Merge remote-tracking branch 'spark-upstream/master' into HEAD

Conflicts:
	README.md
	core/src/main/scala/org/apache/spark/util/collection/OpenHashMap.scala
	core/src/main/scala/org/apache/spark/util/collection/OpenHashSet.scala
	core/src/main/scala/org/apache/spark/util/collection/PrimitiveKeyOpenHashMap.scala
	pom.xml
	project/SparkBuild.scala
	repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala

1 files changed, 76 insertions, 109 deletions

diff --git a/pom.xml b/pom.xml
index a9eccd69cc..ba19c51391 100644
--- a/pom.xml
+++ b/pom.xml
@@ -88,25 +88,34 @@
     <module>core</module>
     <module>bagel</module>
     <module>graph</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>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
 
-    <java.version>1.5</java.version>
-    <scala.version>2.9.3</scala.version>
+    <java.version>1.6</java.version>
+
+    <scala.version>2.10.3</scala.version>
+    <scala.binary.version>2.10</scala.binary.version>
     <mesos.version>0.13.0</mesos.version>
-    <akka.version>2.0.5</akka.version>
+    <akka.group>org.spark-project.akka</akka.group>
+    <akka.version>2.2.3-shaded-protobuf</akka.version>
     <slf4j.version>1.7.2</slf4j.version>
     <log4j.version>1.2.17</log4j.version>
     <hadoop.version>1.0.4</hadoop.version>
+    <protobuf.version>2.4.1</protobuf.version>
     <yarn.version>0.23.7</yarn.version>
     <hbase.version>0.94.6</hbase.version>
 
@@ -116,9 +125,9 @@
 
   <repositories>
     <repository>
-      <id>jboss-repo</id>
-      <name>JBoss Repository</name>
-      <url>http://repository.jboss.org/nexus/content/repositories/releases/</url>
+      <id>maven-repo</id> <!-- This should be at top, it makes maven try the central repo first and then others and hence faster dep resolution -->
+      <name>Maven Repository</name>
+      <url>http://repo.maven.apache.org/maven2</url>
       <releases>
         <enabled>true</enabled>
       </releases>
@@ -127,20 +136,9 @@
       </snapshots>
     </repository>
     <repository>
-      <id>cloudera-repo</id>
-      <name>Cloudera Repository</name>
-      <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
-      <releases>
-        <enabled>true</enabled>
-      </releases>
-      <snapshots>
-        <enabled>false</enabled>
-      </snapshots>
-    </repository>
-    <repository>
-      <id>akka-repo</id>
-      <name>Akka Repository</name>
-      <url>http://repo.akka.io/releases/</url>
+      <id>jboss-repo</id>
+      <name>JBoss Repository</name>
+      <url>http://repository.jboss.org/nexus/content/repositories/releases</url>
       <releases>
         <enabled>true</enabled>
       </releases>
@@ -149,52 +147,11 @@
       </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>
-  <pluginRepositories>
-    <pluginRepository>
-      <id>oss-sonatype-releases</id>
-      <name>OSS Sonatype</name>
-      <url>https://oss.sonatype.org/content/repositories/releases</url>
-      <releases>
-        <enabled>true</enabled>
-      </releases>
-      <snapshots>
-        <enabled>false</enabled>
-      </snapshots>
-    </pluginRepository>
-    <pluginRepository>
-      <id>oss-sonatype-snapshots</id>
-      <name>OSS Sonatype</name>
-      <url>https://oss.sonatype.org/content/repositories/snapshots</url>
-      <releases>
-        <enabled>false</enabled>
-      </releases>
-      <snapshots>
-        <enabled>true</enabled>
-      </snapshots>
-    </pluginRepository>
-    <pluginRepository>
-      <id>oss-sonatype</id>
-      <name>OSS Sonatype</name>
-      <url>https://oss.sonatype.org/content/groups/public</url>
-      <releases>
-        <enabled>true</enabled>
-      </releases>
-      <snapshots>
-        <enabled>true</enabled>
-      </snapshots>
-    </pluginRepository>
-  </pluginRepositories>
 
   <dependencyManagement>
     <dependencies>
@@ -231,7 +188,7 @@
       <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>
@@ -244,13 +201,23 @@
         <version>4.0</version>
       </dependency>
       <dependency>
+        <groupId>com.clearspring.analytics</groupId>
+        <artifactId>stream</artifactId>
+        <version>2.4.0</version>
+      </dependency>
+      <!-- In theory we need not directly depend on protobuf since Spark does not directly
+           use it. However, when building with Hadoop/YARN 2.2 Maven doesn't correctly bump
+           the protobuf version up from the one Mesos gives. For now we include this variable
+           to explicitly bump the version when building with YARN. It would be nice to figure
+           out why Maven can't resolve this correctly (like SBT does). -->
+      <dependency>
         <groupId>com.google.protobuf</groupId>
         <artifactId>protobuf-java</artifactId>
-        <version>2.4.1</version>
+        <version>${protobuf.version}</version>
       </dependency>
       <dependency>
         <groupId>com.twitter</groupId>
-        <artifactId>chill_2.9.3</artifactId>
+        <artifactId>chill_${scala.binary.version}</artifactId>
         <version>0.3.1</version>
       </dependency>
       <dependency>
@@ -259,8 +226,8 @@
         <version>0.3.1</version>
       </dependency>
       <dependency>
-        <groupId>com.typesafe.akka</groupId>
-        <artifactId>akka-actor</artifactId>
+        <groupId>${akka.group}</groupId>
+        <artifactId>akka-actor_${scala.binary.version}</artifactId>
         <version>${akka.version}</version>
         <exclusions>
           <exclusion>
@@ -270,8 +237,8 @@
         </exclusions>
       </dependency>
       <dependency>
-        <groupId>com.typesafe.akka</groupId>
-        <artifactId>akka-remote</artifactId>
+        <groupId>${akka.group}</groupId>
+        <artifactId>akka-remote_${scala.binary.version}</artifactId>
         <version>${akka.version}</version>
         <exclusions>
           <exclusion>
@@ -281,8 +248,8 @@
         </exclusions>
       </dependency>
       <dependency>
-        <groupId>com.typesafe.akka</groupId>
-        <artifactId>akka-slf4j</artifactId>
+        <groupId>${akka.group}</groupId>
+        <artifactId>akka-slf4j_${scala.binary.version}</artifactId>
         <version>${akka.version}</version>
         <exclusions>
           <exclusion>
@@ -302,11 +269,6 @@
         <version>1.2.0</version>
       </dependency>
       <dependency>
-        <groupId>com.github.scala-incubator.io</groupId>
-        <artifactId>scala-io-file_2.9.2</artifactId>
-        <version>0.4.1</version>
-      </dependency>
-      <dependency>
         <groupId>org.apache.mesos</groupId>
         <artifactId>mesos</artifactId>
         <version>${mesos.version}</version>
@@ -314,7 +276,7 @@
       <dependency>
         <groupId>io.netty</groupId>
         <artifactId>netty-all</artifactId>
-        <version>4.0.0.Beta2</version>
+        <version>4.0.13.Final</version>
       </dependency>
       <dependency>
         <groupId>org.apache.derby</groupId>
@@ -324,8 +286,14 @@
       </dependency>
       <dependency>
         <groupId>net.liftweb</groupId>
-        <artifactId>lift-json_2.9.2</artifactId>
-        <version>2.5</version>
+        <artifactId>lift-json_${scala.binary.version}</artifactId>
+        <version>2.5.1</version>
+        <exclusions>
+          <exclusion>
+            <groupId>org.scala-lang</groupId>
+            <artifactId>scalap</artifactId>
+          </exclusion>
+        </exclusions>
       </dependency>
       <dependency>
         <groupId>com.codahale.metrics</groupId>
@@ -368,24 +336,22 @@
         <version>${scala.version}</version>
       </dependency>
       <dependency>
-        <groupId>org.scala-lang</groupId>
-        <artifactId>scalap</artifactId>
-        <version>${scala.version}</version>
-      </dependency>
-
-      <dependency>
         <groupId>log4j</groupId>
         <artifactId>log4j</artifactId>
         <version>${log4j.version}</version>
       </dependency>
-
       <dependency>
         <groupId>org.scalatest</groupId>
-        <artifactId>scalatest_2.9.3</artifactId>
+        <artifactId>scalatest_${scala.binary.version}</artifactId>
         <version>1.9.1</version>
         <scope>test</scope>
       </dependency>
       <dependency>
+        <groupId>commons-io</groupId>
+        <artifactId>commons-io</artifactId>
+        <version>2.4</version>
+      </dependency>
+      <dependency>
         <groupId>org.easymock</groupId>
         <artifactId>easymock</artifactId>
         <version>3.1</version>
@@ -399,7 +365,7 @@
       </dependency>
       <dependency>
         <groupId>org.scalacheck</groupId>
-        <artifactId>scalacheck_2.9.3</artifactId>
+        <artifactId>scalacheck_${scala.binary.version}</artifactId>
         <version>1.10.0</version>
         <scope>test</scope>
       </dependency>
@@ -494,6 +460,7 @@
           </exclusion>
         </exclusions>
       </dependency>
+
       <dependency>
         <groupId>org.apache.hadoop</groupId>
         <artifactId>hadoop-yarn-client</artifactId>
@@ -532,6 +499,10 @@
             <groupId>org.jboss.netty</groupId>
             <artifactId>netty</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>io.netty</groupId>
+            <artifactId>netty</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
     </dependencies>
@@ -740,7 +711,7 @@
 
   <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 -->
@@ -752,25 +723,21 @@
         <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>
+    </profile>
+
+    <profile>
+      <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>
       <id>repl-bin</id>
       <activation>