merge master

Author: dorx

.gitignore

@@ -7,7 +7,7 @@
 sbt/*.jar
 .settings
 .cache
-.generated-mima-excludes
+.generated-mima*
 /build/
 work/
 out/

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.0.0-SNAPSHOT</version>
+    <version>1.1.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

bagel/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.0.0-SNAPSHOT</version>
+    <version>1.1.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala

@@ -38,8 +38,6 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
       sc.stop()
       sc = null
     }
-    // To avoid Akka rebinding to the same port, since it doesn't unbind immediately on shutdown
-    System.clearProperty("spark.driver.port")
   }
 
   test("halting by voting") {
@@ -82,7 +80,7 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
   test("large number of iterations") {
     // This tests whether jobs with a large number of iterations finish in a reasonable time,
     // because non-memoized recursion in RDD or DAGScheduler used to cause them to hang
-    failAfter(10 seconds) {
+    failAfter(30 seconds) {
       sc = new SparkContext("local", "test")
       val verts = sc.parallelize((1 to 4).map(id => (id.toString, new TestVertex(true, 0))))
       val msgs = sc.parallelize(Array[(String, TestMessage)]())
@@ -103,7 +101,7 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
       sc = new SparkContext("local", "test")
       val verts = sc.parallelize((1 to 4).map(id => (id.toString, new TestVertex(true, 0))))
       val msgs = sc.parallelize(Array[(String, TestMessage)]())
-      val numSupersteps = 50
+      val numSupersteps = 20
       val result =
         Bagel.run(sc, verts, msgs, sc.defaultParallelism, StorageLevel.DISK_ONLY) {
           (self: TestVertex, msgs: Option[Array[TestMessage]], superstep: Int) =>

bin/compute-classpath.sh

@@ -38,8 +38,10 @@ else
   JAR_CMD="jar"
 fi
 
-# First check if we have a dependencies jar. If so, include binary classes with the deps jar
-if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
+# A developer option to prepend more recently compiled Spark classes
+if [ -n "$SPARK_PREPEND_CLASSES" ]; then
+  echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
+    "classes ahead of assembly." >&2
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
@@ -51,17 +53,31 @@ if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
+fi
 
-  ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar 2>/dev/null)
+# Use spark-assembly jar from either RELEASE or assembly directory
+if [ -f "$FWDIR/RELEASE" ]; then
+  assembly_folder="$FWDIR"/lib
 else
-  # Else use spark-assembly jar from either RELEASE or assembly directory
-  if [ -f "$FWDIR/RELEASE" ]; then
-    ASSEMBLY_JAR=$(ls "$FWDIR"/lib/spark-assembly*hadoop*.jar 2>/dev/null)
-  else
-    ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*.jar 2>/dev/null)
-  fi
+  assembly_folder="$ASSEMBLY_DIR"
 fi
 
+num_jars=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)
+if [ "$num_jars" -eq "0" ]; then
+  echo "Failed to find Spark assembly in $assembly_folder"
+  echo "You need to build Spark before running this program."
+  exit 1
+fi
+if [ "$num_jars" -gt "1" ]; then
+  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
+  echo "Found multiple Spark assembly jars in $assembly_folder:"
+  echo "$jars_list"
+  echo "Please remove all but one jar."
+  exit 1
+fi
+
+ASSEMBLY_JAR=$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)
+
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then

bin/pyspark

@@ -45,7 +45,7 @@ fi
 . $FWDIR/bin/load-spark-env.sh
 
 # Figure out which Python executable to use
-if [ -z "$PYSPARK_PYTHON" ] ; then
+if [[ -z "$PYSPARK_PYTHON" ]]; then
   PYSPARK_PYTHON="python"
 fi
 export PYSPARK_PYTHON
@@ -59,7 +59,7 @@ export OLD_PYTHONSTARTUP=$PYTHONSTARTUP
 export PYTHONSTARTUP=$FWDIR/python/pyspark/shell.py
 
 # If IPython options are specified, assume user wants to run IPython
-if [ -n "$IPYTHON_OPTS" ]; then
+if [[ -n "$IPYTHON_OPTS" ]]; then
   IPYTHON=1
 fi
 
@@ -76,6 +76,16 @@ for i in "$@"; do
 done
 export PYSPARK_SUBMIT_ARGS
 
+# For pyspark tests
+if [[ -n "$SPARK_TESTING" ]]; then
+  if [[ -n "$PYSPARK_DOC_TEST" ]]; then
+    exec "$PYSPARK_PYTHON" -m doctest $1
+  else
+    exec "$PYSPARK_PYTHON" $1
+  fi
+  exit
+fi
+
 # If a python file is provided, directly run spark-submit.
 if [[ "$1" =~ \.py$ ]]; then
   echo -e "\nWARNING: Running python applications through ./bin/pyspark is deprecated as of Spark 1.0." 1>&2

bin/run-example

@@ -51,7 +51,7 @@ if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then
   EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS"
 fi
 
-./bin/spark-submit \
+"$FWDIR"/bin/spark-submit \
   --master $EXAMPLE_MASTER \
   --class $EXAMPLE_CLASS \
   "$SPARK_EXAMPLES_JAR" \

bin/spark-class

@@ -108,23 +108,6 @@ fi
 export JAVA_OPTS
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
 
-if [ ! -f "$FWDIR/RELEASE" ]; then
-  # Exit if the user hasn't compiled Spark
-  num_jars=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar" | wc -l)
-  jars_list=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar")
-  if [ "$num_jars" -eq "0" ]; then
-    echo "Failed to find Spark assembly in $FWDIR/assembly/target/scala-$SCALA_VERSION/" >&2
-    echo "You need to build Spark before running this program." >&2
-    exit 1
-  fi
-  if [ "$num_jars" -gt "1" ]; then
-    echo "Found multiple Spark assembly jars in $FWDIR/assembly/target/scala-$SCALA_VERSION:" >&2
-    echo "$jars_list"
-    echo "Please remove all but one jar."
-    exit 1
-  fi
-fi
-
 TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
 if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then

core/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.0.0-SNAPSHOT</version>
+    <version>1.1.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -239,7 +239,7 @@
     </dependency>
     <dependency>
       <groupId>org.easymock</groupId>
-      <artifactId>easymock</artifactId>
+      <artifactId>easymockclassextension</artifactId>
       <scope>test</scope>
     </dependency>
     <dependency>

core/src/main/scala/org/apache/spark/ContextCleaner.scala

@@ -96,7 +96,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging {
   }
 
   /** Register a ShuffleDependency for cleanup when it is garbage collected. */
-  def registerShuffleForCleanup(shuffleDependency: ShuffleDependency[_, _]) {
+  def registerShuffleForCleanup(shuffleDependency: ShuffleDependency[_, _, _]) {
     registerForCleanup(shuffleDependency, CleanShuffle(shuffleDependency.shuffleId))
   }