Feedback Datasets](http://research.yahoo.com/pub/2433). +[Collaborative Filtering for Implicit Feedback Datasets](http://www2.research.att.com/~yifanhu/PUB/cf.pdf). Essentially instead of trying to model the matrix of ratings directly, this approach treats the data as a combination of binary preferences and *confidence values*. The ratings are then related to the level of confidence in observed user preferences, rather than explicit ratings given to items. @@ -211,6 +163,271 @@ Available algorithms for gradient descent: * [GradientDescent](api/mllib/index.html#org.apache.spark.mllib.optimization.GradientDescent) +# Using MLLib in Scala + +Following code snippets can be executed in `spark-shell`. + +## Binary Classification + +The following code snippet illustrates how to load a sample dataset, execute a +training algorithm on this training data using a static method in the algorithm +object, and make predictions with the resulting model to compute the training +error. + +{% highlight scala %} +import org.apache.spark.SparkContext +import org.apache.spark.mllib.classification.SVMWithSGD +import org.apache.spark.mllib.regression.LabeledPoint + +// Load and parse the data file +val data = sc.textFile("mllib/data/sample_svm_data.txt") +val parsedData = data.map { line => + val parts = line.split(' ') + LabeledPoint(parts(0).toDouble, parts.tail.map(x => x.toDouble).toArray) +} + +// Run training algorithm to build the model +val numIterations = 20 +val model = SVMWithSGD.train(parsedData, numIterations) + +// Evaluate model on training examples and compute training error +val labelAndPreds = parsedData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) +} +val trainErr = labelAndPreds.filter(r => r._1 != r._2).count.toDouble / parsedData.count +println("Training Error = " + trainErr) +{% endhighlight %} + + +The `SVMWithSGD.train()` method by default performs L2 regularization with the +regularization parameter set to 1.0. If we want to configure this algorithm, we +can customize `SVMWithSGD` further by creating a new object directly and +calling setter methods. All other MLlib algorithms support customization in +this way as well. For example, the following code produces an L1 regularized +variant of SVMs with regularization parameter set to 0.1, and runs the training +algorithm for 200 iterations. + +{% highlight scala %} +import org.apache.spark.mllib.optimization.L1Updater + +val svmAlg = new SVMWithSGD() +svmAlg.optimizer.setNumIterations(200) + .setRegParam(0.1) + .setUpdater(new L1Updater) +val modelL1 = svmAlg.run(parsedData) +{% endhighlight %} + +## Linear Regression +The following example demonstrate how to load training data, parse it as an RDD of LabeledPoint. The +example then uses LinearRegressionWithSGD to build a simple linear model to predict label values. We +compute the Mean Squared Error at the end to evaluate +[goodness of fit](http://en.wikipedia.org/wiki/Goodness_of_fit) + +{% highlight scala %} +import org.apache.spark.mllib.regression.LinearRegressionWithSGD +import org.apache.spark.mllib.regression.LabeledPoint + +// Load and parse the data +val data = sc.textFile("mllib/data/ridge-data/lpsa.data") +val parsedData = data.map { line => + val parts = line.split(',') + LabeledPoint(parts(0).toDouble, parts(1).split(' ').map(x => x.toDouble).toArray) +} + +// Building the model +val numIterations = 20 +val model = LinearRegressionWithSGD.train(parsedData, numIterations) + +// Evaluate model on training examples and compute training error +val valuesAndPreds = parsedData.map { point => + val prediction = model.predict(point.features) + (point.label, prediction) +} +val MSE = valuesAndPreds.map{ case(v, p) => math.pow((v - p), 2)}.reduce(_ + _)/valuesAndPreds.count +println("training Mean Squared Error = " + MSE) +{% endhighlight %} + + +Similarly you can use RidgeRegressionWithSGD and LassoWithSGD and compare training +[Mean Squared Errors](http://en.wikipedia.org/wiki/Mean_squared_error). + +## Clustering +In the following example after loading and parsing data, we use the KMeans object to cluster the data +into two clusters. The number of desired clusters is passed to the algorithm. We then compute Within +Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasing *k*. In fact the +optimal *k* is usually one where there is an "elbow" in the WSSSE graph. + +{% highlight scala %} +import org.apache.spark.mllib.clustering.KMeans + +// Load and parse the data +val data = sc.textFile("kmeans_data.txt") +val parsedData = data.map( _.split(' ').map(_.toDouble)) + +// Cluster the data into two classes using KMeans +val numIterations = 20 +val numClusters = 2 +val clusters = KMeans.train(parsedData, numClusters, numIterations) + +// Evaluate clustering by computing Within Set Sum of Squared Errors +val WSSSE = clusters.computeCost(parsedData) +println("Within Set Sum of Squared Errors = " + WSSSE) +{% endhighlight %} + + +## Collaborative Filtering +In the following example we load rating data. Each row consists of a user, a product and a rating. +We use the default ALS.train() method which assumes ratings are explicit. We evaluate the recommendation +model by measuring the Mean Squared Error of rating prediction. + +{% highlight scala %} +import org.apache.spark.mllib.recommendation.ALS +import org.apache.spark.mllib.recommendation.Rating + +// Load and parse the data +val data = sc.textFile("mllib/data/als/test.data") +val ratings = data.map(_.split(',') match { + case Array(user, item, rate) => Rating(user.toInt, item.toInt, rate.toDouble) +}) + +// Build the recommendation model using ALS +val numIterations = 20 +val model = ALS.train(ratings, 1, 20, 0.01) + +// Evaluate the model on rating data +val usersProducts = ratings.map{ case Rating(user, product, rate) => (user, product)} +val predictions = model.predict(usersProducts).map{ + case Rating(user, product, rate) => ((user, product), rate) +} +val ratesAndPreds = ratings.map{ + case Rating(user, product, rate) => ((user, product), rate) +}.join(predictions) +val MSE = ratesAndPreds.map{ + case ((user, product), (r1, r2)) => math.pow((r1- r2), 2) +}.reduce(_ + _)/ratesAndPreds.count +println("Mean Squared Error = " + MSE) +{% endhighlight %} + +If the rating matrix is derived from other source of information (i.e., it is inferred from +other signals), you can use the trainImplicit method to get better results. + +{% highlight scala %} +val model = ALS.trainImplicit(ratings, 1, 20, 0.01) +{% endhighlight %} + +# Using MLLib in Python +Following examples can be tested in the PySpark shell. + +## Binary Classification +The following example shows how to load a sample dataset, build Logistic Regression model, +and make predictions with the resulting model to compute the training error. + +{% highlight python %} +from pyspark.mllib.classification import LogisticRegressionWithSGD +from numpy import array + +# Load and parse the data +data = sc.textFile("mllib/data/sample_svm_data.txt") +parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')])) +model = LogisticRegressionWithSGD.train(sc, parsedData) + +# Build the model +labelsAndPreds = parsedData.map(lambda point: (int(point.item(0)), + model.predict(point.take(range(1, point.size))))) + +# Evaluating the model on training data +trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count()) +print("Training Error = " + str(trainErr)) +{% endhighlight %} + +## Linear Regression +The following example demonstrate how to load training data, parse it as an RDD of LabeledPoint. The +example then uses LinearRegressionWithSGD to build a simple linear model to predict label values. We +compute the Mean Squared Error at the end to evaluate +[goodness of fit](http://en.wikipedia.org/wiki/Goodness_of_fit) + +{% highlight python %} +from pyspark.mllib.regression import LinearRegressionWithSGD +from numpy import array + +# Load and parse the data +data = sc.textFile("mllib/data/ridge-data/lpsa.data") +parsedData = data.map(lambda line: array([float(x) for x in line.replace(',', ' ').split(' ')])) + +# Build the model +model = LinearRegressionWithSGD.train(sc, parsedData) + +# Evaluate the model on training data +valuesAndPreds = parsedData.map(lambda point: (point.item(0), + model.predict(point.take(range(1, point.size))))) +MSE = valuesAndPreds.map(lambda (v, p): (v - p)**2).reduce(lambda x, y: x + y)/valuesAndPreds.count() +print("Mean Squared Error = " + str(MSE)) +{% endhighlight %} + + +## Clustering +In the following example after loading and parsing data, we use the KMeans object to cluster the data +into two clusters. The number of desired clusters is passed to the algorithm. We then compute Within +Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasing *k*. In fact the +optimal *k* is usually one where there is an "elbow" in the WSSSE graph. + +{% highlight python %} +from pyspark.mllib.clustering import KMeans +from numpy import array +from math import sqrt + +# Load and parse the data +data = sc.textFile("kmeans_data.txt") +parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')])) + +# Build the model (cluster the data) +clusters = KMeans.train(sc, parsedData, 2, maxIterations=10, + runs=30, initialization_mode="random") + +# Evaluate clustering by computing Within Set Sum of Squared Errors +def error(point): + center = clusters.centers[clusters.predict(point)] + return sqrt(sum([x**2 for x in (point - center)])) + +WSSSE = parsedData.map(lambda point: error(point)).reduce(lambda x, y: x + y) +print("Within Set Sum of Squared Error = " + str(WSSSE)) +{% endhighlight %} + +Similarly you can use RidgeRegressionWithSGD and LassoWithSGD and compare training Mean Squared +Errors. + +## Collaborative Filtering +In the following example we load rating data. Each row consists of a user, a product and a rating. +We use the default ALS.train() method which assumes ratings are explicit. We evaluate the +recommendation by measuring the Mean Squared Error of rating prediction. + +{% highlight python %} +from pyspark.mllib.recommendation import ALS +from numpy import array + +# Load and parse the data +data = sc.textFile("mllib/data/als/test.data") +ratings = data.map(lambda line: array([float(x) for x in line.split(',')])) + +# Build the recommendation model using Alternating Least Squares +model = ALS.train(sc, ratings, 1, 20) + +# Evaluate the model on training data +testdata = ratings.map(lambda p: (int(p[0]), int(p[1]))) +predictions = model.predictAll(testdata).map(lambda r: ((r[0], r[1]), r[2])) +ratesAndPreds = ratings.map(lambda r: ((r[0], r[1]), r[2])).join(predictions) +MSE = ratesAndPreds.map(lambda r: (r[1][0] - r[1][1])**2).reduce(lambda x, y: x + y)/ratesAndPreds.count() +print("Mean Squared Error = " + str(MSE)) +{% endhighlight %} + +If the rating matrix is derived from other source of information (i.e., it is inferred from other +signals), you can use the trainImplicit method to get better results. + +{% highlight python %} +# Build the recommendation model using Alternating Least Squares based on implicit ratings +model = ALS.trainImplicit(sc, ratings, 1, 20) +{% endhighlight %} # Singular Value Decomposition @@ -221,13 +438,13 @@ Given an *m x n* matrix *A*, we can compute matrices *U, S, V* such that There is no restriction on m, but we require n^2 doubles to fit in memory. Further, n should be less than m. - + The decomposition is computed by first computing *A^TA = V S^2 V^T*, computing svd locally on that (since n x n is small), -from which we recover S and V. +from which we recover S and V. Then we compute U via easy matrix multiplication as *U = A * V * S^-1* - + Only singular vectors associated with largest k singular values are recovered. If there are k such values, then the dimensions of the return will be: @@ -237,7 +454,7 @@ such values, then the dimensions of the return will be: * *V* is *n x k* and satisfies V^TV = eye(k). All input and output is expected in sparse matrix format, 1-indexed -as tuples of the form ((i,j),value) all in +as tuples of the form ((i,j),value) all in SparseMatrix RDDs. Below is example usage. {% highlight scala %} @@ -261,10 +478,3 @@ val decomposed = SVD.sparseSVD(SparseMatrix(data, m, n), k) val = decomposed.S.data println("singular values = " + s.toArray.mkString) - -{% endhighlight %} - - - - - diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index 96f93e24fe..c4236f8312 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -47,7 +47,7 @@ PySpark will automatically ship these functions to workers, along with any objec Instances of classes will be serialized and shipped to workers by PySpark, but classes themselves cannot be automatically distributed to workers. The [Standalone Use](#standalone-use) section describes how to ship code dependencies to workers. -In addition, PySpark fully supports interactive use---simply run `./pyspark` to launch an interactive shell. +In addition, PySpark fully supports interactive use---simply run `./bin/pyspark` to launch an interactive shell. # Installing and Configuring PySpark @@ -60,17 +60,17 @@ By default, PySpark requires `python` to be available on the system `PATH` and u All of PySpark's library dependencies, including [Py4J](http://py4j.sourceforge.net/), are bundled with PySpark and automatically imported. -Standalone PySpark applications should be run using the `pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`. -The script automatically adds the `pyspark` package to the `PYTHONPATH`. +Standalone PySpark applications should be run using the `bin/pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`. +The script automatically adds the `bin/pyspark` package to the `PYTHONPATH`. # Interactive Use -The `pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options: +The `bin/pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options: {% highlight bash %} $ sbt/sbt assembly -$ ./pyspark +$ ./bin/pyspark {% endhighlight %} The Python shell can be used explore data interactively and is a simple way to learn the API: @@ -82,35 +82,36 @@ The Python shell can be used explore data interactively and is a simple way to l >>> help(pyspark) # Show all pyspark functions {% endhighlight %} -By default, the `pyspark` shell creates SparkContext that runs applications locally on a single core. +By default, the `bin/pyspark` shell creates SparkContext that runs applications locally on a single core. To connect to a non-local cluster, or use multiple cores, set the `MASTER` environment variable. -For example, to use the `pyspark` shell with a [standalone Spark cluster](spark-standalone.html): +For example, to use the `bin/pyspark` shell with a [standalone Spark cluster](spark-standalone.html): {% highlight bash %} -$ MASTER=spark://IP:PORT ./pyspark +$ MASTER=spark://IP:PORT ./bin/pyspark {% endhighlight %} Or, to use four cores on the local machine: {% highlight bash %} -$ MASTER=local[4] ./pyspark +$ MASTER=local[4] ./bin/pyspark {% endhighlight %} ## IPython -It is also possible to launch PySpark in [IPython](http://ipython.org), the enhanced Python interpreter. -To do this, set the `IPYTHON` variable to `1` when running `pyspark`: +It is also possible to launch PySpark in [IPython](http://ipython.org), the +enhanced Python interpreter. PySpark works with IPython 1.0.0 and later. To +use IPython, set the `IPYTHON` variable to `1` when running `bin/pyspark`: {% highlight bash %} -$ IPYTHON=1 ./pyspark +$ IPYTHON=1 ./bin/pyspark {% endhighlight %} Alternatively, you can customize the `ipython` command by setting `IPYTHON_OPTS`. For example, to launch the [IPython Notebook](http://ipython.org/notebook.html) with PyLab graphing support: {% highlight bash %} -$ IPYTHON_OPTS="notebook --pylab inline" ./pyspark +$ IPYTHON_OPTS="notebook --pylab inline" ./bin/pyspark {% endhighlight %} IPython also works on a cluster or on multiple cores if you set the `MASTER` environment variable. @@ -118,7 +119,7 @@ IPython also works on a cluster or on multiple cores if you set the `MASTER` env # Standalone Programs -PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `pyspark`. +PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `bin/pyspark`. The Quick Start guide includes a [complete example](quick-start.html#a-standalone-app-in-python) of a standalone Python application. Code dependencies can be deployed by listing them in the `pyFiles` option in the SparkContext constructor: @@ -153,6 +154,6 @@ Many of the methods also contain [doctests](http://docs.python.org/2/library/doc PySpark also includes several sample programs in the [`python/examples` folder](https://github.com/apache/incubator-spark/tree/master/python/examples). You can run them by passing the files to `pyspark`; e.g.: - ./pyspark python/examples/wordcount.py + ./bin/pyspark python/examples/wordcount.py Each program prints usage help when run without arguments. diff --git a/docs/quick-start.md b/docs/quick-start.md index bdf127d404..153081bdaa 100644 --- a/docs/quick-start.md +++ b/docs/quick-start.md @@ -20,7 +20,7 @@ $ sbt/sbt assembly ## Basics Spark's interactive shell provides a simple way to learn the API, as well as a powerful tool to analyze datasets interactively. -Start the shell by running `./spark-shell` in the Spark directory. +Start the shell by running `./bin/spark-shell` in the Spark directory. Spark's primary abstraction is a distributed collection of items called a Resilient Distributed Dataset (RDD). RDDs can be created from Hadoop InputFormats (such as HDFS files) or by transforming other RDDs. Let's make a new RDD from the text of the README file in the Spark source directory: @@ -99,7 +99,7 @@ scala> linesWithSpark.count() res9: Long = 15 {% endhighlight %} -It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark). +It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `bin/spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark). # A Standalone App in Scala Now say we wanted to write a standalone application using the Spark API. We will walk through a simple application in both Scala (with SBT), Java (with Maven), and Python. If you are using other build systems, consider using the Spark assembly JAR described in the developer guide. @@ -146,7 +146,7 @@ If you also wish to read data from Hadoop's HDFS, you will also need to add a de libraryDependencies += "org.apache.hadoop" % "hadoop-client" % "<your-hdfs-version>" {% endhighlight %} -Finally, for sbt to work correctly, we'll need to layout `SimpleApp.scala` and `simple.sbt` according to the typical directory structure. Once that is in place, we can create a JAR package containing the application's code, then use `sbt run` to execute our program. +Finally, for sbt to work correctly, we'll need to layout `SimpleApp.scala` and `simple.sbt` according to the typical directory structure. Once that is in place, we can create a JAR package containing the application's code, then use `sbt/sbt run` to execute our program. {% highlight bash %} $ find . @@ -157,8 +157,8 @@ $ find . ./src/main/scala ./src/main/scala/SimpleApp.scala -$ sbt package -$ sbt run +$ sbt/sbt package +$ sbt/sbt run ... Lines with a: 46, Lines with b: 23 {% endhighlight %} @@ -277,11 +277,11 @@ We can pass Python functions to Spark, which are automatically serialized along For applications that use custom classes or third-party libraries, we can add those code dependencies to SparkContext to ensure that they will be available on remote machines; this is described in more detail in the [Python programming guide](python-programming-guide.html). `SimpleApp` is simple enough that we do not need to specify any code dependencies. -We can run this application using the `pyspark` script: +We can run this application using the `bin/pyspark` script: {% highlight python %} $ cd $SPARK_HOME -$ ./pyspark SimpleApp.py +$ ./bin/pyspark SimpleApp.py ... Lines with a: 46, Lines with b: 23 {% endhighlight python %} diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md index aa75ca4324..b206270107 100644 --- a/docs/running-on-yarn.md +++ b/docs/running-on-yarn.md @@ -12,7 +12,7 @@ was added to Spark in version 0.6.0, and improved in 0.7.0 and 0.8.0. We need a consolidated Spark JAR (which bundles all the required dependencies) to run Spark jobs on a YARN cluster. This can be built by setting the Hadoop version and `SPARK_YARN` environment variable, as follows: - SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true ./sbt/sbt assembly + SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt/sbt assembly The assembled JAR will be something like this: `./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly_{{site.SPARK_VERSION}}-hadoop2.0.5.jar`. @@ -54,7 +54,7 @@ There are two scheduler mode that can be used to launch spark application on YAR The command to launch the YARN Client is as follows: - SPARK_JAR=<SPARK_ASSEMBLY_JAR_FILE> ./spark-class org.apache.spark.deploy.yarn.Client \ + SPARK_JAR=<SPARK_ASSEMBLY_JAR_FILE> ./bin/spark-class org.apache.spark.deploy.yarn.Client \ --jar <YOUR_APP_JAR_FILE> \ --class <APP_MAIN_CLASS> \ --args <APP_MAIN_ARGUMENTS> \ @@ -72,14 +72,14 @@ The command to launch the YARN Client is as follows: For example: # Build the Spark assembly JAR and the Spark examples JAR - $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true ./sbt/sbt assembly + $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt/sbt assembly # Configure logging $ cp conf/log4j.properties.template conf/log4j.properties # Submit Spark's ApplicationMaster to YARN's ResourceManager, and instruct Spark to run the SparkPi example $ SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \ - ./spark-class org.apache.spark.deploy.yarn.Client \ + ./bin/spark-class org.apache.spark.deploy.yarn.Client \ --jar examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \ --class org.apache.spark.examples.SparkPi \ --args yarn-standalone \ @@ -107,16 +107,16 @@ For example: SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \ SPARK_YARN_APP_JAR=examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \ - ./run-example org.apache.spark.examples.SparkPi yarn-client + ./bin/run-example org.apache.spark.examples.SparkPi yarn-client SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \ SPARK_YARN_APP_JAR=examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \ - MASTER=yarn-client ./spark-shell + MASTER=yarn-client ./bin/spark-shell -# Building Spark for Hadoop/YARN 2.2.x +You can also send extra files to yarn cluster for worker to use by exporting SPARK_YARN_DIST_FILES=file1,file2... etc. -Hadoop 2.2.x users must build Spark and publish it locally. The SBT build process handles Hadoop 2.2.x as a special case. This version of Hadoop has new YARN API changes and depends on a Protobuf version (2.5) that is not compatible with the Akka version (2.0.5) that Spark uses. Therefore, if the Hadoop version (e.g. set through ```SPARK_HADOOP_VERSION```) starts with 2.2.0 or higher then the build process will depend on Akka artifacts distributed by the Spark project compatible with Protobuf 2.5. Furthermore, the build process then uses the directory ```new-yarn``` (instead of ```yarn```), which supports the new YARN API. The build process should seamlessly work out of the box. +# Building Spark for Hadoop/YARN 2.2.x See [Building Spark with Maven](building-with-maven.html) for instructions on how to build Spark using the Maven process. @@ -126,4 +126,3 @@ See [Building Spark with Maven](building-with-maven.html) for instructions on ho - The local directories used for spark will be the local directories configured for YARN (Hadoop Yarn config yarn.nodemanager.local-dirs). If the user specifies spark.local.dir, it will be ignored. - The --files and --archives options support specifying file names with the # similar to Hadoop. For example you can specify: --files localtest.txt#appSees.txt and this will upload the file you have locally named localtest.txt into HDFS but this will be linked to by the name appSees.txt and your application should use the name as appSees.txt to reference it when running on YARN. - The --addJars option allows the SparkContext.addJar function to work if you are using it with local files. It does not need to be used if you are using it with HDFS, HTTP, HTTPS, or FTP files. -- YARN 2.2.x users cannot simply depend on the Spark packages without building Spark, as the published Spark artifacts are compiled to work with the pre 2.2 API. Those users must build Spark and publish it locally. diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md index 1db255ca53..c1ef46a1cd 100644 --- a/docs/scala-programming-guide.md +++ b/docs/scala-programming-guide.md @@ -13,7 +13,7 @@ At a high level, every Spark application consists of a *driver program* that run A second abstraction in Spark is *shared variables* that can be used in parallel operations. By default, when Spark runs a function in parallel as a set of tasks on different nodes, it ships a copy of each variable used in the function to each task. Sometimes, a variable needs to be shared across tasks, or between tasks and the driver program. Spark supports two types of shared variables: *broadcast variables*, which can be used to cache a value in memory on all nodes, and *accumulators*, which are variables that are only "added" to, such as counters and sums. -This guide shows each of these features and walks through some samples. It assumes some familiarity with Scala, especially with the syntax for [closures](http://www.scala-lang.org/node/133). Note that you can also run Spark interactively using the `spark-shell` script. We highly recommend doing that to follow along! +This guide shows each of these features and walks through some samples. It assumes some familiarity with Scala, especially with the syntax for [closures](http://www.scala-lang.org/node/133). Note that you can also run Spark interactively using the `bin/spark-shell` script. We highly recommend doing that to follow along! # Linking with Spark @@ -54,16 +54,16 @@ object for more advanced configuration. The `master` parameter is a string specifying a [Spark or Mesos cluster URL](#master-urls) to connect to, or a special "local" string to run in local mode, as described below. `appName` is a name for your application, which will be shown in the cluster web UI. Finally, the last two parameters are needed to deploy your code to a cluster if running in distributed mode, as described later. -In the Spark shell, a special interpreter-aware SparkContext is already created for you, in the variable called `sc`. Making your own SparkContext will not work. You can set which master the context connects to using the `MASTER` environment variable, and you can add JARs to the classpath with the `ADD_JARS` variable. For example, to run `spark-shell` on four cores, use +In the Spark shell, a special interpreter-aware SparkContext is already created for you, in the variable called `sc`. Making your own SparkContext will not work. You can set which master the context connects to using the `MASTER` environment variable, and you can add JARs to the classpath with the `ADD_JARS` variable. For example, to run `bin/spark-shell` on four cores, use {% highlight bash %} -$ MASTER=local[4] ./spark-shell +$ MASTER=local[4] ./bin/spark-shell {% endhighlight %} Or, to also add `code.jar` to its classpath, use: {% highlight bash %} -$ MASTER=local[4] ADD_JARS=code.jar ./spark-shell +$ MASTER=local[4] ADD_JARS=code.jar ./bin/spark-shell {% endhighlight %} ### Master URLs @@ -95,7 +95,7 @@ If you want to run your application on a cluster, you will need to specify the t * `sparkHome`: The path at which Spark is installed on your worker machines (it should be the same on all of them). * `jars`: A list of JAR files on the local machine containing your application's code and any dependencies, which Spark will deploy to all the worker nodes. You'll need to package your application into a set of JARs using your build system. For example, if you're using SBT, the [sbt-assembly](https://github.com/sbt/sbt-assembly) plugin is a good way to make a single JAR with your code and dependencies. -If you run `spark-shell` on a cluster, you can add JARs to it by specifying the `ADD_JARS` environment variable before you launch it. This variable should contain a comma-separated list of JARs. For example, `ADD_JARS=a.jar,b.jar ./spark-shell` will launch a shell with `a.jar` and `b.jar` on its classpath. In addition, any new classes you define in the shell will automatically be distributed. +If you run `bin/spark-shell` on a cluster, you can add JARs to it by specifying the `ADD_JARS` environment variable before you launch it. This variable should contain a comma-separated list of JARs. For example, `ADD_JARS=a.jar,b.jar ./bin/spark-shell` will launch a shell with `a.jar` and `b.jar` on its classpath. In addition, any new classes you define in the shell will automatically be distributed. # Resilient Distributed Datasets (RDDs) @@ -366,9 +366,9 @@ res2: Int = 10 # Where to Go from Here You can see some [example Spark programs](http://spark.incubator.apache.org/examples.html) on the Spark website. -In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `run-example` script included in Spark; for example: +In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `bin/run-example` script included in Spark; for example: - ./run-example org.apache.spark.examples.SparkPi + ./bin/run-example org.apache.spark.examples.SparkPi Each example program prints usage help when run without any arguments. diff --git a/docs/spark-debugger.md b/docs/spark-debugger.md index d6315d97f4..11c51d5cde 100644 --- a/docs/spark-debugger.md +++ b/docs/spark-debugger.md @@ -39,7 +39,7 @@ where `path/to/event-log` is where you want the event log to go relative to `$SP ### Loading the event log into the debugger -1. Run a Spark shell with `MASTER=<i>host</i> ./spark-shell`. +1. Run a Spark shell with `MASTER=<i>host</i> ./bin/spark-shell`. 2. Use `EventLogReader` to load the event log as follows: {% highlight scala %} spark> val r = new spark.EventLogReader(sc, Some("path/to/event-log")) diff --git a/docs/spark-standalone.md b/docs/spark-standalone.md index f7f0b78908..2a186261b7 100644 --- a/docs/spark-standalone.md +++ b/docs/spark-standalone.md @@ -10,17 +10,13 @@ In addition to running on the Mesos or YARN cluster managers, Spark also provide # Installing Spark Standalone to a Cluster -The easiest way to deploy Spark is by running the `./make-distribution.sh` script to create a binary distribution. -This distribution can be deployed to any machine with the Java runtime installed; there is no need to install Scala. - -The recommended procedure is to deploy and start the master on one node first, get the master spark URL, -then modify `conf/spark-env.sh` in the `dist/` directory before deploying to all the other nodes. +To install Spark Standlone mode, you simply place a compiled version of Spark on each node on the cluster. You can obtain pre-built versions of Spark with each release or [build it yourself](index.html#building). # Starting a Cluster Manually You can start a standalone master server by executing: - ./bin/start-master.sh + ./sbin/start-master.sh Once started, the master will print out a `spark://HOST:PORT` URL for itself, which you can use to connect workers to it, or pass as the "master" argument to `SparkContext`. You can also find this URL on @@ -28,7 +24,7 @@ the master's web UI, which is [http://localhost:8080](http://localhost:8080) by Similarly, you can start one or more workers and connect them to the master via: - ./spark-class org.apache.spark.deploy.worker.Worker spark://IP:PORT + ./bin/spark-class org.apache.spark.deploy.worker.Worker spark://IP:PORT Once you have started a worker, look at the master's web UI ([http://localhost:8080](http://localhost:8080) by default). You should see the new node listed there, along with its number of CPUs and memory (minus one gigabyte left for the OS). @@ -70,12 +66,12 @@ To launch a Spark standalone cluster with the launch scripts, you need to create Once you've set up this file, you can launch or stop your cluster with the following shell scripts, based on Hadoop's deploy scripts, and available in `SPARK_HOME/bin`: -- `bin/start-master.sh` - Starts a master instance on the machine the script is executed on. -- `bin/start-slaves.sh` - Starts a slave instance on each machine specified in the `conf/slaves` file. -- `bin/start-all.sh` - Starts both a master and a number of slaves as described above. -- `bin/stop-master.sh` - Stops the master that was started via the `bin/start-master.sh` script. -- `bin/stop-slaves.sh` - Stops the slave instances that were started via `bin/start-slaves.sh`. -- `bin/stop-all.sh` - Stops both the master and the slaves as described above. +- `sbin/start-master.sh` - Starts a master instance on the machine the script is executed on. +- `sbin/start-slaves.sh` - Starts a slave instance on each machine specified in the `conf/slaves` file. +- `sbin/start-all.sh` - Starts both a master and a number of slaves as described above. +- `sbin/stop-master.sh` - Stops the master that was started via the `bin/start-master.sh` script. +- `sbin/stop-slaves.sh` - Stops the slave instances that were started via `bin/start-slaves.sh`. +- `sbin/stop-all.sh` - Stops both the master and the slaves as described above. Note that these scripts must be executed on the machine you want to run the Spark master on, not your local machine. @@ -143,13 +139,45 @@ constructor](scala-programming-guide.html#initializing-spark). To run an interactive Spark shell against the cluster, run the following command: - MASTER=spark://IP:PORT ./spark-shell + MASTER=spark://IP:PORT ./bin/spark-shell -Note that if you are running spark-shell from one of the spark cluster machines, the `spark-shell` script will +Note that if you are running spark-shell from one of the spark cluster machines, the `bin/spark-shell` script will automatically set MASTER from the `SPARK_MASTER_IP` and `SPARK_MASTER_PORT` variables in `conf/spark-env.sh`. You can also pass an option `-c <numCores>` to control the number of cores that spark-shell uses on the cluster. +# Launching Applications Inside the Cluster + +You may also run your application entirely inside of the cluster by submitting your application driver using the submission client. The syntax for submitting applications is as follows: + + + ./spark-class org.apache.spark.deploy.Client launch + [client-options] \ + <cluster-url> <application-jar-url> <main-class> \ + [application-options] + + cluster-url: The URL of the master node. + application-jar-url: Path to a bundled jar including your application and all dependencies. Currently, the URL must be globally visible inside of your cluster, for instance, an `hdfs://` path or a `file://` path that is present on all nodes. + main-class: The entry point for your application. + + Client Options: + --memory <count> (amount of memory, in MB, allocated for your driver program) + --cores <count> (number of cores allocated for your driver program) + --supervise (whether to automatically restart your driver on application or node failure) + --verbose (prints increased logging output) + +Keep in mind that your driver program will be executed on a remote worker machine. You can control the execution environment in the following ways: + + * _Environment variables_: These will be captured from the environment in which you launch the client and applied when launching the driver program. + * _Java options_: You can add java options by setting `SPARK_JAVA_OPTS` in the environment in which you launch the submission client. + * _Dependencies_: You'll still need to call `sc.addJar` inside of your program to make your bundled application jar visible on all worker nodes. + +Once you submit a driver program, it will appear in the cluster management UI at port 8080 and +be assigned an identifier. If you'd like to prematurely terminate the program, you can do so using +the same client: + + ./spark-class org.apache.spark.deploy.client.DriverClient kill <driverId> + # Resource Scheduling The standalone cluster mode currently only supports a simple FIFO scheduler across applications. @@ -167,6 +195,16 @@ val conf = new SparkConf() val sc = new SparkContext(conf) {% endhighlight %} +In addition, you can configure `spark.deploy.defaultCores` on the cluster master process to change the +default for applications that don't set `spark.cores.max` to something less than infinite. +Do this by adding the following to `conf/spark-env.sh`: + +{% highlight bash %} +export SPARK_JAVA_OPTS="-Dspark.deploy.defaultCores=<value>" +{% endhighlight %} + +This is useful on shared clusters where users might not have configured a maximum number of cores +individually. # Monitoring and Logging diff --git a/docs/streaming-programming-guide.md b/docs/streaming-programming-guide.md index 6f97db6a3e..1c9ece6270 100644 --- a/docs/streaming-programming-guide.md +++ b/docs/streaming-programming-guide.md @@ -245,7 +245,7 @@ $ nc -lk 9999 Then, in a different terminal, you can start NetworkWordCount by using {% highlight bash %} -$ ./run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999 +$ ./bin/run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999 {% endhighlight %} This will make NetworkWordCount connect to the netcat server. Any lines typed in the terminal running the netcat server will be counted and printed on screen. @@ -283,7 +283,7 @@ Time: 1357008430000 ms </td> </table> -You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files. +You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./bin/run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files. # DStream Persistence Similar to RDDs, DStreams also allow developers to persist the stream's data in memory. That is, using `persist()` method on a DStream would automatically persist every RDD of that DStream in memory. This is useful if the data in the DStream will be computed multiple times (e.g., multiple operations on the same data). For window-based operations like `reduceByWindow` and `reduceByKeyAndWindow` and state-based operations like `updateStateByKey`, this is implicitly true. Hence, DStreams generated by window-based operations are automatically persisted in memory, without the developer calling `persist()`. diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index a2b0e7e7f4..d82a1e1490 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -436,7 +436,7 @@ def setup_cluster(conn, master_nodes, slave_nodes, opts, deploy_ssh_key): def setup_standalone_cluster(master, slave_nodes, opts): slave_ips = '\n'.join([i.public_dns_name for i in slave_nodes]) ssh(master, opts, "echo \"%s\" > spark/conf/slaves" % (slave_ips)) - ssh(master, opts, "/root/spark/bin/start-all.sh") + ssh(master, opts, "/root/spark/sbin/start-all.sh") def setup_spark_cluster(master, opts): ssh(master, opts, "chmod u+x spark-ec2/setup.sh") diff --git a/examples/pom.xml b/examples/pom.xml index 7a7032c319..cb4f7ee33b 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -72,6 +72,31 @@ <scope>provided</scope> </dependency> <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-twitter_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-kafka_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-flume_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-zeromq_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-mqtt_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> <groupId>org.apache.hbase</groupId> <artifactId>hbase</artifactId> <version>0.94.6</version> @@ -87,21 +112,6 @@ </exclusions> </dependency> <dependency> - <groupId>com.sksamuel.kafka</groupId> - <artifactId>kafka_${scala.binary.version}</artifactId> - <version>0.8.0-beta1</version> - <exclusions> - <exclusion> - <groupId>com.sun.jmx</groupId> - <artifactId>jmxri</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jdmk</groupId> - <artifactId>jmxtools</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> <groupId>org.eclipse.jetty</groupId> <artifactId>jetty-server</artifactId> </dependency> @@ -174,7 +184,7 @@ <artifactId>maven-shade-plugin</artifactId> <configuration> <shadedArtifactAttached>false</shadedArtifactAttached> - <outputFile>${project.build.directory}/scala-${scala.version}/${project.artifactId}-assembly-${project.version}.jar</outputFile> + <outputFile>${project.build.directory}/scala-${scala.binary.version}/${project.artifactId}-assembly-${project.version}.jar</outputFile> <artifactSet> <includes> <include>*:*</include> @@ -203,6 +213,9 @@ <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> <resource>reference.conf</resource> </transformer> + <transformer implementation="org.apache.maven.plugins.shade.resource.DontIncludeResourceTransformer"> + <resource>log4j.properties</resource> + </transformer> </transformers> </configuration> </execution> diff --git a/examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java b/examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java index be0d38589c..d552c47b22 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java @@ -24,19 +24,19 @@ import org.apache.spark.api.java.function.Function2; import java.io.Serializable; import java.util.Arrays; -import java.util.StringTokenizer; import java.util.Random; +import java.util.regex.Pattern; /** * Logistic regression based classification. */ -public class JavaHdfsLR { +public final class JavaHdfsLR { - static int D = 10; // Number of dimensions - static Random rand = new Random(42); + private static final int D = 10; // Number of dimensions + private static final Random rand = new Random(42); static class DataPoint implements Serializable { - public DataPoint(double[] x, double y) { + DataPoint(double[] x, double y) { this.x = x; this.y = y; } @@ -46,20 +46,22 @@ public class JavaHdfsLR { } static class ParsePoint extends Function<String, DataPoint> { + private static final Pattern SPACE = Pattern.compile(" "); + + @Override public DataPoint call(String line) { - StringTokenizer tok = new StringTokenizer(line, " "); - double y = Double.parseDouble(tok.nextToken()); + String[] tok = SPACE.split(line); + double y = Double.parseDouble(tok[0]); double[] x = new double[D]; - int i = 0; - while (i < D) { - x[i] = Double.parseDouble(tok.nextToken()); - i += 1; + for (int i = 0; i < D; i++) { + x[i] = Double.parseDouble(tok[i + 1]); } return new DataPoint(x, y); } } static class VectorSum extends Function2<double[], double[], double[]> { + @Override public double[] call(double[] a, double[] b) { double[] result = new double[D]; for (int j = 0; j < D; j++) { @@ -70,12 +72,13 @@ public class JavaHdfsLR { } static class ComputeGradient extends Function<DataPoint, double[]> { - double[] weights; + private final double[] weights; - public ComputeGradient(double[] weights) { + ComputeGradient(double[] weights) { this.weights = weights; } + @Override public double[] call(DataPoint p) { double[] gradient = new double[D]; for (int i = 0; i < D; i++) { @@ -106,7 +109,7 @@ public class JavaHdfsLR { } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaHdfsLR", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaHdfsLR.class)); JavaRDD<String> lines = sc.textFile(args[1]); JavaRDD<DataPoint> points = lines.map(new ParsePoint()).cache(); int ITERATIONS = Integer.parseInt(args[2]); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaKMeans.java b/examples/src/main/java/org/apache/spark/examples/JavaKMeans.java index 5a6afe7eae..0dc879275a 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaKMeans.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaKMeans.java @@ -27,19 +27,24 @@ import org.apache.spark.util.Vector; import java.util.List; import java.util.Map; +import java.util.regex.Pattern; /** * K-means clustering using Java API. */ -public class JavaKMeans { +public final class JavaKMeans { + + private static final Pattern SPACE = Pattern.compile(" "); /** Parses numbers split by whitespace to a vector */ static Vector parseVector(String line) { - String[] splits = line.split(" "); + String[] splits = SPACE.split(line); double[] data = new double[splits.length]; int i = 0; - for (String s : splits) - data[i] = Double.parseDouble(splits[i++]); + for (String s : splits) { + data[i] = Double.parseDouble(s); + i++; + } return new Vector(data); } @@ -74,7 +79,7 @@ public class JavaKMeans { System.exit(1); } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaKMeans", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaKMeans.class)); String path = args[1]; int K = Integer.parseInt(args[2]); double convergeDist = Double.parseDouble(args[3]); @@ -82,7 +87,7 @@ public class JavaKMeans { JavaRDD<Vector> data = sc.textFile(path).map( new Function<String, Vector>() { @Override - public Vector call(String line) throws Exception { + public Vector call(String line) { return parseVector(line); } } @@ -96,7 +101,7 @@ public class JavaKMeans { JavaPairRDD<Integer, Vector> closest = data.map( new PairFunction<Vector, Integer, Vector>() { @Override - public Tuple2<Integer, Vector> call(Vector vector) throws Exception { + public Tuple2<Integer, Vector> call(Vector vector) { return new Tuple2<Integer, Vector>( closestPoint(vector, centroids), vector); } @@ -107,7 +112,8 @@ public class JavaKMeans { JavaPairRDD<Integer, List<Vector>> pointsGroup = closest.groupByKey(); Map<Integer, Vector> newCentroids = pointsGroup.mapValues( new Function<List<Vector>, Vector>() { - public Vector call(List<Vector> ps) throws Exception { + @Override + public Vector call(List<Vector> ps) { return average(ps); } }).collectAsMap(); @@ -122,8 +128,9 @@ public class JavaKMeans { } while (tempDist > convergeDist); System.out.println("Final centers:"); - for (Vector c : centroids) + for (Vector c : centroids) { System.out.println(c); + } System.exit(0); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java b/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java index 407cd7ccfa..9eb1cadd71 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java @@ -35,9 +35,9 @@ import java.util.regex.Pattern; /** * Executes a roll up-style query against Apache logs. */ -public class JavaLogQuery { +public final class JavaLogQuery { - public static List<String> exampleApacheLogs = Lists.newArrayList( + public static final List<String> exampleApacheLogs = Lists.newArrayList( "10.10.10.10 - \"FRED\" [18/Jan/2013:17:56:07 +1100] \"GET http://images.com/2013/Generic.jpg " + "HTTP/1.1\" 304 315 \"http://referall.com/\" \"Mozilla/4.0 (compatible; MSIE 7.0; " + "Windows NT 5.1; GTB7.4; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; " + @@ -51,14 +51,14 @@ public class JavaLogQuery { "3.5.30729; Release=ARP)\" \"UD-1\" - \"image/jpeg\" \"whatever\" 0.352 \"-\" - \"\" 256 977 988 \"\" " + "0 73.23.2.15 images.com 1358492557 - Whatup"); - public static Pattern apacheLogRegex = Pattern.compile( + public static final Pattern apacheLogRegex = Pattern.compile( "^([\\d.]+) (\\S+) (\\S+) \\[([\\w\\d:/]+\\s[+\\-]\\d{4})\\] \"(.+?)\" (\\d{3}) ([\\d\\-]+) \"([^\"]+)\" \"([^\"]+)\".*"); /** Tracks the total query count and number of aggregate bytes for a particular group. */ public static class Stats implements Serializable { - private int count; - private int numBytes; + private final int count; + private final int numBytes; public Stats(int count, int numBytes) { this.count = count; @@ -92,32 +92,32 @@ public class JavaLogQuery { if (m.find()) { int bytes = Integer.parseInt(m.group(7)); return new Stats(1, bytes); - } - else + } else { return new Stats(1, 0); + } } - public static void main(String[] args) throws Exception { + public static void main(String[] args) { if (args.length == 0) { System.err.println("Usage: JavaLogQuery <master> [logFile]"); System.exit(1); } JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaLogQuery.class)); JavaRDD<String> dataSet = (args.length == 2) ? jsc.textFile(args[1]) : jsc.parallelize(exampleApacheLogs); JavaPairRDD<Tuple3<String, String, String>, Stats> extracted = dataSet.map(new PairFunction<String, Tuple3<String, String, String>, Stats>() { @Override - public Tuple2<Tuple3<String, String, String>, Stats> call(String s) throws Exception { + public Tuple2<Tuple3<String, String, String>, Stats> call(String s) { return new Tuple2<Tuple3<String, String, String>, Stats>(extractKey(s), extractStats(s)); } }); JavaPairRDD<Tuple3<String, String, String>, Stats> counts = extracted.reduceByKey(new Function2<Stats, Stats, Stats>() { @Override - public Stats call(Stats stats, Stats stats2) throws Exception { + public Stats call(Stats stats, Stats stats2) { return stats.merge(stats2); } }); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java b/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java index 89aed8f279..a84245b0c7 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java @@ -28,6 +28,7 @@ import org.apache.spark.api.java.function.PairFunction; import java.util.List; import java.util.ArrayList; +import java.util.regex.Pattern; /** * Computes the PageRank of URLs from an input file. Input file should @@ -38,7 +39,9 @@ import java.util.ArrayList; * ... * where URL and their neighbors are separated by space(s). */ -public class JavaPageRank { +public final class JavaPageRank { + private static final Pattern SPACES = Pattern.compile("\\s+"); + private static class Sum extends Function2<Double, Double, Double> { @Override public Double call(Double a, Double b) { @@ -53,7 +56,7 @@ public class JavaPageRank { } JavaSparkContext ctx = new JavaSparkContext(args[0], "JavaPageRank", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaPageRank.class)); // Loads in input file. It should be in format of: // URL neighbor URL @@ -66,7 +69,7 @@ public class JavaPageRank { JavaPairRDD<String, List<String>> links = lines.map(new PairFunction<String, String, String>() { @Override public Tuple2<String, String> call(String s) { - String[] parts = s.split("\\s+"); + String[] parts = SPACES.split(s); return new Tuple2<String, String>(parts[0], parts[1]); } }).distinct().groupByKey().cache(); @@ -74,7 +77,7 @@ public class JavaPageRank { // Loads all URLs with other URL(s) link to from input file and initialize ranks of them to one. JavaPairRDD<String, Double> ranks = links.mapValues(new Function<List<String>, Double>() { @Override - public Double call(List<String> rs) throws Exception { + public Double call(List<String> rs) { return 1.0; } }); @@ -97,7 +100,7 @@ public class JavaPageRank { // Re-calculates URL ranks based on neighbor contributions. ranks = contribs.reduceByKey(new Sum()).mapValues(new Function<Double, Double>() { @Override - public Double call(Double sum) throws Exception { + public Double call(Double sum) { return 0.15 + sum * 0.85; } }); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaSparkPi.java b/examples/src/main/java/org/apache/spark/examples/JavaSparkPi.java index 4a2380caf5..3ec4a58d48 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaSparkPi.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaSparkPi.java @@ -26,8 +26,7 @@ import java.util.ArrayList; import java.util.List; /** Computes an approximation to pi */ -public class JavaSparkPi { - +public final class JavaSparkPi { public static void main(String[] args) throws Exception { if (args.length == 0) { @@ -36,26 +35,27 @@ public class JavaSparkPi { } JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaSparkPi.class)); int slices = (args.length == 2) ? Integer.parseInt(args[1]) : 2; int n = 100000 * slices; List<Integer> l = new ArrayList<Integer>(n); - for (int i = 0; i < n; i++) + for (int i = 0; i < n; i++) { l.add(i); + } JavaRDD<Integer> dataSet = jsc.parallelize(l, slices); int count = dataSet.map(new Function<Integer, Integer>() { @Override - public Integer call(Integer integer) throws Exception { + public Integer call(Integer integer) { double x = Math.random() * 2 - 1; double y = Math.random() * 2 - 1; return (x * x + y * y < 1) ? 1 : 0; } }).reduce(new Function2<Integer, Integer, Integer>() { @Override - public Integer call(Integer integer, Integer integer2) throws Exception { + public Integer call(Integer integer, Integer integer2) { return integer + integer2; } }); diff --git a/examples/src/main/java/org/apache/spark/examples/JavaTC.java b/examples/src/main/java/org/apache/spark/examples/JavaTC.java index 17f21f6b77..2ceb0fd94b 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaTC.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaTC.java @@ -31,11 +31,11 @@ import java.util.Set; /** * Transitive closure on a graph, implemented in Java. */ -public class JavaTC { +public final class JavaTC { - static int numEdges = 200; - static int numVertices = 100; - static Random rand = new Random(42); + private static final int numEdges = 200; + private static final int numVertices = 100; + private static final Random rand = new Random(42); static List<Tuple2<Integer, Integer>> generateGraph() { Set<Tuple2<Integer, Integer>> edges = new HashSet<Tuple2<Integer, Integer>>(numEdges); @@ -43,15 +43,18 @@ public class JavaTC { int from = rand.nextInt(numVertices); int to = rand.nextInt(numVertices); Tuple2<Integer, Integer> e = new Tuple2<Integer, Integer>(from, to); - if (from != to) edges.add(e); + if (from != to) { + edges.add(e); + } } return new ArrayList<Tuple2<Integer, Integer>>(edges); } static class ProjectFn extends PairFunction<Tuple2<Integer, Tuple2<Integer, Integer>>, Integer, Integer> { - static ProjectFn INSTANCE = new ProjectFn(); + static final ProjectFn INSTANCE = new ProjectFn(); + @Override public Tuple2<Integer, Integer> call(Tuple2<Integer, Tuple2<Integer, Integer>> triple) { return new Tuple2<Integer, Integer>(triple._2()._2(), triple._2()._1()); } @@ -64,7 +67,7 @@ public class JavaTC { } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaTC", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaTC.class)); Integer slices = (args.length > 1) ? Integer.parseInt(args[1]): 2; JavaPairRDD<Integer, Integer> tc = sc.parallelizePairs(generateGraph(), slices).cache(); @@ -76,6 +79,7 @@ public class JavaTC { // Because join() joins on keys, the edges are stored in reversed order. JavaPairRDD<Integer, Integer> edges = tc.map( new PairFunction<Tuple2<Integer, Integer>, Integer, Integer>() { + @Override public Tuple2<Integer, Integer> call(Tuple2<Integer, Integer> e) { return new Tuple2<Integer, Integer>(e._2(), e._1()); } diff --git a/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java b/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java index bd6383e13d..6651f98d56 100644 --- a/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java +++ b/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java @@ -27,8 +27,11 @@ import org.apache.spark.api.java.function.PairFunction; import java.util.Arrays; import java.util.List; +import java.util.regex.Pattern; + +public final class JavaWordCount { + private static final Pattern SPACE = Pattern.compile(" "); -public class JavaWordCount { public static void main(String[] args) throws Exception { if (args.length < 2) { System.err.println("Usage: JavaWordCount <master> <file>"); @@ -36,22 +39,25 @@ public class JavaWordCount { } JavaSparkContext ctx = new JavaSparkContext(args[0], "JavaWordCount", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaWordCount.class)); JavaRDD<String> lines = ctx.textFile(args[1], 1); JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() { + @Override public Iterable<String> call(String s) { - return Arrays.asList(s.split(" ")); + return Arrays.asList(SPACE.split(s)); } }); JavaPairRDD<String, Integer> ones = words.map(new PairFunction<String, String, Integer>() { + @Override public Tuple2<String, Integer> call(String s) { return new Tuple2<String, Integer>(s, 1); } }); JavaPairRDD<String, Integer> counts = ones.reduceByKey(new Function2<Integer, Integer, Integer>() { + @Override public Integer call(Integer i1, Integer i2) { return i1 + i2; } diff --git a/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java b/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java index 45a0d237da..435a86e62a 100644 --- a/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java +++ b/examples/src/main/java/org/apache/spark/mllib/examples/JavaALS.java @@ -26,28 +26,32 @@ import org.apache.spark.mllib.recommendation.MatrixFactorizationModel; import org.apache.spark.mllib.recommendation.Rating; import java.util.Arrays; -import java.util.StringTokenizer; +import java.util.regex.Pattern; import scala.Tuple2; /** * Example using MLLib ALS from Java. */ -public class JavaALS { +public final class JavaALS { static class ParseRating extends Function<String, Rating> { + private static final Pattern COMMA = Pattern.compile(","); + + @Override public Rating call(String line) { - StringTokenizer tok = new StringTokenizer(line, ","); - int x = Integer.parseInt(tok.nextToken()); - int y = Integer.parseInt(tok.nextToken()); - double rating = Double.parseDouble(tok.nextToken()); + String[] tok = COMMA.split(line); + int x = Integer.parseInt(tok[0]); + int y = Integer.parseInt(tok[1]); + double rating = Double.parseDouble(tok[2]); return new Rating(x, y, rating); } } static class FeaturesToString extends Function<Tuple2<Object, double[]>, String> { + @Override public String call(Tuple2<Object, double[]> element) { - return element._1().toString() + "," + Arrays.toString(element._2()); + return element._1() + "," + Arrays.toString(element._2()); } } @@ -68,7 +72,7 @@ public class JavaALS { } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaALS", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaALS.class)); JavaRDD<String> lines = sc.textFile(args[1]); JavaRDD<Rating> ratings = lines.map(new ParseRating()); diff --git a/examples/src/main/java/org/apache/spark/mllib/examples/JavaKMeans.java b/examples/src/main/java/org/apache/spark/mllib/examples/JavaKMeans.java index cd59a139b9..4b2658f257 100644 --- a/examples/src/main/java/org/apache/spark/mllib/examples/JavaKMeans.java +++ b/examples/src/main/java/org/apache/spark/mllib/examples/JavaKMeans.java @@ -25,20 +25,22 @@ import org.apache.spark.mllib.clustering.KMeans; import org.apache.spark.mllib.clustering.KMeansModel; import java.util.Arrays; -import java.util.StringTokenizer; +import java.util.regex.Pattern; /** * Example using MLLib KMeans from Java. */ -public class JavaKMeans { +public final class JavaKMeans { static class ParsePoint extends Function<String, double[]> { + private static final Pattern SPACE = Pattern.compile(" "); + + @Override public double[] call(String line) { - StringTokenizer tok = new StringTokenizer(line, " "); - int numTokens = tok.countTokens(); - double[] point = new double[numTokens]; - for (int i = 0; i < numTokens; ++i) { - point[i] = Double.parseDouble(tok.nextToken()); + String[] tok = SPACE.split(line); + double[] point = new double[tok.length]; + for (int i = 0; i < tok.length; ++i) { + point[i] = Double.parseDouble(tok[i]); } return point; } @@ -62,7 +64,7 @@ public class JavaKMeans { } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaKMeans", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaKMeans.class)); JavaRDD<String> lines = sc.textFile(args[1]); JavaRDD<double[]> points = lines.map(new ParsePoint()); diff --git a/examples/src/main/java/org/apache/spark/mllib/examples/JavaLR.java b/examples/src/main/java/org/apache/spark/mllib/examples/JavaLR.java index 258061c8e6..21586ce817 100644 --- a/examples/src/main/java/org/apache/spark/mllib/examples/JavaLR.java +++ b/examples/src/main/java/org/apache/spark/mllib/examples/JavaLR.java @@ -27,22 +27,25 @@ import org.apache.spark.mllib.classification.LogisticRegressionModel; import org.apache.spark.mllib.regression.LabeledPoint; import java.util.Arrays; -import java.util.StringTokenizer; +import java.util.regex.Pattern; /** * Logistic regression based classification using ML Lib. */ -public class JavaLR { +public final class JavaLR { static class ParsePoint extends Function<String, LabeledPoint> { + private static final Pattern COMMA = Pattern.compile(","); + private static final Pattern SPACE = Pattern.compile(" "); + + @Override public LabeledPoint call(String line) { - String[] parts = line.split(","); + String[] parts = COMMA.split(line); double y = Double.parseDouble(parts[0]); - StringTokenizer tok = new StringTokenizer(parts[1], " "); - int numTokens = tok.countTokens(); - double[] x = new double[numTokens]; - for (int i = 0; i < numTokens; ++i) { - x[i] = Double.parseDouble(tok.nextToken()); + String[] tok = SPACE.split(parts[1]); + double[] x = new double[tok.length]; + for (int i = 0; i < tok.length; ++i) { + x[i] = Double.parseDouble(tok[i]); } return new LabeledPoint(y, x); } @@ -59,7 +62,7 @@ public class JavaLR { } JavaSparkContext sc = new JavaSparkContext(args[0], "JavaLR", - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaLR.class)); JavaRDD<String> lines = sc.textFile(args[1]); JavaRDD<LabeledPoint> points = lines.map(new ParsePoint()).cache(); double stepSize = Double.parseDouble(args[2]); diff --git a/examples/src/main/java/org/apache/spark/streaming/examples/JavaFlumeEventCount.java b/examples/src/main/java/org/apache/spark/streaming/examples/JavaFlumeEventCount.java index 261813bf2f..b11cfa667e 100644 --- a/examples/src/main/java/org/apache/spark/streaming/examples/JavaFlumeEventCount.java +++ b/examples/src/main/java/org/apache/spark/streaming/examples/JavaFlumeEventCount.java @@ -20,7 +20,8 @@ package org.apache.spark.streaming.examples; import org.apache.spark.api.java.function.Function; import org.apache.spark.streaming.*; import org.apache.spark.streaming.api.java.*; -import org.apache.spark.streaming.dstream.SparkFlumeEvent; +import org.apache.spark.streaming.flume.FlumeUtils; +import org.apache.spark.streaming.flume.SparkFlumeEvent; /** * Produces a count of events received from Flume. @@ -36,7 +37,10 @@ import org.apache.spark.streaming.dstream.SparkFlumeEvent; * creates a server and listens for flume events. * <port> is the port the Flume receiver will listen on. */ -public class JavaFlumeEventCount { +public final class JavaFlumeEventCount { + private JavaFlumeEventCount() { + } + public static void main(String[] args) { if (args.length != 3) { System.err.println("Usage: JavaFlumeEventCount <master> <host> <port>"); @@ -49,10 +53,10 @@ public class JavaFlumeEventCount { Duration batchInterval = new Duration(2000); - JavaStreamingContext sc = new JavaStreamingContext(master, "FlumeEventCount", batchInterval, - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); - - JavaDStream<SparkFlumeEvent> flumeStream = sc.flumeStream("localhost", port); + JavaStreamingContext ssc = new JavaStreamingContext(master, "FlumeEventCount", batchInterval, + System.getenv("SPARK_HOME"), + JavaStreamingContext.jarOfClass(JavaFlumeEventCount.class)); + JavaDStream<SparkFlumeEvent> flumeStream = FlumeUtils.createStream(ssc, "localhost", port); flumeStream.count(); @@ -63,6 +67,6 @@ public class JavaFlumeEventCount { } }).print(); - sc.start(); + ssc.start(); } } diff --git a/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java b/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java index 22994fb2ec..16b8a948e6 100644 --- a/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java +++ b/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java @@ -19,6 +19,7 @@ package org.apache.spark.streaming.examples; import java.util.Map; import java.util.HashMap; +import java.util.regex.Pattern; import com.google.common.collect.Lists; import org.apache.spark.api.java.function.FlatMapFunction; @@ -29,6 +30,7 @@ import org.apache.spark.streaming.Duration; import org.apache.spark.streaming.api.java.JavaDStream; import org.apache.spark.streaming.api.java.JavaPairDStream; import org.apache.spark.streaming.api.java.JavaStreamingContext; +import org.apache.spark.streaming.kafka.KafkaUtils; import scala.Tuple2; /** @@ -41,11 +43,16 @@ import scala.Tuple2; * <numThreads> is the number of threads the kafka consumer should use * * Example: - * `./run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02, + * `./bin/run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02, * zoo03 my-consumer-group topic1,topic2 1` */ -public class JavaKafkaWordCount { +public final class JavaKafkaWordCount { + private static final Pattern SPACE = Pattern.compile(" "); + + private JavaKafkaWordCount() { + } + public static void main(String[] args) { if (args.length < 5) { System.err.println("Usage: KafkaWordCount <master> <zkQuorum> <group> <topics> <numThreads>"); @@ -53,8 +60,9 @@ public class JavaKafkaWordCount { } // Create the context with a 1 second batch size - JavaStreamingContext ssc = new JavaStreamingContext(args[0], "KafkaWordCount", - new Duration(2000), System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + JavaStreamingContext jssc = new JavaStreamingContext(args[0], "KafkaWordCount", + new Duration(2000), System.getenv("SPARK_HOME"), + JavaStreamingContext.jarOfClass(JavaKafkaWordCount.class)); int numThreads = Integer.parseInt(args[4]); Map<String, Integer> topicMap = new HashMap<String, Integer>(); @@ -63,11 +71,11 @@ public class JavaKafkaWordCount { topicMap.put(topic, numThreads); } - JavaPairDStream<String, String> messages = ssc.kafkaStream(args[1], args[2], topicMap); + JavaPairDStream<String, String> messages = KafkaUtils.createStream(jssc, args[1], args[2], topicMap); JavaDStream<String> lines = messages.map(new Function<Tuple2<String, String>, String>() { @Override - public String call(Tuple2<String, String> tuple2) throws Exception { + public String call(Tuple2<String, String> tuple2) { return tuple2._2(); } }); @@ -75,24 +83,24 @@ public class JavaKafkaWordCount { JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() { @Override public Iterable<String> call(String x) { - return Lists.newArrayList(x.split(" ")); + return Lists.newArrayList(SPACE.split(x)); } }); JavaPairDStream<String, Integer> wordCounts = words.map( new PairFunction<String, String, Integer>() { @Override - public Tuple2<String, Integer> call(String s) throws Exception { + public Tuple2<String, Integer> call(String s) { return new Tuple2<String, Integer>(s, 1); } }).reduceByKey(new Function2<Integer, Integer, Integer>() { @Override - public Integer call(Integer i1, Integer i2) throws Exception { + public Integer call(Integer i1, Integer i2) { return i1 + i2; } }); wordCounts.print(); - ssc.start(); + jssc.start(); } } diff --git a/examples/src/main/java/org/apache/spark/streaming/examples/JavaNetworkWordCount.java b/examples/src/main/java/org/apache/spark/streaming/examples/JavaNetworkWordCount.java index def87c199b..1e2efd359c 100644 --- a/examples/src/main/java/org/apache/spark/streaming/examples/JavaNetworkWordCount.java +++ b/examples/src/main/java/org/apache/spark/streaming/examples/JavaNetworkWordCount.java @@ -27,6 +27,8 @@ import org.apache.spark.streaming.api.java.JavaDStream; import org.apache.spark.streaming.api.java.JavaPairDStream; import org.apache.spark.streaming.api.java.JavaStreamingContext; +import java.util.regex.Pattern; + /** * Counts words in UTF8 encoded, '\n' delimited text received from the network every second. * Usage: NetworkWordCount <master> <hostname> <port> @@ -38,7 +40,12 @@ import org.apache.spark.streaming.api.java.JavaStreamingContext; * and then run the example * `$ ./run spark.streaming.examples.JavaNetworkWordCount local[2] localhost 9999` */ -public class JavaNetworkWordCount { +public final class JavaNetworkWordCount { + private static final Pattern SPACE = Pattern.compile(" "); + + private JavaNetworkWordCount() { + } + public static void main(String[] args) { if (args.length < 3) { System.err.println("Usage: NetworkWordCount <master> <hostname> <port>\n" + @@ -48,7 +55,8 @@ public class JavaNetworkWordCount { // Create the context with a 1 second batch size JavaStreamingContext ssc = new JavaStreamingContext(args[0], "NetworkWordCount", - new Duration(1000), System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + new Duration(1000), System.getenv("SPARK_HOME"), + JavaStreamingContext.jarOfClass(JavaNetworkWordCount.class)); // Create a NetworkInputDStream on target ip:port and count the // words in input stream of \n delimited test (eg. generated by 'nc') @@ -56,18 +64,18 @@ public class JavaNetworkWordCount { JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() { @Override public Iterable<String> call(String x) { - return Lists.newArrayList(x.split(" ")); + return Lists.newArrayList(SPACE.split(x)); } }); JavaPairDStream<String, Integer> wordCounts = words.map( new PairFunction<String, String, Integer>() { @Override - public Tuple2<String, Integer> call(String s) throws Exception { + public Tuple2<String, Integer> call(String s) { return new Tuple2<String, Integer>(s, 1); } }).reduceByKey(new Function2<Integer, Integer, Integer>() { @Override - public Integer call(Integer i1, Integer i2) throws Exception { + public Integer call(Integer i1, Integer i2) { return i1 + i2; } }); diff --git a/examples/src/main/java/org/apache/spark/streaming/examples/JavaQueueStream.java b/examples/src/main/java/org/apache/spark/streaming/examples/JavaQueueStream.java index c8c7389dd1..e05551ab83 100644 --- a/examples/src/main/java/org/apache/spark/streaming/examples/JavaQueueStream.java +++ b/examples/src/main/java/org/apache/spark/streaming/examples/JavaQueueStream.java @@ -31,8 +31,11 @@ import java.util.LinkedList; import java.util.List; import java.util.Queue; -public class JavaQueueStream { - public static void main(String[] args) throws InterruptedException { +public final class JavaQueueStream { + private JavaQueueStream() { + } + + public static void main(String[] args) throws Exception { if (args.length < 1) { System.err.println("Usage: JavaQueueStream <master>"); System.exit(1); @@ -40,7 +43,7 @@ public class JavaQueueStream { // Create the context JavaStreamingContext ssc = new JavaStreamingContext(args[0], "QueueStream", new Duration(1000), - System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + System.getenv("SPARK_HOME"), JavaStreamingContext.jarOfClass(JavaQueueStream.class)); // Create the queue through which RDDs can be pushed to // a QueueInputDStream @@ -62,14 +65,14 @@ public class JavaQueueStream { JavaPairDStream<Integer, Integer> mappedStream = inputStream.map( new PairFunction<Integer, Integer, Integer>() { @Override - public Tuple2<Integer, Integer> call(Integer i) throws Exception { + public Tuple2<Integer, Integer> call(Integer i) { return new Tuple2<Integer, Integer>(i % 10, 1); } }); JavaPairDStream<Integer, Integer> reducedStream = mappedStream.reduceByKey( new Function2<Integer, Integer, Integer>() { @Override - public Integer call(Integer i1, Integer i2) throws Exception { + public Integer call(Integer i1, Integer i2) { return i1 + i2; } }); diff --git a/examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala b/examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala index a119980992..0097dade19 100644 --- a/examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala @@ -33,7 +33,7 @@ object BroadcastTest { System.setProperty("spark.broadcast.blockSize", blockSize) val sc = new SparkContext(args(0), "Broadcast Test", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val slices = if (args.length > 1) args(1).toInt else 2 val num = if (args.length > 2) args(2).toInt else 1000000 diff --git a/examples/src/main/scala/org/apache/spark/examples/DriverSubmissionTest.scala b/examples/src/main/scala/org/apache/spark/examples/DriverSubmissionTest.scala new file mode 100644 index 0000000000..65251e9319 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/DriverSubmissionTest.scala @@ -0,0 +1,46 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.examples + +import scala.collection.JavaConversions._ + +/** Prints out environmental information, sleeps, and then exits. Made to + * test driver submission in the standalone scheduler. */ +object DriverSubmissionTest { + def main(args: Array[String]) { + if (args.size < 1) { + println("Usage: DriverSubmissionTest <seconds-to-sleep>") + System.exit(0) + } + val numSecondsToSleep = args(0).toInt + + val env = System.getenv() + val properties = System.getProperties() + + println("Environment variables containing SPARK_TEST:") + env.filter{case (k, v) => k.contains("SPARK_TEST")}.foreach(println) + + println("System properties containing spark.test:") + properties.filter{case (k, v) => k.toString.contains("spark.test")}.foreach(println) + + for (i <- 1 until numSecondsToSleep) { + println(s"Alive for $i out of $numSecondsToSleep seconds") + Thread.sleep(1000) + } + } +} diff --git a/examples/src/main/scala/org/apache/spark/examples/ExceptionHandlingTest.scala b/examples/src/main/scala/org/apache/spark/examples/ExceptionHandlingTest.scala index 92eb96bd8e..b3eb611dd2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ExceptionHandlingTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ExceptionHandlingTest.scala @@ -27,7 +27,7 @@ object ExceptionHandlingTest { } val sc = new SparkContext(args(0), "ExceptionHandlingTest", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) sc.parallelize(0 until sc.defaultParallelism).foreach { i => if (math.random > 0.75) throw new Exception("Testing exception handling") diff --git a/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala b/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala index 42c2e0e8e1..39752fdd0e 100644 --- a/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala @@ -34,7 +34,7 @@ object GroupByTest { var numReducers = if (args.length > 4) args(4).toInt else numMappers val sc = new SparkContext(args(0), "GroupBy Test", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random diff --git a/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala b/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala index efe2e93b0d..65d67356be 100644 --- a/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala @@ -26,7 +26,7 @@ import org.apache.hadoop.hbase.mapreduce.TableInputFormat object HBaseTest { def main(args: Array[String]) { val sc = new SparkContext(args(0), "HBaseTest", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val conf = HBaseConfiguration.create() diff --git a/examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala b/examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala index d6a88d3032..c3597d94a2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala @@ -22,7 +22,7 @@ import org.apache.spark._ object HdfsTest { def main(args: Array[String]) { val sc = new SparkContext(args(0), "HdfsTest", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val file = sc.textFile(args(1)) val mapped = file.map(s => s.length).cache() for (iter <- 1 to 10) { diff --git a/examples/src/main/scala/org/apache/spark/examples/LogQuery.scala b/examples/src/main/scala/org/apache/spark/examples/LogQuery.scala index 17ff3ce764..bddb54b39c 100644 --- a/examples/src/main/scala/org/apache/spark/examples/LogQuery.scala +++ b/examples/src/main/scala/org/apache/spark/examples/LogQuery.scala @@ -45,7 +45,7 @@ object LogQuery { } val sc = new SparkContext(args(0), "Log Query", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val dataSet = if (args.length == 2) sc.textFile(args(1)) diff --git a/examples/src/main/scala/org/apache/spark/examples/MultiBroadcastTest.scala b/examples/src/main/scala/org/apache/spark/examples/MultiBroadcastTest.scala index e1afc29f9a..4aef04fc06 100644 --- a/examples/src/main/scala/org/apache/spark/examples/MultiBroadcastTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/MultiBroadcastTest.scala @@ -28,7 +28,7 @@ object MultiBroadcastTest { } val sc = new SparkContext(args(0), "Multi-Broadcast Test", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val slices = if (args.length > 1) args(1).toInt else 2 val num = if (args.length > 2) args(2).toInt else 1000000 diff --git a/examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala b/examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala index 37ddfb5db7..73b0e216ca 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala @@ -36,7 +36,7 @@ object SimpleSkewedGroupByTest { var ratio = if (args.length > 5) args(5).toInt else 5.0 val sc = new SparkContext(args(0), "GroupBy Test", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random diff --git a/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala b/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala index 9c954b2b5b..31c6d108f3 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala @@ -34,7 +34,7 @@ object SkewedGroupByTest { var numReducers = if (args.length > 4) args(4).toInt else numMappers val sc = new SparkContext(args(0), "GroupBy Test", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala b/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala index 814944ba1c..30c86d83e6 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala @@ -112,7 +112,7 @@ object SparkALS { printf("Running with M=%d, U=%d, F=%d, iters=%d\n", M, U, F, ITERATIONS) val sc = new SparkContext(host, "SparkALS", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val R = generateR() diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala index 86dd9ca1b3..ff72532db1 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala @@ -54,7 +54,7 @@ object SparkHdfsLR { val inputPath = args(1) val conf = SparkHadoopUtil.get.newConfiguration() val sc = new SparkContext(args(0), "SparkHdfsLR", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")), Map(), + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass), Map(), InputFormatInfo.computePreferredLocations( Seq(new InputFormatInfo(conf, classOf[org.apache.hadoop.mapred.TextInputFormat], inputPath)))) val lines = sc.textFile(inputPath) diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala b/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala index bc2db39c12..8c99025eaa 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala @@ -55,7 +55,7 @@ object SparkKMeans { System.exit(1) } val sc = new SparkContext(args(0), "SparkLocalKMeans", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val lines = sc.textFile(args(1)) val data = lines.map(parseVector _).cache() val K = args(2).toInt diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala index 9ed9fe4d76..c54a55bdb4 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala @@ -49,7 +49,7 @@ object SparkLR { System.exit(1) } val sc = new SparkContext(args(0), "SparkLR", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val numSlices = if (args.length > 1) args(1).toInt else 2 val points = sc.parallelize(generateData, numSlices).cache() diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkPageRank.scala b/examples/src/main/scala/org/apache/spark/examples/SparkPageRank.scala index a508c0df57..d203f4d20e 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkPageRank.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkPageRank.scala @@ -38,7 +38,7 @@ object SparkPageRank { } var iters = args(2).toInt val ctx = new SparkContext(args(0), "PageRank", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val lines = ctx.textFile(args(1), 1) val links = lines.map{ s => val parts = s.split("\\s+") diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkPi.scala b/examples/src/main/scala/org/apache/spark/examples/SparkPi.scala index a689e5a360..e5a09ecec0 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkPi.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkPi.scala @@ -29,7 +29,7 @@ object SparkPi { System.exit(1) } val spark = new SparkContext(args(0), "SparkPi", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val slices = if (args.length > 1) args(1).toInt else 2 val n = 100000 * slices val count = spark.parallelize(1 to n, slices).map { i => diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkTC.scala b/examples/src/main/scala/org/apache/spark/examples/SparkTC.scala index 8543ce0e32..24e8afa26b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SparkTC.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SparkTC.scala @@ -46,7 +46,7 @@ object SparkTC { System.exit(1) } val spark = new SparkContext(args(0), "SparkTC", - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass)) val slices = if (args.length > 1) args(1).toInt else 2 var tc = spark.parallelize(generateGraph, slices).cache() diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala index 2402409e6e..4e0058cd70 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala @@ -134,9 +134,9 @@ object FeederActor { * <hostname> and <port> describe the AkkaSystem that Spark Sample feeder is running on. * * To run this example locally, you may run Feeder Actor as - * `$ ./run-example spark.streaming.examples.FeederActor 127.0.1.1 9999` + * `$ ./bin/run-example org.apache.spark.streaming.examples.FeederActor 127.0.1.1 9999` * and then run the example - * `$ ./run-example spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999` + * `$ ./bin/run-example org.apache.spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999` */ object ActorWordCount { def main(args: Array[String]) { @@ -151,7 +151,7 @@ object ActorWordCount { // Create the context and set the batch size val ssc = new StreamingContext(master, "ActorWordCount", Seconds(2), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) /* * Following is the use of actorStream to plug in custom actor as receiver diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/FlumeEventCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/FlumeEventCount.scala index 9f6e163454..ae3709b3d9 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/FlumeEventCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/FlumeEventCount.scala @@ -20,6 +20,7 @@ package org.apache.spark.streaming.examples import org.apache.spark.util.IntParam import org.apache.spark.storage.StorageLevel import org.apache.spark.streaming._ +import org.apache.spark.streaming.flume._ /** * Produces a count of events received from Flume. @@ -48,10 +49,10 @@ object FlumeEventCount { val batchInterval = Milliseconds(2000) // Create the context and set the batch size val ssc = new StreamingContext(master, "FlumeEventCount", batchInterval, - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Create a flume stream - val stream = ssc.flumeStream(host,port,StorageLevel.MEMORY_ONLY) + val stream = FlumeUtils.createStream(ssc, host,port,StorageLevel.MEMORY_ONLY_SER_2) // Print out the count of events received from this server in each batch stream.count().map(cnt => "Received " + cnt + " flume events." ).print() diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala index bc8564b3ba..ea6ea67419 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala @@ -28,7 +28,7 @@ import org.apache.spark.streaming.StreamingContext._ * <directory> is the directory that Spark Streaming will use to find and read new text files. * * To run this on your local machine on directory `localdir`, run this example - * `$ ./run-example spark.streaming.examples.HdfsWordCount local[2] localdir` + * `$ ./bin/run-example org.apache.spark.streaming.examples.HdfsWordCount local[2] localdir` * Then create a text file in `localdir` and the words in the file will get counted. */ object HdfsWordCount { @@ -40,7 +40,7 @@ object HdfsWordCount { // Create the context val ssc = new StreamingContext(args(0), "HdfsWordCount", Seconds(2), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Create the FileInputDStream on the directory and use the // stream to count words in new files created diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala index 570ba4c81a..31a94bd224 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala @@ -24,6 +24,7 @@ import kafka.producer._ import org.apache.spark.streaming._ import org.apache.spark.streaming.StreamingContext._ import org.apache.spark.streaming.util.RawTextHelper._ +import org.apache.spark.streaming.kafka._ /** * Consumes messages from one or more topics in Kafka and does wordcount. @@ -35,7 +36,7 @@ import org.apache.spark.streaming.util.RawTextHelper._ * <numThreads> is the number of threads the kafka consumer should use * * Example: - * `./run-example spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1` + * `./bin/run-example org.apache.spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1` */ object KafkaWordCount { def main(args: Array[String]) { @@ -48,11 +49,11 @@ object KafkaWordCount { val Array(master, zkQuorum, group, topics, numThreads) = args val ssc = new StreamingContext(master, "KafkaWordCount", Seconds(2), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) ssc.checkpoint("checkpoint") val topicpMap = topics.split(",").map((_,numThreads.toInt)).toMap - val lines = ssc.kafkaStream(zkQuorum, group, topicpMap).map(_._2) + val lines = KafkaUtils.createStream(ssc, zkQuorum, group, topicpMap).map(_._2) val words = lines.flatMap(_.split(" ")) val wordCounts = words.map(x => (x, 1l)) .reduceByKeyAndWindow(add _, subtract _, Minutes(10), Seconds(2), 2) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala index ff332a0282..325290b66f 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala @@ -17,11 +17,6 @@ package org.apache.spark.streaming.examples -import org.apache.spark.streaming.{ Seconds, StreamingContext } -import org.apache.spark.streaming.StreamingContext._ -import org.apache.spark.streaming.dstream.MQTTReceiver -import org.apache.spark.storage.StorageLevel - import org.eclipse.paho.client.mqttv3.MqttClient import org.eclipse.paho.client.mqttv3.MqttClientPersistence import org.eclipse.paho.client.mqttv3.persist.MqttDefaultFilePersistence @@ -29,6 +24,11 @@ import org.eclipse.paho.client.mqttv3.MqttException import org.eclipse.paho.client.mqttv3.MqttMessage import org.eclipse.paho.client.mqttv3.MqttTopic +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{Seconds, StreamingContext} +import org.apache.spark.streaming.StreamingContext._ +import org.apache.spark.streaming.mqtt._ + /** * A simple Mqtt publisher for demonstration purposes, repeatedly publishes * Space separated String Message "hello mqtt demo for spark streaming" @@ -79,9 +79,9 @@ object MQTTPublisher { * <MqttbrokerUrl> and <topic> describe where Mqtt publisher is running. * * To run this example locally, you may run publisher as - * `$ ./run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo` + * `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo` * and run the example as - * `$ ./run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo` + * `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo` */ object MQTTWordCount { @@ -96,8 +96,8 @@ object MQTTWordCount { val Seq(master, brokerUrl, topic) = args.toSeq val ssc = new StreamingContext(master, "MqttWordCount", Seconds(2), System.getenv("SPARK_HOME"), - Seq(System.getenv("SPARK_EXAMPLES_JAR"))) - val lines = ssc.mqttStream(brokerUrl, topic, StorageLevel.MEMORY_ONLY) + StreamingContext.jarOfClass(this.getClass)) + val lines = MQTTUtils.createStream(ssc, brokerUrl, topic, StorageLevel.MEMORY_ONLY_SER_2) val words = lines.flatMap(x => x.toString.split(" ")) val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala index e2487dca5f..6a32c75373 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala @@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._ * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./run-example spark.streaming.examples.NetworkWordCount local[2] localhost 9999` + * `$ ./bin/run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999` */ object NetworkWordCount { def main(args: Array[String]) { @@ -41,7 +41,7 @@ object NetworkWordCount { // Create the context with a 1 second batch size val ssc = new StreamingContext(args(0), "NetworkWordCount", Seconds(1), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Create a NetworkInputDStream on target ip:port and count the // words in input stream of \n delimited test (eg. generated by 'nc') diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/QueueStream.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/QueueStream.scala index fad512eeba..9d640e716b 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/QueueStream.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/QueueStream.scala @@ -33,7 +33,7 @@ object QueueStream { // Create the context val ssc = new StreamingContext(args(0), "QueueStream", Seconds(1), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Create the queue through which RDDs can be pushed to // a QueueInputDStream diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/RawNetworkGrep.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/RawNetworkGrep.scala index 0b45c30d20..c0706d0724 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/RawNetworkGrep.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/RawNetworkGrep.scala @@ -49,7 +49,7 @@ object RawNetworkGrep { // Create the context val ssc = new StreamingContext(master, "RawNetworkGrep", Milliseconds(batchMillis), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Warm up the JVMs on master and slave for JIT compilation to kick in RawTextHelper.warmUp(ssc.sparkContext) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala index cb30c4edb3..002db57d59 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala @@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._ * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./run-example spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999` + * `$ ./bin/run-example org.apache.spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999` */ object StatefulNetworkWordCount { def main(args: Array[String]) { @@ -49,7 +49,7 @@ object StatefulNetworkWordCount { // Create the context with a 1 second batch size val ssc = new StreamingContext(args(0), "NetworkWordCumulativeCountUpdateStateByKey", Seconds(1), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) ssc.checkpoint(".") // Create a NetworkInputDStream on target ip:port and count the diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdCMS.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdCMS.scala index 35b6329ab3..3ccdc908e2 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdCMS.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdCMS.scala @@ -23,6 +23,8 @@ import com.twitter.algebird._ import org.apache.spark.streaming.StreamingContext._ import org.apache.spark.SparkContext._ +import org.apache.spark.streaming.twitter._ + /** * Illustrates the use of the Count-Min Sketch, from Twitter's Algebird library, to compute * windowed and global Top-K estimates of user IDs occurring in a Twitter stream. @@ -33,7 +35,7 @@ import org.apache.spark.SparkContext._ * <p> * <p> * <a href="http://highlyscalable.wordpress.com/2012/05/01/probabilistic-structures-web-analytics-data-mining/"> - * This blog post</a> has a good overview of the Count-Min Sketch (CMS). The CMS is a datastructure + * This blog post</a> has a good overview of the Count-Min Sketch (CMS). The CMS is a data structure * for approximate frequency estimation in data streams (e.g. Top-K elements, frequency of any given element, etc), * that uses space sub-linear in the number of elements in the stream. Once elements are added to the CMS, the * estimated count of an element can be computed, as well as "heavy-hitters" that occur more than a threshold @@ -60,8 +62,8 @@ object TwitterAlgebirdCMS { val (master, filters) = (args.head, args.tail) val ssc = new StreamingContext(master, "TwitterAlgebirdCMS", Seconds(10), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) - val stream = ssc.twitterStream(None, filters, StorageLevel.MEMORY_ONLY_SER) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) + val stream = TwitterUtils.createStream(ssc, None, filters, StorageLevel.MEMORY_ONLY_SER_2) val users = stream.map(status => status.getUser.getId) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdHLL.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdHLL.scala index 8bfde2a829..c7e83e76b0 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdHLL.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterAlgebirdHLL.scala @@ -21,7 +21,7 @@ import org.apache.spark.streaming.{Seconds, StreamingContext} import org.apache.spark.storage.StorageLevel import com.twitter.algebird.HyperLogLog._ import com.twitter.algebird.HyperLogLogMonoid -import org.apache.spark.streaming.dstream.TwitterInputDStream +import org.apache.spark.streaming.twitter._ /** * Illustrates the use of the HyperLogLog algorithm, from Twitter's Algebird library, to compute @@ -49,8 +49,8 @@ object TwitterAlgebirdHLL { val (master, filters) = (args.head, args.tail) val ssc = new StreamingContext(master, "TwitterAlgebirdHLL", Seconds(5), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) - val stream = ssc.twitterStream(None, filters, StorageLevel.MEMORY_ONLY_SER) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) + val stream = TwitterUtils.createStream(ssc, None, filters, StorageLevel.MEMORY_ONLY_SER) val users = stream.map(status => status.getUser.getId) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterPopularTags.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterPopularTags.scala index 27aa6b14bf..e2b0418d55 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterPopularTags.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/TwitterPopularTags.scala @@ -20,6 +20,7 @@ package org.apache.spark.streaming.examples import org.apache.spark.streaming.{Seconds, StreamingContext} import StreamingContext._ import org.apache.spark.SparkContext._ +import org.apache.spark.streaming.twitter._ /** * Calculates popular hashtags (topics) over sliding 10 and 60 second windows from a Twitter @@ -38,8 +39,8 @@ object TwitterPopularTags { val (master, filters) = (args.head, args.tail) val ssc = new StreamingContext(master, "TwitterPopularTags", Seconds(2), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) - val stream = ssc.twitterStream(None, filters) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) + val stream = TwitterUtils.createStream(ssc, None, filters) val hashTags = stream.flatMap(status => status.getText.split(" ").filter(_.startsWith("#"))) diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala index e83ce78aa5..03902ec353 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala @@ -20,11 +20,13 @@ package org.apache.spark.streaming.examples import akka.actor.ActorSystem import akka.actor.actorRef2Scala import akka.zeromq._ -import org.apache.spark.streaming.{ Seconds, StreamingContext } -import org.apache.spark.streaming.StreamingContext._ import akka.zeromq.Subscribe import akka.util.ByteString +import org.apache.spark.streaming.{Seconds, StreamingContext} +import org.apache.spark.streaming.StreamingContext._ +import org.apache.spark.streaming.zeromq._ + /** * A simple publisher for demonstration purposes, repeatedly publishes random Messages * every one second. @@ -62,9 +64,9 @@ object SimpleZeroMQPublisher { * <zeroMQurl> and <topic> describe where zeroMq publisher is running. * * To run this example locally, you may run publisher as - * `$ ./run-example spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar` + * `$ ./bin/run-example org.apache.spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar` * and run the example as - * `$ ./run-example spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo` + * `$ ./bin/run-example org.apache.spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo` */ object ZeroMQWordCount { def main(args: Array[String]) { @@ -78,16 +80,15 @@ object ZeroMQWordCount { // Create the context and set the batch size val ssc = new StreamingContext(master, "ZeroMQWordCount", Seconds(2), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) def bytesToStringIterator(x: Seq[ByteString]) = (x.map(_.utf8String)).iterator //For this stream, a zeroMQ publisher should be running. - val lines = ssc.zeroMQStream(url, Subscribe(topic), bytesToStringIterator) + val lines = ZeroMQUtils.createStream(ssc, url, Subscribe(topic), bytesToStringIterator _) val words = lines.flatMap(_.split(" ")) val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _) wordCounts.print() ssc.start() } - } diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala index de70c50473..4fe57de4a4 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala @@ -39,8 +39,8 @@ object PageView extends Serializable { /** Generates streaming events to simulate page views on a website. * * This should be used in tandem with PageViewStream.scala. Example: - * $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10 - * $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444 + * $ ./bin/run-example org.apache.spark.streaming.examples.clickstream.PageViewGenerator 44444 10 + * $ ./bin/run-example org.apache.spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444 * * When running this, you may want to set the root logging level to ERROR in * conf/log4j.properties to reduce the verbosity of the output. diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala index 8282cc9269..807af199f4 100644 --- a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala +++ b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala @@ -25,8 +25,8 @@ import org.apache.spark.SparkContext._ * operators available in Spark streaming. * * This should be used in tandem with PageViewStream.scala. Example: - * $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10 - * $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444 + * $ ./bin/run-example org.apache.spark.streaming.examples.clickstream.PageViewGenerator 44444 10 + * $ ./bin/run-example org.apache.spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444 */ object PageViewStream { def main(args: Array[String]) { @@ -42,7 +42,7 @@ object PageViewStream { // Create the context val ssc = new StreamingContext("local[2]", "PageViewStream", Seconds(1), - System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass)) // Create a NetworkInputDStream on target host:port and convert each line to a PageView val pageViews = ssc.socketTextStream(host, port) diff --git a/external/flume/pom.xml b/external/flume/pom.xml new file mode 100644 index 0000000000..443910a03a --- /dev/null +++ b/external/flume/pom.xml @@ -0,0 +1,93 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-flume_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project External Flume</name> + <url>http://spark.incubator.apache.org/</url> + + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <type>test-jar</type> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.apache.flume</groupId> + <artifactId>flume-ng-sdk</artifactId> + <version>1.2.0</version> + <exclusions> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + <exclusion> + <groupId>org.xerial.snappy</groupId> + <artifactId>*</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.scalatest</groupId> + <artifactId>scalatest_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.scalacheck</groupId> + <artifactId>scalacheck_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.novocode</groupId> + <artifactId>junit-interface</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <scope>test</scope> + </dependency> + </dependencies> + <build> + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.scalatest</groupId> + <artifactId>scalatest-maven-plugin</artifactId> + </plugin> + </plugins> + </build> +</project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlumeInputDStream.scala b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeInputDStream.scala index 60d79175f1..ce3ef47cfe 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FlumeInputDStream.scala +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeInputDStream.scala @@ -15,7 +15,7 @@ * limitations under the License. */ -package org.apache.spark.streaming.dstream +package org.apache.spark.streaming.flume import java.net.InetSocketAddress import java.io.{ObjectInput, ObjectOutput, Externalizable} @@ -30,9 +30,10 @@ import org.apache.flume.source.avro.Status import org.apache.avro.ipc.specific.SpecificResponder import org.apache.avro.ipc.NettyServer -import org.apache.spark.streaming.StreamingContext import org.apache.spark.util.Utils import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.StreamingContext +import org.apache.spark.streaming.dstream._ private[streaming] class FlumeInputDStream[T: ClassTag]( diff --git a/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala new file mode 100644 index 0000000000..834b775d4f --- /dev/null +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala @@ -0,0 +1,70 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.flume + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{StreamingContext, DStream} +import org.apache.spark.streaming.api.java.{JavaStreamingContext, JavaDStream} + +object FlumeUtils { + /** + * Create a input stream from a Flume source. + * @param ssc StreamingContext object + * @param hostname Hostname of the slave machine to which the flume data will be sent + * @param port Port of the slave machine to which the flume data will be sent + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream ( + ssc: StreamingContext, + hostname: String, + port: Int, + storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 + ): DStream[SparkFlumeEvent] = { + val inputStream = new FlumeInputDStream[SparkFlumeEvent](ssc, hostname, port, storageLevel) + ssc.registerInputStream(inputStream) + inputStream + } + + /** + * Creates a input stream from a Flume source. + * @param hostname Hostname of the slave machine to which the flume data will be sent + * @param port Port of the slave machine to which the flume data will be sent + */ + def createStream( + jssc: JavaStreamingContext, + hostname: String, + port: Int + ): JavaDStream[SparkFlumeEvent] = { + createStream(jssc.ssc, hostname, port) + } + + /** + * Creates a input stream from a Flume source. + * @param hostname Hostname of the slave machine to which the flume data will be sent + * @param port Port of the slave machine to which the flume data will be sent + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream( + jssc: JavaStreamingContext, + hostname: String, + port: Int, + storageLevel: StorageLevel + ): JavaDStream[SparkFlumeEvent] = { + createStream(jssc.ssc, hostname, port, storageLevel) + } +} diff --git a/external/flume/src/test/java/org/apache/spark/streaming/flume/JavaFlumeStreamSuite.java b/external/flume/src/test/java/org/apache/spark/streaming/flume/JavaFlumeStreamSuite.java new file mode 100644 index 0000000000..733389b98d --- /dev/null +++ b/external/flume/src/test/java/org/apache/spark/streaming/flume/JavaFlumeStreamSuite.java @@ -0,0 +1,34 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.flume; + +import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.LocalJavaStreamingContext; +import org.apache.spark.streaming.api.java.JavaDStream; + +import org.junit.Test; + +public class JavaFlumeStreamSuite extends LocalJavaStreamingContext { + @Test + public void testFlumeStream() { + // tests the API, does not actually test data receiving + JavaDStream<SparkFlumeEvent> test1 = FlumeUtils.createStream(ssc, "localhost", 12345); + JavaDStream<SparkFlumeEvent> test2 = FlumeUtils.createStream(ssc, "localhost", 12345, + StorageLevel.MEMORY_AND_DISK_SER_2()); + } +} diff --git a/external/flume/src/test/resources/log4j.properties b/external/flume/src/test/resources/log4j.properties new file mode 100644 index 0000000000..063529a9cb --- /dev/null +++ b/external/flume/src/test/resources/log4j.properties @@ -0,0 +1,29 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# Set everything to be logged to the file streaming/target/unit-tests.log +log4j.rootCategory=INFO, file +# log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false +log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN + diff --git a/external/flume/src/test/scala/org/apache/spark/streaming/flume/FlumeStreamSuite.scala b/external/flume/src/test/scala/org/apache/spark/streaming/flume/FlumeStreamSuite.scala new file mode 100644 index 0000000000..2e8e9fac45 --- /dev/null +++ b/external/flume/src/test/scala/org/apache/spark/streaming/flume/FlumeStreamSuite.scala @@ -0,0 +1,86 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.flume + +import scala.collection.JavaConversions._ +import scala.collection.mutable.{ArrayBuffer, SynchronizedBuffer} + +import java.net.InetSocketAddress +import java.nio.ByteBuffer +import java.nio.charset.Charset + +import org.apache.avro.ipc.NettyTransceiver +import org.apache.avro.ipc.specific.SpecificRequestor +import org.apache.flume.source.avro.{AvroFlumeEvent, AvroSourceProtocol} + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{TestOutputStream, StreamingContext, TestSuiteBase} +import org.apache.spark.streaming.util.ManualClock + +class FlumeStreamSuite extends TestSuiteBase { + + val testPort = 9999 + + test("flume input stream") { + // Set up the streaming context and input streams + val ssc = new StreamingContext(conf, batchDuration) + val flumeStream = FlumeUtils.createStream(ssc, "localhost", testPort, StorageLevel.MEMORY_AND_DISK) + val outputBuffer = new ArrayBuffer[Seq[SparkFlumeEvent]] + with SynchronizedBuffer[Seq[SparkFlumeEvent]] + val outputStream = new TestOutputStream(flumeStream, outputBuffer) + ssc.registerOutputStream(outputStream) + ssc.start() + + val clock = ssc.scheduler.clock.asInstanceOf[ManualClock] + val input = Seq(1, 2, 3, 4, 5) + Thread.sleep(1000) + val transceiver = new NettyTransceiver(new InetSocketAddress("localhost", testPort)) + val client = SpecificRequestor.getClient( + classOf[AvroSourceProtocol], transceiver) + + for (i <- 0 until input.size) { + val event = new AvroFlumeEvent + event.setBody(ByteBuffer.wrap(input(i).toString.getBytes())) + event.setHeaders(Map[CharSequence, CharSequence]("test" -> "header")) + client.append(event) + Thread.sleep(500) + clock.addToTime(batchDuration.milliseconds) + } + + val startTime = System.currentTimeMillis() + while (outputBuffer.size < input.size && System.currentTimeMillis() - startTime < maxWaitTimeMillis) { + logInfo("output.size = " + outputBuffer.size + ", input.size = " + input.size) + Thread.sleep(100) + } + Thread.sleep(1000) + val timeTaken = System.currentTimeMillis() - startTime + assert(timeTaken < maxWaitTimeMillis, "Operation timed out after " + timeTaken + " ms") + logInfo("Stopping context") + ssc.stop() + + val decoder = Charset.forName("UTF-8").newDecoder() + + assert(outputBuffer.size === input.length) + for (i <- 0 until outputBuffer.size) { + assert(outputBuffer(i).size === 1) + val str = decoder.decode(outputBuffer(i).head.event.getBody) + assert(str.toString === input(i).toString) + assert(outputBuffer(i).head.event.getHeaders.get("test") === "header") + } + } +} diff --git a/external/kafka/pom.xml b/external/kafka/pom.xml new file mode 100644 index 0000000000..f782e0e126 --- /dev/null +++ b/external/kafka/pom.xml @@ -0,0 +1,97 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-kafka_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project External Kafka</name> + <url>http://spark.incubator.apache.org/</url> + + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <type>test-jar</type> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.sksamuel.kafka</groupId> + <artifactId>kafka_${scala.binary.version}</artifactId> + <version>0.8.0-beta1</version> + <exclusions> + <exclusion> + <groupId>com.sun.jmx</groupId> + <artifactId>jmxri</artifactId> + </exclusion> + <exclusion> + <groupId>com.sun.jdmk</groupId> + <artifactId>jmxtools</artifactId> + </exclusion> + <exclusion> + <groupId>net.sf.jopt-simple</groupId> + <artifactId>jopt-simple</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.scalatest</groupId> + <artifactId>scalatest_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.scalacheck</groupId> + <artifactId>scalacheck_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.novocode</groupId> + <artifactId>junit-interface</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <scope>test</scope> + </dependency> + </dependencies> + <build> + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.scalatest</groupId> + <artifactId>scalatest-maven-plugin</artifactId> + </plugin> + </plugins> + </build> +</project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/KafkaInputDStream.scala b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaInputDStream.scala index 526f5564c7..a2cd49c573 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/KafkaInputDStream.scala +++ b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaInputDStream.scala @@ -15,11 +15,10 @@ * limitations under the License. */ -package org.apache.spark.streaming.dstream +package org.apache.spark.streaming.kafka -import org.apache.spark.Logging -import org.apache.spark.storage.StorageLevel -import org.apache.spark.streaming.StreamingContext +import scala.collection.Map +import scala.reflect.ClassTag import java.util.Properties import java.util.concurrent.Executors @@ -30,8 +29,10 @@ import kafka.utils.VerifiableProperties import kafka.utils.ZKStringSerializer import org.I0Itec.zkclient._ -import scala.collection.Map -import scala.reflect.ClassTag +import org.apache.spark.Logging +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.StreamingContext +import org.apache.spark.streaming.dstream._ /** * Input stream that pulls messages from a Kafka Broker. diff --git a/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaUtils.scala b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaUtils.scala new file mode 100644 index 0000000000..c2d851f943 --- /dev/null +++ b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaUtils.scala @@ -0,0 +1,153 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.kafka + +import scala.reflect.ClassTag +import scala.collection.JavaConversions._ + +import java.lang.{Integer => JInt} +import java.util.{Map => JMap} + +import kafka.serializer.{Decoder, StringDecoder} + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{StreamingContext, DStream} +import org.apache.spark.streaming.api.java.{JavaStreamingContext, JavaPairDStream} + + +object KafkaUtils { + /** + * Create an input stream that pulls messages from a Kafka Broker. + * @param ssc StreamingContext object + * @param zkQuorum Zookeeper quorum (hostname:port,hostname:port,..) + * @param groupId The group id for this consumer + * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed + * in its own thread + * @param storageLevel Storage level to use for storing the received objects + * (default: StorageLevel.MEMORY_AND_DISK_SER_2) + */ + def createStream( + ssc: StreamingContext, + zkQuorum: String, + groupId: String, + topics: Map[String, Int], + storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 + ): DStream[(String, String)] = { + val kafkaParams = Map[String, String]( + "zookeeper.connect" -> zkQuorum, "group.id" -> groupId, + "zookeeper.connection.timeout.ms" -> "10000") + createStream[String, String, StringDecoder, StringDecoder]( + ssc, kafkaParams, topics, storageLevel) + } + + /** + * Create an input stream that pulls messages from a Kafka Broker. + * @param ssc StreamingContext object + * @param kafkaParams Map of kafka configuration parameters, + * see http://kafka.apache.org/08/configuration.html + * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed + * in its own thread. + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream[K: ClassTag, V: ClassTag, U <: Decoder[_]: Manifest, T <: Decoder[_]: Manifest]( + ssc: StreamingContext, + kafkaParams: Map[String, String], + topics: Map[String, Int], + storageLevel: StorageLevel + ): DStream[(K, V)] = { + val inputStream = new KafkaInputDStream[K, V, U, T](ssc, kafkaParams, topics, storageLevel) + ssc.registerInputStream(inputStream) + inputStream + } + + /** + * Create an input stream that pulls messages form a Kafka Broker. + * @param jssc JavaStreamingContext object + * @param zkQuorum Zookeeper quorum (hostname:port,hostname:port,..) + * @param groupId The group id for this consumer + * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed + * in its own thread + */ + def createStream( + jssc: JavaStreamingContext, + zkQuorum: String, + groupId: String, + topics: JMap[String, JInt] + ): JavaPairDStream[String, String] = { + implicit val cmt: ClassTag[String] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] + createStream(jssc.ssc, zkQuorum, groupId, Map(topics.mapValues(_.intValue()).toSeq: _*)) + } + + /** + * Create an input stream that pulls messages form a Kafka Broker. + * @param jssc JavaStreamingContext object + * @param zkQuorum Zookeeper quorum (hostname:port,hostname:port,..). + * @param groupId The group id for this consumer. + * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed + * in its own thread. + * @param storageLevel RDD storage level. + * + */ + def createStream( + jssc: JavaStreamingContext, + zkQuorum: String, + groupId: String, + topics: JMap[String, JInt], + storageLevel: StorageLevel + ): JavaPairDStream[String, String] = { + implicit val cmt: ClassTag[String] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] + createStream(jssc.ssc, zkQuorum, groupId, Map(topics.mapValues(_.intValue()).toSeq: _*), storageLevel) + } + + /** + * Create an input stream that pulls messages form a Kafka Broker. + * @param jssc JavaStreamingContext object + * @param keyTypeClass Key type of RDD + * @param valueTypeClass value type of RDD + * @param keyDecoderClass Type of kafka key decoder + * @param valueDecoderClass Type of kafka value decoder + * @param kafkaParams Map of kafka configuration parameters, + * see http://kafka.apache.org/08/configuration.html + * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed + * in its own thread + * @param storageLevel RDD storage level. Defaults to MEMORY_AND_DISK_2. + */ + def createStream[K, V, U <: Decoder[_], T <: Decoder[_]]( + jssc: JavaStreamingContext, + keyTypeClass: Class[K], + valueTypeClass: Class[V], + keyDecoderClass: Class[U], + valueDecoderClass: Class[T], + kafkaParams: JMap[String, String], + topics: JMap[String, JInt], + storageLevel: StorageLevel + ): JavaPairDStream[K, V] = { + implicit val keyCmt: ClassTag[K] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[K]] + implicit val valueCmt: ClassTag[V] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[V]] + + implicit val keyCmd: Manifest[U] = implicitly[Manifest[AnyRef]].asInstanceOf[Manifest[U]] + implicit val valueCmd: Manifest[T] = implicitly[Manifest[AnyRef]].asInstanceOf[Manifest[T]] + + createStream[K, V, U, T]( + jssc.ssc, kafkaParams.toMap, Map(topics.mapValues(_.intValue()).toSeq: _*), storageLevel) + } +} diff --git a/external/kafka/src/test/java/org/apache/spark/streaming/kafka/JavaKafkaStreamSuite.java b/external/kafka/src/test/java/org/apache/spark/streaming/kafka/JavaKafkaStreamSuite.java new file mode 100644 index 0000000000..7b4999447e --- /dev/null +++ b/external/kafka/src/test/java/org/apache/spark/streaming/kafka/JavaKafkaStreamSuite.java @@ -0,0 +1,45 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.kafka; + +import java.util.HashMap; +import org.junit.Test; +import com.google.common.collect.Maps; +import kafka.serializer.StringDecoder; +import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.LocalJavaStreamingContext; +import org.apache.spark.streaming.api.java.JavaPairDStream; + +public class JavaKafkaStreamSuite extends LocalJavaStreamingContext { + @Test + public void testKafkaStream() { + HashMap<String, Integer> topics = Maps.newHashMap(); + + // tests the API, does not actually test data receiving + JavaPairDStream<String, String> test1 = KafkaUtils.createStream(ssc, "localhost:12345", "group", topics); + JavaPairDStream<String, String> test2 = KafkaUtils.createStream(ssc, "localhost:12345", "group", topics, + StorageLevel.MEMORY_AND_DISK_SER_2()); + + HashMap<String, String> kafkaParams = Maps.newHashMap(); + kafkaParams.put("zookeeper.connect", "localhost:12345"); + kafkaParams.put("group.id","consumer-group"); + JavaPairDStream<String, String> test3 = KafkaUtils.createStream(ssc, + String.class, String.class, StringDecoder.class, StringDecoder.class, + kafkaParams, topics, StorageLevel.MEMORY_AND_DISK_SER_2()); + } +} diff --git a/external/kafka/src/test/resources/log4j.properties b/external/kafka/src/test/resources/log4j.properties new file mode 100644 index 0000000000..063529a9cb --- /dev/null +++ b/external/kafka/src/test/resources/log4j.properties @@ -0,0 +1,29 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# Set everything to be logged to the file streaming/target/unit-tests.log +log4j.rootCategory=INFO, file +# log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false +log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN + diff --git a/external/kafka/src/test/scala/org/apache/spark/streaming/kafka/KafkaStreamSuite.scala b/external/kafka/src/test/scala/org/apache/spark/streaming/kafka/KafkaStreamSuite.scala new file mode 100644 index 0000000000..9c81f23c19 --- /dev/null +++ b/external/kafka/src/test/scala/org/apache/spark/streaming/kafka/KafkaStreamSuite.scala @@ -0,0 +1,39 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.kafka + +import kafka.serializer.StringDecoder +import org.apache.spark.streaming.{StreamingContext, TestSuiteBase} +import org.apache.spark.storage.StorageLevel + +class KafkaStreamSuite extends TestSuiteBase { + + test("kafka input stream") { + val ssc = new StreamingContext(master, framework, batchDuration) + val topics = Map("my-topic" -> 1) + + // tests the API, does not actually test data receiving + val test1 = KafkaUtils.createStream(ssc, "localhost:1234", "group", topics) + val test2 = KafkaUtils.createStream(ssc, "localhost:12345", "group", topics, StorageLevel.MEMORY_AND_DISK_SER_2) + val kafkaParams = Map("zookeeper.connect"->"localhost:12345","group.id"->"consumer-group") + val test3 = KafkaUtils.createStream[String, String, StringDecoder, StringDecoder]( + ssc, kafkaParams, topics, StorageLevel.MEMORY_AND_DISK_SER_2) + + // TODO: Actually test receiving data + } +} diff --git a/external/mqtt/pom.xml b/external/mqtt/pom.xml new file mode 100644 index 0000000000..31b4fa87de --- /dev/null +++ b/external/mqtt/pom.xml @@ -0,0 +1,108 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-mqtt_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project External MQTT</name> + <url>http://spark.incubator.apache.org/</url> + + <repositories> + <repository> + <id>mqtt-repo</id> + <name>MQTT Repository</name> + <url>https://repo.eclipse.org/content/repositories/paho-releases</url> + <releases> + <enabled>true</enabled> + </releases> + <snapshots> + <enabled>false</enabled> + </snapshots> + </repository> + </repositories> + + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <type>test-jar</type> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.eclipse.paho</groupId> + <artifactId>mqtt-client</artifactId> + <version>0.4.0</version> + </dependency> + <dependency> + <groupId>${akka.group}</groupId> + <artifactId>akka-zeromq_${scala.binary.version}</artifactId> + <version>${akka.version}</version> + <exclusions> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.scalatest</groupId> + <artifactId>scalatest_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.scalacheck</groupId> + <artifactId>scalacheck_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.novocode</groupId> + <artifactId>junit-interface</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <scope>test</scope> + </dependency> + </dependencies> + <build> + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.scalatest</groupId> + <artifactId>scalatest-maven-plugin</artifactId> + </plugin> + </plugins> + </build> +</project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MQTTInputDStream.scala b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTInputDStream.scala index ef4a737568..c8987a3ee0 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/MQTTInputDStream.scala +++ b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTInputDStream.scala @@ -15,11 +15,12 @@ * limitations under the License. */ -package org.apache.spark.streaming.dstream +package org.apache.spark.streaming.mqtt -import org.apache.spark.Logging -import org.apache.spark.storage.StorageLevel -import org.apache.spark.streaming.{ Time, DStreamCheckpointData, StreamingContext } +import scala.collection.Map +import scala.collection.mutable.HashMap +import scala.collection.JavaConversions._ +import scala.reflect.ClassTag import java.util.Properties import java.util.concurrent.Executors @@ -34,10 +35,10 @@ import org.eclipse.paho.client.mqttv3.MqttException import org.eclipse.paho.client.mqttv3.MqttMessage import org.eclipse.paho.client.mqttv3.MqttTopic -import scala.collection.Map -import scala.collection.mutable.HashMap -import scala.collection.JavaConversions._ -import scala.reflect.ClassTag +import org.apache.spark.Logging +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.StreamingContext +import org.apache.spark.streaming.dstream._ /** * Input stream that subscribe messages from a Mqtt Broker. @@ -49,15 +50,14 @@ import scala.reflect.ClassTag private[streaming] class MQTTInputDStream[T: ClassTag]( - @transient ssc_ : StreamingContext, - brokerUrl: String, - topic: String, - storageLevel: StorageLevel + @transient ssc_ : StreamingContext, + brokerUrl: String, + topic: String, + storageLevel: StorageLevel ) extends NetworkInputDStream[T](ssc_) with Logging { def getReceiver(): NetworkReceiver[T] = { - new MQTTReceiver(brokerUrl, topic, storageLevel) - .asInstanceOf[NetworkReceiver[T]] + new MQTTReceiver(brokerUrl, topic, storageLevel).asInstanceOf[NetworkReceiver[T]] } } diff --git a/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTUtils.scala b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTUtils.scala new file mode 100644 index 0000000000..0e6c25dbee --- /dev/null +++ b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTUtils.scala @@ -0,0 +1,75 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.mqtt + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{StreamingContext, DStream} +import org.apache.spark.streaming.api.java.{JavaStreamingContext, JavaDStream} +import scala.reflect.ClassTag + +object MQTTUtils { + /** + * Create an input stream that receives messages pushed by a MQTT publisher. + * @param ssc StreamingContext object + * @param brokerUrl Url of remote MQTT publisher + * @param topic Topic name to subscribe to + * @param storageLevel RDD storage level. Defaults to StorageLevel.MEMORY_AND_DISK_SER_2. + */ + def createStream( + ssc: StreamingContext, + brokerUrl: String, + topic: String, + storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 + ): DStream[String] = { + val inputStream = new MQTTInputDStream[String](ssc, brokerUrl, topic, storageLevel) + ssc.registerInputStream(inputStream) + inputStream + } + + /** + * Create an input stream that receives messages pushed by a MQTT publisher. + * @param jssc JavaStreamingContext object + * @param brokerUrl Url of remote MQTT publisher + * @param topic Topic name to subscribe to + */ + def createStream( + jssc: JavaStreamingContext, + brokerUrl: String, + topic: String + ): JavaDStream[String] = { + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] + createStream(jssc.ssc, brokerUrl, topic) + } + + /** + * Create an input stream that receives messages pushed by a MQTT publisher. + * @param jssc JavaStreamingContext object + * @param brokerUrl Url of remote MQTT publisher + * @param topic Topic name to subscribe to + * @param storageLevel RDD storage level. + */ + def createStream( + jssc: JavaStreamingContext, + brokerUrl: String, + topic: String, + storageLevel: StorageLevel + ): JavaDStream[String] = { + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] + createStream(jssc.ssc, brokerUrl, topic, storageLevel) + } +} diff --git a/external/mqtt/src/test/java/org/apache/spark/streaming/mqtt/JavaMQTTStreamSuite.java b/external/mqtt/src/test/java/org/apache/spark/streaming/mqtt/JavaMQTTStreamSuite.java new file mode 100644 index 0000000000..44743aaecf --- /dev/null +++ b/external/mqtt/src/test/java/org/apache/spark/streaming/mqtt/JavaMQTTStreamSuite.java @@ -0,0 +1,37 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.mqtt; + +import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.api.java.JavaDStream; +import org.junit.Test; + +import org.apache.spark.streaming.LocalJavaStreamingContext; + +public class JavaMQTTStreamSuite extends LocalJavaStreamingContext { + @Test + public void testMQTTStream() { + String brokerUrl = "abc"; + String topic = "def"; + + // tests the API, does not actually test data receiving + JavaDStream<String> test1 = MQTTUtils.createStream(ssc, brokerUrl, topic); + JavaDStream<String> test2 = MQTTUtils.createStream(ssc, brokerUrl, topic, + StorageLevel.MEMORY_AND_DISK_SER_2()); + } +} diff --git a/external/mqtt/src/test/resources/log4j.properties b/external/mqtt/src/test/resources/log4j.properties new file mode 100644 index 0000000000..063529a9cb --- /dev/null +++ b/external/mqtt/src/test/resources/log4j.properties @@ -0,0 +1,29 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# Set everything to be logged to the file streaming/target/unit-tests.log +log4j.rootCategory=INFO, file +# log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false +log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN + diff --git a/external/mqtt/src/test/scala/org/apache/spark/streaming/mqtt/MQTTStreamSuite.scala b/external/mqtt/src/test/scala/org/apache/spark/streaming/mqtt/MQTTStreamSuite.scala new file mode 100644 index 0000000000..fcc159e85a --- /dev/null +++ b/external/mqtt/src/test/scala/org/apache/spark/streaming/mqtt/MQTTStreamSuite.scala @@ -0,0 +1,36 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.mqtt + +import org.apache.spark.streaming.{StreamingContext, TestSuiteBase} +import org.apache.spark.storage.StorageLevel + +class MQTTStreamSuite extends TestSuiteBase { + + test("MQTT input stream") { + val ssc = new StreamingContext(master, framework, batchDuration) + val brokerUrl = "abc" + val topic = "def" + + // tests the API, does not actually test data receiving + val test1 = MQTTUtils.createStream(ssc, brokerUrl, topic) + val test2 = MQTTUtils.createStream(ssc, brokerUrl, topic, StorageLevel.MEMORY_AND_DISK_SER_2) + + // TODO: Actually test receiving data + } +} diff --git a/external/twitter/pom.xml b/external/twitter/pom.xml new file mode 100644 index 0000000000..216e6c1d8f --- /dev/null +++ b/external/twitter/pom.xml @@ -0,0 +1,89 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-twitter_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project External Twitter</name> + <url>http://spark.incubator.apache.org/</url> + + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <type>test-jar</type> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.twitter4j</groupId> + <artifactId>twitter4j-stream</artifactId> + <version>3.0.3</version> + <exclusions> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.scalatest</groupId> + <artifactId>scalatest_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.scalacheck</groupId> + <artifactId>scalacheck_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.novocode</groupId> + <artifactId>junit-interface</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <scope>test</scope> + </dependency> + </dependencies> + <build> + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.scalatest</groupId> + <artifactId>scalatest-maven-plugin</artifactId> + </plugin> + </plugins> + </build> +</project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TwitterInputDStream.scala b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala index 387e15b0e6..5cc721d7f9 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TwitterInputDStream.scala +++ b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala @@ -15,18 +15,19 @@ * limitations under the License. */ -package org.apache.spark.streaming.dstream +package org.apache.spark.streaming.twitter -import org.apache.spark._ -import org.apache.spark.streaming._ -import storage.StorageLevel +import java.util.prefs.Preferences import twitter4j._ import twitter4j.auth.Authorization -import java.util.prefs.Preferences import twitter4j.conf.ConfigurationBuilder import twitter4j.conf.PropertyConfiguration import twitter4j.auth.OAuthAuthorization import twitter4j.auth.AccessToken +import org.apache.spark._ +import org.apache.spark.streaming._ +import org.apache.spark.streaming.dstream._ +import org.apache.spark.storage.StorageLevel /* A stream of Twitter statuses, potentially filtered by one or more keywords. * diff --git a/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterUtils.scala b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterUtils.scala new file mode 100644 index 0000000000..5e506ffabc --- /dev/null +++ b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterUtils.scala @@ -0,0 +1,126 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.twitter + +import twitter4j.Status +import twitter4j.auth.Authorization +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{StreamingContext, DStream} +import org.apache.spark.streaming.api.java.{JavaDStream, JavaStreamingContext} + +object TwitterUtils { + /** + * Create a input stream that returns tweets received from Twitter. + * @param ssc StreamingContext object + * @param twitterAuth Twitter4J authentication, or None to use Twitter4J's default OAuth + * authorization; this uses the system properties twitter4j.oauth.consumerKey, + * twitter4j.oauth.consumerSecret, twitter4j.oauth.accessToken and + * twitter4j.oauth.accessTokenSecret + * @param filters Set of filter strings to get only those tweets that match them + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream( + ssc: StreamingContext, + twitterAuth: Option[Authorization], + filters: Seq[String] = Nil, + storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 + ): DStream[Status] = { + val inputStream = new TwitterInputDStream(ssc, twitterAuth, filters, storageLevel) + ssc.registerInputStream(inputStream) + inputStream + } + + /** + * Create a input stream that returns tweets received from Twitter using Twitter4J's default + * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, + * twitter4j.oauth.consumerSecret, twitter4j.oauth.accessToken and + * twitter4j.oauth.accessTokenSecret. + * @param jssc JavaStreamingContext object + */ + def createStream(jssc: JavaStreamingContext): JavaDStream[Status] = { + createStream(jssc.ssc, None) + } + + /** + * Create a input stream that returns tweets received from Twitter using Twitter4J's default + * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, + * twitter4j.oauth.consumerSecret, twitter4j.oauth.accessToken and + * twitter4j.oauth.accessTokenSecret. + * @param jssc JavaStreamingContext object + * @param filters Set of filter strings to get only those tweets that match them + */ + def createStream(jssc: JavaStreamingContext, filters: Array[String]): JavaDStream[Status] = { + createStream(jssc.ssc, None, filters) + } + + /** + * Create a input stream that returns tweets received from Twitter using Twitter4J's default + * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, + * twitter4j.oauth.consumerSecret, twitter4j.oauth.accessToken and + * twitter4j.oauth.accessTokenSecret. + * @param jssc JavaStreamingContext object + * @param filters Set of filter strings to get only those tweets that match them + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream( + jssc: JavaStreamingContext, + filters: Array[String], + storageLevel: StorageLevel + ): JavaDStream[Status] = { + createStream(jssc.ssc, None, filters, storageLevel) + } + + /** + * Create a input stream that returns tweets received from Twitter. + * @param jssc JavaStreamingContext object + * @param twitterAuth Twitter4J Authorization + */ + def createStream(jssc: JavaStreamingContext, twitterAuth: Authorization): JavaDStream[Status] = { + createStream(jssc.ssc, Some(twitterAuth)) + } + + /** + * Create a input stream that returns tweets received from Twitter. + * @param jssc JavaStreamingContext object + * @param twitterAuth Twitter4J Authorization + * @param filters Set of filter strings to get only those tweets that match them + */ + def createStream( + jssc: JavaStreamingContext, + twitterAuth: Authorization, + filters: Array[String] + ): JavaDStream[Status] = { + createStream(jssc.ssc, Some(twitterAuth), filters) + } + + /** + * Create a input stream that returns tweets received from Twitter. + * @param jssc JavaStreamingContext object + * @param twitterAuth Twitter4J Authorization object + * @param filters Set of filter strings to get only those tweets that match them + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream( + jssc: JavaStreamingContext, + twitterAuth: Authorization, + filters: Array[String], + storageLevel: StorageLevel + ): JavaDStream[Status] = { + createStream(jssc.ssc, Some(twitterAuth), filters, storageLevel) + } +} diff --git a/external/twitter/src/test/java/org/apache/spark/streaming/twitter/JavaTwitterStreamSuite.java b/external/twitter/src/test/java/org/apache/spark/streaming/twitter/JavaTwitterStreamSuite.java new file mode 100644 index 0000000000..e46b4e5c75 --- /dev/null +++ b/external/twitter/src/test/java/org/apache/spark/streaming/twitter/JavaTwitterStreamSuite.java @@ -0,0 +1,46 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.twitter; + +import java.util.Arrays; + +import org.junit.Test; +import twitter4j.Status; +import twitter4j.auth.Authorization; +import twitter4j.auth.NullAuthorization; +import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.LocalJavaStreamingContext; +import org.apache.spark.streaming.api.java.JavaDStream; + +public class JavaTwitterStreamSuite extends LocalJavaStreamingContext { + @Test + public void testTwitterStream() { + String[] filters = (String[])Arrays.<String>asList("filter1", "filter2").toArray(); + Authorization auth = NullAuthorization.getInstance(); + + // tests the API, does not actually test data receiving + JavaDStream<Status> test1 = TwitterUtils.createStream(ssc); + JavaDStream<Status> test2 = TwitterUtils.createStream(ssc, filters); + JavaDStream<Status> test3 = TwitterUtils.createStream( + ssc, filters, StorageLevel.MEMORY_AND_DISK_SER_2()); + JavaDStream<Status> test4 = TwitterUtils.createStream(ssc, auth); + JavaDStream<Status> test5 = TwitterUtils.createStream(ssc, auth, filters); + JavaDStream<Status> test6 = TwitterUtils.createStream(ssc, + auth, filters, StorageLevel.MEMORY_AND_DISK_SER_2()); + } +} diff --git a/external/twitter/src/test/resources/log4j.properties b/external/twitter/src/test/resources/log4j.properties new file mode 100644 index 0000000000..063529a9cb --- /dev/null +++ b/external/twitter/src/test/resources/log4j.properties @@ -0,0 +1,29 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# Set everything to be logged to the file streaming/target/unit-tests.log +log4j.rootCategory=INFO, file +# log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false +log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN + diff --git a/external/twitter/src/test/scala/org/apache/spark/streaming/twitter/TwitterStreamSuite.scala b/external/twitter/src/test/scala/org/apache/spark/streaming/twitter/TwitterStreamSuite.scala new file mode 100644 index 0000000000..a0a8fe617b --- /dev/null +++ b/external/twitter/src/test/scala/org/apache/spark/streaming/twitter/TwitterStreamSuite.scala @@ -0,0 +1,43 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.twitter + +import org.apache.spark.streaming.{StreamingContext, TestSuiteBase} +import org.apache.spark.storage.StorageLevel +import twitter4j.auth.{NullAuthorization, Authorization} + +class TwitterStreamSuite extends TestSuiteBase { + + test("kafka input stream") { + val ssc = new StreamingContext(master, framework, batchDuration) + val filters = Seq("filter1", "filter2") + val authorization: Authorization = NullAuthorization.getInstance() + + // tests the API, does not actually test data receiving + val test1 = TwitterUtils.createStream(ssc, None) + val test2 = TwitterUtils.createStream(ssc, None, filters) + val test3 = TwitterUtils.createStream(ssc, None, filters, StorageLevel.MEMORY_AND_DISK_SER_2) + val test4 = TwitterUtils.createStream(ssc, Some(authorization)) + val test5 = TwitterUtils.createStream(ssc, Some(authorization), filters) + val test6 = TwitterUtils.createStream(ssc, Some(authorization), filters, + StorageLevel.MEMORY_AND_DISK_SER_2) + + // Note that actually testing the data receiving is hard as authentication keys are + // necessary for accessing Twitter live stream + } +} diff --git a/external/zeromq/pom.xml b/external/zeromq/pom.xml new file mode 100644 index 0000000000..c240d59574 --- /dev/null +++ b/external/zeromq/pom.xml @@ -0,0 +1,89 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> + +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>spark-parent</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming-zeromq_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project External ZeroMQ</name> + <url>http://spark.incubator.apache.org/</url> + + <dependencies> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + </dependency> + <dependency> + <groupId>org.apache.spark</groupId> + <artifactId>spark-streaming_${scala.binary.version}</artifactId> + <version>${project.version}</version> + <type>test-jar</type> + <scope>test</scope> + </dependency> + <dependency> + <groupId>${akka.group}</groupId> + <artifactId>akka-zeromq_${scala.binary.version}</artifactId> + <version>${akka.version}</version> + <exclusions> + <exclusion> + <groupId>org.jboss.netty</groupId> + <artifactId>netty</artifactId> + </exclusion> + </exclusions> + </dependency> + <dependency> + <groupId>org.scalatest</groupId> + <artifactId>scalatest_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.scalacheck</groupId> + <artifactId>scalacheck_${scala.binary.version}</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>com.novocode</groupId> + <artifactId>junit-interface</artifactId> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.slf4j</groupId> + <artifactId>slf4j-log4j12</artifactId> + <scope>test</scope> + </dependency> + </dependencies> + <build> + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.scalatest</groupId> + <artifactId>scalatest-maven-plugin</artifactId> + </plugin> + </plugins> + </build> +</project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/receivers/ZeroMQReceiver.scala b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/ZeroMQReceiver.scala index f164d516b0..769761e3b8 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/receivers/ZeroMQReceiver.scala +++ b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/ZeroMQReceiver.scala @@ -15,7 +15,7 @@ * limitations under the License. */ -package org.apache.spark.streaming.receivers +package org.apache.spark.streaming.zeromq import scala.reflect.ClassTag @@ -24,6 +24,7 @@ import akka.util.ByteString import akka.zeromq._ import org.apache.spark.Logging +import org.apache.spark.streaming.receivers._ /** * A receiver to subscribe to ZeroMQ stream. diff --git a/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/ZeroMQUtils.scala b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/ZeroMQUtils.scala new file mode 100644 index 0000000000..546d9df3b5 --- /dev/null +++ b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/ZeroMQUtils.scala @@ -0,0 +1,126 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.zeromq + +import scala.reflect.ClassTag +import scala.collection.JavaConversions._ +import akka.actor.{Props, SupervisorStrategy} +import akka.util.ByteString +import akka.zeromq.Subscribe +import org.apache.spark.api.java.function.{Function => JFunction} +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.receivers.ReceiverSupervisorStrategy +import org.apache.spark.streaming.{StreamingContext, DStream} +import org.apache.spark.streaming.api.java.{JavaStreamingContext, JavaDStream} + +object ZeroMQUtils { + /** + * Create an input stream that receives messages pushed by a zeromq publisher. + * @param ssc StreamingContext object + * @param publisherUrl Url of remote zeromq publisher + * @param subscribe Topic to subscribe to + * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic + * and each frame has sequence of byte thus it needs the converter + * (which might be deserializer of bytes) to translate from sequence + * of sequence of bytes, where sequence refer to a frame + * and sub sequence refer to its payload. + * @param storageLevel RDD storage level. Defaults to StorageLevel.MEMORY_AND_DISK_SER_2. + */ + def createStream[T: ClassTag]( + ssc: StreamingContext, + publisherUrl: String, + subscribe: Subscribe, + bytesToObjects: Seq[ByteString] ⇒ Iterator[T], + storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2, + supervisorStrategy: SupervisorStrategy = ReceiverSupervisorStrategy.defaultStrategy + ): DStream[T] = { + ssc.actorStream(Props(new ZeroMQReceiver(publisherUrl, subscribe, bytesToObjects)), + "ZeroMQReceiver", storageLevel, supervisorStrategy) + } + + /** + * Create an input stream that receives messages pushed by a zeromq publisher. + * @param jssc JavaStreamingContext object + * @param publisherUrl Url of remote ZeroMQ publisher + * @param subscribe Topic to subscribe to + * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence + * of byte thus it needs the converter(which might be deserializer of bytes) + * to translate from sequence of sequence of bytes, where sequence refer to a frame + * and sub sequence refer to its payload. + * @param storageLevel Storage level to use for storing the received objects + */ + def createStream[T]( + jssc: JavaStreamingContext, + publisherUrl: String, + subscribe: Subscribe, + bytesToObjects: JFunction[Array[Array[Byte]], java.lang.Iterable[T]], + storageLevel: StorageLevel, + supervisorStrategy: SupervisorStrategy + ): JavaDStream[T] = { + implicit val cm: ClassTag[T] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] + val fn = (x: Seq[ByteString]) => bytesToObjects.apply(x.map(_.toArray).toArray).toIterator + createStream[T](jssc.ssc, publisherUrl, subscribe, fn, storageLevel, supervisorStrategy) + } + + /** + * Create an input stream that receives messages pushed by a zeromq publisher. + * @param jssc JavaStreamingContext object + * @param publisherUrl Url of remote zeromq publisher + * @param subscribe Topic to subscribe to + * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence + * of byte thus it needs the converter(which might be deserializer of bytes) + * to translate from sequence of sequence of bytes, where sequence refer to a frame + * and sub sequence refer to its payload. + * @param storageLevel RDD storage level. + */ + def createStream[T]( + jssc: JavaStreamingContext, + publisherUrl: String, + subscribe: Subscribe, + bytesToObjects: JFunction[Array[Array[Byte]], java.lang.Iterable[T]], + storageLevel: StorageLevel + ): JavaDStream[T] = { + implicit val cm: ClassTag[T] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] + val fn = (x: Seq[ByteString]) => bytesToObjects.apply(x.map(_.toArray).toArray).toIterator + createStream[T](jssc.ssc, publisherUrl, subscribe, fn, storageLevel) + } + + /** + * Create an input stream that receives messages pushed by a zeromq publisher. + * @param jssc JavaStreamingContext object + * @param publisherUrl Url of remote zeromq publisher + * @param subscribe Topic to subscribe to + * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence + * of byte thus it needs the converter(which might be deserializer of bytes) + * to translate from sequence of sequence of bytes, where sequence refer to a frame + * and sub sequence refer to its payload. + */ + def createStream[T]( + jssc: JavaStreamingContext, + publisherUrl: String, + subscribe: Subscribe, + bytesToObjects: JFunction[Array[Array[Byte]], java.lang.Iterable[T]] + ): JavaDStream[T] = { + implicit val cm: ClassTag[T] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] + val fn = (x: Seq[ByteString]) => bytesToObjects.apply(x.map(_.toArray).toArray).toIterator + createStream[T](jssc.ssc, publisherUrl, subscribe, fn) + } +} diff --git a/external/zeromq/src/test/java/org/apache/spark/streaming/zeromq/JavaZeroMQStreamSuite.java b/external/zeromq/src/test/java/org/apache/spark/streaming/zeromq/JavaZeroMQStreamSuite.java new file mode 100644 index 0000000000..d2361e14b8 --- /dev/null +++ b/external/zeromq/src/test/java/org/apache/spark/streaming/zeromq/JavaZeroMQStreamSuite.java @@ -0,0 +1,50 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.zeromq; + +import org.junit.Test; +import akka.actor.SupervisorStrategy; +import akka.util.ByteString; +import akka.zeromq.Subscribe; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.LocalJavaStreamingContext; +import org.apache.spark.streaming.api.java.JavaDStream; + +public class JavaZeroMQStreamSuite extends LocalJavaStreamingContext { + + @Test // tests the API, does not actually test data receiving + public void testZeroMQStream() { + String publishUrl = "abc"; + Subscribe subscribe = new Subscribe((ByteString)null); + Function<byte[][], Iterable<String>> bytesToObjects = new Function<byte[][], Iterable<String>>() { + @Override + public Iterable<String> call(byte[][] bytes) throws Exception { + return null; + } + }; + + JavaDStream<String> test1 = ZeroMQUtils.<String>createStream( + ssc, publishUrl, subscribe, bytesToObjects); + JavaDStream<String> test2 = ZeroMQUtils.<String>createStream( + ssc, publishUrl, subscribe, bytesToObjects, StorageLevel.MEMORY_AND_DISK_SER_2()); + JavaDStream<String> test3 = ZeroMQUtils.<String>createStream( + ssc,publishUrl, subscribe, bytesToObjects, StorageLevel.MEMORY_AND_DISK_SER_2(), + SupervisorStrategy.defaultStrategy()); + } +} diff --git a/external/zeromq/src/test/resources/log4j.properties b/external/zeromq/src/test/resources/log4j.properties new file mode 100644 index 0000000000..063529a9cb --- /dev/null +++ b/external/zeromq/src/test/resources/log4j.properties @@ -0,0 +1,29 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# Set everything to be logged to the file streaming/target/unit-tests.log +log4j.rootCategory=INFO, file +# log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false +log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN + diff --git a/external/zeromq/src/test/scala/org/apache/spark/streaming/zeromq/ZeroMQStreamSuite.scala b/external/zeromq/src/test/scala/org/apache/spark/streaming/zeromq/ZeroMQStreamSuite.scala new file mode 100644 index 0000000000..4193b8a02f --- /dev/null +++ b/external/zeromq/src/test/scala/org/apache/spark/streaming/zeromq/ZeroMQStreamSuite.scala @@ -0,0 +1,44 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.zeromq + +import akka.actor.SupervisorStrategy +import akka.util.ByteString +import akka.zeromq.Subscribe + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.{StreamingContext, TestSuiteBase} + +class ZeroMQStreamSuite extends TestSuiteBase { + + test("zeromq input stream") { + val ssc = new StreamingContext(master, framework, batchDuration) + val publishUrl = "abc" + val subscribe = new Subscribe(null.asInstanceOf[ByteString]) + val bytesToObjects = (bytes: Seq[ByteString]) => null.asInstanceOf[Iterator[String]] + + // tests the API, does not actually test data receiving + val test1 = ZeroMQUtils.createStream(ssc, publishUrl, subscribe, bytesToObjects) + val test2 = ZeroMQUtils.createStream( + ssc, publishUrl, subscribe, bytesToObjects, StorageLevel.MEMORY_AND_DISK_SER_2) + val test3 = ZeroMQUtils.createStream(ssc, publishUrl, subscribe, bytesToObjects, + StorageLevel.MEMORY_AND_DISK_SER_2, SupervisorStrategy.defaultStrategy) + + // TODO: Actually test data receiving + } +} diff --git a/make-distribution.sh b/make-distribution.sh index 32bbdb90a5..e6b5956d1e 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -31,10 +31,10 @@ # # Recommended deploy/testing procedure (standalone mode): # 1) Rsync / deploy the dist/ dir to one host -# 2) cd to deploy dir; ./bin/start-master.sh +# 2) cd to deploy dir; ./sbin/start-master.sh # 3) Verify master is up by visiting web page, ie http://master-ip:8080. Note the spark:// URL. -# 4) ./bin/start-slave.sh 1 <<spark:// URL>> -# 5) MASTER="spark://my-master-ip:7077" ./spark-shell +# 4) ./sbin/start-slave.sh 1 <<spark:// URL>> +# 5) MASTER="spark://my-master-ip:7077" ./bin/spark-shell # # Figure out where the Spark framework is installed @@ -43,7 +43,17 @@ DISTDIR="$FWDIR/dist" # Get version from SBT export TERM=dumb # Prevents color codes in SBT output -VERSION=$($FWDIR/sbt/sbt "show version" | tail -1 | cut -f 2 | sed 's/^\([a-zA-Z0-9.-]*\).*/\1/') + +VERSIONSTRING=$($FWDIR/sbt/sbt "show version") + +if [ $? == -1 ] ;then + echo -e "You need sbt installed and available on your path." + echo -e "Download sbt from http://www.scala-sbt.org/" + exit -1; +fi + +VERSION=$(echo "${VERSIONSTRING}" | tail -1 | cut -f 2 | sed 's/^\([a-zA-Z0-9.-]*\).*/\1/') +echo "Version is ${VERSION}" # Initialize defaults SPARK_HADOOP_VERSION=1.0.4 @@ -83,7 +93,9 @@ fi # Build fat JAR export SPARK_HADOOP_VERSION export SPARK_YARN -"$FWDIR/sbt/sbt" "assembly/assembly" +cd $FWDIR + +"sbt/sbt" "assembly/assembly" # Make directories rm -rf "$DISTDIR" @@ -98,10 +110,7 @@ mkdir "$DISTDIR"/conf cp "$FWDIR"/conf/*.template "$DISTDIR"/conf cp -r "$FWDIR/bin" "$DISTDIR" cp -r "$FWDIR/python" "$DISTDIR" -cp "$FWDIR/spark-class" "$DISTDIR" -cp "$FWDIR/spark-shell" "$DISTDIR" -cp "$FWDIR/spark-executor" "$DISTDIR" -cp "$FWDIR/pyspark" "$DISTDIR" +cp -r "$FWDIR/sbin" "$DISTDIR" if [ "$MAKE_TGZ" == "true" ]; then diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala index 8247c1ebc5..2d8623392e 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala @@ -197,6 +197,7 @@ class PythonMLLibAPI extends Serializable { return ret } + /** Unpack a Rating object from an array of bytes */ private def unpackRating(ratingBytes: Array[Byte]): Rating = { val bb = ByteBuffer.wrap(ratingBytes) bb.order(ByteOrder.nativeOrder()) @@ -206,6 +207,35 @@ class PythonMLLibAPI extends Serializable { return new Rating(user, product, rating) } + /** Unpack a tuple of Ints from an array of bytes */ + private[spark] def unpackTuple(tupleBytes: Array[Byte]): (Int, Int) = { + val bb = ByteBuffer.wrap(tupleBytes) + bb.order(ByteOrder.nativeOrder()) + val v1 = bb.getInt() + val v2 = bb.getInt() + (v1, v2) + } + + /** + * Serialize a Rating object into an array of bytes. + * It can be deserialized using RatingDeserializer(). + * + * @param rate + * @return + */ + private[spark] def serializeRating(rate: Rating): Array[Byte] = { + val len = 3 + val bytes = new Array[Byte](4 + 8 * len) + val bb = ByteBuffer.wrap(bytes) + bb.order(ByteOrder.nativeOrder()) + bb.putInt(len) + val db = bb.asDoubleBuffer() + db.put(rate.user.toDouble) + db.put(rate.product.toDouble) + db.put(rate.rating) + bytes + } + /** * Java stub for Python mllib ALS.train(). This stub returns a handle * to the Java object instead of the content of the Java object. Extra care diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala new file mode 100644 index 0000000000..524300d6ae --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.mllib.classification + +import scala.collection.mutable + +import org.jblas.DoubleMatrix + +import org.apache.spark.Logging +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.rdd.RDD + +/** + * Model for Naive Bayes Classifiers. + * + * @param pi Log of class priors, whose dimension is C. + * @param theta Log of class conditional probabilities, whose dimension is CXD. + */ +class NaiveBayesModel(pi: Array[Double], theta: Array[Array[Double]]) + extends ClassificationModel with Serializable { + + // Create a column vector that can be used for predictions + private val _pi = new DoubleMatrix(pi.length, 1, pi: _*) + private val _theta = new DoubleMatrix(theta) + + def predict(testData: RDD[Array[Double]]): RDD[Double] = testData.map(predict) + + def predict(testData: Array[Double]): Double = { + val dataMatrix = new DoubleMatrix(testData.length, 1, testData: _*) + val result = _pi.add(_theta.mmul(dataMatrix)) + result.argmax() + } +} + +/** + * Trains a Naive Bayes model given an RDD of `(label, features)` pairs. + * + * @param lambda The smooth parameter + */ +class NaiveBayes private (val lambda: Double = 1.0) + extends Serializable with Logging { + + /** + * Run the algorithm with the configured parameters on an input RDD of LabeledPoint entries. + * + * @param data RDD of (label, array of features) pairs. + */ + def run(data: RDD[LabeledPoint]) = { + // Aggregates all sample points to driver side to get sample count and summed feature vector + // for each label. The shape of `zeroCombiner` & `aggregated` is: + // + // label: Int -> (count: Int, featuresSum: DoubleMatrix) + val zeroCombiner = mutable.Map.empty[Int, (Int, DoubleMatrix)] + val aggregated = data.aggregate(zeroCombiner)({ (combiner, point) => + point match { + case LabeledPoint(label, features) => + val (count, featuresSum) = combiner.getOrElse(label.toInt, (0, DoubleMatrix.zeros(1))) + val fs = new DoubleMatrix(features.length, 1, features: _*) + combiner += label.toInt -> (count + 1, featuresSum.addi(fs)) + } + }, { (lhs, rhs) => + for ((label, (c, fs)) <- rhs) { + val (count, featuresSum) = lhs.getOrElse(label, (0, DoubleMatrix.zeros(1))) + lhs(label) = (count + c, featuresSum.addi(fs)) + } + lhs + }) + + // Kinds of label + val C = aggregated.size + // Total sample count + val N = aggregated.values.map(_._1).sum + + val pi = new Array[Double](C) + val theta = new Array[Array[Double]](C) + val piLogDenom = math.log(N + C * lambda) + + for ((label, (count, fs)) <- aggregated) { + val thetaLogDenom = math.log(fs.sum() + fs.length * lambda) + pi(label) = math.log(count + lambda) - piLogDenom + theta(label) = fs.toArray.map(f => math.log(f + lambda) - thetaLogDenom) + } + + new NaiveBayesModel(pi, theta) + } +} + +object NaiveBayes { + /** + * Trains a Naive Bayes model given an RDD of `(label, features)` pairs. + * + * This is the Multinomial NB ([[http://tinyurl.com/lsdw6p]]) which can handle all kinds of + * discrete data. For example, by converting documents into TF-IDF vectors, it can be used for + * document classification. By making every vector a 0-1 vector. it can also be used as + * Bernoulli NB ([[http://tinyurl.com/p7c96j6]]). + * + * @param input RDD of `(label, array of features)` pairs. Every vector should be a frequency + * vector or a count vector. + * @param lambda The smooth parameter + */ + def train(input: RDD[LabeledPoint], lambda: Double = 1.0): NaiveBayesModel = { + new NaiveBayes(lambda).run(input) + } +} diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala index 749e7364f4..c590492e7a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala @@ -50,8 +50,8 @@ class LogisticGradient extends Gradient { val gradient = data.mul(gradientMultiplier) val loss = - if (margin > 0) { - math.log(1 + math.exp(0 - margin)) + if (label > 0) { + math.log(1 + math.exp(margin)) } else { math.log(1 + math.exp(margin)) - margin } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala index af43d89c70..443fc5de5b 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala @@ -19,8 +19,11 @@ package org.apache.spark.mllib.recommendation import org.apache.spark.rdd.RDD import org.apache.spark.SparkContext._ +import org.apache.spark.mllib.api.python.PythonMLLibAPI import org.jblas._ +import org.apache.spark.api.java.JavaRDD + /** * Model representing the result of matrix factorization. @@ -44,6 +47,39 @@ class MatrixFactorizationModel( userVector.dot(productVector) } - // TODO: Figure out what good bulk prediction methods would look like. + /** + * Predict the rating of many users for many products. + * The output RDD has an element per each element in the input RDD (including all duplicates) + * unless a user or product is missing in the training set. + * + * @param usersProducts RDD of (user, product) pairs. + * @return RDD of Ratings. + */ + def predict(usersProducts: RDD[(Int, Int)]): RDD[Rating] = { + val users = userFeatures.join(usersProducts).map{ + case (user, (uFeatures, product)) => (product, (user, uFeatures)) + } + users.join(productFeatures).map { + case (product, ((user, uFeatures), pFeatures)) => + val userVector = new DoubleMatrix(uFeatures) + val productVector = new DoubleMatrix(pFeatures) + Rating(user, product, userVector.dot(productVector)) + } + } + + /** + * Predict the rating of many users for many products. + * This is a Java stub for python predictAll() + * + * @param usersProductsJRDD A JavaRDD with serialized tuples (user, product) + * @return JavaRDD of serialized Rating objects. + */ + def predict(usersProductsJRDD: JavaRDD[Array[Byte]]): JavaRDD[Array[Byte]] = { + val pythonAPI = new PythonMLLibAPI() + val usersProducts = usersProductsJRDD.rdd.map(xBytes => pythonAPI.unpackTuple(xBytes)) + predict(usersProducts).map(rate => pythonAPI.serializeRating(rate)) + } + + // TODO: Figure out what other good bulk prediction methods would look like. // Probably want a way to get the top users for a product or vice-versa. } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala new file mode 100644 index 0000000000..b615f76e66 --- /dev/null +++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala @@ -0,0 +1,108 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.mllib.classification + +import scala.util.Random + +import org.scalatest.BeforeAndAfterAll +import org.scalatest.FunSuite + +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.SparkContext + +object NaiveBayesSuite { + + private def calcLabel(p: Double, pi: Array[Double]): Int = { + var sum = 0.0 + for (j <- 0 until pi.length) { + sum += pi(j) + if (p < sum) return j + } + -1 + } + + // Generate input of the form Y = (theta * x).argmax() + def generateNaiveBayesInput( + pi: Array[Double], // 1XC + theta: Array[Array[Double]], // CXD + nPoints: Int, + seed: Int): Seq[LabeledPoint] = { + val D = theta(0).length + val rnd = new Random(seed) + + val _pi = pi.map(math.pow(math.E, _)) + val _theta = theta.map(row => row.map(math.pow(math.E, _))) + + for (i <- 0 until nPoints) yield { + val y = calcLabel(rnd.nextDouble(), _pi) + val xi = Array.tabulate[Double](D) { j => + if (rnd.nextDouble() < _theta(y)(j)) 1 else 0 + } + + LabeledPoint(y, xi) + } + } +} + +class NaiveBayesSuite extends FunSuite with BeforeAndAfterAll { + @transient private var sc: SparkContext = _ + + override def beforeAll() { + sc = new SparkContext("local", "test") + } + + override def afterAll() { + sc.stop() + System.clearProperty("spark.driver.port") + } + + def validatePrediction(predictions: Seq[Double], input: Seq[LabeledPoint]) { + val numOfPredictions = predictions.zip(input).count { + case (prediction, expected) => + prediction != expected.label + } + // At least 80% of the predictions should be on. + assert(numOfPredictions < input.length / 5) + } + + test("Naive Bayes") { + val nPoints = 10000 + + val pi = Array(0.5, 0.3, 0.2).map(math.log) + val theta = Array( + Array(0.91, 0.03, 0.03, 0.03), // label 0 + Array(0.03, 0.91, 0.03, 0.03), // label 1 + Array(0.03, 0.03, 0.91, 0.03) // label 2 + ).map(_.map(math.log)) + + val testData = NaiveBayesSuite.generateNaiveBayesInput(pi, theta, nPoints, 42) + val testRDD = sc.parallelize(testData, 2) + testRDD.cache() + + val model = NaiveBayes.train(testRDD) + + val validationData = NaiveBayesSuite.generateNaiveBayesInput(pi, theta, nPoints, 17) + val validationRDD = sc.parallelize(validationData, 2) + + // Test prediction on RDD. + validatePrediction(model.predict(validationRDD.map(_.features)).collect(), validationData) + + // Test prediction on Array. + validatePrediction(validationData.map(row => model.predict(row.features)), validationData) + } +} diff --git a/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala new file mode 100644 index 0000000000..a6028a1e98 --- /dev/null +++ b/mllib/src/test/scala/org/apache/spark/mllib/optimization/GradientDescentSuite.scala @@ -0,0 +1,116 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.mllib.optimization + +import scala.util.Random +import scala.collection.JavaConversions._ + +import org.scalatest.BeforeAndAfterAll +import org.scalatest.FunSuite +import org.scalatest.matchers.ShouldMatchers + +import org.apache.spark.SparkContext +import org.apache.spark.mllib.regression._ + +object GradientDescentSuite { + + def generateLogisticInputAsList( + offset: Double, + scale: Double, + nPoints: Int, + seed: Int): java.util.List[LabeledPoint] = { + seqAsJavaList(generateGDInput(offset, scale, nPoints, seed)) + } + + // Generate input of the form Y = logistic(offset + scale * X) + def generateGDInput( + offset: Double, + scale: Double, + nPoints: Int, + seed: Int): Seq[LabeledPoint] = { + val rnd = new Random(seed) + val x1 = Array.fill[Double](nPoints)(rnd.nextGaussian()) + + val unifRand = new scala.util.Random(45) + val rLogis = (0 until nPoints).map { i => + val u = unifRand.nextDouble() + math.log(u) - math.log(1.0-u) + } + + val y: Seq[Int] = (0 until nPoints).map { i => + val yVal = offset + scale * x1(i) + rLogis(i) + if (yVal > 0) 1 else 0 + } + + val testData = (0 until nPoints).map(i => LabeledPoint(y(i), Array(x1(i)))) + testData + } +} + +class GradientDescentSuite extends FunSuite with BeforeAndAfterAll with ShouldMatchers { + @transient private var sc: SparkContext = _ + + override def beforeAll() { + sc = new SparkContext("local", "test") + } + + override def afterAll() { + sc.stop() + System.clearProperty("spark.driver.port") + } + + test("Assert the loss is decreasing.") { + val nPoints = 10000 + val A = 2.0 + val B = -1.5 + + val initialB = -1.0 + val initialWeights = Array(initialB) + + val gradient = new LogisticGradient() + val updater = new SimpleUpdater() + val stepSize = 1.0 + val numIterations = 10 + val regParam = 0 + val miniBatchFrac = 1.0 + + // Add a extra variable consisting of all 1.0's for the intercept. + val testData = GradientDescentSuite.generateGDInput(A, B, nPoints, 42) + val data = testData.map { case LabeledPoint(label, features) => + label -> Array(1.0, features: _*) + } + + val dataRDD = sc.parallelize(data, 2).cache() + val initialWeightsWithIntercept = Array(1.0, initialWeights: _*) + + val (_, loss) = GradientDescent.runMiniBatchSGD( + dataRDD, + gradient, + updater, + stepSize, + numIterations, + regParam, + miniBatchFrac, + initialWeightsWithIntercept) + + assert(loss.last - loss.head < 0, "loss isn't decreasing.") + + val lossDiff = loss.init.zip(loss.tail).map { case (lhs, rhs) => lhs - rhs } + assert(lossDiff.count(_ > 0).toDouble / lossDiff.size > 0.8) + } +} diff --git a/mllib/src/test/scala/org/apache/spark/mllib/recommendation/ALSSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/recommendation/ALSSuite.scala index fafc5ec5f2..e683a90f57 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/recommendation/ALSSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/recommendation/ALSSuite.scala @@ -90,18 +90,34 @@ class ALSSuite extends FunSuite with BeforeAndAfterAll { testALS(50, 100, 1, 15, 0.7, 0.3) } + test("rank-1 matrices bulk") { + testALS(50, 100, 1, 15, 0.7, 0.3, false, true) + } + test("rank-2 matrices") { testALS(100, 200, 2, 15, 0.7, 0.3) } + test("rank-2 matrices bulk") { + testALS(100, 200, 2, 15, 0.7, 0.3, false, true) + } + test("rank-1 matrices implicit") { testALS(80, 160, 1, 15, 0.7, 0.4, true) } + test("rank-1 matrices implicit bulk") { + testALS(80, 160, 1, 15, 0.7, 0.4, true, true) + } + test("rank-2 matrices implicit") { testALS(100, 200, 2, 15, 0.7, 0.4, true) } + test("rank-2 matrices implicit bulk") { + testALS(100, 200, 2, 15, 0.7, 0.4, true, true) + } + /** * Test if we can correctly factorize R = U * P where U and P are of known rank. * @@ -111,9 +127,12 @@ class ALSSuite extends FunSuite with BeforeAndAfterAll { * @param iterations number of iterations to run * @param samplingRate what fraction of the user-product pairs are known * @param matchThreshold max difference allowed to consider a predicted rating correct + * @param implicitPrefs flag to test implicit feedback + * @param bulkPredict flag to test bulk prediciton */ def testALS(users: Int, products: Int, features: Int, iterations: Int, - samplingRate: Double, matchThreshold: Double, implicitPrefs: Boolean = false) + samplingRate: Double, matchThreshold: Double, implicitPrefs: Boolean = false, + bulkPredict: Boolean = false) { val (sampledRatings, trueRatings, truePrefs) = ALSSuite.generateRatings(users, products, features, samplingRate, implicitPrefs) @@ -130,7 +149,17 @@ class ALSSuite extends FunSuite with BeforeAndAfterAll { for ((p, vec) <- model.productFeatures.collect(); i <- 0 until features) { predictedP.put(p, i, vec(i)) } - val predictedRatings = predictedU.mmul(predictedP.transpose) + val predictedRatings = bulkPredict match { + case false => predictedU.mmul(predictedP.transpose) + case true => + val allRatings = new DoubleMatrix(users, products) + val usersProducts = for (u <- 0 until users; p <- 0 until products) yield (u, p) + val userProductsRDD = sc.parallelize(usersProducts) + model.predict(userProductsRDD).collect().foreach { elem => + allRatings.put(elem.user, elem.product, elem.rating) + } + allRatings + } if (!implicitPrefs) { for (u <- 0 until users; p <- 0 until products) { diff --git a/new-yarn/pom.xml b/new-yarn/pom.xml deleted file mode 100644 index 4cd28f34e3..0000000000 --- a/new-yarn/pom.xml +++ /dev/null @@ -1,161 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<!-- - ~ Licensed to the Apache Software Foundation (ASF) under one or more - ~ contributor license agreements. See the NOTICE file distributed with - ~ this work for additional information regarding copyright ownership. - ~ The ASF licenses this file to You under the Apache License, Version 2.0 - ~ (the "License"); you may not use this file except in compliance with - ~ the License. You may obtain a copy of the License at - ~ - ~ http://www.apache.org/licenses/LICENSE-2.0 - ~ - ~ Unless required by applicable law or agreed to in writing, software - ~ distributed under the License is distributed on an "AS IS" BASIS, - ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - ~ See the License for the specific language governing permissions and - ~ limitations under the License. - --> -<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> - <modelVersion>4.0.0</modelVersion> - <parent> - <groupId>org.apache.spark</groupId> - <artifactId>spark-parent</artifactId> - <version>0.9.0-incubating-SNAPSHOT</version> - <relativePath>../pom.xml</relativePath> - </parent> - - <groupId>org.apache.spark</groupId> - <artifactId>spark-yarn_2.10</artifactId> - <packaging>jar</packaging> - <name>Spark Project YARN Support</name> - <url>http://spark.incubator.apache.org/</url> - - <dependencies> - <dependency> - <groupId>org.apache.spark</groupId> - <artifactId>spark-core_2.10</artifactId> - <version>${project.version}</version> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-api</artifactId> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-common</artifactId> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-yarn-client</artifactId> - </dependency> - <dependency> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-client</artifactId> - <version>${yarn.version}</version> - </dependency> - <dependency> - <groupId>org.apache.avro</groupId> - <artifactId>avro</artifactId> - </dependency> - <dependency> - <groupId>org.apache.avro</groupId> - <artifactId>avro-ipc</artifactId> - </dependency> - <dependency> - <groupId>org.scalatest</groupId> - <artifactId>scalatest_2.10</artifactId> - <scope>test</scope> - </dependency> - <dependency> - <groupId>org.mockito</groupId> - <artifactId>mockito-all</artifactId> - <scope>test</scope> - </dependency> - </dependencies> - - <build> - <outputDirectory>target/scala-${scala.version}/classes</outputDirectory> - <testOutputDirectory>target/scala-${scala.version}/test-classes</testOutputDirectory> - <plugins> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-shade-plugin</artifactId> - <configuration> - <shadedArtifactAttached>false</shadedArtifactAttached> - <outputFile>${project.build.directory}/${project.artifactId}-${project.version}-shaded.jar</outputFile> - <artifactSet> - <includes> - <include>*:*</include> - </includes> - </artifactSet> - <filters> - <filter> - <artifact>*:*</artifact> - <excludes> - <exclude>META-INF/*.SF</exclude> - <exclude>META-INF/*.DSA</exclude> - <exclude>META-INF/*.RSA</exclude> - </excludes> - </filter> - </filters> - </configuration> - <executions> - <execution> - <phase>package</phase> - <goals> - <goal>shade</goal> - </goals> - <configuration> - <transformers> - <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" /> - <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> - <resource>reference.conf</resource> - </transformer> - </transformers> - </configuration> - </execution> - </executions> - </plugin> - <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-antrun-plugin</artifactId> - <executions> - <execution> - <phase>test</phase> - <goals> - <goal>run</goal> - </goals> - <configuration> - <exportAntProperties>true</exportAntProperties> - <tasks> - <property name="spark.classpath" refid="maven.test.classpath" /> - <property environment="env" /> - <fail message="Please set the SCALA_HOME (or SCALA_LIBRARY_PATH if scala is on the path) environment variables and retry."> - <condition> - <not> - <or> - <isset property="env.SCALA_HOME" /> - <isset property="env.SCALA_LIBRARY_PATH" /> - </or> - </not> - </condition> - </fail> - </tasks> - </configuration> - </execution> - </executions> - </plugin> - <plugin> - <groupId>org.scalatest</groupId> - <artifactId>scalatest-maven-plugin</artifactId> - <configuration> - <environmentVariables> - <SPARK_HOME>${basedir}/..</SPARK_HOME> - <SPARK_TESTING>1</SPARK_TESTING> - <SPARK_CLASSPATH>${spark.classpath}</SPARK_CLASSPATH> - </environmentVariables> - </configuration> - </plugin> - </plugins> - </build> -</project> diff --git a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala deleted file mode 100644 index 4b69f5078b..0000000000 --- a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.scheduler.cluster - -import org.apache.hadoop.yarn.api.records.{ApplicationId, YarnApplicationState} -import org.apache.spark.{SparkException, Logging, SparkContext} -import org.apache.spark.deploy.yarn.{Client, ClientArguments} -import org.apache.spark.scheduler.TaskSchedulerImpl - -private[spark] class YarnClientSchedulerBackend( - scheduler: TaskSchedulerImpl, - sc: SparkContext) - extends CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem) - with Logging { - - var client: Client = null - var appId: ApplicationId = null - - override def start() { - super.start() - - val defalutWorkerCores = "2" - val defalutWorkerMemory = "512m" - val defaultWorkerNumber = "1" - - val userJar = System.getenv("SPARK_YARN_APP_JAR") - var workerCores = System.getenv("SPARK_WORKER_CORES") - var workerMemory = System.getenv("SPARK_WORKER_MEMORY") - var workerNumber = System.getenv("SPARK_WORKER_INSTANCES") - - if (userJar == null) - throw new SparkException("env SPARK_YARN_APP_JAR is not set") - - if (workerCores == null) - workerCores = defalutWorkerCores - if (workerMemory == null) - workerMemory = defalutWorkerMemory - if (workerNumber == null) - workerNumber = defaultWorkerNumber - - val driverHost = conf.get("spark.driver.host") - val driverPort = conf.get("spark.driver.port") - val hostport = driverHost + ":" + driverPort - - val argsArray = Array[String]( - "--class", "notused", - "--jar", userJar, - "--args", hostport, - "--worker-memory", workerMemory, - "--worker-cores", workerCores, - "--num-workers", workerNumber, - "--master-class", "org.apache.spark.deploy.yarn.WorkerLauncher" - ) - - val args = new ClientArguments(argsArray) - client = new Client(args) - appId = client.runApp() - waitForApp() - } - - def waitForApp() { - - // TODO : need a better way to find out whether the workers are ready or not - // maybe by resource usage report? - while(true) { - val report = client.getApplicationReport(appId) - - logInfo("Application report from ASM: \n" + - "\t appMasterRpcPort: " + report.getRpcPort() + "\n" + - "\t appStartTime: " + report.getStartTime() + "\n" + - "\t yarnAppState: " + report.getYarnApplicationState() + "\n" - ) - - // Ready to go, or already gone. - val state = report.getYarnApplicationState() - if (state == YarnApplicationState.RUNNING) { - return - } else if (state == YarnApplicationState.FINISHED || - state == YarnApplicationState.FAILED || - state == YarnApplicationState.KILLED) { - throw new SparkException("Yarn application already ended," + - "might be killed or not able to launch application master.") - } - - Thread.sleep(1000) - } - } - - override def stop() { - super.stop() - client.stop() - logInfo("Stoped") - } - -} @@ -87,12 +87,17 @@ <modules> <module>core</module> <module>bagel</module> - <module>examples</module> <module>mllib</module> <module>tools</module> <module>streaming</module> <module>repl</module> <module>assembly</module> + <module>external/twitter</module> + <module>external/kafka</module> + <module>external/flume</module> + <module>external/zeromq</module> + <module>external/mqtt</module> + <module>examples</module> </modules> <properties> @@ -141,15 +146,9 @@ </snapshots> </repository> <repository> - <id>mqtt-repo</id> - <name>MQTT Repository</name> - <url>https://repo.eclipse.org/content/repositories/paho-releases</url> - <releases> - <enabled>true</enabled> - </releases> - <snapshots> - <enabled>false</enabled> - </snapshots> + <id>cloudera-repo</id> + <name>Cloudera Repository</name> + <url>https://repository.cloudera.com/artifactory/cloudera-repos</url> </repository> </repositories> @@ -188,7 +187,7 @@ <dependency> <groupId>com.ning</groupId> <artifactId>compress-lzf</artifactId> - <version>0.8.4</version> + <version>1.0.0</version> </dependency> <dependency> <groupId>org.xerial.snappy</groupId> @@ -260,7 +259,7 @@ </dependency> <dependency> <groupId>${akka.group}</groupId> - <artifactId>akka-zeromq_${scala.binary.version}</artifactId> + <artifactId>akka-testkit_${scala.binary.version}</artifactId> <version>${akka.version}</version> <exclusions> <exclusion> @@ -358,6 +357,12 @@ <scope>test</scope> </dependency> <dependency> + <groupId>org.mockito</groupId> + <artifactId>mockito-all</artifactId> + <scope>test</scope> + <version>1.8.5</version> + </dependency> + <dependency> <groupId>commons-io</groupId> <artifactId>commons-io</artifactId> <version>2.4</version> @@ -722,12 +727,11 @@ <profiles> <profile> - <id>hadoop2-yarn</id> + <id>yarn-alpha</id> <properties> <hadoop.major.version>2</hadoop.major.version> <!-- 0.23.* is same as 2.0.* - except hardened to run production jobs --> <hadoop.version>0.23.7</hadoop.version> - <protobuf.version>2.5.0</protobuf.version> <!--<hadoop.version>2.0.5-alpha</hadoop.version> --> </properties> @@ -735,57 +739,20 @@ <module>yarn</module> </modules> - <repositories> - <repository> - <id>maven-root</id> - <name>Maven root repository</name> - <url>http://repo1.maven.org/maven2</url> - <releases> - <enabled>true</enabled> - </releases> - <snapshots> - <enabled>false</enabled> - </snapshots> - </repository> - </repositories> - - <dependencyManagement> - <dependencies> - </dependencies> - </dependencyManagement> </profile> <profile> - <id>new-yarn</id> - <properties> - <hadoop.major.version>2</hadoop.major.version> - <hadoop.version>2.2.0</hadoop.version> - <protobuf.version>2.5.0</protobuf.version> - </properties> - - <modules> - <module>new-yarn</module> - </modules> - - <repositories> - <repository> - <id>maven-root</id> - <name>Maven root repository</name> - <url>http://repo1.maven.org/maven2</url> - <releases> - <enabled>true</enabled> - </releases> - <snapshots> - <enabled>false</enabled> - </snapshots> - </repository> - </repositories> + <id>yarn</id> + <properties> + <hadoop.major.version>2</hadoop.major.version> + <hadoop.version>2.2.0</hadoop.version> + <protobuf.version>2.5.0</protobuf.version> + </properties> + <modules> + <module>yarn</module> + </modules> - <dependencyManagement> - <dependencies> - </dependencies> - </dependencyManagement> - </profile> + </profile> <profile> <id>repl-bin</id> diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 2eef2dfa5e..f794918d22 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -20,6 +20,7 @@ import sbt.Classpaths.publishTask import Keys._ import sbtassembly.Plugin._ import AssemblyKeys._ +import scala.util.Properties // For Sonatype publishing //import com.jsuereth.pgp.sbtplugin.PgpKeys._ @@ -49,9 +50,6 @@ object SparkBuild extends Build { lazy val repl = Project("repl", file("repl"), settings = replSettings) .dependsOn(core, bagel, mllib) - lazy val examples = Project("examples", file("examples"), settings = examplesSettings) - .dependsOn(core, mllib, bagel, streaming) - lazy val tools = Project("tools", file("tools"), settings = toolsSettings) dependsOn(core) dependsOn(streaming) lazy val bagel = Project("bagel", file("bagel"), settings = bagelSettings) dependsOn(core) @@ -68,10 +66,11 @@ object SparkBuild extends Build { // A configuration to set an alternative publishLocalConfiguration lazy val MavenCompile = config("m2r") extend(Compile) lazy val publishLocalBoth = TaskKey[Unit]("publish-local", "publish local for m2 and ivy") + val sparkHome = System.getProperty("user.dir") // Allows build configuration to be set through environment variables - lazy val hadoopVersion = scala.util.Properties.envOrElse("SPARK_HADOOP_VERSION", DEFAULT_HADOOP_VERSION) - lazy val isNewHadoop = scala.util.Properties.envOrNone("SPARK_IS_NEW_HADOOP") match { + lazy val hadoopVersion = Properties.envOrElse("SPARK_HADOOP_VERSION", DEFAULT_HADOOP_VERSION) + lazy val isNewHadoop = Properties.envOrNone("SPARK_IS_NEW_HADOOP") match { case None => { val isNewHadoopVersion = "2.[2-9]+".r.findFirstIn(hadoopVersion).isDefined (isNewHadoopVersion|| DEFAULT_IS_NEW_HADOOP) @@ -79,23 +78,43 @@ object SparkBuild extends Build { case Some(v) => v.toBoolean } - lazy val isYarnEnabled = scala.util.Properties.envOrNone("SPARK_YARN") match { + lazy val isYarnEnabled = Properties.envOrNone("SPARK_YARN") match { case None => DEFAULT_YARN case Some(v) => v.toBoolean } // Conditionally include the yarn sub-project - lazy val yarn = Project("yarn", file(if (isNewHadoop) "new-yarn" else "yarn"), settings = yarnSettings) dependsOn(core) - - //lazy val yarn = Project("yarn", file("yarn"), settings = yarnSettings) dependsOn(core) - - lazy val maybeYarn = if (isYarnEnabled) Seq[ClasspathDependency](yarn) else Seq[ClasspathDependency]() - lazy val maybeYarnRef = if (isYarnEnabled) Seq[ProjectReference](yarn) else Seq[ProjectReference]() + lazy val yarnAlpha = Project("yarn-alpha", file("yarn/alpha"), settings = yarnAlphaSettings) dependsOn(core) + lazy val yarn = Project("yarn", file("yarn/stable"), settings = yarnSettings) dependsOn(core) + + lazy val maybeYarn = if (isYarnEnabled) Seq[ClasspathDependency](if (isNewHadoop) yarn else yarnAlpha) else Seq[ClasspathDependency]() + lazy val maybeYarnRef = if (isYarnEnabled) Seq[ProjectReference](if (isNewHadoop) yarn else yarnAlpha) else Seq[ProjectReference]() + + lazy val externalTwitter = Project("external-twitter", file("external/twitter"), settings = twitterSettings) + .dependsOn(streaming % "compile->compile;test->test") + + lazy val externalKafka = Project("external-kafka", file("external/kafka"), settings = kafkaSettings) + .dependsOn(streaming % "compile->compile;test->test") + + lazy val externalFlume = Project("external-flume", file("external/flume"), settings = flumeSettings) + .dependsOn(streaming % "compile->compile;test->test") + + lazy val externalZeromq = Project("external-zeromq", file("external/zeromq"), settings = zeromqSettings) + .dependsOn(streaming % "compile->compile;test->test") + + lazy val externalMqtt = Project("external-mqtt", file("external/mqtt"), settings = mqttSettings) + .dependsOn(streaming % "compile->compile;test->test") + + lazy val allExternal = Seq[ClasspathDependency](externalTwitter, externalKafka, externalFlume, externalZeromq, externalMqtt) + lazy val allExternalRefs = Seq[ProjectReference](externalTwitter, externalKafka, externalFlume, externalZeromq, externalMqtt) + + lazy val examples = Project("examples", file("examples"), settings = examplesSettings) + .dependsOn(core, mllib, bagel, streaming, externalTwitter) dependsOn(allExternal: _*) // Everything except assembly, tools and examples belong to packageProjects lazy val packageProjects = Seq[ProjectReference](core, repl, bagel, streaming, mllib) ++ maybeYarnRef - lazy val allProjects = packageProjects ++ Seq[ProjectReference](examples, tools, assemblyProj) + lazy val allProjects = packageProjects ++ allExternalRefs ++ Seq[ProjectReference](examples, tools, assemblyProj) def sharedSettings = Defaults.defaultSettings ++ Seq( organization := "org.apache.spark", @@ -112,8 +131,9 @@ object SparkBuild extends Build { // Fork new JVMs for tests and set Java options for those fork := true, + javaOptions in Test += "-Dspark.home=" + sparkHome, + javaOptions in Test += "-Dspark.testing=1", javaOptions += "-Xmx3g", - // Show full stack trace and duration in test cases. testOptions in Test += Tests.Argument("-oDF"), @@ -123,7 +143,7 @@ object SparkBuild extends Build { // also check the local Maven repository ~/.m2 resolvers ++= Seq(Resolver.file("Local Maven Repo", file(Path.userHome + "/.m2/repository"))), - // For Sonatype publishing + // For Sonatype publishing resolvers ++= Seq("sonatype-snapshots" at "https://oss.sonatype.org/content/repositories/snapshots", "sonatype-staging" at "https://oss.sonatype.org/service/local/staging/deploy/maven2/"), @@ -165,7 +185,7 @@ object SparkBuild extends Build { </issueManagement> ), -/* + /* publishTo <<= version { (v: String) => val nexus = "https://oss.sonatype.org/" if (v.trim.endsWith("SNAPSHOT")) @@ -174,8 +194,7 @@ object SparkBuild extends Build { Some("sonatype-staging" at nexus + "service/local/staging/deploy/maven2") }, -*/ - + */ libraryDependencies ++= Seq( "io.netty" % "netty-all" % "4.0.13.Final", @@ -226,11 +245,12 @@ object SparkBuild extends Build { "org.slf4j" % "slf4j-api" % slf4jVersion, "org.slf4j" % "slf4j-log4j12" % slf4jVersion, "commons-daemon" % "commons-daemon" % "1.0.10", // workaround for bug HADOOP-9407 - "com.ning" % "compress-lzf" % "0.8.4", + "com.ning" % "compress-lzf" % "1.0.0", "org.xerial.snappy" % "snappy-java" % "1.0.5", "org.ow2.asm" % "asm" % "4.0", "org.spark-project.akka" %% "akka-remote" % "2.2.3-shaded-protobuf" excludeAll(excludeNetty), "org.spark-project.akka" %% "akka-slf4j" % "2.2.3-shaded-protobuf" excludeAll(excludeNetty), + "org.spark-project.akka" %% "akka-testkit" % "2.2.3-shaded-protobuf" % "test", "net.liftweb" %% "lift-json" % "2.5.1" excludeAll(excludeNetty), "it.unimi.dsi" % "fastutil" % "6.4.4", "colt" % "colt" % "1.2.0", @@ -264,7 +284,6 @@ object SparkBuild extends Build { libraryDependencies <+= scalaVersion(v => "org.scala-lang" % "scala-reflect" % v ) ) - def examplesSettings = sharedSettings ++ Seq( name := "spark-examples", libraryDependencies ++= Seq( @@ -301,29 +320,34 @@ object SparkBuild extends Build { def streamingSettings = sharedSettings ++ Seq( name := "spark-streaming", - resolvers ++= Seq( - "Eclipse Repository" at "https://repo.eclipse.org/content/repositories/paho-releases/", - "Apache repo" at "https://repository.apache.org/content/repositories/releases" - ), - libraryDependencies ++= Seq( - "org.apache.flume" % "flume-ng-sdk" % "1.2.0" % "compile" excludeAll(excludeNetty, excludeSnappy), - "com.sksamuel.kafka" %% "kafka" % "0.8.0-beta1" - exclude("com.sun.jdmk", "jmxtools") - exclude("com.sun.jmx", "jmxri") - exclude("net.sf.jopt-simple", "jopt-simple") - excludeAll(excludeNetty), - "org.eclipse.paho" % "mqtt-client" % "0.4.0", - "com.github.sgroschupf" % "zkclient" % "0.1" excludeAll(excludeNetty), - "org.twitter4j" % "twitter4j-stream" % "3.0.3" excludeAll(excludeNetty), - "org.spark-project.akka" %% "akka-zeromq" % "2.2.3-shaded-protobuf" excludeAll(excludeNetty) + "commons-io" % "commons-io" % "2.4" ) ) - def yarnSettings = sharedSettings ++ Seq( - name := "spark-yarn" + def yarnCommonSettings = sharedSettings ++ Seq( + unmanagedSourceDirectories in Compile <++= baseDirectory { base => + Seq( + base / "../common/src/main/scala" + ) + }, + + unmanagedSourceDirectories in Test <++= baseDirectory { base => + Seq( + base / "../common/src/test/scala" + ) + } + ) ++ extraYarnSettings + def yarnAlphaSettings = yarnCommonSettings ++ Seq( + name := "spark-yarn-alpha" + ) + + def yarnSettings = yarnCommonSettings ++ Seq( + name := "spark-yarn" + ) + // Conditionally include the YARN dependencies because some tools look at all sub-projects and will complain // if we refer to nonexistent dependencies (e.g. hadoop-yarn-api from a Hadoop version without YARN). def extraYarnSettings = if(isYarnEnabled) yarnEnabledSettings else Seq() @@ -331,14 +355,15 @@ object SparkBuild extends Build { def yarnEnabledSettings = Seq( libraryDependencies ++= Seq( // Exclude rule required for all ? - "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), - "org.apache.hadoop" % "hadoop-yarn-api" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), + "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), + "org.apache.hadoop" % "hadoop-yarn-api" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), "org.apache.hadoop" % "hadoop-yarn-common" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), "org.apache.hadoop" % "hadoop-yarn-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib) ) ) def assemblyProjSettings = sharedSettings ++ Seq( + libraryDependencies += "net.sf.py4j" % "py4j" % "0.8.1", name := "spark-assembly", assembleDeps in Compile <<= (packageProjects.map(packageBin in Compile in _) ++ Seq(packageDependency in Compile)).dependOn, jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" }, @@ -356,4 +381,43 @@ object SparkBuild extends Build { case _ => MergeStrategy.first } ) + + def twitterSettings() = sharedSettings ++ Seq( + name := "spark-streaming-twitter", + libraryDependencies ++= Seq( + "org.twitter4j" % "twitter4j-stream" % "3.0.3" excludeAll(excludeNetty) + ) + ) + + def kafkaSettings() = sharedSettings ++ Seq( + name := "spark-streaming-kafka", + libraryDependencies ++= Seq( + "com.github.sgroschupf" % "zkclient" % "0.1" excludeAll(excludeNetty), + "com.sksamuel.kafka" %% "kafka" % "0.8.0-beta1" + exclude("com.sun.jdmk", "jmxtools") + exclude("com.sun.jmx", "jmxri") + exclude("net.sf.jopt-simple", "jopt-simple") + excludeAll(excludeNetty) + ) + ) + + def flumeSettings() = sharedSettings ++ Seq( + name := "spark-streaming-flume", + libraryDependencies ++= Seq( + "org.apache.flume" % "flume-ng-sdk" % "1.2.0" % "compile" excludeAll(excludeNetty, excludeSnappy) + ) + ) + + def zeromqSettings() = sharedSettings ++ Seq( + name := "spark-streaming-zeromq", + libraryDependencies ++= Seq( + "org.spark-project.akka" %% "akka-zeromq" % "2.2.3-shaded-protobuf" excludeAll(excludeNetty) + ) + ) + + def mqttSettings() = streamingSettings ++ Seq( + name := "spark-streaming-mqtt", + resolvers ++= Seq("Eclipse Repo" at "https://repo.eclipse.org/content/repositories/paho-releases/"), + libraryDependencies ++= Seq("org.eclipse.paho" % "mqtt-client" % "0.4.0") + ) } diff --git a/project/build.properties b/project/build.properties index 9647277162..839f5fbb0c 100644 --- a/project/build.properties +++ b/project/build.properties @@ -14,5 +14,4 @@ # See the License for the specific language governing permissions and # limitations under the License. # - sbt.version=0.12.4 diff --git a/python/lib/py4j-0.8.1-src.zip b/python/lib/py4j-0.8.1-src.zip Binary files differnew file mode 100644 index 0000000000..2069a328d1 --- /dev/null +++ b/python/lib/py4j-0.8.1-src.zip diff --git a/python/lib/py4j0.7.egg b/python/lib/py4j0.7.egg Binary files differdeleted file mode 100644 index f8a339d8ee..0000000000 --- a/python/lib/py4j0.7.egg +++ /dev/null diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py index 2b2c3a061a..a51d5af79b 100644 --- a/python/pyspark/__init__.py +++ b/python/pyspark/__init__.py @@ -40,7 +40,7 @@ Public classes: import sys import os -sys.path.insert(0, os.path.join(os.environ["SPARK_HOME"], "python/lib/py4j0.7.egg")) +sys.path.insert(0, os.path.join(os.environ["SPARK_HOME"], "python/lib/py4j-0.8.1-src.zip")) from pyspark.conf import SparkConf diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py index d8ca9fce00..c15add5237 100644 --- a/python/pyspark/java_gateway.py +++ b/python/pyspark/java_gateway.py @@ -31,7 +31,7 @@ def launch_gateway(): # Launch the Py4j gateway using Spark's run command so that we pick up the # proper classpath and SPARK_MEM settings from spark-env.sh on_windows = platform.system() == "Windows" - script = "spark-class.cmd" if on_windows else "spark-class" + script = "./bin/spark-class.cmd" if on_windows else "./bin/spark-class" command = [os.path.join(SPARK_HOME, script), "py4j.GatewayServer", "--die-on-broken-pipe", "0"] if not on_windows: diff --git a/python/pyspark/mllib/_common.py b/python/pyspark/mllib/_common.py index e74ba0fabc..769d88dfb9 100644 --- a/python/pyspark/mllib/_common.py +++ b/python/pyspark/mllib/_common.py @@ -18,6 +18,9 @@ from numpy import ndarray, copyto, float64, int64, int32, ones, array_equal, array, dot, shape from pyspark import SparkContext +from pyspark.serializers import Serializer +import struct + # Double vector format: # # [8-byte 1] [8-byte length] [length*8 bytes of data] @@ -213,6 +216,28 @@ def _serialize_rating(r): intpart[0], intpart[1], doublepart[0] = r return ba +class RatingDeserializer(Serializer): + def loads(self, stream): + length = struct.unpack("!i", stream.read(4))[0] + ba = stream.read(length) + res = ndarray(shape=(3, ), buffer=ba, dtype="float64", offset=4) + return int(res[0]), int(res[1]), res[2] + + def load_stream(self, stream): + while True: + try: + yield self.loads(stream) + except struct.error: + return + except EOFError: + return + +def _serialize_tuple(t): + ba = bytearray(8) + intpart = ndarray(shape=[2], buffer=ba, dtype=int32) + intpart[0], intpart[1] = t + return ba + def _test(): import doctest globs = globals().copy() diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py index 14d06cba21..0eeb5bb66b 100644 --- a/python/pyspark/mllib/recommendation.py +++ b/python/pyspark/mllib/recommendation.py @@ -20,7 +20,9 @@ from pyspark.mllib._common import \ _get_unmangled_rdd, _get_unmangled_double_vector_rdd, \ _serialize_double_matrix, _deserialize_double_matrix, \ _serialize_double_vector, _deserialize_double_vector, \ - _get_initial_weights, _serialize_rating, _regression_train_wrapper + _get_initial_weights, _serialize_rating, _regression_train_wrapper, \ + _serialize_tuple, RatingDeserializer +from pyspark.rdd import RDD class MatrixFactorizationModel(object): """A matrix factorisation model trained by regularized alternating @@ -33,6 +35,9 @@ class MatrixFactorizationModel(object): >>> model = ALS.trainImplicit(sc, ratings, 1) >>> model.predict(2,2) is not None True + >>> testset = sc.parallelize([(1, 2), (1, 1)]) + >>> model.predictAll(testset).count == 2 + True """ def __init__(self, sc, java_model): @@ -45,6 +50,11 @@ class MatrixFactorizationModel(object): def predict(self, user, product): return self._java_model.predict(user, product) + def predictAll(self, usersProducts): + usersProductsJRDD = _get_unmangled_rdd(usersProducts, _serialize_tuple) + return RDD(self._java_model.predict(usersProductsJRDD._jrdd), + self._context, RatingDeserializer()) + class ALS(object): @classmethod def train(cls, sc, ratings, rank, iterations=5, lambda_=0.01, blocks=-1): diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index f87923e6fa..6fb4a7b3be 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -23,6 +23,7 @@ import operator import os import sys import shlex +import traceback from subprocess import Popen, PIPE from tempfile import NamedTemporaryFile from threading import Thread @@ -39,6 +40,46 @@ from py4j.java_collections import ListConverter, MapConverter __all__ = ["RDD"] +def _extract_concise_traceback(): + tb = traceback.extract_stack() + if len(tb) == 0: + return "I'm lost!" + # HACK: This function is in a file called 'rdd.py' in the top level of + # everything PySpark. Just trim off the directory name and assume + # everything in that tree is PySpark guts. + file, line, module, what = tb[len(tb) - 1] + sparkpath = os.path.dirname(file) + first_spark_frame = len(tb) - 1 + for i in range(0, len(tb)): + file, line, fun, what = tb[i] + if file.startswith(sparkpath): + first_spark_frame = i + break + if first_spark_frame == 0: + file, line, fun, what = tb[0] + return "%s at %s:%d" % (fun, file, line) + sfile, sline, sfun, swhat = tb[first_spark_frame] + ufile, uline, ufun, uwhat = tb[first_spark_frame-1] + return "%s at %s:%d" % (sfun, ufile, uline) + +_spark_stack_depth = 0 + +class _JavaStackTrace(object): + def __init__(self, sc): + self._traceback = _extract_concise_traceback() + self._context = sc + + def __enter__(self): + global _spark_stack_depth + if _spark_stack_depth == 0: + self._context._jsc.setCallSite(self._traceback) + _spark_stack_depth += 1 + + def __exit__(self, type, value, tb): + global _spark_stack_depth + _spark_stack_depth -= 1 + if _spark_stack_depth == 0: + self._context._jsc.setCallSite(None) class RDD(object): """ @@ -401,7 +442,8 @@ class RDD(object): """ Return a list that contains all of the elements in this RDD. """ - bytesInJava = self._jrdd.collect().iterator() + with _JavaStackTrace(self.context) as st: + bytesInJava = self._jrdd.collect().iterator() return list(self._collect_iterator_through_file(bytesInJava)) def _collect_iterator_through_file(self, iterator): @@ -582,13 +624,14 @@ class RDD(object): # TODO(shivaram): Similar to the scala implementation, update the take # method to scan multiple splits based on an estimate of how many elements # we have per-split. - for partition in range(mapped._jrdd.splits().size()): - partitionsToTake = self.ctx._gateway.new_array(self.ctx._jvm.int, 1) - partitionsToTake[0] = partition - iterator = mapped._jrdd.collectPartitions(partitionsToTake)[0].iterator() - items.extend(mapped._collect_iterator_through_file(iterator)) - if len(items) >= num: - break + with _JavaStackTrace(self.context) as st: + for partition in range(mapped._jrdd.splits().size()): + partitionsToTake = self.ctx._gateway.new_array(self.ctx._jvm.int, 1) + partitionsToTake[0] = partition + iterator = mapped._jrdd.collectPartitions(partitionsToTake)[0].iterator() + items.extend(mapped._collect_iterator_through_file(iterator)) + if len(items) >= num: + break return items[:num] def first(self): @@ -765,9 +808,10 @@ class RDD(object): yield outputSerializer.dumps(items) keyed = PipelinedRDD(self, add_shuffle_key) keyed._bypass_serializer = True - pairRDD = self.ctx._jvm.PairwiseRDD(keyed._jrdd.rdd()).asJavaPairRDD() - partitioner = self.ctx._jvm.PythonPartitioner(numPartitions, - id(partitionFunc)) + with _JavaStackTrace(self.context) as st: + pairRDD = self.ctx._jvm.PairwiseRDD(keyed._jrdd.rdd()).asJavaPairRDD() + partitioner = self.ctx._jvm.PythonPartitioner(numPartitions, + id(partitionFunc)) jrdd = pairRDD.partitionBy(partitioner).values() rdd = RDD(jrdd, self.ctx, BatchedSerializer(outputSerializer)) # This is required so that id(partitionFunc) remains unique, even if diff --git a/python/pyspark/shell.py b/python/pyspark/shell.py index ef07eb437b..1602227a27 100644 --- a/python/pyspark/shell.py +++ b/python/pyspark/shell.py @@ -47,7 +47,7 @@ print "Spark context available as sc." if add_files != None: print "Adding files: [%s]" % ", ".join(add_files) -# The ./pyspark script stores the old PYTHONSTARTUP value in OLD_PYTHONSTARTUP, +# The ./bin/pyspark script stores the old PYTHONSTARTUP value in OLD_PYTHONSTARTUP, # which allows us to execute the user's PYTHONSTARTUP file: _pythonstartup = os.environ.get('OLD_PYTHONSTARTUP') if _pythonstartup and os.path.isfile(_pythonstartup): diff --git a/python/run-tests b/python/run-tests index 4b71fff7c1..feba97cee0 100755 --- a/python/run-tests +++ b/python/run-tests @@ -29,7 +29,7 @@ FAILED=0 rm -f unit-tests.log function run_test() { - SPARK_TESTING=0 $FWDIR/pyspark $1 2>&1 | tee -a unit-tests.log + SPARK_TESTING=0 $FWDIR/bin/pyspark $1 2>&1 | tee -a unit-tests.log FAILED=$((PIPESTATUS[0]||$FAILED)) } diff --git a/repl-bin/src/deb/bin/run b/repl-bin/src/deb/bin/run index 47bb654baf..3a6f22f41f 100755 --- a/repl-bin/src/deb/bin/run +++ b/repl-bin/src/deb/bin/run @@ -48,8 +48,7 @@ fi export JAVA_OPTS # Build up classpath -CLASSPATH="$SPARK_CLASSPATH" -CLASSPATH+=":$FWDIR/conf" +CLASSPATH=":$FWDIR/conf" for jar in `find $FWDIR -name '*jar'`; do CLASSPATH+=":$jar" done diff --git a/repl/pom.xml b/repl/pom.xml index b0e7877bbb..2dfe7ac900 100644 --- a/repl/pom.xml +++ b/repl/pom.xml @@ -127,7 +127,6 @@ <environmentVariables> <SPARK_HOME>${basedir}/..</SPARK_HOME> <SPARK_TESTING>1</SPARK_TESTING> - <SPARK_CLASSPATH>${spark.classpath}</SPARK_CLASSPATH> </environmentVariables> </configuration> </plugin> diff --git a/repl/src/main/scala/org/apache/spark/repl/SparkCommandLine.scala b/repl/src/main/scala/org/apache/spark/repl/SparkCommandLine.scala new file mode 100644 index 0000000000..05816941b5 --- /dev/null +++ b/repl/src/main/scala/org/apache/spark/repl/SparkCommandLine.scala @@ -0,0 +1,37 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.repl + +import scala.tools.nsc.{Settings, CompilerCommand} +import scala.Predef._ + +/** + * Command class enabling Spark-specific command line options (provided by + * <i>org.apache.spark.repl.SparkRunnerSettings</i>). + */ +class SparkCommandLine(args: List[String], override val settings: Settings) + extends CompilerCommand(args, settings) { + + def this(args: List[String], error: String => Unit) { + this(args, new SparkRunnerSettings(error)) + } + + def this(args: List[String]) { + this(args, str => Console.println("Error: " + str)) + } +} diff --git a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala index f108c70f21..87d94d51be 100644 --- a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala +++ b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala @@ -835,7 +835,7 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, // runs :load `file` on any files passed via -i def loadFiles(settings: Settings) = settings match { - case settings: GenericRunnerSettings => + case settings: SparkRunnerSettings => for (filename <- settings.loadfiles.value) { val cmd = ":load " + filename command(cmd) @@ -902,7 +902,6 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, addThunk(printWelcome()) addThunk(initializeSpark()) - loadFiles(settings) // it is broken on startup; go ahead and exit if (intp.reporter.hasErrors) return false @@ -922,6 +921,8 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, } // printWelcome() + loadFiles(settings) + try loop() catch AbstractOrMissingHandler() finally closeInterpreter() @@ -942,12 +943,14 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, val conf = new SparkConf() .setMaster(master) .setAppName("Spark shell") - .setSparkHome(System.getenv("SPARK_HOME")) .setJars(jars) .set("spark.repl.class.uri", intp.classServer.uri) if (execUri != null) { conf.set("spark.executor.uri", execUri) } + if (System.getenv("SPARK_HOME") != null) { + conf.setSparkHome(System.getenv("SPARK_HOME")) + } sparkContext = new SparkContext(conf) echo("Created spark context..") sparkContext @@ -955,7 +958,7 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, /** process command-line arguments and do as they request */ def process(args: Array[String]): Boolean = { - val command = new CommandLine(args.toList, echo) + val command = new SparkCommandLine(args.toList, msg => echo(msg)) def neededHelp(): String = (if (command.settings.help.value) command.usageMsg + "\n" else "") + (if (command.settings.Xhelp.value) command.xusageMsg + "\n" else "") diff --git a/repl/src/main/scala/org/apache/spark/repl/SparkRunnerSettings.scala b/repl/src/main/scala/org/apache/spark/repl/SparkRunnerSettings.scala new file mode 100644 index 0000000000..7fd5fbb424 --- /dev/null +++ b/repl/src/main/scala/org/apache/spark/repl/SparkRunnerSettings.scala @@ -0,0 +1,32 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.repl + +import scala.tools.nsc.Settings + +/** + * <i>scala.tools.nsc.Settings</i> implementation adding Spark-specific REPL + * command line options. + */ +class SparkRunnerSettings(error: String => Unit) extends Settings(error){ + + val loadfiles = MultiStringSetting( + "-i", + "file", + "load a file (assumes the code is given interactively)") +} diff --git a/bin/slaves.sh b/sbin/slaves.sh index c367c2fd8e..a5bc2183d8 100755 --- a/bin/slaves.sh +++ b/sbin/slaves.sh @@ -36,10 +36,10 @@ if [ $# -le 0 ]; then exit 1 fi -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" # If the slaves file is specified in the command line, # then it takes precedence over the definition in diff --git a/bin/spark-config.sh b/sbin/spark-config.sh index cd2c7b7b0d..cd2c7b7b0d 100755 --- a/bin/spark-config.sh +++ b/sbin/spark-config.sh diff --git a/bin/spark-daemon.sh b/sbin/spark-daemon.sh index a0c0d44b58..2be2b3d7c0 100755 --- a/bin/spark-daemon.sh +++ b/sbin/spark-daemon.sh @@ -37,10 +37,10 @@ if [ $# -le 1 ]; then exit 1 fi -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" # get arguments @@ -147,7 +147,7 @@ case $startStop in spark_rotate_log "$log" echo starting $command, logging to $log cd "$SPARK_PREFIX" - nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/spark-class $command "$@" >> "$log" 2>&1 < /dev/null & + nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/bin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null & newpid=$! echo $newpid > $pid sleep 2 diff --git a/bin/spark-daemons.sh b/sbin/spark-daemons.sh index 64286cb2da..5d9f2bb51c 100755 --- a/bin/spark-daemons.sh +++ b/sbin/spark-daemons.sh @@ -27,9 +27,9 @@ if [ $# -le 1 ]; then exit 1 fi -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" -exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/spark-daemon.sh" "$@" +exec "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/spark-daemon.sh" "$@" diff --git a/spark-executor b/sbin/spark-executor index 2c07c54843..de5bfab563 100755 --- a/spark-executor +++ b/sbin/spark-executor @@ -17,6 +17,7 @@ # limitations under the License. # -FWDIR="`dirname $0`" +FWDIR="$(cd `dirname $0`/..; pwd)" + echo "Running spark-executor with framework dir = $FWDIR" -exec $FWDIR/spark-class org.apache.spark.executor.MesosExecutorBackend +exec $FWDIR/bin/spark-class org.apache.spark.executor.MesosExecutorBackend diff --git a/bin/start-all.sh b/sbin/start-all.sh index 0182f1ab24..2daf49db35 100755 --- a/bin/start-all.sh +++ b/sbin/start-all.sh @@ -21,14 +21,14 @@ # Starts the master on this node. # Starts a worker on each node specified in conf/slaves -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` # Load the Spark configuration -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" # Start Master -"$bin"/start-master.sh +"$sbin"/start-master.sh # Start Workers -"$bin"/start-slaves.sh +"$sbin"/start-slaves.sh diff --git a/bin/start-master.sh b/sbin/start-master.sh index 648c7ae75f..3dcf7cc348 100755 --- a/bin/start-master.sh +++ b/sbin/start-master.sh @@ -19,10 +19,10 @@ # Starts the master on the machine this script is executed on. -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then . "${SPARK_CONF_DIR}/spark-env.sh" @@ -49,4 +49,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then fi fi -"$bin"/spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT +"$sbin"/spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT diff --git a/bin/start-slave.sh b/sbin/start-slave.sh index 4eefa20944..524be38c62 100755 --- a/bin/start-slave.sh +++ b/sbin/start-slave.sh @@ -20,8 +20,8 @@ # Usage: start-slave.sh <worker#> <master-spark-URL> # where <master-spark-URL> is like "spark://localhost:7077" -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` # Set SPARK_PUBLIC_DNS so slaves can be linked in master web UI if [ "$SPARK_PUBLIC_DNS" = "" ]; then @@ -32,4 +32,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then fi fi -"$bin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker "$@" +"$sbin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker "$@" diff --git a/bin/start-slaves.sh b/sbin/start-slaves.sh index 00dc4888b2..fd5cdeb1e6 100755 --- a/bin/start-slaves.sh +++ b/sbin/start-slaves.sh @@ -17,10 +17,10 @@ # limitations under the License. # -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then . "${SPARK_CONF_DIR}/spark-env.sh" @@ -37,12 +37,12 @@ fi # Launch the slaves if [ "$SPARK_WORKER_INSTANCES" = "" ]; then - exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT + exec "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT else if [ "$SPARK_WORKER_WEBUI_PORT" = "" ]; then SPARK_WORKER_WEBUI_PORT=8081 fi for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do - "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" $(( $i + 1 )) spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT --webui-port $(( $SPARK_WORKER_WEBUI_PORT + $i )) + "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/start-slave.sh" $(( $i + 1 )) spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT --webui-port $(( $SPARK_WORKER_WEBUI_PORT + $i )) done fi diff --git a/bin/stop-all.sh b/sbin/stop-all.sh index b6c83a7ba4..60b358d374 100755 --- a/bin/stop-all.sh +++ b/sbin/stop-all.sh @@ -21,12 +21,12 @@ # Run this on the master nde -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` # Load the Spark configuration -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" # Stop the slaves, then the master -"$bin"/stop-slaves.sh -"$bin"/stop-master.sh +"$sbin"/stop-slaves.sh +"$sbin"/stop-master.sh diff --git a/bin/stop-master.sh b/sbin/stop-master.sh index 310e33bedc..2adabd4265 100755 --- a/bin/stop-master.sh +++ b/sbin/stop-master.sh @@ -19,9 +19,9 @@ # Starts the master on the machine this script is executed on. -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" -"$bin"/spark-daemon.sh stop org.apache.spark.deploy.master.Master 1 +"$sbin"/spark-daemon.sh stop org.apache.spark.deploy.master.Master 1 diff --git a/bin/stop-slaves.sh b/sbin/stop-slaves.sh index fcb8555d4e..eb803b4900 100755 --- a/bin/stop-slaves.sh +++ b/sbin/stop-slaves.sh @@ -17,19 +17,19 @@ # limitations under the License. # -bin=`dirname "$0"` -bin=`cd "$bin"; pwd` +sbin=`dirname "$0"` +sbin=`cd "$sbin"; pwd` -. "$bin/spark-config.sh" +. "$sbin/spark-config.sh" if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then . "${SPARK_CONF_DIR}/spark-env.sh" fi if [ "$SPARK_WORKER_INSTANCES" = "" ]; then - "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker 1 + "$sbin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker 1 else for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do - "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker $(( $i + 1 )) + "$sbin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker $(( $i + 1 )) done fi @@ -1,4 +1,4 @@ -#!/usr/bin/env bash +#!/bin/bash # # Licensed to the Apache Software Foundation (ASF) under one or more @@ -17,27 +17,34 @@ # limitations under the License. # -cygwin=false -case "`uname`" in - CYGWIN*) cygwin=true;; -esac +# This script launches sbt for this project. If present it uses the system +# version of sbt. If there is no system version of sbt it attempts to download +# sbt locally. +SBT_VERSION=`awk -F "=" '/sbt\\.version/ {print $2}' ./project/build.properties` +URL1=http://typesafe.artifactoryonline.com/typesafe/ivy-releases/org.scala-sbt/sbt-launch/${SBT_VERSION}/sbt-launch.jar +URL2=http://repo.typesafe.com/typesafe/ivy-releases/org.scala-sbt/sbt-launch/${SBT_VERSION}/sbt-launch.jar +JAR=sbt/sbt-launch-${SBT_VERSION}.jar -EXTRA_ARGS="-Xmx1200m -XX:MaxPermSize=350m -XX:ReservedCodeCacheSize=256m" -if [ "$MESOS_HOME" != "" ]; then - EXTRA_ARGS="$EXTRA_ARGS -Djava.library.path=$MESOS_HOME/lib/java" +# Download sbt launch jar if it hasn't been downloaded yet +if [ ! -f ${JAR} ]; then + # Download + printf "Attempting to fetch sbt\n" + if hash curl 2>/dev/null; then + curl --progress-bar ${URL1} > ${JAR} || curl --progress-bar ${URL2} > ${JAR} + elif hash wget 2>/dev/null; then + wget --progress=bar ${URL1} -O ${JAR} || wget --progress=bar ${URL2} -O ${JAR} + else + printf "You do not have curl or wget installed, please install sbt manually from http://www.scala-sbt.org/\n" + exit -1 + fi fi - -export SPARK_HOME=$(cd "$(dirname $0)/.." 2>&1 >/dev/null ; pwd) -export SPARK_TESTING=1 # To put test classes on classpath - -SBT_JAR="$SPARK_HOME"/sbt/sbt-launch-*.jar -if $cygwin; then - SBT_JAR=`cygpath -w $SBT_JAR` - export SPARK_HOME=`cygpath -w $SPARK_HOME` - EXTRA_ARGS="$EXTRA_ARGS -Djline.terminal=jline.UnixTerminal -Dsbt.cygwin=true" - stty -icanon min 1 -echo > /dev/null 2>&1 - java $EXTRA_ARGS $SBT_OPTS -jar $SBT_JAR "$@" - stty icanon echo > /dev/null 2>&1 -else - java $EXTRA_ARGS $SBT_OPTS -jar $SBT_JAR "$@" -fi
\ No newline at end of file +if [ ! -f ${JAR} ]; then + # We failed to download + printf "Our attempt to download sbt locally to ${JAR} failed. Please install sbt manually from http://www.scala-sbt.org/\n" + exit -1 +fi +printf "Launching sbt from ${JAR}\n" +java \ + -Xmx1200m -XX:MaxPermSize=350m -XX:ReservedCodeCacheSize=256m \ + -jar ${JAR} \ + "$@" diff --git a/sbt/sbt-launch-0.11.3-2.jar b/sbt/sbt-launch-0.11.3-2.jar Binary files differdeleted file mode 100644 index 23e5c3f311..0000000000 --- a/sbt/sbt-launch-0.11.3-2.jar +++ /dev/null diff --git a/sbt/sbt.cmd b/sbt/sbt.cmd deleted file mode 100644 index 681fe00f92..0000000000 --- a/sbt/sbt.cmd +++ /dev/null @@ -1,25 +0,0 @@ -@echo off - -rem -rem Licensed to the Apache Software Foundation (ASF) under one or more -rem contributor license agreements. See the NOTICE file distributed with -rem this work for additional information regarding copyright ownership. -rem The ASF licenses this file to You under the Apache License, Version 2.0 -rem (the "License"); you may not use this file except in compliance with -rem the License. You may obtain a copy of the License at -rem -rem http://www.apache.org/licenses/LICENSE-2.0 -rem -rem Unless required by applicable law or agreed to in writing, software -rem distributed under the License is distributed on an "AS IS" BASIS, -rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -rem See the License for the specific language governing permissions and -rem limitations under the License. -rem - -set EXTRA_ARGS= -if not "%MESOS_HOME%x"=="x" set EXTRA_ARGS=-Djava.library.path=%MESOS_HOME%\lib\java - -set SPARK_HOME=%~dp0.. - -java -Xmx1200M -XX:MaxPermSize=200m -XX:ReservedCodeCacheSize=256m %EXTRA_ARGS% -jar %SPARK_HOME%\sbt\sbt-launch-0.11.3-2.jar "%*" diff --git a/streaming/pom.xml b/streaming/pom.xml index e3b6fee9b2..459756912d 100644 --- a/streaming/pom.xml +++ b/streaming/pom.xml @@ -61,59 +61,10 @@ <version>1.9.11</version> </dependency> <dependency> - <groupId>com.sksamuel.kafka</groupId> - <artifactId>kafka_${scala.binary.version}</artifactId> - <version>0.8.0-beta1</version> - <exclusions> - <exclusion> - <groupId>com.sun.jmx</groupId> - <artifactId>jmxri</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jdmk</groupId> - <artifactId>jmxtools</artifactId> - </exclusion> - <exclusion> - <groupId>net.sf.jopt-simple</groupId> - <artifactId>jopt-simple</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.flume</groupId> - <artifactId>flume-ng-sdk</artifactId> - <version>1.2.0</version> - <exclusions> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>org.xerial.snappy</groupId> - <artifactId>*</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.twitter4j</groupId> - <artifactId>twitter4j-stream</artifactId> - <version>3.0.3</version> - <exclusions> - <exclusion> - <groupId>org.jboss.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> </dependency> <dependency> - <groupId>${akka.group}</groupId> - <artifactId>akka-zeromq_${scala.binary.version}</artifactId> - </dependency> - <dependency> <groupId>org.scalatest</groupId> <artifactId>scalatest_${scala.binary.version}</artifactId> <scope>test</scope> @@ -137,11 +88,6 @@ <groupId>commons-io</groupId> <artifactId>commons-io</artifactId> </dependency> - <dependency> - <groupId>org.eclipse.paho</groupId> - <artifactId>mqtt-client</artifactId> - <version>0.4.0</version> - </dependency> </dependencies> <build> <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> @@ -151,6 +97,35 @@ <groupId>org.scalatest</groupId> <artifactId>scalatest-maven-plugin</artifactId> </plugin> + + <!-- + This plugin forces the generation of jar containing streaming test classes, + so that the tests classes of external modules can use them. The two execution profiles + are necessary - first one for 'mvn package', second one for 'mvn compile'. Ideally, + 'mvn compile' should not compile test classes and therefore should not need this. + However, an open Maven bug (http://jira.codehaus.org/browse/MNG-3559) + causes the compilation to fail if streaming test-jar is not generated. Hence, the + second execution profile for 'mvn compile'. + --> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-jar-plugin</artifactId> + <version>2.2</version> + <executions> + <execution> + <goals> + <goal>test-jar</goal> + </goals> + </execution> + <execution> + <id>test-jar-on-compile</id> + <phase>compile</phase> + <goals> + <goal>test-jar</goal> + </goals> + </execution> + </executions> + </plugin> </plugins> </build> </project> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/PairDStreamFunctions.scala b/streaming/src/main/scala/org/apache/spark/streaming/PairDStreamFunctions.scala index 80af96c060..56dbcbda23 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/PairDStreamFunctions.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/PairDStreamFunctions.scala @@ -108,8 +108,9 @@ extends Serializable { createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiner: (C, C) => C, - partitioner: Partitioner) : DStream[(K, C)] = { - new ShuffledDStream[K, V, C](self, createCombiner, mergeValue, mergeCombiner, partitioner) + partitioner: Partitioner, + mapSideCombine: Boolean = true): DStream[(K, C)] = { + new ShuffledDStream[K, V, C](self, createCombiner, mergeValue, mergeCombiner, partitioner, mapSideCombine) } /** @@ -173,7 +174,13 @@ extends Serializable { slideDuration: Duration, partitioner: Partitioner ): DStream[(K, Seq[V])] = { - self.window(windowDuration, slideDuration).groupByKey(partitioner) + val createCombiner = (v: Seq[V]) => new ArrayBuffer[V] ++= v + val mergeValue = (buf: ArrayBuffer[V], v: Seq[V]) => buf ++= v + val mergeCombiner = (buf1: ArrayBuffer[V], buf2: ArrayBuffer[V]) => buf1 ++= buf2 + self.groupByKey(partitioner) + .window(windowDuration, slideDuration) + .combineByKey[ArrayBuffer[V]](createCombiner, mergeValue, mergeCombiner, partitioner) + .asInstanceOf[DStream[(K, Seq[V])]] } /** diff --git a/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala index 304986f187..693cb7fc30 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala @@ -17,23 +17,6 @@ package org.apache.spark.streaming -import akka.actor.Props -import akka.actor.SupervisorStrategy -import akka.zeromq.Subscribe -import akka.util.ByteString - -import org.apache.spark.streaming.dstream._ -import org.apache.spark.streaming.scheduler.StreamingListener - -import org.apache.spark._ -import org.apache.spark.rdd.RDD -import org.apache.spark.streaming.receivers.ReceiverSupervisorStrategy -import org.apache.spark.streaming.receivers.ZeroMQReceiver -import org.apache.spark.storage.StorageLevel -import org.apache.spark.util.MetadataCleaner -import org.apache.spark.streaming.receivers.ActorReceiver -import org.apache.spark.streaming.scheduler.{JobScheduler, NetworkInputTracker} - import scala.collection.mutable.Queue import scala.collection.Map import scala.reflect.ClassTag @@ -41,14 +24,21 @@ import scala.reflect.ClassTag import java.io.InputStream import java.util.concurrent.atomic.AtomicInteger +import akka.actor.Props +import akka.actor.SupervisorStrategy import org.apache.hadoop.io.LongWritable import org.apache.hadoop.io.Text import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat} import org.apache.hadoop.mapreduce.lib.input.TextInputFormat import org.apache.hadoop.fs.Path -import twitter4j.Status -import twitter4j.auth.Authorization +import org.apache.spark._ +import org.apache.spark.rdd.RDD +import org.apache.spark.storage.StorageLevel +import org.apache.spark.util.MetadataCleaner +import org.apache.spark.streaming.dstream._ +import org.apache.spark.streaming.receivers._ +import org.apache.spark.streaming.scheduler._ /** * A StreamingContext is the main entry point for Spark Streaming functionality. Besides the basic @@ -238,74 +228,6 @@ class StreamingContext private ( } /** - * Create an input stream that receives messages pushed by a zeromq publisher. - * @param publisherUrl Url of remote zeromq publisher - * @param subscribe topic to subscribe to - * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic - * and each frame has sequence of byte thus it needs the converter - * (which might be deserializer of bytes) to translate from sequence - * of sequence of bytes, where sequence refer to a frame - * and sub sequence refer to its payload. - * @param storageLevel RDD storage level. Defaults to memory-only. - */ - def zeroMQStream[T: ClassTag]( - publisherUrl:String, - subscribe: Subscribe, - bytesToObjects: Seq[ByteString] ⇒ Iterator[T], - storageLevel: StorageLevel = StorageLevel.MEMORY_ONLY_SER_2, - supervisorStrategy: SupervisorStrategy = ReceiverSupervisorStrategy.defaultStrategy - ): DStream[T] = { - actorStream(Props(new ZeroMQReceiver(publisherUrl, subscribe, bytesToObjects)), - "ZeroMQReceiver", storageLevel, supervisorStrategy) - } - - /** - * Create an input stream that pulls messages from a Kafka Broker. - * @param zkQuorum Zookeper quorum (hostname:port,hostname:port,..). - * @param groupId The group id for this consumer. - * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed - * in its own thread. - * @param storageLevel Storage level to use for storing the received objects - * (default: StorageLevel.MEMORY_AND_DISK_SER_2) - */ - def kafkaStream( - zkQuorum: String, - groupId: String, - topics: Map[String, Int], - storageLevel: StorageLevel = StorageLevel.MEMORY_ONLY_SER_2 - ): DStream[(String, String)] = { - val kafkaParams = Map[String, String]( - "zookeeper.connect" -> zkQuorum, "group.id" -> groupId, - "zookeeper.connection.timeout.ms" -> "10000") - kafkaStream[String, String, kafka.serializer.StringDecoder, kafka.serializer.StringDecoder]( - kafkaParams, - topics, - storageLevel) - } - - /** - * Create an input stream that pulls messages from a Kafka Broker. - * @param kafkaParams Map of kafka configuration paramaters. - * See: http://kafka.apache.org/configuration.html - * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed - * in its own thread. - * @param storageLevel Storage level to use for storing the received objects - */ - def kafkaStream[ - K: ClassTag, - V: ClassTag, - U <: kafka.serializer.Decoder[_]: Manifest, - T <: kafka.serializer.Decoder[_]: Manifest]( - kafkaParams: Map[String, String], - topics: Map[String, Int], - storageLevel: StorageLevel - ): DStream[(K, V)] = { - val inputStream = new KafkaInputDStream[K, V, U, T](this, kafkaParams, topics, storageLevel) - registerInputStream(inputStream) - inputStream - } - - /** * Create a input stream from TCP source hostname:port. Data is received using * a TCP socket and the receive bytes is interpreted as UTF8 encoded `\n` delimited * lines. @@ -344,22 +266,6 @@ class StreamingContext private ( } /** - * Create a input stream from a Flume source. - * @param hostname Hostname of the slave machine to which the flume data will be sent - * @param port Port of the slave machine to which the flume data will be sent - * @param storageLevel Storage level to use for storing the received objects - */ - def flumeStream ( - hostname: String, - port: Int, - storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 - ): DStream[SparkFlumeEvent] = { - val inputStream = new FlumeInputDStream[SparkFlumeEvent](this, hostname, port, storageLevel) - registerInputStream(inputStream) - inputStream - } - - /** * Create a input stream from network source hostname:port, where data is received * as serialized blocks (serialized using the Spark's serializer) that can be directly * pushed into the block manager without deserializing them. This is the most efficient @@ -434,24 +340,6 @@ class StreamingContext private ( } /** - * Create a input stream that returns tweets received from Twitter. - * @param twitterAuth Twitter4J authentication, or None to use Twitter4J's default OAuth - * authorization; this uses the system properties twitter4j.oauth.consumerKey, - * .consumerSecret, .accessToken and .accessTokenSecret. - * @param filters Set of filter strings to get only those tweets that match them - * @param storageLevel Storage level to use for storing the received objects - */ - def twitterStream( - twitterAuth: Option[Authorization] = None, - filters: Seq[String] = Nil, - storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2 - ): DStream[Status] = { - val inputStream = new TwitterInputDStream(this, twitterAuth, filters, storageLevel) - registerInputStream(inputStream) - inputStream - } - - /** * Create an input stream from a queue of RDDs. In each batch, * it will process either one or all of the RDDs returned by the queue. * @param queue Queue of RDDs @@ -484,21 +372,6 @@ class StreamingContext private ( inputStream } -/** - * Create an input stream that receives messages pushed by a mqtt publisher. - * @param brokerUrl Url of remote mqtt publisher - * @param topic topic name to subscribe to - * @param storageLevel RDD storage level. Defaults to memory-only. - */ - - def mqttStream( - brokerUrl: String, - topic: String, - storageLevel: StorageLevel = StorageLevel.MEMORY_ONLY_SER_2): DStream[String] = { - val inputStream = new MQTTInputDStream[String](this, brokerUrl, topic, storageLevel) - registerInputStream(inputStream) - inputStream - } /** * Create a unified DStream from multiple DStreams of the same type and same slide duration. */ @@ -595,6 +468,12 @@ object StreamingContext { new PairDStreamFunctions[K, V](stream) } + /** + * Find the JAR from which a given class was loaded, to make it easy for users to pass + * their JARs to SparkContext. + */ + def jarOfClass(cls: Class[_]) = SparkContext.jarOfClass(cls) + protected[streaming] def createNewSparkContext(conf: SparkConf): SparkContext = { // Set the default cleaner delay to an hour if not already set. // This should be sufficient for even 1 second batch intervals. diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala index dfd6e27c3e..6c3467d405 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala @@ -155,7 +155,7 @@ class JavaPairDStream[K, V](val dstream: DStream[(K, V)])( /** * Combine elements of each key in DStream's RDDs using custom function. This is similar to the - * combineByKey for RDDs. Please refer to combineByKey in [[org.apache.spark.PairRDDFunctions]] for more + * combineByKey for RDDs. Please refer to combineByKey in [[org.apache.spark.rdd.PairRDDFunctions]] for more * information. */ def combineByKey[C](createCombiner: JFunction[V, C], @@ -169,6 +169,22 @@ class JavaPairDStream[K, V](val dstream: DStream[(K, V)])( } /** + * Combine elements of each key in DStream's RDDs using custom function. This is similar to the + * combineByKey for RDDs. Please refer to combineByKey in [[org.apache.spark.rdd.PairRDDFunctions]] for more + * information. + */ + def combineByKey[C](createCombiner: JFunction[V, C], + mergeValue: JFunction2[C, V, C], + mergeCombiners: JFunction2[C, C, C], + partitioner: Partitioner, + mapSideCombine: Boolean + ): JavaPairDStream[K, C] = { + implicit val cm: ClassTag[C] = + implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[C]] + dstream.combineByKey(createCombiner, mergeValue, mergeCombiners, partitioner, mapSideCombine) + } + + /** * Return a new DStream by applying `groupByKey` over a sliding window. This is similar to * `DStream.groupByKey()` but applies it over a sliding window. The new DStream generates RDDs * with the same interval as this DStream. Hash partitioning is used to generate the RDDs with diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala index b79173c6aa..7068f32517 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala @@ -17,29 +17,23 @@ package org.apache.spark.streaming.api.java -import java.lang.{Integer => JInt} -import java.io.InputStream -import java.util.{Map => JMap, List => JList} import scala.collection.JavaConversions._ import scala.reflect.ClassTag -import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat} -import twitter4j.Status -import akka.actor.Props -import akka.actor.SupervisorStrategy -import akka.zeromq.Subscribe -import akka.util.ByteString +import java.io.InputStream +import java.lang.{Integer => JInt} +import java.util.{List => JList, Map => JMap} -import twitter4j.auth.Authorization +import akka.actor.{Props, SupervisorStrategy} +import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat} +import org.apache.spark.{SparkConf, SparkContext} +import org.apache.spark.api.java.{JavaPairRDD, JavaRDD, JavaSparkContext} +import org.apache.spark.api.java.function.{Function => JFunction, Function2 => JFunction2} import org.apache.spark.rdd.RDD import org.apache.spark.storage.StorageLevel -import org.apache.spark.api.java.function.{Function => JFunction, Function2 => JFunction2} -import org.apache.spark.api.java.{JavaPairRDD, JavaSparkContext, JavaRDD} import org.apache.spark.streaming._ -import org.apache.spark.streaming.dstream._ -import org.apache.spark.SparkConf import org.apache.spark.streaming.scheduler.StreamingListener /** @@ -143,81 +137,6 @@ class JavaStreamingContext(val ssc: StreamingContext) { val sc: JavaSparkContext = new JavaSparkContext(ssc.sc) /** - * Create an input stream that pulls messages form a Kafka Broker. - * @param zkQuorum Zookeper quorum (hostname:port,hostname:port,..). - * @param groupId The group id for this consumer. - * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed - * in its own thread. - */ - def kafkaStream( - zkQuorum: String, - groupId: String, - topics: JMap[String, JInt]) - : JavaPairDStream[String, String] = { - implicit val cmt: ClassTag[String] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] - ssc.kafkaStream(zkQuorum, groupId, Map(topics.mapValues(_.intValue()).toSeq: _*), - StorageLevel.MEMORY_ONLY_SER_2) - - } - - /** - * Create an input stream that pulls messages form a Kafka Broker. - * @param zkQuorum Zookeper quorum (hostname:port,hostname:port,..). - * @param groupId The group id for this consumer. - * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed - * in its own thread. - * @param storageLevel RDD storage level. Defaults to memory-only - * - */ - def kafkaStream( - zkQuorum: String, - groupId: String, - topics: JMap[String, JInt], - storageLevel: StorageLevel) - : JavaPairDStream[String, String] = { - implicit val cmt: ClassTag[String] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[String]] - ssc.kafkaStream(zkQuorum, groupId, Map(topics.mapValues(_.intValue()).toSeq: _*), - storageLevel) - } - - /** - * Create an input stream that pulls messages form a Kafka Broker. - * @param keyTypeClass Key type of RDD - * @param valueTypeClass value type of RDD - * @param keyDecoderClass Type of kafka key decoder - * @param valueDecoderClass Type of kafka value decoder - * @param kafkaParams Map of kafka configuration paramaters. - * See: http://kafka.apache.org/configuration.html - * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed - * in its own thread. - * @param storageLevel RDD storage level. Defaults to memory-only - */ - def kafkaStream[K, V, U <: kafka.serializer.Decoder[_], T <: kafka.serializer.Decoder[_]]( - keyTypeClass: Class[K], - valueTypeClass: Class[V], - keyDecoderClass: Class[U], - valueDecoderClass: Class[T], - kafkaParams: JMap[String, String], - topics: JMap[String, JInt], - storageLevel: StorageLevel) - : JavaPairDStream[K, V] = { - implicit val keyCmt: ClassTag[K] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[K]] - implicit val valueCmt: ClassTag[V] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[V]] - - implicit val keyCmd: Manifest[U] = implicitly[Manifest[AnyRef]].asInstanceOf[Manifest[U]] - implicit val valueCmd: Manifest[T] = implicitly[Manifest[AnyRef]].asInstanceOf[Manifest[T]] - - ssc.kafkaStream[K, V, U, T]( - kafkaParams.toMap, - Map(topics.mapValues(_.intValue()).toSeq: _*), - storageLevel) - } - - /** * Create a input stream from network source hostname:port. Data is received using * a TCP socket and the receive bytes is interpreted as UTF8 encoded \n delimited * lines. @@ -331,98 +250,6 @@ class JavaStreamingContext(val ssc: StreamingContext) { } /** - * Creates a input stream from a Flume source. - * @param hostname Hostname of the slave machine to which the flume data will be sent - * @param port Port of the slave machine to which the flume data will be sent - * @param storageLevel Storage level to use for storing the received objects - */ - def flumeStream(hostname: String, port: Int, storageLevel: StorageLevel): - JavaDStream[SparkFlumeEvent] = { - ssc.flumeStream(hostname, port, storageLevel) - } - - - /** - * Create a input stream from a Flume source. - * @param hostname Hostname of the slave machine to which the flume data will be sent - * @param port Port of the slave machine to which the flume data will be sent - */ - def flumeStream(hostname: String, port: Int): JavaDStream[SparkFlumeEvent] = { - ssc.flumeStream(hostname, port) - } - - /** - * Create a input stream that returns tweets received from Twitter. - * @param twitterAuth Twitter4J Authorization object - * @param filters Set of filter strings to get only those tweets that match them - * @param storageLevel Storage level to use for storing the received objects - */ - def twitterStream( - twitterAuth: Authorization, - filters: Array[String], - storageLevel: StorageLevel - ): JavaDStream[Status] = { - ssc.twitterStream(Some(twitterAuth), filters, storageLevel) - } - - /** - * Create a input stream that returns tweets received from Twitter using Twitter4J's default - * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, - * .consumerSecret, .accessToken and .accessTokenSecret to be set. - * @param filters Set of filter strings to get only those tweets that match them - * @param storageLevel Storage level to use for storing the received objects - */ - def twitterStream( - filters: Array[String], - storageLevel: StorageLevel - ): JavaDStream[Status] = { - ssc.twitterStream(None, filters, storageLevel) - } - - /** - * Create a input stream that returns tweets received from Twitter. - * @param twitterAuth Twitter4J Authorization - * @param filters Set of filter strings to get only those tweets that match them - */ - def twitterStream( - twitterAuth: Authorization, - filters: Array[String] - ): JavaDStream[Status] = { - ssc.twitterStream(Some(twitterAuth), filters) - } - - /** - * Create a input stream that returns tweets received from Twitter using Twitter4J's default - * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, - * .consumerSecret, .accessToken and .accessTokenSecret to be set. - * @param filters Set of filter strings to get only those tweets that match them - */ - def twitterStream( - filters: Array[String] - ): JavaDStream[Status] = { - ssc.twitterStream(None, filters) - } - - /** - * Create a input stream that returns tweets received from Twitter. - * @param twitterAuth Twitter4J Authorization - */ - def twitterStream( - twitterAuth: Authorization - ): JavaDStream[Status] = { - ssc.twitterStream(Some(twitterAuth)) - } - - /** - * Create a input stream that returns tweets received from Twitter using Twitter4J's default - * OAuth authentication; this requires the system properties twitter4j.oauth.consumerKey, - * .consumerSecret, .accessToken and .accessTokenSecret to be set. - */ - def twitterStream(): JavaDStream[Status] = { - ssc.twitterStream() - } - - /** * Create an input stream with any arbitrary user implemented actor receiver. * @param props Props object defining creation of the actor * @param name Name of the actor @@ -485,70 +312,6 @@ class JavaStreamingContext(val ssc: StreamingContext) { } /** - * Create an input stream that receives messages pushed by a zeromq publisher. - * @param publisherUrl Url of remote zeromq publisher - * @param subscribe topic to subscribe to - * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence - * of byte thus it needs the converter(which might be deserializer of bytes) - * to translate from sequence of sequence of bytes, where sequence refer to a frame - * and sub sequence refer to its payload. - * @param storageLevel Storage level to use for storing the received objects - */ - def zeroMQStream[T]( - publisherUrl:String, - subscribe: Subscribe, - bytesToObjects: Seq[ByteString] ⇒ Iterator[T], - storageLevel: StorageLevel, - supervisorStrategy: SupervisorStrategy - ): JavaDStream[T] = { - implicit val cm: ClassTag[T] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] - ssc.zeroMQStream[T](publisherUrl, subscribe, bytesToObjects, storageLevel, supervisorStrategy) - } - - /** - * Create an input stream that receives messages pushed by a zeromq publisher. - * @param publisherUrl Url of remote zeromq publisher - * @param subscribe topic to subscribe to - * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence - * of byte thus it needs the converter(which might be deserializer of bytes) - * to translate from sequence of sequence of bytes, where sequence refer to a frame - * and sub sequence refer to its payload. - * @param storageLevel RDD storage level. Defaults to memory-only. - */ - def zeroMQStream[T]( - publisherUrl:String, - subscribe: Subscribe, - bytesToObjects: JFunction[Array[Array[Byte]], java.lang.Iterable[T]], - storageLevel: StorageLevel - ): JavaDStream[T] = { - implicit val cm: ClassTag[T] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] - def fn(x: Seq[ByteString]) = bytesToObjects.apply(x.map(_.toArray).toArray).toIterator - ssc.zeroMQStream[T](publisherUrl, subscribe, fn, storageLevel) - } - - /** - * Create an input stream that receives messages pushed by a zeromq publisher. - * @param publisherUrl Url of remote zeromq publisher - * @param subscribe topic to subscribe to - * @param bytesToObjects A zeroMQ stream publishes sequence of frames for each topic and each frame has sequence - * of byte thus it needs the converter(which might be deserializer of bytes) - * to translate from sequence of sequence of bytes, where sequence refer to a frame - * and sub sequence refer to its payload. - */ - def zeroMQStream[T]( - publisherUrl:String, - subscribe: Subscribe, - bytesToObjects: JFunction[Array[Array[Byte]], java.lang.Iterable[T]] - ): JavaDStream[T] = { - implicit val cm: ClassTag[T] = - implicitly[ClassTag[AnyRef]].asInstanceOf[ClassTag[T]] - def fn(x: Seq[ByteString]) = bytesToObjects.apply(x.map(_.toArray).toArray).toIterator - ssc.zeroMQStream[T](publisherUrl, subscribe, fn) - } - - /** * Registers an output stream that will be computed every interval */ def registerOutputStream(outputStream: JavaDStreamLike[_, _, _]) { @@ -716,5 +479,12 @@ class JavaStreamingContext(val ssc: StreamingContext) { * Sstops the execution of the streams. */ def stop() = ssc.stop() +} +object JavaStreamingContext { + /** + * Find the JAR from which a given class was loaded, to make it easy for users to pass + * their JARs to SparkContext. + */ + def jarOfClass(cls: Class[_]) = SparkContext.jarOfClass(cls).toArray } diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/NetworkInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/NetworkInputDStream.scala index 27d474c0a0..d41f726f83 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/NetworkInputDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/NetworkInputDStream.scala @@ -175,7 +175,7 @@ abstract class NetworkReceiver[T: ClassTag]() extends Serializable with Logging private class NetworkReceiverActor extends Actor { logInfo("Attempting to register with tracker") val ip = env.conf.get("spark.driver.host", "localhost") - val port = env.conf.get("spark.driver.port", "7077").toInt + val port = env.conf.getInt("spark.driver.port", 7077) val url = "akka.tcp://spark@%s:%s/user/NetworkInputTracker".format(ip, port) val tracker = env.actorSystem.actorSelection(url) val timeout = 5.seconds @@ -212,7 +212,7 @@ abstract class NetworkReceiver[T: ClassTag]() extends Serializable with Logging case class Block(id: BlockId, buffer: ArrayBuffer[T], metadata: Any = null) val clock = new SystemClock() - val blockInterval = env.conf.get("spark.streaming.blockInterval", "200").toLong + val blockInterval = env.conf.getLong("spark.streaming.blockInterval", 200) val blockIntervalTimer = new RecurringTimer(clock, blockInterval, updateCurrentBuffer) val blockStorageLevel = storageLevel val blocksForPushing = new ArrayBlockingQueue[Block](1000) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala index e6e0022097..84e69f277b 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/ShuffledDStream.scala @@ -29,8 +29,9 @@ class ShuffledDStream[K: ClassTag, V: ClassTag, C: ClassTag]( createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiner: (C, C) => C, - partitioner: Partitioner - ) extends DStream [(K,C)] (parent.ssc) { + partitioner: Partitioner, + mapSideCombine: Boolean = true + ) extends DStream[(K,C)] (parent.ssc) { override def dependencies = List(parent) @@ -38,8 +39,8 @@ class ShuffledDStream[K: ClassTag, V: ClassTag, C: ClassTag]( override def compute(validTime: Time): Option[RDD[(K,C)]] = { parent.getOrCompute(validTime) match { - case Some(rdd) => - Some(rdd.combineByKey[C](createCombiner, mergeValue, mergeCombiner, partitioner)) + case Some(rdd) => Some(rdd.combineByKey[C]( + createCombiner, mergeValue, mergeCombiner, partitioner, mapSideCombine)) case None => None } } diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/WindowedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/WindowedDStream.scala index 73d959331a..89c43ff935 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/WindowedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/WindowedDStream.scala @@ -17,10 +17,10 @@ package org.apache.spark.streaming.dstream -import org.apache.spark.rdd.RDD -import org.apache.spark.rdd.UnionRDD +import org.apache.spark.rdd.{PartitionerAwareUnionRDD, RDD, UnionRDD} import org.apache.spark.storage.StorageLevel -import org.apache.spark.streaming.{Duration, Interval, Time, DStream} +import org.apache.spark.streaming._ +import org.apache.spark.streaming.Duration import scala.reflect.ClassTag @@ -51,6 +51,14 @@ class WindowedDStream[T: ClassTag]( override def compute(validTime: Time): Option[RDD[T]] = { val currentWindow = new Interval(validTime - windowDuration + parent.slideDuration, validTime) - Some(new UnionRDD(ssc.sc, parent.slice(currentWindow))) + val rddsInWindow = parent.slice(currentWindow) + val windowRDD = if (rddsInWindow.flatMap(_.partitioner).distinct.length == 1) { + logDebug("Using partition aware union for windowing at " + validTime) + new PartitionerAwareUnionRDD(ssc.sc, rddsInWindow) + } else { + logDebug("Using normal union for windowing at " + validTime) + new UnionRDD(ssc.sc,rddsInWindow) + } + Some(windowRDD) } } diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/Job.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/Job.scala index 7341bfbc99..c8ee93bf5b 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/Job.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/Job.scala @@ -38,4 +38,4 @@ class Job(val time: Time, func: () => _) { } override def toString = id -}
\ No newline at end of file +} diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala index 5f8be93a98..3c624e8199 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala @@ -104,7 +104,7 @@ class JobGenerator(jobScheduler: JobScheduler) extends Logging { // or if the property is defined set it to that time if (clock.isInstanceOf[ManualClock]) { val lastTime = ssc.initialCheckpoint.checkpointTime.milliseconds - val jumpTime = ssc.sc.conf.get("spark.streaming.manualClock.jump", "0").toLong + val jumpTime = ssc.sc.conf.getLong("spark.streaming.manualClock.jump", 0) clock.asInstanceOf[ManualClock].setTime(lastTime + jumpTime) } diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobScheduler.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobScheduler.scala index 9304fc1a93..30c070c274 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobScheduler.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobScheduler.scala @@ -31,7 +31,7 @@ private[streaming] class JobScheduler(val ssc: StreamingContext) extends Logging { val jobSets = new ConcurrentHashMap[Time, JobSet] - val numConcurrentJobs = ssc.conf.get("spark.streaming.concurrentJobs", "1").toInt + val numConcurrentJobs = ssc.conf.getInt("spark.streaming.concurrentJobs", 1) val executor = Executors.newFixedThreadPool(numConcurrentJobs) val generator = new JobGenerator(this) val listenerBus = new StreamingListenerBus() diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/NetworkInputTracker.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/NetworkInputTracker.scala index abff55d77c..75f7244643 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/NetworkInputTracker.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/NetworkInputTracker.scala @@ -160,7 +160,9 @@ class NetworkInputTracker( } // Run the dummy Spark job to ensure that all slaves have registered. // This avoids all the receivers to be scheduled on the same node. - ssc.sparkContext.makeRDD(1 to 50, 50).map(x => (x, 1)).reduceByKey(_ + _, 20).collect() + if (!ssc.sparkContext.isLocal) { + ssc.sparkContext.makeRDD(1 to 50, 50).map(x => (x, 1)).reduceByKey(_ + _, 20).collect() + } // Distribute the receivers and start them ssc.sparkContext.runJob(tempRDD, startReceiver) diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java index d53d433693..0d2145da9a 100644 --- a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java +++ b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java @@ -17,24 +17,19 @@ package org.apache.spark.streaming; -import com.google.common.base.Optional; -import com.google.common.collect.Lists; -import com.google.common.collect.Maps; -import com.google.common.io.Files; - -import kafka.serializer.StringDecoder; +import scala.Tuple2; -import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat; -import org.apache.spark.SparkConf; -import org.apache.spark.streaming.api.java.JavaDStreamLike; import org.junit.After; import org.junit.Assert; -import org.junit.Before; import org.junit.Test; +import java.io.*; +import java.util.*; -import scala.Tuple2; -import twitter4j.Status; +import com.google.common.base.Optional; +import com.google.common.collect.Lists; +import com.google.common.io.Files; +import org.apache.spark.SparkConf; import org.apache.spark.HashPartitioner; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaRDD; @@ -44,42 +39,11 @@ import org.apache.spark.storage.StorageLevel; import org.apache.spark.streaming.api.java.JavaDStream; import org.apache.spark.streaming.api.java.JavaPairDStream; import org.apache.spark.streaming.api.java.JavaStreamingContext; -import org.apache.spark.streaming.dstream.SparkFlumeEvent; -import org.apache.spark.streaming.JavaTestUtils; -import org.apache.spark.streaming.JavaCheckpointTestUtils; - -import java.io.*; -import java.util.*; - -import akka.actor.Props; -import akka.zeromq.Subscribe; - // The test suite itself is Serializable so that anonymous Function implementations can be // serialized, as an alternative to converting these anonymous classes to static inner classes; // see http://stackoverflow.com/questions/758570/. -public class JavaAPISuite implements Serializable { - private transient JavaStreamingContext ssc; - - @Before - public void setUp() { - SparkConf conf = new SparkConf() - .setMaster("local[2]") - .setAppName("test") - .set("spark.streaming.clock", "org.apache.spark.streaming.util.ManualClock"); - ssc = new JavaStreamingContext(conf, new Duration(1000)); - ssc.checkpoint("checkpoint"); - } - - @After - public void tearDown() { - ssc.stop(); - ssc = null; - - // To avoid Akka rebinding to the same port, since it doesn't unbind immediately on shutdown - System.clearProperty("spark.driver.port"); - } - +public class JavaAPISuite extends LocalJavaStreamingContext implements Serializable { @Test public void testCount() { List<List<Integer>> inputData = Arrays.asList( @@ -1601,26 +1565,6 @@ public class JavaAPISuite implements Serializable { // Java arguments and assign it to a JavaDStream without producing type errors. Testing of the // InputStream functionality is deferred to the existing Scala tests. @Test - public void testKafkaStream() { - HashMap<String, Integer> topics = Maps.newHashMap(); - JavaPairDStream<String, String> test1 = ssc.kafkaStream("localhost:12345", "group", topics); - JavaPairDStream<String, String> test2 = ssc.kafkaStream("localhost:12345", "group", topics, - StorageLevel.MEMORY_AND_DISK()); - - HashMap<String, String> kafkaParams = Maps.newHashMap(); - kafkaParams.put("zookeeper.connect","localhost:12345"); - kafkaParams.put("group.id","consumer-group"); - JavaPairDStream<String, String> test3 = ssc.kafkaStream( - String.class, - String.class, - StringDecoder.class, - StringDecoder.class, - kafkaParams, - topics, - StorageLevel.MEMORY_AND_DISK()); - } - - @Test public void testSocketTextStream() { JavaDStream<String> test = ssc.socketTextStream("localhost", 12345); } @@ -1658,36 +1602,4 @@ public class JavaAPISuite implements Serializable { public void testRawSocketStream() { JavaDStream<String> test = ssc.rawSocketStream("localhost", 12345); } - - @Test - public void testFlumeStream() { - JavaDStream<SparkFlumeEvent> test = ssc.flumeStream("localhost", 12345, StorageLevel.MEMORY_ONLY()); - } - - @Test - public void testFileStream() { - JavaPairDStream<String, String> foo = - ssc.<String, String, SequenceFileInputFormat<String,String>>fileStream("/tmp/foo"); - } - - @Test - public void testTwitterStream() { - String[] filters = new String[] { "good", "bad", "ugly" }; - JavaDStream<Status> test = ssc.twitterStream(filters, StorageLevel.MEMORY_ONLY()); - } - - @Test - public void testActorStream() { - JavaDStream<String> test = ssc.actorStream((Props)null, "TestActor", StorageLevel.MEMORY_ONLY()); - } - - @Test - public void testZeroMQStream() { - JavaDStream<String> test = ssc.zeroMQStream("url", (Subscribe) null, new Function<byte[][], Iterable<String>>() { - @Override - public Iterable<String> call(byte[][] b) throws Exception { - return null; - } - }); - } } diff --git a/streaming/src/test/java/org/apache/spark/streaming/LocalJavaStreamingContext.java b/streaming/src/test/java/org/apache/spark/streaming/LocalJavaStreamingContext.java new file mode 100644 index 0000000000..34bee56885 --- /dev/null +++ b/streaming/src/test/java/org/apache/spark/streaming/LocalJavaStreamingContext.java @@ -0,0 +1,46 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming; + +import org.apache.spark.streaming.api.java.JavaStreamingContext; +import org.junit.After; +import org.junit.Before; + +public abstract class LocalJavaStreamingContext { + + protected transient JavaStreamingContext ssc; + + @Before + public void setUp() { + System.clearProperty("spark.driver.port"); + System.clearProperty("spark.hostPort"); + System.setProperty("spark.streaming.clock", "org.apache.spark.streaming.util.ManualClock"); + ssc = new JavaStreamingContext("local[2]", "test", new Duration(1000)); + ssc.checkpoint("checkpoint"); + } + + @After + public void tearDown() { + ssc.stop(); + ssc = null; + + // To avoid Akka rebinding to the same port, since it doesn't unbind immediately on shutdown + System.clearProperty("spark.driver.port"); + System.clearProperty("spark.hostPort"); + } +} diff --git a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala index 5185954521..a8e053278a 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala @@ -23,7 +23,7 @@ import akka.actor.IOManager import akka.actor.Props import akka.util.ByteString -import org.apache.spark.streaming.dstream.{FileInputDStream, NetworkReceiver, SparkFlumeEvent} +import org.apache.spark.streaming.dstream.{NetworkReceiver} import java.net.{InetSocketAddress, SocketException, Socket, ServerSocket} import java.io.{File, BufferedWriter, OutputStreamWriter} import java.util.concurrent.{Executors, TimeUnit, ArrayBlockingQueue} @@ -31,18 +31,11 @@ import collection.mutable.{SynchronizedBuffer, ArrayBuffer} import util.ManualClock import org.apache.spark.storage.StorageLevel import org.apache.spark.streaming.receivers.Receiver -import org.apache.spark.{SparkContext, Logging} +import org.apache.spark.Logging import scala.util.Random import org.apache.commons.io.FileUtils import org.scalatest.BeforeAndAfter -import org.apache.flume.source.avro.AvroSourceProtocol -import org.apache.flume.source.avro.AvroFlumeEvent -import org.apache.flume.source.avro.Status -import org.apache.avro.ipc.{specific, NettyTransceiver} -import org.apache.avro.ipc.specific.SpecificRequestor -import java.nio.ByteBuffer import collection.JavaConversions._ -import java.nio.charset.Charset import com.google.common.io.Files import java.util.concurrent.atomic.AtomicInteger @@ -56,7 +49,7 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { testServer.start() // Set up the streaming context and input streams - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) + val ssc = new StreamingContext(conf, batchDuration) val networkStream = ssc.socketTextStream("localhost", testServer.port, StorageLevel.MEMORY_AND_DISK) val outputBuffer = new ArrayBuffer[Seq[String]] with SynchronizedBuffer[Seq[String]] val outputStream = new TestOutputStream(networkStream, outputBuffer) @@ -99,62 +92,13 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { } - test("flume input stream") { - // Set up the streaming context and input streams - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) - val flumeStream = ssc.flumeStream("localhost", testPort, StorageLevel.MEMORY_AND_DISK) - val outputBuffer = new ArrayBuffer[Seq[SparkFlumeEvent]] - with SynchronizedBuffer[Seq[SparkFlumeEvent]] - val outputStream = new TestOutputStream(flumeStream, outputBuffer) - ssc.registerOutputStream(outputStream) - ssc.start() - - val clock = ssc.scheduler.clock.asInstanceOf[ManualClock] - val input = Seq(1, 2, 3, 4, 5) - Thread.sleep(1000) - val transceiver = new NettyTransceiver(new InetSocketAddress("localhost", testPort)) - val client = SpecificRequestor.getClient( - classOf[AvroSourceProtocol], transceiver) - - for (i <- 0 until input.size) { - val event = new AvroFlumeEvent - event.setBody(ByteBuffer.wrap(input(i).toString.getBytes())) - event.setHeaders(Map[CharSequence, CharSequence]("test" -> "header")) - client.append(event) - Thread.sleep(500) - clock.addToTime(batchDuration.milliseconds) - } - - val startTime = System.currentTimeMillis() - while (outputBuffer.size < input.size && System.currentTimeMillis() - startTime < maxWaitTimeMillis) { - logInfo("output.size = " + outputBuffer.size + ", input.size = " + input.size) - Thread.sleep(100) - } - Thread.sleep(1000) - val timeTaken = System.currentTimeMillis() - startTime - assert(timeTaken < maxWaitTimeMillis, "Operation timed out after " + timeTaken + " ms") - logInfo("Stopping context") - ssc.stop() - - val decoder = Charset.forName("UTF-8").newDecoder() - - assert(outputBuffer.size === input.length) - for (i <- 0 until outputBuffer.size) { - assert(outputBuffer(i).size === 1) - val str = decoder.decode(outputBuffer(i).head.event.getBody) - assert(str.toString === input(i).toString) - assert(outputBuffer(i).head.event.getHeaders.get("test") === "header") - } - } - - test("file input stream") { // Disable manual clock as FileInputDStream does not work with manual clock conf.set("spark.streaming.clock", "org.apache.spark.streaming.util.SystemClock") // Set up the streaming context and input streams val testDir = Files.createTempDir() - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) + val ssc = new StreamingContext(conf, batchDuration) val fileStream = ssc.textFileStream(testDir.toString) val outputBuffer = new ArrayBuffer[Seq[String]] with SynchronizedBuffer[Seq[String]] def output = outputBuffer.flatMap(x => x) @@ -206,7 +150,7 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { testServer.start() // Set up the streaming context and input streams - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) + val ssc = new StreamingContext(conf, batchDuration) val networkStream = ssc.actorStream[String](Props(new TestActor(port)), "TestActor", StorageLevel.MEMORY_AND_DISK) //Had to pass the local value of port to prevent from closing over entire scope val outputBuffer = new ArrayBuffer[Seq[String]] with SynchronizedBuffer[Seq[String]] @@ -249,20 +193,6 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { } } - test("kafka input stream") { - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) - val topics = Map("my-topic" -> 1) - val test1 = ssc.kafkaStream("localhost:12345", "group", topics) - val test2 = ssc.kafkaStream("localhost:12345", "group", topics, StorageLevel.MEMORY_AND_DISK) - - // Test specifying decoder - val kafkaParams = Map("zookeeper.connect"->"localhost:12345","group.id"->"consumer-group") - val test3 = ssc.kafkaStream[ - String, - String, - kafka.serializer.StringDecoder, - kafka.serializer.StringDecoder](kafkaParams, topics, StorageLevel.MEMORY_AND_DISK) - } test("multi-thread receiver") { // set up the test receiver @@ -273,7 +203,7 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { MultiThreadTestReceiver.haveAllThreadsFinished = false // set up the network stream using the test receiver - val ssc = new StreamingContext(new SparkContext(conf), batchDuration) + val ssc = new StreamingContext(conf, batchDuration) val networkStream = ssc.networkStream[Int](testReceiver) val countStream = networkStream.count val outputBuffer = new ArrayBuffer[Seq[Long]] with SynchronizedBuffer[Seq[Long]] diff --git a/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala b/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala index 33464bc3a1..b20d02f996 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala @@ -142,16 +142,12 @@ trait TestSuiteBase extends FunSuite with BeforeAndAfter with Logging { // Default before function for any streaming test suite. Override this // if you want to add your stuff to "before" (i.e., don't call before { } ) def beforeFunction() { - //if (useManualClock) { - // System.setProperty( - // "spark.streaming.clock", - // "org.apache.spark.streaming.util.ManualClock" - // ) - //} else { - // System.clearProperty("spark.streaming.clock") - //} if (useManualClock) { + logInfo("Using manual clock") conf.set("spark.streaming.clock", "org.apache.spark.streaming.util.ManualClock") + } else { + logInfo("Using real clock") + conf.set("spark.streaming.clock", "org.apache.spark.streaming.util.SystemClock") } } @@ -175,9 +171,8 @@ trait TestSuiteBase extends FunSuite with BeforeAndAfter with Logging { operation: DStream[U] => DStream[V], numPartitions: Int = numInputPartitions ): StreamingContext = { - val sc = new SparkContext(conf) // Create StreamingContext - val ssc = new StreamingContext(sc, batchDuration) + val ssc = new StreamingContext(conf, batchDuration) if (checkpointDir != null) { ssc.checkpoint(checkpointDir) } @@ -201,9 +196,8 @@ trait TestSuiteBase extends FunSuite with BeforeAndAfter with Logging { input2: Seq[Seq[V]], operation: (DStream[U], DStream[V]) => DStream[W] ): StreamingContext = { - val sc = new SparkContext(conf) // Create StreamingContext - val ssc = new StreamingContext(sc, batchDuration) + val ssc = new StreamingContext(conf, batchDuration) if (checkpointDir != null) { ssc.checkpoint(checkpointDir) } @@ -279,7 +273,7 @@ trait TestSuiteBase extends FunSuite with BeforeAndAfter with Logging { val startTime = System.currentTimeMillis() while (output.size < numExpectedOutput && System.currentTimeMillis() - startTime < maxWaitTimeMillis) { logInfo("output.size = " + output.size + ", numExpectedOutput = " + numExpectedOutput) - Thread.sleep(100) + Thread.sleep(10) } val timeTaken = System.currentTimeMillis() - startTime diff --git a/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala index c92c34d49b..c39abfc21b 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/WindowOperationsSuite.scala @@ -224,9 +224,7 @@ class WindowOperationsSuite extends TestSuiteBase { val slideDuration = Seconds(1) val numBatches = expectedOutput.size * (slideDuration / batchDuration).toInt val operation = (s: DStream[(String, Int)]) => { - s.groupByKeyAndWindow(windowDuration, slideDuration) - .map(x => (x._1, x._2.toSet)) - .persist() + s.groupByKeyAndWindow(windowDuration, slideDuration).map(x => (x._1, x._2.toSet)) } testOperation(input, operation, expectedOutput, numBatches, true) } diff --git a/yarn/README.md b/yarn/README.md new file mode 100644 index 0000000000..65ee85447e --- /dev/null +++ b/yarn/README.md @@ -0,0 +1,12 @@ +# YARN DIRECTORY LAYOUT + +Hadoop Yarn related codes are organized in separate directories to minimize duplicated code. + + * common : Common codes that do not depending on specific version of Hadoop. + + * alpha / stable : Codes that involve specific version of Hadoop YARN API. + + alpha represents 0.23 and 2.0.x + stable represents 2.2 and later, until the API changes again. + +alpha / stable will build together with common dir into a single jar diff --git a/yarn/alpha/pom.xml b/yarn/alpha/pom.xml new file mode 100644 index 0000000000..8291e9e7a3 --- /dev/null +++ b/yarn/alpha/pom.xml @@ -0,0 +1,32 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>yarn-parent_2.10</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-yarn-alpha_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project YARN Alpha API</name> + +</project> diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index dc9228180f..2bb11e54c5 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -36,15 +36,18 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{ConverterUtils, Records} -import org.apache.spark.{SparkContext, Logging} +import org.apache.spark.{SparkConf, SparkContext, Logging} import org.apache.spark.util.Utils +class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration, + sparkConf: SparkConf) extends Logging { -class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) extends Logging { + def this(args: ApplicationMasterArguments, sparkConf: SparkConf) = + this(args, new Configuration(), sparkConf) - def this(args: ApplicationMasterArguments) = this(args, new Configuration()) + def this(args: ApplicationMasterArguments) = this(args, new SparkConf()) - private var rpc: YarnRPC = YarnRPC.create(conf) + private val rpc: YarnRPC = YarnRPC.create(conf) private var resourceManager: AMRMProtocol = _ private var appAttemptId: ApplicationAttemptId = _ private var userThread: Thread = _ @@ -57,14 +60,19 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e private val maxAppAttempts: Int = conf.getInt(YarnConfiguration.RM_AM_MAX_RETRIES, YarnConfiguration.DEFAULT_RM_AM_MAX_RETRIES) private var isLastAMRetry: Boolean = true - // default to numWorkers * 2, with minimum of 3 - private val maxNumWorkerFailures = conf.getOrElse("spark.yarn.max.worker.failures", - math.max(args.numWorkers * 2, 3).toString()).toInt + + // Default to numWorkers * 2, with minimum of 3 + private val maxNumWorkerFailures = sparkConf.getInt("spark.yarn.max.worker.failures", + math.max(args.numWorkers * 2, 3)) def run() { // Setup the directories so things go to yarn approved directories rather // then user specified and /tmp. - conf.set("spark.local.dir", getLocalDirs()) + System.setProperty("spark.local.dir", getLocalDirs()) + + // set the web ui port to be ephemeral for yarn so we don't conflict with + // other spark processes running on the same box + System.setProperty("spark.ui.port", "0") // Use priority 30 as its higher then HDFS. Its same priority as MapReduce is using. ShutdownHookManager.get().addShutdownHook(new AppMasterShutdownHook(this), 30) @@ -99,8 +107,6 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // This a bit hacky, but we need to wait until the spark.driver.port property has // been set by the Thread executing the user class. - waitForSparkMaster() - waitForSparkContextInitialized() // Do this after spark master is up and SparkContext is created so that we can register UI Url @@ -122,7 +128,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // LOCAL_DIRS => 2.X, YARN_LOCAL_DIRS => 0.23.X val localDirs = Option(System.getenv("YARN_LOCAL_DIRS")) .getOrElse(Option(System.getenv("LOCAL_DIRS")) - .getOrElse("")) + .getOrElse("")) if (localDirs.isEmpty()) { throw new Exception("Yarn Local dirs can't be empty") @@ -161,35 +167,11 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e resourceManager.registerApplicationMaster(appMasterRequest) } - private def waitForSparkMaster() { - logInfo("Waiting for spark driver to be reachable.") - var driverUp = false - var tries = 0 - val numTries = conf.getOrElse("spark.yarn.applicationMaster.waitTries", "10").toInt - while(!driverUp && tries < numTries) { - val driverHost = conf.get("spark.driver.host") - val driverPort = conf.get("spark.driver.port") - try { - val socket = new Socket(driverHost, driverPort.toInt) - socket.close() - logInfo("Driver now available: %s:%s".format(driverHost, driverPort)) - driverUp = true - } catch { - case e: Exception => { - logWarning("Failed to connect to driver at %s:%s, retrying ...". - format(driverHost, driverPort)) - Thread.sleep(100) - tries = tries + 1 - } - } - } - } - - private def startUserClass(): Thread = { + private def startUserClass(): Thread = { logInfo("Starting the user JAR in a separate Thread") val mainMethod = Class.forName( args.userClass, - false /* initialize */, + false /* initialize */ , Thread.currentThread.getContextClassLoader).getMethod("main", classOf[Array[String]]) val t = new Thread { override def run() { @@ -226,7 +208,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e ApplicationMaster.sparkContextRef.synchronized { var count = 0 val waitTime = 10000L - val numTries = conf.getOrElse("spark.yarn.ApplicationMaster.waitTries", "10").toInt + val numTries = sparkConf.getInt("spark.yarn.ApplicationMaster.waitTries", 10) while (ApplicationMaster.sparkContextRef.get() == null && count < numTries) { logInfo("Waiting for spark context initialization ... " + count) count = count + 1 @@ -242,7 +224,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e resourceManager, appAttemptId, args, - sparkContext.preferredNodeLocationData) + sparkContext.preferredNodeLocationData, + sparkContext.getConf) } else { logWarning("Unable to retrieve sparkContext inspite of waiting for %d, numTries = %d". format(count * waitTime, numTries)) @@ -250,7 +233,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e yarnConf, resourceManager, appAttemptId, - args) + args, + sparkContext.getConf) } } } finally { @@ -294,7 +278,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // we want to be reasonably responsive without causing too many requests to RM. val schedulerInterval = - conf.getOrElse("spark.yarn.scheduler.heartbeat.interval-ms", "5000").toLong + sparkConf.getLong("spark.yarn.scheduler.heartbeat.interval-ms", 5000) // must be <= timeoutInterval / 2. val interval = math.min(timeoutInterval / 2, schedulerInterval) @@ -304,7 +288,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e } private def launchReporterThread(_sleepTime: Long): Thread = { - val sleepTime = if (_sleepTime <= 0 ) 0 else _sleepTime + val sleepTime = if (_sleepTime <= 0) 0 else _sleepTime val t = new Thread { override def run() { @@ -377,7 +361,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e private def cleanupStagingDir() { var stagingDirPath: Path = null try { - val preserveFiles = conf.getOrElse("spark.yarn.preserve.staging.files", "false").toBoolean + val preserveFiles = sparkConf.get("spark.yarn.preserve.staging.files", "false").toBoolean if (!preserveFiles) { stagingDirPath = new Path(System.getenv("SPARK_YARN_STAGING_DIR")) if (stagingDirPath == null) { @@ -403,6 +387,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e if (appMaster.isLastAMRetry) appMaster.cleanupStagingDir() } } + } object ApplicationMaster { @@ -412,6 +397,7 @@ object ApplicationMaster { // TODO: Currently, task to container is computed once (TaskSetManager) - which need not be // optimal as more containers are available. Might need to handle this better. private val ALLOCATOR_LOOP_WAIT_COUNT = 30 + def incrementAllocatorLoop(by: Int) { val count = yarnAllocatorLoop.getAndAdd(by) if (count >= ALLOCATOR_LOOP_WAIT_COUNT) { @@ -450,6 +436,7 @@ object ApplicationMaster { // This is not only logs, but also ensures that log system is initialized for this instance // when we are actually 'run'-ing. logInfo("Adding shutdown hook for context " + sc) + override def run() { logInfo("Invoking sc stop from shutdown hook") sc.stop() @@ -458,7 +445,7 @@ object ApplicationMaster { master.finishApplicationMaster(FinalApplicationStatus.SUCCEEDED) } } - } ) + }) } // Wait for initialization to complete and atleast 'some' nodes can get allocated. diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/Client.scala index 595a7ee8c3..23781ea35c 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -40,14 +40,18 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{Apps, Records} -import org.apache.spark.Logging +import org.apache.spark.{Logging, SparkConf} import org.apache.spark.util.Utils import org.apache.spark.deploy.SparkHadoopUtil -class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl with Logging { +class Client(args: ClientArguments, conf: Configuration, sparkConf: SparkConf) + extends YarnClientImpl with Logging { - def this(args: ClientArguments) = this(new Configuration(), args) + def this(args: ClientArguments, sparkConf: SparkConf) = + this(args, new Configuration(), sparkConf) + + def this(args: ClientArguments) = this(args, new SparkConf()) var rpc: YarnRPC = YarnRPC.create(conf) val yarnConf: YarnConfiguration = new YarnConfiguration(conf) @@ -98,7 +102,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl (System.getenv("SPARK_JAR") == null) -> "Error: You must set SPARK_JAR environment variable!", (args.userJar == null) -> "Error: You must specify a user jar!", (args.userClass == null) -> "Error: You must specify a user class!", - (args.numWorkers <= 0) -> "Error: You must specify atleast 1 worker!", + (args.numWorkers <= 0) -> "Error: You must specify at least 1 worker!", (args.amMemory <= YarnAllocationHandler.MEMORY_OVERHEAD) -> ("Error: AM memory size must be " + "greater than: " + YarnAllocationHandler.MEMORY_OVERHEAD), (args.workerMemory <= YarnAllocationHandler.MEMORY_OVERHEAD) -> ("Error: Worker memory size " + @@ -121,7 +125,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl clusterMetrics.getNumNodeManagers) val queueInfo: QueueInfo = super.getQueueInfo(args.amQueue) - logInfo("""Queue info ... queueName = %s, queueCurrentCapacity = %s, queueMaxCapacity = %s, + logInfo( """Queue info ... queueName = %s, queueCurrentCapacity = %s, queueMaxCapacity = %s, queueApplicationCount = %s, queueChildQueueCount = %s""".format( queueInfo.getQueueName, queueInfo.getCurrentCapacity, @@ -141,7 +145,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl } val amMem = args.amMemory + YarnAllocationHandler.MEMORY_OVERHEAD if (amMem > maxMem) { - logError("AM size is to large to run on this cluster " + amMem) + logError("AM size is to large to run on this cluster " + amMem) System.exit(1) } @@ -230,7 +234,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl } } val dst = new Path(fs.getHomeDirectory(), appStagingDir) - val replication = conf.getOrElse("spark.yarn.submit.file.replication", "3").toShort + val replication = sparkConf.getInt("spark.yarn.submit.file.replication", 3).toShort if (UserGroupInformation.isSecurityEnabled()) { val dstFs = dst.getFileSystem(conf) @@ -306,7 +310,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl val env = new HashMap[String, String]() - Client.populateClasspath(yarnConf, log4jConfLocalRes != null, env) + Client.populateClasspath(yarnConf, sparkConf, log4jConfLocalRes != null, env) env("SPARK_YARN_MODE") = "true" env("SPARK_YARN_STAGING_DIR") = stagingDir @@ -326,7 +330,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl val prefix = " --args " val args = clientArgs.userArgs val retval = new StringBuilder() - for (arg <- args){ + for (arg <- args) { retval.append(prefix).append(" '").append(arg).append("' ") } retval.toString @@ -422,7 +426,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl } def monitorApplication(appId: ApplicationId): Boolean = { - val interval = new SparkConf().getOrElse("spark.yarn.report.interval", "1000").toLong + val interval = sparkConf.getLong("spark.yarn.report.interval", 1000) while (true) { Thread.sleep(interval) @@ -465,9 +469,10 @@ object Client { // Note that anything with SPARK prefix gets propagated to all (remote) processes System.setProperty("SPARK_YARN_MODE", "true") - val args = new ClientArguments(argStrings) + val sparkConf = new SparkConf + val args = new ClientArguments(argStrings, sparkConf) - new Client(args).run + new Client(args, sparkConf).run } // Based on code from org.apache.hadoop.mapreduce.v2.util.MRApps @@ -477,7 +482,7 @@ object Client { } } - def populateClasspath(conf: Configuration, addLog4j: Boolean, env: HashMap[String, String]) { + def populateClasspath(conf: Configuration, sparkConf: SparkConf, addLog4j: Boolean, env: HashMap[String, String]) { Apps.addToEnvironment(env, Environment.CLASSPATH.name, Environment.PWD.$()) // If log4j present, ensure ours overrides all others if (addLog4j) { @@ -485,8 +490,7 @@ object Client { Path.SEPARATOR + LOG4J_PROP) } // Normally the users app.jar is last in case conflicts with spark jars - val userClasspathFirst = conf.getOrElse("spark.yarn.user.classpath.first", "false") - .toBoolean + val userClasspathFirst = sparkConf.get("spark.yarn.user.classpath.first", "false").toBoolean if (userClasspathFirst) { Apps.addToEnvironment(env, Environment.CLASSPATH.name, Environment.PWD.$() + Path.SEPARATOR + APP_JAR) diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala index c1e79cbe66..ddfec1a4ac 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala @@ -29,36 +29,41 @@ import org.apache.hadoop.yarn.util.{ConverterUtils, Records} import akka.actor._ import akka.remote._ import akka.actor.Terminated -import org.apache.spark.{SparkContext, Logging} +import org.apache.spark.{SparkConf, SparkContext, Logging} import org.apache.spark.util.{Utils, AkkaUtils} import org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend import org.apache.spark.scheduler.SplitInfo -class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) extends Logging { +class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration, sparkConf: SparkConf) + extends Logging { - def this(args: ApplicationMasterArguments) = this(args, new Configuration()) + def this(args: ApplicationMasterArguments, sparkConf: SparkConf) = this(args, new Configuration(), sparkConf) + + def this(args: ApplicationMasterArguments) = this(args, new SparkConf()) private val rpc: YarnRPC = YarnRPC.create(conf) - private var resourceManager: AMRMProtocol = null - private var appAttemptId: ApplicationAttemptId = null - private var reporterThread: Thread = null + private var resourceManager: AMRMProtocol = _ + private var appAttemptId: ApplicationAttemptId = _ + private var reporterThread: Thread = _ private val yarnConf: YarnConfiguration = new YarnConfiguration(conf) - private var yarnAllocator: YarnAllocationHandler = null + private var yarnAllocator: YarnAllocationHandler = _ private var driverClosed:Boolean = false - val actorSystem : ActorSystem = AkkaUtils.createActorSystem("sparkYarnAM", Utils.localHostName, 0)._1 - var actor: ActorRef = null + val actorSystem : ActorSystem = AkkaUtils.createActorSystem("sparkYarnAM", Utils.localHostName, 0, + conf = sparkConf)._1 + var actor: ActorRef = _ // This actor just working as a monitor to watch on Driver Actor. class MonitorActor(driverUrl: String) extends Actor { - var driver: ActorSelection = null + var driver: ActorSelection = _ override def preStart() { logInfo("Listen to driver: " + driverUrl) driver = context.actorSelection(driverUrl) - driver ! "hello" + // Send a hello message thus the connection is actually established, thus we can monitor Lifecycle Events. + driver ! "Hello" context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent]) } @@ -162,8 +167,8 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte Thread.sleep(100) } } - conf.set("spark.driver.host", driverHost) - conf.set("spark.driver.port", driverPort.toString) + sparkConf.set("spark.driver.host", driverHost) + sparkConf.set("spark.driver.port", driverPort.toString) val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format( driverHost, driverPort.toString, CoarseGrainedSchedulerBackend.ACTOR_NAME) @@ -175,9 +180,11 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte private def allocateWorkers() { // Fixme: should get preferredNodeLocationData from SparkContext, just fake a empty one for now. - val preferredNodeLocationData: scala.collection.Map[String, scala.collection.Set[SplitInfo]] = scala.collection.immutable.Map() + val preferredNodeLocationData: scala.collection.Map[String, scala.collection.Set[SplitInfo]] = + scala.collection.immutable.Map() - yarnAllocator = YarnAllocationHandler.newAllocator(yarnConf, resourceManager, appAttemptId, args, preferredNodeLocationData) + yarnAllocator = YarnAllocationHandler.newAllocator(yarnConf, resourceManager, appAttemptId, + args, preferredNodeLocationData, sparkConf) logInfo("Allocating " + args.numWorkers + " workers.") // Wait until all containers have finished diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala index 6a90cc51cf..132630e5ef 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala @@ -37,12 +37,13 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{Apps, ConverterUtils, Records, ProtoUtils} -import org.apache.spark.Logging +import org.apache.spark.{SparkConf, Logging} class WorkerRunnable( container: Container, conf: Configuration, + sparkConf: SparkConf, masterAddress: String, slaveId: String, hostname: String, @@ -51,7 +52,7 @@ class WorkerRunnable( extends Runnable with Logging { var rpc: YarnRPC = YarnRPC.create(conf) - var cm: ContainerManager = null + var cm: ContainerManager = _ val yarnConf: YarnConfiguration = new YarnConfiguration(conf) def run = { @@ -200,7 +201,7 @@ class WorkerRunnable( def prepareEnvironment: HashMap[String, String] = { val env = new HashMap[String, String]() - Client.populateClasspath(yarnConf, System.getenv("SPARK_YARN_LOG4J_PATH") != null, env) + Client.populateClasspath(yarnConf, sparkConf, System.getenv("SPARK_YARN_LOG4J_PATH") != null, env) // Allow users to specify some environment variables Apps.setEnvFromInputString(env, System.getenv("SPARK_YARN_USER_ENV")) diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala index 5966a0f757..e91257be8e 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala @@ -26,7 +26,7 @@ import scala.collection import scala.collection.JavaConversions._ import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet} -import org.apache.spark.Logging +import org.apache.spark.{Logging, SparkConf} import org.apache.spark.scheduler.{SplitInfo,TaskSchedulerImpl} import org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend import org.apache.spark.util.Utils @@ -62,7 +62,8 @@ private[yarn] class YarnAllocationHandler( val workerMemory: Int, val workerCores: Int, val preferredHostToCount: Map[String, Int], - val preferredRackToCount: Map[String, Int]) + val preferredRackToCount: Map[String, Int], + val sparkConf: SparkConf) extends Logging { // These three are locked on allocatedHostToContainersMap. Complementary data structures // allocatedHostToContainersMap : containers which are running : host, Set<containerid> @@ -239,7 +240,7 @@ private[yarn] class YarnAllocationHandler( // (workerIdCounter) val workerId = workerIdCounter.incrementAndGet().toString val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format( - conf.get("spark.driver.host"), conf.get("spark.driver.port"), + sparkConf.get("spark.driver.host"), sparkConf.get("spark.driver.port"), CoarseGrainedSchedulerBackend.ACTOR_NAME) logInfo("launching container on " + containerId + " host " + workerHostname) @@ -260,7 +261,7 @@ private[yarn] class YarnAllocationHandler( } new Thread( - new WorkerRunnable(container, conf, driverUrl, workerId, + new WorkerRunnable(container, conf, sparkConf, driverUrl, workerId, workerHostname, workerMemory, workerCores) ).start() } @@ -552,7 +553,8 @@ object YarnAllocationHandler { conf: Configuration, resourceManager: AMRMProtocol, appAttemptId: ApplicationAttemptId, - args: ApplicationMasterArguments): YarnAllocationHandler = { + args: ApplicationMasterArguments, + sparkConf: SparkConf): YarnAllocationHandler = { new YarnAllocationHandler( conf, @@ -562,7 +564,8 @@ object YarnAllocationHandler { args.workerMemory, args.workerCores, Map[String, Int](), - Map[String, Int]()) + Map[String, Int](), + sparkConf) } def newAllocator( @@ -571,7 +574,8 @@ object YarnAllocationHandler { appAttemptId: ApplicationAttemptId, args: ApplicationMasterArguments, map: collection.Map[String, - collection.Set[SplitInfo]]): YarnAllocationHandler = { + collection.Set[SplitInfo]], + sparkConf: SparkConf): YarnAllocationHandler = { val (hostToCount, rackToCount) = generateNodeToWeight(conf, map) new YarnAllocationHandler( @@ -582,7 +586,8 @@ object YarnAllocationHandler { args.workerMemory, args.workerCores, hostToCount, - rackToCount) + rackToCount, + sparkConf) } def newAllocator( @@ -592,7 +597,8 @@ object YarnAllocationHandler { maxWorkers: Int, workerMemory: Int, workerCores: Int, - map: collection.Map[String, collection.Set[SplitInfo]]): YarnAllocationHandler = { + map: collection.Map[String, collection.Set[SplitInfo]], + sparkConf: SparkConf): YarnAllocationHandler = { val (hostToCount, rackToCount) = generateNodeToWeight(conf, map) @@ -604,7 +610,8 @@ object YarnAllocationHandler { workerMemory, workerCores, hostToCount, - rackToCount) + rackToCount, + sparkConf) } // A simple method to copy the split info map. diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala index f76a5ddd39..f76a5ddd39 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala +++ b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala index 1a9bb97b3e..1419f215c7 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala +++ b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala @@ -19,13 +19,14 @@ package org.apache.spark.deploy.yarn import scala.collection.mutable.{ArrayBuffer, HashMap} +import org.apache.spark.SparkConf import org.apache.spark.scheduler.{InputFormatInfo, SplitInfo} import org.apache.spark.util.IntParam import org.apache.spark.util.MemoryParam // TODO: Add code and support for ensuring that yarn resource 'tasks' are location aware ! -class ClientArguments(val args: Array[String]) { +class ClientArguments(val args: Array[String], val sparkConf: SparkConf) { var addJars: String = null var files: String = null var archives: String = null @@ -35,7 +36,7 @@ class ClientArguments(val args: Array[String]) { var workerMemory = 1024 // MB var workerCores = 1 var numWorkers = 2 - var amQueue = conf.getOrElse("QUEUE", "default") + var amQueue = sparkConf.get("QUEUE", "default") var amMemory: Int = 512 // MB var amClass: String = "org.apache.spark.deploy.yarn.ApplicationMaster" var appName: String = "Spark" diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala index 5f159b073f..5f159b073f 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala +++ b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala index 2ba2366ead..2ba2366ead 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala +++ b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala diff --git a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala index 522e0a9ad7..522e0a9ad7 100644 --- a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala diff --git a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala index 4b69f5078b..4b1b5da048 100644 --- a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala @@ -39,6 +39,7 @@ private[spark] class YarnClientSchedulerBackend( val defaultWorkerNumber = "1" val userJar = System.getenv("SPARK_YARN_APP_JAR") + val distFiles = System.getenv("SPARK_YARN_DIST_FILES") var workerCores = System.getenv("SPARK_WORKER_CORES") var workerMemory = System.getenv("SPARK_WORKER_MEMORY") var workerNumber = System.getenv("SPARK_WORKER_INSTANCES") @@ -64,11 +65,12 @@ private[spark] class YarnClientSchedulerBackend( "--worker-memory", workerMemory, "--worker-cores", workerCores, "--num-workers", workerNumber, - "--master-class", "org.apache.spark.deploy.yarn.WorkerLauncher" + "--master-class", "org.apache.spark.deploy.yarn.WorkerLauncher", + "--files", distFiles ) - val args = new ClientArguments(argsArray) - client = new Client(args) + val args = new ClientArguments(argsArray, conf) + client = new Client(args, conf) appId = client.runApp() waitForApp() } diff --git a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala index a4638cc863..a4638cc863 100644 --- a/new-yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala diff --git a/new-yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala b/yarn/common/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala index 2941356bc5..2941356bc5 100644 --- a/new-yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala +++ b/yarn/common/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala diff --git a/yarn/pom.xml b/yarn/pom.xml index bc64a190fd..aea8b0cdde 100644 --- a/yarn/pom.xml +++ b/yarn/pom.xml @@ -25,11 +25,10 @@ </parent> <groupId>org.apache.spark</groupId> - <artifactId>spark-yarn_2.10</artifactId> - <packaging>jar</packaging> - <name>Spark Project YARN Support</name> - <url>http://spark.incubator.apache.org/</url> - + <artifactId>yarn-parent_2.10</artifactId> + <packaging>pom</packaging> + <name>Spark Project YARN Parent POM</name> + <dependencies> <dependency> <groupId>org.apache.spark</groupId> @@ -73,45 +72,52 @@ </dependency> </dependencies> + <profiles> + <profile> + <id>yarn-alpha</id> + <modules> + <module>alpha</module> + </modules> + </profile> + + <profile> + <id>yarn</id> + <modules> + <module>stable</module> + </modules> + </profile> + </profiles> + <build> - <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> - <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> <plugins> <plugin> - <groupId>org.apache.maven.plugins</groupId> - <artifactId>maven-shade-plugin</artifactId> - <configuration> - <shadedArtifactAttached>false</shadedArtifactAttached> - <outputFile>${project.build.directory}/${project.artifactId}-${project.version}-shaded.jar</outputFile> - <artifactSet> - <includes> - <include>*:*</include> - </includes> - </artifactSet> - <filters> - <filter> - <artifact>*:*</artifact> - <excludes> - <exclude>META-INF/*.SF</exclude> - <exclude>META-INF/*.DSA</exclude> - <exclude>META-INF/*.RSA</exclude> - </excludes> - </filter> - </filters> - </configuration> + <groupId>org.codehaus.mojo</groupId> + <artifactId>build-helper-maven-plugin</artifactId> <executions> <execution> - <phase>package</phase> + <id>add-scala-sources</id> + <phase>generate-sources</phase> + <goals> + <goal>add-source</goal> + </goals> + <configuration> + <sources> + <source>src/main/scala</source> + <source>../common/src/main/scala</source> + </sources> + </configuration> + </execution> + <execution> + <id>add-scala-test-sources</id> + <phase>generate-test-sources</phase> <goals> - <goal>shade</goal> + <goal>add-test-source</goal> </goals> <configuration> - <transformers> - <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" /> - <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> - <resource>reference.conf</resource> - </transformer> - </transformers> + <sources> + <source>src/test/scala</source> + <source>../common/src/test/scala</source> + </sources> </configuration> </execution> </executions> @@ -150,12 +156,16 @@ <artifactId>scalatest-maven-plugin</artifactId> <configuration> <environmentVariables> - <SPARK_HOME>${basedir}/..</SPARK_HOME> + <SPARK_HOME>${basedir}/../..</SPARK_HOME> <SPARK_TESTING>1</SPARK_TESTING> <SPARK_CLASSPATH>${spark.classpath}</SPARK_CLASSPATH> </environmentVariables> </configuration> </plugin> </plugins> + + <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> + <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> </build> + </project> diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala deleted file mode 100644 index f76a5ddd39..0000000000 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMasterArguments.scala +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.deploy.yarn - -import org.apache.spark.util.IntParam -import collection.mutable.ArrayBuffer - -class ApplicationMasterArguments(val args: Array[String]) { - var userJar: String = null - var userClass: String = null - var userArgs: Seq[String] = Seq[String]() - var workerMemory = 1024 - var workerCores = 1 - var numWorkers = 2 - - parseArgs(args.toList) - - private def parseArgs(inputArgs: List[String]): Unit = { - val userArgsBuffer = new ArrayBuffer[String]() - - var args = inputArgs - - while (! args.isEmpty) { - - args match { - case ("--jar") :: value :: tail => - userJar = value - args = tail - - case ("--class") :: value :: tail => - userClass = value - args = tail - - case ("--args") :: value :: tail => - userArgsBuffer += value - args = tail - - case ("--num-workers") :: IntParam(value) :: tail => - numWorkers = value - args = tail - - case ("--worker-memory") :: IntParam(value) :: tail => - workerMemory = value - args = tail - - case ("--worker-cores") :: IntParam(value) :: tail => - workerCores = value - args = tail - - case Nil => - if (userJar == null || userClass == null) { - printUsageAndExit(1) - } - - case _ => - printUsageAndExit(1, args) - } - } - - userArgs = userArgsBuffer.readOnly - } - - def printUsageAndExit(exitCode: Int, unknownParam: Any = null) { - if (unknownParam != null) { - System.err.println("Unknown/unsupported param " + unknownParam) - } - System.err.println( - "Usage: org.apache.spark.deploy.yarn.ApplicationMaster [options] \n" + - "Options:\n" + - " --jar JAR_PATH Path to your application's JAR file (required)\n" + - " --class CLASS_NAME Name of your application's main class (required)\n" + - " --args ARGS Arguments to be passed to your application's main class.\n" + - " Mutliple invocations are possible, each will be passed in order.\n" + - " --num-workers NUM Number of workers to start (Default: 2)\n" + - " --worker-cores NUM Number of cores for the workers (Default: 1)\n" + - " --worker-memory MEM Memory per Worker (e.g. 1000M, 2G) (Default: 1G)\n") - System.exit(exitCode) - } -} diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala deleted file mode 100644 index e9e46a193b..0000000000 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientArguments.scala +++ /dev/null @@ -1,146 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.deploy.yarn - -import org.apache.spark.util.MemoryParam -import org.apache.spark.util.IntParam -import collection.mutable.{ArrayBuffer, HashMap} -import org.apache.spark.scheduler.{InputFormatInfo, SplitInfo} - -// TODO: Add code and support for ensuring that yarn resource 'asks' are location aware ! -class ClientArguments(val args: Array[String]) { - var addJars: String = null - var files: String = null - var archives: String = null - var userJar: String = null - var userClass: String = null - var userArgs: Seq[String] = Seq[String]() - var workerMemory = 1024 - var workerCores = 1 - var numWorkers = 2 - var amQueue = conf.getOrElse("QUEUE", "default") - var amMemory: Int = 512 - var amClass: String = "org.apache.spark.deploy.yarn.ApplicationMaster" - var appName: String = "Spark" - // TODO - var inputFormatInfo: List[InputFormatInfo] = null - - parseArgs(args.toList) - - private def parseArgs(inputArgs: List[String]): Unit = { - val userArgsBuffer: ArrayBuffer[String] = new ArrayBuffer[String]() - val inputFormatMap: HashMap[String, InputFormatInfo] = new HashMap[String, InputFormatInfo]() - - var args = inputArgs - - while (! args.isEmpty) { - - args match { - case ("--jar") :: value :: tail => - userJar = value - args = tail - - case ("--class") :: value :: tail => - userClass = value - args = tail - - case ("--args") :: value :: tail => - userArgsBuffer += value - args = tail - - case ("--master-class") :: value :: tail => - amClass = value - args = tail - - case ("--master-memory") :: MemoryParam(value) :: tail => - amMemory = value - args = tail - - case ("--worker-memory") :: MemoryParam(value) :: tail => - workerMemory = value - args = tail - - case ("--num-workers") :: IntParam(value) :: tail => - numWorkers = value - args = tail - - case ("--worker-cores") :: IntParam(value) :: tail => - workerCores = value - args = tail - - case ("--queue") :: value :: tail => - amQueue = value - args = tail - - case ("--name") :: value :: tail => - appName = value - args = tail - - case ("--addJars") :: value :: tail => - addJars = value - args = tail - - case ("--files") :: value :: tail => - files = value - args = tail - - case ("--archives") :: value :: tail => - archives = value - args = tail - - case Nil => - if (userJar == null || userClass == null) { - printUsageAndExit(1) - } - - case _ => - printUsageAndExit(1, args) - } - } - - userArgs = userArgsBuffer.readOnly - inputFormatInfo = inputFormatMap.values.toList - } - - - def printUsageAndExit(exitCode: Int, unknownParam: Any = null) { - if (unknownParam != null) { - System.err.println("Unknown/unsupported param " + unknownParam) - } - System.err.println( - "Usage: org.apache.spark.deploy.yarn.Client [options] \n" + - "Options:\n" + - " --jar JAR_PATH Path to your application's JAR file (required)\n" + - " --class CLASS_NAME Name of your application's main class (required)\n" + - " --args ARGS Arguments to be passed to your application's main class.\n" + - " Mutliple invocations are possible, each will be passed in order.\n" + - " --num-workers NUM Number of workers to start (Default: 2)\n" + - " --worker-cores NUM Number of cores for the workers (Default: 1). This is unsused right now.\n" + - " --master-class CLASS_NAME Class Name for Master (Default: spark.deploy.yarn.ApplicationMaster)\n" + - " --master-memory MEM Memory for Master (e.g. 1000M, 2G) (Default: 512 Mb)\n" + - " --worker-memory MEM Memory per Worker (e.g. 1000M, 2G) (Default: 1G)\n" + - " --name NAME The name of your application (Default: Spark)\n" + - " --queue QUEUE The hadoop queue to use for allocation requests (Default: 'default')\n" + - " --addJars jars Comma separated list of local jars that want SparkContext.addJar to work with.\n" + - " --files files Comma separated list of files to be distributed with the job.\n" + - " --archives archives Comma separated list of archives to be distributed with the job." - ) - System.exit(exitCode) - } - -} diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala deleted file mode 100644 index 5f159b073f..0000000000 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala +++ /dev/null @@ -1,228 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.deploy.yarn - -import java.net.URI - -import org.apache.hadoop.conf.Configuration -import org.apache.hadoop.fs.FileStatus -import org.apache.hadoop.fs.FileSystem -import org.apache.hadoop.fs.Path -import org.apache.hadoop.fs.permission.FsAction -import org.apache.hadoop.yarn.api.records.LocalResource -import org.apache.hadoop.yarn.api.records.LocalResourceVisibility -import org.apache.hadoop.yarn.api.records.LocalResourceType -import org.apache.hadoop.yarn.util.{Records, ConverterUtils} - -import org.apache.spark.Logging - -import scala.collection.mutable.HashMap -import scala.collection.mutable.LinkedHashMap -import scala.collection.mutable.Map - - -/** Client side methods to setup the Hadoop distributed cache */ -class ClientDistributedCacheManager() extends Logging { - private val distCacheFiles: Map[String, Tuple3[String, String, String]] = - LinkedHashMap[String, Tuple3[String, String, String]]() - private val distCacheArchives: Map[String, Tuple3[String, String, String]] = - LinkedHashMap[String, Tuple3[String, String, String]]() - - - /** - * Add a resource to the list of distributed cache resources. This list can - * be sent to the ApplicationMaster and possibly the workers so that it can - * be downloaded into the Hadoop distributed cache for use by this application. - * Adds the LocalResource to the localResources HashMap passed in and saves - * the stats of the resources to they can be sent to the workers and verified. - * - * @param fs FileSystem - * @param conf Configuration - * @param destPath path to the resource - * @param localResources localResource hashMap to insert the resource into - * @param resourceType LocalResourceType - * @param link link presented in the distributed cache to the destination - * @param statCache cache to store the file/directory stats - * @param appMasterOnly Whether to only add the resource to the app master - */ - def addResource( - fs: FileSystem, - conf: Configuration, - destPath: Path, - localResources: HashMap[String, LocalResource], - resourceType: LocalResourceType, - link: String, - statCache: Map[URI, FileStatus], - appMasterOnly: Boolean = false) = { - val destStatus = fs.getFileStatus(destPath) - val amJarRsrc = Records.newRecord(classOf[LocalResource]).asInstanceOf[LocalResource] - amJarRsrc.setType(resourceType) - val visibility = getVisibility(conf, destPath.toUri(), statCache) - amJarRsrc.setVisibility(visibility) - amJarRsrc.setResource(ConverterUtils.getYarnUrlFromPath(destPath)) - amJarRsrc.setTimestamp(destStatus.getModificationTime()) - amJarRsrc.setSize(destStatus.getLen()) - if (link == null || link.isEmpty()) throw new Exception("You must specify a valid link name") - localResources(link) = amJarRsrc - - if (appMasterOnly == false) { - val uri = destPath.toUri() - val pathURI = new URI(uri.getScheme(), uri.getAuthority(), uri.getPath(), null, link) - if (resourceType == LocalResourceType.FILE) { - distCacheFiles(pathURI.toString()) = (destStatus.getLen().toString(), - destStatus.getModificationTime().toString(), visibility.name()) - } else { - distCacheArchives(pathURI.toString()) = (destStatus.getLen().toString(), - destStatus.getModificationTime().toString(), visibility.name()) - } - } - } - - /** - * Adds the necessary cache file env variables to the env passed in - * @param env - */ - def setDistFilesEnv(env: Map[String, String]) = { - val (keys, tupleValues) = distCacheFiles.unzip - val (sizes, timeStamps, visibilities) = tupleValues.unzip3 - - if (keys.size > 0) { - env("SPARK_YARN_CACHE_FILES") = keys.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_FILES_TIME_STAMPS") = - timeStamps.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_FILES_FILE_SIZES") = - sizes.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_FILES_VISIBILITIES") = - visibilities.reduceLeft[String] { (acc,n) => acc + "," + n } - } - } - - /** - * Adds the necessary cache archive env variables to the env passed in - * @param env - */ - def setDistArchivesEnv(env: Map[String, String]) = { - val (keys, tupleValues) = distCacheArchives.unzip - val (sizes, timeStamps, visibilities) = tupleValues.unzip3 - - if (keys.size > 0) { - env("SPARK_YARN_CACHE_ARCHIVES") = keys.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_ARCHIVES_TIME_STAMPS") = - timeStamps.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_ARCHIVES_FILE_SIZES") = - sizes.reduceLeft[String] { (acc,n) => acc + "," + n } - env("SPARK_YARN_CACHE_ARCHIVES_VISIBILITIES") = - visibilities.reduceLeft[String] { (acc,n) => acc + "," + n } - } - } - - /** - * Returns the local resource visibility depending on the cache file permissions - * @param conf - * @param uri - * @param statCache - * @return LocalResourceVisibility - */ - def getVisibility(conf: Configuration, uri: URI, statCache: Map[URI, FileStatus]): - LocalResourceVisibility = { - if (isPublic(conf, uri, statCache)) { - return LocalResourceVisibility.PUBLIC - } - return LocalResourceVisibility.PRIVATE - } - - /** - * Returns a boolean to denote whether a cache file is visible to all(public) - * or not - * @param conf - * @param uri - * @param statCache - * @return true if the path in the uri is visible to all, false otherwise - */ - def isPublic(conf: Configuration, uri: URI, statCache: Map[URI, FileStatus]): Boolean = { - val fs = FileSystem.get(uri, conf) - val current = new Path(uri.getPath()) - //the leaf level file should be readable by others - if (!checkPermissionOfOther(fs, current, FsAction.READ, statCache)) { - return false - } - return ancestorsHaveExecutePermissions(fs, current.getParent(), statCache) - } - - /** - * Returns true if all ancestors of the specified path have the 'execute' - * permission set for all users (i.e. that other users can traverse - * the directory heirarchy to the given path) - * @param fs - * @param path - * @param statCache - * @return true if all ancestors have the 'execute' permission set for all users - */ - def ancestorsHaveExecutePermissions(fs: FileSystem, path: Path, - statCache: Map[URI, FileStatus]): Boolean = { - var current = path - while (current != null) { - //the subdirs in the path should have execute permissions for others - if (!checkPermissionOfOther(fs, current, FsAction.EXECUTE, statCache)) { - return false - } - current = current.getParent() - } - return true - } - - /** - * Checks for a given path whether the Other permissions on it - * imply the permission in the passed FsAction - * @param fs - * @param path - * @param action - * @param statCache - * @return true if the path in the uri is visible to all, false otherwise - */ - def checkPermissionOfOther(fs: FileSystem, path: Path, - action: FsAction, statCache: Map[URI, FileStatus]): Boolean = { - val status = getFileStatus(fs, path.toUri(), statCache) - val perms = status.getPermission() - val otherAction = perms.getOtherAction() - if (otherAction.implies(action)) { - return true - } - return false - } - - /** - * Checks to see if the given uri exists in the cache, if it does it - * returns the existing FileStatus, otherwise it stats the uri, stores - * it in the cache, and returns the FileStatus. - * @param fs - * @param uri - * @param statCache - * @return FileStatus - */ - def getFileStatus(fs: FileSystem, uri: URI, statCache: Map[URI, FileStatus]): FileStatus = { - val stat = statCache.get(uri) match { - case Some(existstat) => existstat - case None => - val newStat = fs.getFileStatus(new Path(uri)) - statCache.put(uri, newStat) - newStat - } - return stat - } -} diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala deleted file mode 100644 index 2ba2366ead..0000000000 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala +++ /dev/null @@ -1,43 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.deploy.yarn - -import org.apache.spark.deploy.SparkHadoopUtil -import org.apache.hadoop.mapred.JobConf -import org.apache.hadoop.security.UserGroupInformation -import org.apache.hadoop.yarn.conf.YarnConfiguration -import org.apache.hadoop.conf.Configuration - -/** - * Contains util methods to interact with Hadoop from spark. - */ -class YarnSparkHadoopUtil extends SparkHadoopUtil { - - // Note that all params which start with SPARK are propagated all the way through, so if in yarn mode, this MUST be set to true. - override def isYarnMode(): Boolean = { true } - - // Return an appropriate (subclass) of Configuration. Creating config can initializes some hadoop subsystems - // Always create a new config, dont reuse yarnConf. - override def newConfiguration(): Configuration = new YarnConfiguration(new Configuration()) - - // add any user credentials to the job conf which are necessary for running on a secure Hadoop cluster - override def addCredentials(conf: JobConf) { - val jobCreds = conf.getCredentials() - jobCreds.mergeAll(UserGroupInformation.getCurrentUser().getCredentials()) - } -} diff --git a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala deleted file mode 100644 index 522e0a9ad7..0000000000 --- a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientClusterScheduler.scala +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.scheduler.cluster - -import org.apache.spark._ -import org.apache.hadoop.conf.Configuration -import org.apache.spark.deploy.yarn.YarnAllocationHandler -import org.apache.spark.scheduler.TaskSchedulerImpl -import org.apache.spark.util.Utils - -/** - * - * This scheduler launch worker through Yarn - by call into Client to launch WorkerLauncher as AM. - */ -private[spark] class YarnClientClusterScheduler(sc: SparkContext, conf: Configuration) extends TaskSchedulerImpl(sc) { - - def this(sc: SparkContext) = this(sc, new Configuration()) - - // By default, rack is unknown - override def getRackForHost(hostPort: String): Option[String] = { - val host = Utils.parseHostPort(hostPort)._1 - val retval = YarnAllocationHandler.lookupRack(conf, host) - if (retval != null) Some(retval) else None - } - - override def postStartHook() { - - // The yarn application is running, but the worker might not yet ready - // Wait for a few seconds for the slaves to bootstrap and register with master - best case attempt - Thread.sleep(2000L) - logInfo("YarnClientClusterScheduler.postStartHook done") - } -} diff --git a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala deleted file mode 100644 index 2d9fbcb400..0000000000 --- a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClusterScheduler.scala +++ /dev/null @@ -1,59 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.scheduler.cluster - -import org.apache.hadoop.conf.Configuration - -import org.apache.spark._ -import org.apache.spark.deploy.yarn.{ApplicationMaster, YarnAllocationHandler} -import org.apache.spark.scheduler.TaskSchedulerImpl -import org.apache.spark.util.Utils - -/** - * - * This is a simple extension to ClusterScheduler - to ensure that appropriate initialization of - * ApplicationMaster, etc. is done - */ -private[spark] class YarnClusterScheduler(sc: SparkContext, conf: Configuration) - extends TaskSchedulerImpl(sc) { - - logInfo("Created YarnClusterScheduler") - - def this(sc: SparkContext) = this(sc, new Configuration()) - - // Nothing else for now ... initialize application master : which needs sparkContext to determine how to allocate - // Note that only the first creation of SparkContext influences (and ideally, there must be only one SparkContext, right ?) - // Subsequent creations are ignored - since nodes are already allocated by then. - - - // By default, rack is unknown - override def getRackForHost(hostPort: String): Option[String] = { - val host = Utils.parseHostPort(hostPort)._1 - val retval = YarnAllocationHandler.lookupRack(conf, host) - if (retval != null) Some(retval) else None - } - - override def postStartHook() { - val sparkContextInitialized = ApplicationMaster.sparkContextInitialized(sc) - if (sparkContextInitialized){ - // Wait for a few seconds for the slaves to bootstrap and register with master - best case attempt - Thread.sleep(3000L) - } - logInfo("YarnClusterScheduler.postStartHook done") - } -} diff --git a/yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala b/yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala deleted file mode 100644 index 2941356bc5..0000000000 --- a/yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManagerSuite.scala +++ /dev/null @@ -1,220 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark.deploy.yarn - -import java.net.URI - -import org.scalatest.FunSuite -import org.scalatest.mock.MockitoSugar -import org.mockito.Mockito.when - -import org.apache.hadoop.conf.Configuration -import org.apache.hadoop.fs.FileStatus -import org.apache.hadoop.fs.FileSystem -import org.apache.hadoop.fs.Path -import org.apache.hadoop.fs.permission.FsAction -import org.apache.hadoop.yarn.api.records.LocalResource -import org.apache.hadoop.yarn.api.records.LocalResourceVisibility -import org.apache.hadoop.yarn.api.records.LocalResourceType -import org.apache.hadoop.yarn.util.{Records, ConverterUtils} - -import scala.collection.mutable.HashMap -import scala.collection.mutable.Map - - -class ClientDistributedCacheManagerSuite extends FunSuite with MockitoSugar { - - class MockClientDistributedCacheManager extends ClientDistributedCacheManager { - override def getVisibility(conf: Configuration, uri: URI, statCache: Map[URI, FileStatus]): - LocalResourceVisibility = { - return LocalResourceVisibility.PRIVATE - } - } - - test("test getFileStatus empty") { - val distMgr = new ClientDistributedCacheManager() - val fs = mock[FileSystem] - val uri = new URI("/tmp/testing") - when(fs.getFileStatus(new Path(uri))).thenReturn(new FileStatus()) - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus]() - val stat = distMgr.getFileStatus(fs, uri, statCache) - assert(stat.getPath() === null) - } - - test("test getFileStatus cached") { - val distMgr = new ClientDistributedCacheManager() - val fs = mock[FileSystem] - val uri = new URI("/tmp/testing") - val realFileStatus = new FileStatus(10, false, 1, 1024, 10, 10, null, "testOwner", - null, new Path("/tmp/testing")) - when(fs.getFileStatus(new Path(uri))).thenReturn(new FileStatus()) - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus](uri -> realFileStatus) - val stat = distMgr.getFileStatus(fs, uri, statCache) - assert(stat.getPath().toString() === "/tmp/testing") - } - - test("test addResource") { - val distMgr = new MockClientDistributedCacheManager() - val fs = mock[FileSystem] - val conf = new Configuration() - val destPath = new Path("file:///foo.invalid.com:8080/tmp/testing") - val localResources = HashMap[String, LocalResource]() - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus]() - when(fs.getFileStatus(destPath)).thenReturn(new FileStatus()) - - distMgr.addResource(fs, conf, destPath, localResources, LocalResourceType.FILE, "link", - statCache, false) - val resource = localResources("link") - assert(resource.getVisibility() === LocalResourceVisibility.PRIVATE) - assert(ConverterUtils.getPathFromYarnURL(resource.getResource()) === destPath) - assert(resource.getTimestamp() === 0) - assert(resource.getSize() === 0) - assert(resource.getType() === LocalResourceType.FILE) - - val env = new HashMap[String, String]() - distMgr.setDistFilesEnv(env) - assert(env("SPARK_YARN_CACHE_FILES") === "file:/foo.invalid.com:8080/tmp/testing#link") - assert(env("SPARK_YARN_CACHE_FILES_TIME_STAMPS") === "0") - assert(env("SPARK_YARN_CACHE_FILES_FILE_SIZES") === "0") - assert(env("SPARK_YARN_CACHE_FILES_VISIBILITIES") === LocalResourceVisibility.PRIVATE.name()) - - distMgr.setDistArchivesEnv(env) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_TIME_STAMPS") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_FILE_SIZES") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_VISIBILITIES") === None) - - //add another one and verify both there and order correct - val realFileStatus = new FileStatus(20, false, 1, 1024, 10, 30, null, "testOwner", - null, new Path("/tmp/testing2")) - val destPath2 = new Path("file:///foo.invalid.com:8080/tmp/testing2") - when(fs.getFileStatus(destPath2)).thenReturn(realFileStatus) - distMgr.addResource(fs, conf, destPath2, localResources, LocalResourceType.FILE, "link2", - statCache, false) - val resource2 = localResources("link2") - assert(resource2.getVisibility() === LocalResourceVisibility.PRIVATE) - assert(ConverterUtils.getPathFromYarnURL(resource2.getResource()) === destPath2) - assert(resource2.getTimestamp() === 10) - assert(resource2.getSize() === 20) - assert(resource2.getType() === LocalResourceType.FILE) - - val env2 = new HashMap[String, String]() - distMgr.setDistFilesEnv(env2) - val timestamps = env2("SPARK_YARN_CACHE_FILES_TIME_STAMPS").split(',') - val files = env2("SPARK_YARN_CACHE_FILES").split(',') - val sizes = env2("SPARK_YARN_CACHE_FILES_FILE_SIZES").split(',') - val visibilities = env2("SPARK_YARN_CACHE_FILES_VISIBILITIES") .split(',') - assert(files(0) === "file:/foo.invalid.com:8080/tmp/testing#link") - assert(timestamps(0) === "0") - assert(sizes(0) === "0") - assert(visibilities(0) === LocalResourceVisibility.PRIVATE.name()) - - assert(files(1) === "file:/foo.invalid.com:8080/tmp/testing2#link2") - assert(timestamps(1) === "10") - assert(sizes(1) === "20") - assert(visibilities(1) === LocalResourceVisibility.PRIVATE.name()) - } - - test("test addResource link null") { - val distMgr = new MockClientDistributedCacheManager() - val fs = mock[FileSystem] - val conf = new Configuration() - val destPath = new Path("file:///foo.invalid.com:8080/tmp/testing") - val localResources = HashMap[String, LocalResource]() - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus]() - when(fs.getFileStatus(destPath)).thenReturn(new FileStatus()) - - intercept[Exception] { - distMgr.addResource(fs, conf, destPath, localResources, LocalResourceType.FILE, null, - statCache, false) - } - assert(localResources.get("link") === None) - assert(localResources.size === 0) - } - - test("test addResource appmaster only") { - val distMgr = new MockClientDistributedCacheManager() - val fs = mock[FileSystem] - val conf = new Configuration() - val destPath = new Path("file:///foo.invalid.com:8080/tmp/testing") - val localResources = HashMap[String, LocalResource]() - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus]() - val realFileStatus = new FileStatus(20, false, 1, 1024, 10, 30, null, "testOwner", - null, new Path("/tmp/testing")) - when(fs.getFileStatus(destPath)).thenReturn(realFileStatus) - - distMgr.addResource(fs, conf, destPath, localResources, LocalResourceType.ARCHIVE, "link", - statCache, true) - val resource = localResources("link") - assert(resource.getVisibility() === LocalResourceVisibility.PRIVATE) - assert(ConverterUtils.getPathFromYarnURL(resource.getResource()) === destPath) - assert(resource.getTimestamp() === 10) - assert(resource.getSize() === 20) - assert(resource.getType() === LocalResourceType.ARCHIVE) - - val env = new HashMap[String, String]() - distMgr.setDistFilesEnv(env) - assert(env.get("SPARK_YARN_CACHE_FILES") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_TIME_STAMPS") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_FILE_SIZES") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_VISIBILITIES") === None) - - distMgr.setDistArchivesEnv(env) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_TIME_STAMPS") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_FILE_SIZES") === None) - assert(env.get("SPARK_YARN_CACHE_ARCHIVES_VISIBILITIES") === None) - } - - test("test addResource archive") { - val distMgr = new MockClientDistributedCacheManager() - val fs = mock[FileSystem] - val conf = new Configuration() - val destPath = new Path("file:///foo.invalid.com:8080/tmp/testing") - val localResources = HashMap[String, LocalResource]() - val statCache: Map[URI, FileStatus] = HashMap[URI, FileStatus]() - val realFileStatus = new FileStatus(20, false, 1, 1024, 10, 30, null, "testOwner", - null, new Path("/tmp/testing")) - when(fs.getFileStatus(destPath)).thenReturn(realFileStatus) - - distMgr.addResource(fs, conf, destPath, localResources, LocalResourceType.ARCHIVE, "link", - statCache, false) - val resource = localResources("link") - assert(resource.getVisibility() === LocalResourceVisibility.PRIVATE) - assert(ConverterUtils.getPathFromYarnURL(resource.getResource()) === destPath) - assert(resource.getTimestamp() === 10) - assert(resource.getSize() === 20) - assert(resource.getType() === LocalResourceType.ARCHIVE) - - val env = new HashMap[String, String]() - - distMgr.setDistArchivesEnv(env) - assert(env("SPARK_YARN_CACHE_ARCHIVES") === "file:/foo.invalid.com:8080/tmp/testing#link") - assert(env("SPARK_YARN_CACHE_ARCHIVES_TIME_STAMPS") === "10") - assert(env("SPARK_YARN_CACHE_ARCHIVES_FILE_SIZES") === "20") - assert(env("SPARK_YARN_CACHE_ARCHIVES_VISIBILITIES") === LocalResourceVisibility.PRIVATE.name()) - - distMgr.setDistFilesEnv(env) - assert(env.get("SPARK_YARN_CACHE_FILES") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_TIME_STAMPS") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_FILE_SIZES") === None) - assert(env.get("SPARK_YARN_CACHE_FILES_VISIBILITIES") === None) - } - - -} diff --git a/yarn/stable/pom.xml b/yarn/stable/pom.xml new file mode 100644 index 0000000000..62fe3e2742 --- /dev/null +++ b/yarn/stable/pom.xml @@ -0,0 +1,32 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + ~ Licensed to the Apache Software Foundation (ASF) under one or more + ~ contributor license agreements. See the NOTICE file distributed with + ~ this work for additional information regarding copyright ownership. + ~ The ASF licenses this file to You under the Apache License, Version 2.0 + ~ (the "License"); you may not use this file except in compliance with + ~ the License. You may obtain a copy of the License at + ~ + ~ http://www.apache.org/licenses/LICENSE-2.0 + ~ + ~ Unless required by applicable law or agreed to in writing, software + ~ distributed under the License is distributed on an "AS IS" BASIS, + ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + ~ See the License for the specific language governing permissions and + ~ limitations under the License. + --> +<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>org.apache.spark</groupId> + <artifactId>yarn-parent_2.10</artifactId> + <version>0.9.0-incubating-SNAPSHOT</version> + <relativePath>../pom.xml</relativePath> + </parent> + + <groupId>org.apache.spark</groupId> + <artifactId>spark-yarn_2.10</artifactId> + <packaging>jar</packaging> + <name>Spark Project YARN Stable API</name> + +</project> diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index 91e35e2d34..69ae14ce83 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -38,15 +38,18 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{ConverterUtils, Records} -import org.apache.spark.{SparkContext, Logging} +import org.apache.spark.{SparkConf, SparkContext, Logging} import org.apache.spark.util.Utils -class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) extends Logging { +class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration, + sparkConf: SparkConf) extends Logging { - def this(args: ApplicationMasterArguments) = this(args, new Configuration()) + def this(args: ApplicationMasterArguments, sparkConf: SparkConf) = + this(args, new Configuration(), sparkConf) + + def this(args: ApplicationMasterArguments) = this(args, new SparkConf()) - private var rpc: YarnRPC = YarnRPC.create(conf) private val yarnConf: YarnConfiguration = new YarnConfiguration(conf) private var appAttemptId: ApplicationAttemptId = _ private var userThread: Thread = _ @@ -61,13 +64,17 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e private var amClient: AMRMClient[ContainerRequest] = _ // Default to numWorkers * 2, with minimum of 3 - private val maxNumWorkerFailures = conf.getOrElse("spark.yarn.max.worker.failures", - math.max(args.numWorkers * 2, 3).toString()).toInt + private val maxNumWorkerFailures = sparkConf.getInt("spark.yarn.max.worker.failures", + math.max(args.numWorkers * 2, 3)) def run() { // Setup the directories so things go to YARN approved directories rather // than user specified and /tmp. - conf.set("spark.local.dir", getLocalDirs()) + System.setProperty("spark.local.dir", getLocalDirs()) + + // set the web ui port to be ephemeral for yarn so we don't conflict with + // other spark processes running on the same box + System.setProperty("spark.ui.port", "0") // Use priority 30 as it's higher then HDFS. It's same priority as MapReduce is using. ShutdownHookManager.get().addShutdownHook(new AppMasterShutdownHook(this), 30) @@ -89,8 +96,6 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // This a bit hacky, but we need to wait until the spark.driver.port property has // been set by the Thread executing the user class. - waitForSparkMaster() - waitForSparkContextInitialized() // Do this after Spark master is up and SparkContext is created so that we can register UI Url. @@ -112,7 +117,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // LOCAL_DIRS => 2.X, YARN_LOCAL_DIRS => 0.23.X val localDirs = Option(System.getenv("YARN_LOCAL_DIRS")) .getOrElse(Option(System.getenv("LOCAL_DIRS")) - .getOrElse("")) + .getOrElse("")) if (localDirs.isEmpty()) { throw new Exception("Yarn Local dirs can't be empty") @@ -134,35 +139,11 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e amClient.registerApplicationMaster(Utils.localHostName(), 0, uiAddress) } - private def waitForSparkMaster() { - logInfo("Waiting for Spark driver to be reachable.") - var driverUp = false - var tries = 0 - val numTries = conf.getOrElse("spark.yarn.applicationMaster.waitTries", "10").toInt - while (!driverUp && tries < numTries) { - val driverHost = conf.get("spark.driver.host") - val driverPort = conf.get("spark.driver.port") - try { - val socket = new Socket(driverHost, driverPort.toInt) - socket.close() - logInfo("Driver now available: %s:%s".format(driverHost, driverPort)) - driverUp = true - } catch { - case e: Exception => { - logWarning("Failed to connect to driver at %s:%s, retrying ...". - format(driverHost, driverPort)) - Thread.sleep(100) - tries = tries + 1 - } - } - } - } - - private def startUserClass(): Thread = { + private def startUserClass(): Thread = { logInfo("Starting the user JAR in a separate Thread") val mainMethod = Class.forName( args.userClass, - false /* initialize */, + false /* initialize */ , Thread.currentThread.getContextClassLoader).getMethod("main", classOf[Array[String]]) val t = new Thread { override def run() { @@ -199,7 +180,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e ApplicationMaster.sparkContextRef.synchronized { var numTries = 0 val waitTime = 10000L - val maxNumTries = conf.getOrElse("spark.yarn.ApplicationMaster.waitTries", "10").toInt + val maxNumTries = sparkConf.getInt("spark.yarn.applicationMaster.waitTries", 10) while (ApplicationMaster.sparkContextRef.get() == null && numTries < maxNumTries) { logInfo("Waiting for Spark context initialization ... " + numTries) numTries = numTries + 1 @@ -215,7 +196,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e amClient, appAttemptId, args, - sparkContext.preferredNodeLocationData) + sparkContext.preferredNodeLocationData, + sparkContext.getConf) } else { logWarning("Unable to retrieve SparkContext inspite of waiting for %d, maxNumTries = %d". format(numTries * waitTime, maxNumTries)) @@ -223,7 +205,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e yarnConf, amClient, appAttemptId, - args) + args, + sparkContext.getConf) } } } finally { @@ -265,7 +248,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e // we want to be reasonably responsive without causing too many requests to RM. val schedulerInterval = - conf.getOrElse("spark.yarn.scheduler.heartbeat.interval-ms", "5000").toLong + sparkConf.getLong("spark.yarn.scheduler.heartbeat.interval-ms", 5000) + // must be <= timeoutInterval / 2. val interval = math.min(timeoutInterval / 2, schedulerInterval) @@ -275,7 +259,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e } private def launchReporterThread(_sleepTime: Long): Thread = { - val sleepTime = if (_sleepTime <= 0 ) 0 else _sleepTime + val sleepTime = if (_sleepTime <= 0) 0 else _sleepTime val t = new Thread { override def run() { @@ -334,7 +318,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e logInfo("finishApplicationMaster with " + status) // Set tracking URL to empty since we don't have a history server. - amClient.unregisterApplicationMaster(status, "" /* appMessage */, "" /* appTrackingUrl */) + amClient.unregisterApplicationMaster(status, "" /* appMessage */ , "" /* appTrackingUrl */) } /** @@ -343,7 +327,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e private def cleanupStagingDir() { var stagingDirPath: Path = null try { - val preserveFiles = conf.getOrElse("spark.yarn.preserve.staging.files", "false").toBoolean + val preserveFiles = sparkConf.get("spark.yarn.preserve.staging.files", "false").toBoolean if (!preserveFiles) { stagingDirPath = new Path(System.getenv("SPARK_YARN_STAGING_DIR")) if (stagingDirPath == null) { @@ -369,6 +353,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration) e if (appMaster.isLastAMRetry) appMaster.cleanupStagingDir() } } + } object ApplicationMaster { @@ -419,6 +404,7 @@ object ApplicationMaster { // This is not only logs, but also ensures that log system is initialized for this instance // when we are actually 'run'-ing. logInfo("Adding shutdown hook for context " + sc) + override def run() { logInfo("Invoking sc stop from shutdown hook") sc.stop() @@ -427,7 +413,7 @@ object ApplicationMaster { master.finishApplicationMaster(FinalApplicationStatus.SUCCEEDED) } } - } ) + }) } // Wait for initialization to complete and atleast 'some' nodes can get allocated. diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/Client.scala index 1bba6a5ae4..be323d7783 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -40,7 +40,7 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{Apps, Records} -import org.apache.spark.Logging +import org.apache.spark.{Logging, SparkConf} import org.apache.spark.util.Utils import org.apache.spark.deploy.SparkHadoopUtil @@ -50,7 +50,13 @@ import org.apache.spark.deploy.SparkHadoopUtil * Client submits an application to the global ResourceManager to launch Spark's ApplicationMaster, * which will launch a Spark master process and negotiate resources throughout its duration. */ -class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl with Logging { +class Client(args: ClientArguments, conf: Configuration, sparkConf: SparkConf) + extends YarnClientImpl with Logging { + + def this(args: ClientArguments, sparkConf: SparkConf) = + this(args, new Configuration(), sparkConf) + + def this(args: ClientArguments) = this(args, new SparkConf()) var rpc: YarnRPC = YarnRPC.create(conf) val yarnConf: YarnConfiguration = new YarnConfiguration(conf) @@ -63,8 +69,6 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl // App files are world-wide readable and owner writable -> rw-r--r-- val APP_FILE_PERMISSION: FsPermission = FsPermission.createImmutable(0644: Short) - def this(args: ClientArguments) = this(new Configuration(), args) - def runApp(): ApplicationId = { validateArgs() // Initialize and start the client service. @@ -118,7 +122,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl (System.getenv("SPARK_JAR") == null) -> "Error: You must set SPARK_JAR environment variable!", (args.userJar == null) -> "Error: You must specify a user jar!", (args.userClass == null) -> "Error: You must specify a user class!", - (args.numWorkers <= 0) -> "Error: You must specify atleast 1 worker!", + (args.numWorkers <= 0) -> "Error: You must specify at least 1 worker!", (args.amMemory <= YarnAllocationHandler.MEMORY_OVERHEAD) -> ("Error: AM memory size must be" + "greater than: " + YarnAllocationHandler.MEMORY_OVERHEAD), (args.workerMemory <= YarnAllocationHandler.MEMORY_OVERHEAD) -> ("Error: Worker memory size" + @@ -141,7 +145,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl clusterMetrics.getNumNodeManagers) val queueInfo: QueueInfo = super.getQueueInfo(args.amQueue) - logInfo("""Queue info ... queueName: %s, queueCurrentCapacity: %s, queueMaxCapacity: %s, + logInfo( """Queue info ... queueName: %s, queueCurrentCapacity: %s, queueMaxCapacity: %s, queueApplicationCount = %s, queueChildQueueCount = %s""".format( queueInfo.getQueueName, queueInfo.getCurrentCapacity, @@ -244,7 +248,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl } } val dst = new Path(fs.getHomeDirectory(), appStagingDir) - val replication = conf.getOrElse("spark.yarn.submit.file.replication", "3").toShort + val replication = sparkConf.getInt("spark.yarn.submit.file.replication", 3).toShort if (UserGroupInformation.isSecurityEnabled()) { val dstFs = dst.getFileSystem(conf) @@ -324,7 +328,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl val env = new HashMap[String, String]() - Client.populateClasspath(yarnConf, log4jConfLocalRes != null, env) + Client.populateClasspath(yarnConf, sparkConf, log4jConfLocalRes != null, env) env("SPARK_YARN_MODE") = "true" env("SPARK_YARN_STAGING_DIR") = stagingDir @@ -345,7 +349,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl val prefix = " --args " val args = clientArgs.userArgs val retval = new StringBuilder() - for (arg <- args){ + for (arg <- args) { retval.append(prefix).append(" '").append(arg).append("' ") } retval.toString @@ -437,7 +441,7 @@ class Client(conf: Configuration, args: ClientArguments) extends YarnClientImpl } def monitorApplication(appId: ApplicationId): Boolean = { - val interval = new SparkConf().getOrElse("spark.yarn.report.interval", "1000").toLong + val interval = sparkConf.getLong("spark.yarn.report.interval", 1000) while (true) { Thread.sleep(interval) @@ -480,10 +484,10 @@ object Client { // Note: anything env variable with SPARK_ prefix gets propagated to all (remote) processes - // see Client#setupLaunchEnv(). System.setProperty("SPARK_YARN_MODE", "true") + val sparkConf = new SparkConf() + val args = new ClientArguments(argStrings, sparkConf) - val args = new ClientArguments(argStrings) - - (new Client(args)).run() + new Client(args, sparkConf).run() } // Based on code from org.apache.hadoop.mapreduce.v2.util.MRApps @@ -493,7 +497,7 @@ object Client { } } - def populateClasspath(conf: Configuration, addLog4j: Boolean, env: HashMap[String, String]) { + def populateClasspath(conf: Configuration, sparkConf: SparkConf, addLog4j: Boolean, env: HashMap[String, String]) { Apps.addToEnvironment(env, Environment.CLASSPATH.name, Environment.PWD.$()) // If log4j present, ensure ours overrides all others if (addLog4j) { @@ -501,7 +505,7 @@ object Client { Path.SEPARATOR + LOG4J_PROP) } // Normally the users app.jar is last in case conflicts with spark jars - val userClasspathFirst = conf.getOrElse("spark.yarn.user.classpath.first", "false") + val userClasspathFirst = sparkConf.get("spark.yarn.user.classpath.first", "false") .toBoolean if (userClasspathFirst) { Apps.addToEnvironment(env, Environment.CLASSPATH.name, Environment.PWD.$() + diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala index f7d73f0d83..49248a8516 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/WorkerLauncher.scala @@ -28,16 +28,20 @@ import org.apache.hadoop.yarn.util.{ConverterUtils, Records} import akka.actor._ import akka.remote._ import akka.actor.Terminated -import org.apache.spark.{SparkContext, Logging} +import org.apache.spark.{SparkConf, SparkContext, Logging} import org.apache.spark.util.{Utils, AkkaUtils} import org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend import org.apache.spark.scheduler.SplitInfo import org.apache.hadoop.yarn.client.api.AMRMClient import org.apache.hadoop.yarn.client.api.AMRMClient.ContainerRequest -class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) extends Logging { +class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration, sparkConf: SparkConf) + extends Logging { - def this(args: ApplicationMasterArguments) = this(args, new Configuration()) + def this(args: ApplicationMasterArguments, sparkConf: SparkConf) = + this(args, new Configuration(), sparkConf) + + def this(args: ApplicationMasterArguments) = this(args, new SparkConf()) private var appAttemptId: ApplicationAttemptId = _ private var reporterThread: Thread = _ @@ -48,23 +52,26 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte private var amClient: AMRMClient[ContainerRequest] = _ - val actorSystem : ActorSystem = AkkaUtils.createActorSystem("sparkYarnAM", Utils.localHostName, 0)._1 + val actorSystem: ActorSystem = AkkaUtils.createActorSystem("sparkYarnAM", Utils.localHostName, 0, + conf = sparkConf)._1 var actor: ActorRef = _ // This actor just working as a monitor to watch on Driver Actor. class MonitorActor(driverUrl: String) extends Actor { - var driver: ActorSelection = null + var driver: ActorSelection = _ override def preStart() { logInfo("Listen to driver: " + driverUrl) driver = context.actorSelection(driverUrl) + // Send a hello message thus the connection is actually established, thus we can monitor Lifecycle Events. + driver ! "Hello" context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent]) } override def receive = { case x: DisassociatedEvent => - logInfo("Driver terminated or disconnected! Shutting down.") + logInfo(s"Driver terminated or disconnected! Shutting down. $x") driverClosed = true } } @@ -90,7 +97,7 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte // must be <= timeoutInterval/ 2. // On other hand, also ensure that we are reasonably responsive without causing too many requests to RM. // so atleast 1 minute or timeoutInterval / 10 - whichever is higher. - val interval = math.min(timeoutInterval / 2, math.max(timeoutInterval/ 10, 60000L)) + val interval = math.min(timeoutInterval / 2, math.max(timeoutInterval / 10, 60000L)) reporterThread = launchReporterThread(interval) // Wait for the reporter thread to Finish. @@ -136,8 +143,8 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte Thread.sleep(100) } } - conf.set("spark.driver.host", driverHost) - conf.set("spark.driver.port", driverPort.toString) + sparkConf.set("spark.driver.host", driverHost) + sparkConf.set("spark.driver.port", driverPort.toString) val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format( driverHost, driverPort.toString, CoarseGrainedSchedulerBackend.ACTOR_NAME) @@ -157,7 +164,8 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte amClient, appAttemptId, args, - preferredNodeLocationData) + preferredNodeLocationData, + sparkConf) logInfo("Allocating " + args.numWorkers + " workers.") // Wait until all containers have finished @@ -165,7 +173,7 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte // TODO: Handle container failure yarnAllocator.addResourceRequests(args.numWorkers) - while(yarnAllocator.getNumWorkersRunning < args.numWorkers) { + while (yarnAllocator.getNumWorkersRunning < args.numWorkers) { yarnAllocator.allocateResources() Thread.sleep(100) } @@ -176,7 +184,7 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte // TODO: We might want to extend this to allocate more containers in case they die ! private def launchReporterThread(_sleepTime: Long): Thread = { - val sleepTime = if (_sleepTime <= 0 ) 0 else _sleepTime + val sleepTime = if (_sleepTime <= 0) 0 else _sleepTime val t = new Thread { override def run() { @@ -208,7 +216,7 @@ class WorkerLauncher(args: ApplicationMasterArguments, conf: Configuration) exte def finishApplicationMaster(status: FinalApplicationStatus) { logInfo("finish ApplicationMaster with " + status) - amClient.unregisterApplicationMaster(status, "" /* appMessage */, "" /* appTrackingUrl */) + amClient.unregisterApplicationMaster(status, "" /* appMessage */ , "" /* appTrackingUrl */) } } diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala index 9f5523c4b9..b7699050bb 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/WorkerRunnable.scala @@ -39,12 +39,13 @@ import org.apache.hadoop.yarn.conf.YarnConfiguration import org.apache.hadoop.yarn.ipc.YarnRPC import org.apache.hadoop.yarn.util.{Apps, ConverterUtils, Records} -import org.apache.spark.Logging +import org.apache.spark.{SparkConf, Logging} class WorkerRunnable( container: Container, conf: Configuration, + sparkConf: SparkConf, masterAddress: String, slaveId: String, hostname: String, @@ -197,7 +198,7 @@ class WorkerRunnable( def prepareEnvironment: HashMap[String, String] = { val env = new HashMap[String, String]() - Client.populateClasspath(yarnConf, System.getenv("SPARK_YARN_LOG4J_PATH") != null, env) + Client.populateClasspath(yarnConf, sparkConf, System.getenv("SPARK_YARN_LOG4J_PATH") != null, env) // Allow users to specify some environment variables Apps.setEnvFromInputString(env, System.getenv("SPARK_YARN_USER_ENV")) diff --git a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala index abc3447746..738ff986d8 100644 --- a/new-yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala @@ -26,7 +26,7 @@ import scala.collection import scala.collection.JavaConversions._ import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet} -import org.apache.spark.Logging +import org.apache.spark.{Logging, SparkConf} import org.apache.spark.scheduler.{SplitInfo,TaskSchedulerImpl} import org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend import org.apache.spark.util.Utils @@ -42,7 +42,7 @@ import org.apache.hadoop.yarn.client.api.AMRMClient.ContainerRequest import org.apache.hadoop.yarn.util.{RackResolver, Records} -object AllocationType extends Enumeration ("HOST", "RACK", "ANY") { +object AllocationType extends Enumeration { type AllocationType = Value val HOST, RACK, ANY = Value } @@ -64,7 +64,8 @@ private[yarn] class YarnAllocationHandler( val workerMemory: Int, val workerCores: Int, val preferredHostToCount: Map[String, Int], - val preferredRackToCount: Map[String, Int]) + val preferredRackToCount: Map[String, Int], + val sparkConf: SparkConf) extends Logging { // These three are locked on allocatedHostToContainersMap. Complementary data structures // allocatedHostToContainersMap : containers which are running : host, Set<containerid> @@ -254,8 +255,8 @@ private[yarn] class YarnAllocationHandler( } else { val workerId = workerIdCounter.incrementAndGet().toString val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format( - conf.get("spark.driver.host"), - conf.get("spark.driver.port"), + sparkConf.get("spark.driver.host"), + sparkConf.get("spark.driver.port"), CoarseGrainedSchedulerBackend.ACTOR_NAME) logInfo("Launching container %s for on host %s".format(containerId, workerHostname)) @@ -279,6 +280,7 @@ private[yarn] class YarnAllocationHandler( val workerRunnable = new WorkerRunnable( container, conf, + sparkConf, driverUrl, workerId, workerHostname, @@ -565,7 +567,8 @@ object YarnAllocationHandler { conf: Configuration, amClient: AMRMClient[ContainerRequest], appAttemptId: ApplicationAttemptId, - args: ApplicationMasterArguments + args: ApplicationMasterArguments, + sparkConf: SparkConf ): YarnAllocationHandler = { new YarnAllocationHandler( conf, @@ -575,7 +578,8 @@ object YarnAllocationHandler { args.workerMemory, args.workerCores, Map[String, Int](), - Map[String, Int]()) + Map[String, Int](), + sparkConf) } def newAllocator( @@ -584,7 +588,8 @@ object YarnAllocationHandler { appAttemptId: ApplicationAttemptId, args: ApplicationMasterArguments, map: collection.Map[String, - collection.Set[SplitInfo]] + collection.Set[SplitInfo]], + sparkConf: SparkConf ): YarnAllocationHandler = { val (hostToSplitCount, rackToSplitCount) = generateNodeToWeight(conf, map) new YarnAllocationHandler( @@ -595,7 +600,8 @@ object YarnAllocationHandler { args.workerMemory, args.workerCores, hostToSplitCount, - rackToSplitCount) + rackToSplitCount, + sparkConf) } def newAllocator( @@ -605,7 +611,8 @@ object YarnAllocationHandler { maxWorkers: Int, workerMemory: Int, workerCores: Int, - map: collection.Map[String, collection.Set[SplitInfo]] + map: collection.Map[String, collection.Set[SplitInfo]], + sparkConf: SparkConf ): YarnAllocationHandler = { val (hostToCount, rackToCount) = generateNodeToWeight(conf, map) new YarnAllocationHandler( @@ -616,7 +623,8 @@ object YarnAllocationHandler { workerMemory, workerCores, hostToCount, - rackToCount) + rackToCount, + sparkConf) } // A simple method to copy the split info map. |