Merging latest changes from spark main branch

10 files changed, 59 insertions, 106 deletions

diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd
index eb836b0ffd..cf38188c4b 100644
--- a/bin/compute-classpath.cmd
+++ b/bin/compute-classpath.cmd
@@ -28,28 +28,27 @@ set FWDIR=%~dp0..\
 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"
 
-set CORE_DIR=%FWDIR%core
-set REPL_DIR=%FWDIR%repl
-set EXAMPLES_DIR=%FWDIR%examples
-set BAGEL_DIR=%FWDIR%bagel
-set MLLIB_DIR=%FWDIR%mllib
-set TOOLS_DIR=%FWDIR%tools
-set STREAMING_DIR=%FWDIR%streaming
-set PYSPARK_DIR=%FWDIR%python
-
 rem Build up classpath
-set CLASSPATH=%SPARK_CLASSPATH%;%MESOS_CLASSPATH%;%FWDIR%conf;%CORE_DIR%\target\scala-%SCALA_VERSION%\classes
-set CLASSPATH=%CLASSPATH%;%CORE_DIR%\target\scala-%SCALA_VERSION%\test-classes;%CORE_DIR%\src\main\resources
-set CLASSPATH=%CLASSPATH%;%STREAMING_DIR%\target\scala-%SCALA_VERSION%\classes;%STREAMING_DIR%\target\scala-%SCALA_VERSION%\test-classes
-set CLASSPATH=%CLASSPATH%;%STREAMING_DIR%\lib\org\apache\kafka\kafka\0.7.2-spark\*
-set CLASSPATH=%CLASSPATH%;%REPL_DIR%\target\scala-%SCALA_VERSION%\classes;%EXAMPLES_DIR%\target\scala-%SCALA_VERSION%\classes
-set CLASSPATH=%CLASSPATH%;%FWDIR%lib_managed\jars\*
-set CLASSPATH=%CLASSPATH%;%FWDIR%lib_managed\bundles\*
-set CLASSPATH=%CLASSPATH%;%FWDIR%repl\lib\*
-set CLASSPATH=%CLASSPATH%;%FWDIR%python\lib\*
-set CLASSPATH=%CLASSPATH%;%BAGEL_DIR%\target\scala-%SCALA_VERSION%\classes
-set CLASSPATH=%CLASSPATH%;%MLLIB_DIR%\target\scala-%SCALA_VERSION%\classes
-set CLASSPATH=%CLASSPATH%;%TOOLS_DIR%\target\scala-%SCALA_VERSION%\classes
+set CLASSPATH=%SPARK_CLASSPATH%;%FWDIR%conf
+if exist "%FWDIR%RELEASE" (
+  for %%d in ("%FWDIR%jars\spark-assembly*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+) else (
+  for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do (
+    set ASSEMBLY_JAR=%%d
+  )
+)
+set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR%
+
+if "x%SPARK_TESTING%"=="x1" (
+  rem Add test clases to path
+  set CLASSPATH=%CLASSPATH%;%FWDIR%core\target\scala-%SCALA_VERSION%\test-classes
+  set CLASSPATH=%CLASSPATH%;%FWDIR%repl\target\scala-%SCALA_VERSION%\test-classes
+  set CLASSPATH=%CLASSPATH%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\test-classes
+  set CLASSPATH=%CLASSPATH%;%FWDIR%bagel\target\scala-%SCALA_VERSION%\test-classes
+  set CLASSPATH=%CLASSPATH%;%FWDIR%streaming\target\scala-%SCALA_VERSION%\test-classes
+)
 
 rem Add hadoop conf dir - else FileSystem.*, etc fail
 rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
@@ -62,9 +61,6 @@ if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
   set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
 :no_yarn_conf_dir
 
-rem Add Scala standard library
-set CLASSPATH=%CLASSPATH%;%SCALA_HOME%\lib\scala-library.jar;%SCALA_HOME%\lib\scala-compiler.jar;%SCALA_HOME%\lib\jline.jar
-
 rem A bit of a hack to allow calling this script within run2.cmd without seeing output
 if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
 
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
index 36d0abbd03..6ad1ca6ef8 100755
--- a/bin/compute-classpath.sh
+++ b/bin/compute-classpath.sh
@@ -30,77 +30,27 @@ if [ -e $FWDIR/conf/spark-env.sh ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 
-CORE_DIR="$FWDIR/core"
-REPL_DIR="$FWDIR/repl"
-REPL_BIN_DIR="$FWDIR/repl-bin"
-EXAMPLES_DIR="$FWDIR/examples"
-BAGEL_DIR="$FWDIR/bagel"
-MLLIB_DIR="$FWDIR/mllib"
-TOOLS_DIR="$FWDIR/tools"
-GRAPH_DIR="$FWDIR/graph"
-STREAMING_DIR="$FWDIR/streaming"
-PYSPARK_DIR="$FWDIR/python"
 
 # Build up classpath
-CLASSPATH="$SPARK_CLASSPATH"
-
-function dev_classpath {
-  CLASSPATH="$CLASSPATH:$FWDIR/conf"
-  CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes"
-  if [ -n "$SPARK_TESTING" ] ; then
-    CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes"
-    CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes"
-  fi
-  CLASSPATH="$CLASSPATH:$CORE_DIR/src/main/resources"
-  CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar
-  if [ -e "$FWDIR/lib_managed" ]; then
-    CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*"
-    CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*"
-  fi
-  CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*"
-  # Add the shaded JAR for Maven builds
-  if [ -e $REPL_BIN_DIR/target ]; then
-    for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do
-      CLASSPATH="$CLASSPATH:$jar"
-    done
-    # The shaded JAR doesn't contain examples, so include those separately
-    EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
-    CLASSPATH+=":$EXAMPLES_JAR"
-  fi
-  CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$GRAPH_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$TOOLS_DIR/target/scala-$SCALA_VERSION/classes"
-  for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
-    CLASSPATH="$CLASSPATH:$jar"
-  done
-  # Add Scala standard library
-  if [ -z "$SCALA_LIBRARY_PATH" ]; then
-    if [ -z "$SCALA_HOME" ]; then
-      echo "SCALA_HOME is not set" >&2
-      exit 1
-    fi
-    SCALA_LIBRARY_PATH="$SCALA_HOME/lib"
-  fi
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-library.jar"
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-compiler.jar"
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/jline.jar"
-}
-
-function release_classpath {
-  CLASSPATH="$CLASSPATH:$FWDIR/jars/*"
-}
-
+CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
 if [ -f "$FWDIR/RELEASE" ]; then
-  release_classpath
+  ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark-assembly*.jar`
 else
-  dev_classpath
+  ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar`
+fi
+CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
+
+# Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1
+if [[ $SPARK_TESTING == 1 ]]; then
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/graph/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/test-classes"
 fi
 
-# Add hadoop conf dir - else FileSystem.*, etc fail !
+# Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !
 # Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
 # the configurtion files.
 if [ "x" != "x$HADOOP_CONF_DIR" ]; then
diff --git a/bin/slaves.sh b/bin/slaves.sh
index c8fb5ca473..752565b759 100755
--- a/bin/slaves.sh
+++ b/bin/slaves.sh
@@ -42,7 +42,7 @@ bin=`cd "$bin"; pwd`
 . "$bin/spark-config.sh"
 
 # If the slaves file is specified in the command line,
-# then it takes precedence over the definition in 
+# then it takes precedence over the definition in
 # spark-env.sh. Save it here.
 HOSTLIST=$SPARK_SLAVES
 
@@ -58,8 +58,6 @@ if [ "$HOSTLIST" = "" ]; then
   fi
 fi
 
-echo $"${@// /\\ }"
-
 # By default disable strict host key checking
 if [ "$SPARK_SSH_OPTS" = "" ]; then
   SPARK_SSH_OPTS="-o StrictHostKeyChecking=no"
diff --git a/bin/spark-daemon.sh b/bin/spark-daemon.sh
index a5b88ca785..5bfe967fbf 100755
--- a/bin/spark-daemon.sh
+++ b/bin/spark-daemon.sh
@@ -75,6 +75,9 @@ if [ "$SPARK_IDENT_STRING" = "" ]; then
   export SPARK_IDENT_STRING="$USER"
 fi
 
+
+export SPARK_PRINT_LAUNCH_COMMAND="1"
+
 # get log directory
 if [ "$SPARK_LOG_DIR" = "" ]; then
   export SPARK_LOG_DIR="$SPARK_HOME/logs"
@@ -85,7 +88,7 @@ TEST_LOG_DIR=$?
 if [ "${TEST_LOG_DIR}" = "0" ]; then
   rm -f $SPARK_LOG_DIR/.spark_test
 else
-  chown $SPARK_IDENT_STRING $SPARK_LOG_DIR 
+  chown $SPARK_IDENT_STRING $SPARK_LOG_DIR
 fi
 
 if [ "$SPARK_PID_DIR" = "" ]; then
@@ -107,7 +110,7 @@ fi
 case $startStop in
 
   (start)
-    
+
     mkdir -p "$SPARK_PID_DIR"
 
     if [ -f $pid ]; then
@@ -122,14 +125,21 @@ case $startStop in
       rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $SPARK_MASTER/ "$SPARK_HOME"
     fi
 
-    spark_rotate_log $log
+    spark_rotate_log "$log"
     echo starting $command, logging to $log
     cd "$SPARK_PREFIX"
-    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/run $command "$@" > "$log" 2>&1 < /dev/null &
-    echo $! > $pid
-    sleep 1; head "$log"
+    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
+    newpid=$!
+    echo $newpid > $pid
+    sleep 2
+    # Check if the process has died; in that case we'll tail the log so the user can see
+    if ! kill -0 $newpid >/dev/null 2>&1; then
+      echo "failed to launch $command:"
+      tail -2 "$log" | sed 's/^/  /'
+      echo "full log in $log"
+    fi
     ;;
-          
+
   (stop)
 
     if [ -f $pid ]; then
diff --git a/bin/start-master.sh b/bin/start-master.sh
index 2288fb19d7..648c7ae75f 100755
--- a/bin/start-master.sh
+++ b/bin/start-master.sh
@@ -49,4 +49,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
     fi
 fi
 
-"$bin"/spark-daemon.sh start spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
+"$bin"/spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
diff --git a/bin/start-slave.sh b/bin/start-slave.sh
index d6db16882d..4eefa20944 100755
--- a/bin/start-slave.sh
+++ b/bin/start-slave.sh
@@ -32,4 +32,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
     fi
 fi
 
-"$bin"/spark-daemon.sh start spark.deploy.worker.Worker "$@"
+"$bin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker "$@"
diff --git a/bin/start-slaves.sh b/bin/start-slaves.sh
index dad7c3df76..00dc4888b2 100755
--- a/bin/start-slaves.sh
+++ b/bin/start-slaves.sh
@@ -35,8 +35,6 @@ if [ "$SPARK_MASTER_IP" = "" ]; then
   SPARK_MASTER_IP=`hostname`
 fi
 
-echo "Master IP: $SPARK_MASTER_IP"
-
 # Launch the slaves
 if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
   exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT
diff --git a/bin/stop-all.sh b/bin/stop-all.sh
index a043ac0095..b6c83a7ba4 100755
--- a/bin/stop-all.sh
+++ b/bin/stop-all.sh
@@ -20,6 +20,7 @@
 # Start all spark daemons.
 # Run this on the master nde
 
+
 bin=`dirname "$0"`
 bin=`cd "$bin"; pwd`
 
diff --git a/bin/stop-master.sh b/bin/stop-master.sh
index 31a610bf9d..310e33bedc 100755
--- a/bin/stop-master.sh
+++ b/bin/stop-master.sh
@@ -24,4 +24,4 @@ bin=`cd "$bin"; pwd`
 
 . "$bin/spark-config.sh"
 
-"$bin"/spark-daemon.sh stop spark.deploy.master.Master 1
+"$bin"/spark-daemon.sh stop org.apache.spark.deploy.master.Master 1
diff --git a/bin/stop-slaves.sh b/bin/stop-slaves.sh
index 8e056f23d4..03e416a132 100755
--- a/bin/stop-slaves.sh
+++ b/bin/stop-slaves.sh
@@ -29,9 +29,9 @@ if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
 fi
 
 if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
-  "$bin"/spark-daemons.sh stop spark.deploy.worker.Worker 1
+  "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker 1
 else
   for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
-    "$bin"/spark-daemons.sh stop spark.deploy.worker.Worker $(( $i + 1 ))
+    "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker $(( $i + 1 ))
   done
 fi