Merge remote-tracking branch 'apache/master' into state-cleanup

Conflicts: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala core/src/main/scala/org/apache/spark/storage/BlockManager.scala core/src/main/scala/org/apache/spark/storage/BlockManagerMasterActor.scala core/src/main/scala/org/apache/spark/storage/BlockManagerMessages.scala
apache · Apr 8, 2014 · f489fdc · f489fdc
2 parents d25a86e + 0307db0
commit f489fdc
Show file tree

Hide file tree

Showing 135 changed files with 2,472 additions and 753 deletions.
diff --git a/.rat-excludes b/.rat-excludes
@@ -39,3 +39,4 @@ work
 .*\.q
 golden
 test.out/*
+.*iml
diff --git a/assembly/pom.xml b/assembly/pom.xml
@@ -163,6 +163,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>
@@ -208,7 +218,7 @@
           <plugin>
             <groupId>org.codehaus.mojo</groupId>
             <artifactId>buildnumber-maven-plugin</artifactId>
-            <version>1.1</version>
+            <version>1.2</version>
             <executions>
               <execution>
                 <phase>validate</phase>

diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
@@ -30,21 +30,7 @@ FWDIR="$(cd `dirname $0`/..; pwd)"
 # Build up classpath
 CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
 
-# Support for interacting with Hive.  Since hive pulls in a lot of dependencies that might break
-# existing Spark applications, it is not included in the standard spark assembly.  Instead, we only
-# include it in the classpath if the user has explicitly requested it by running "sbt hive/assembly"
-# Hopefully we will find a way to avoid uber-jars entirely and deploy only the needed packages in
-# the future.
-if [ -f "$FWDIR"/sql/hive/target/scala-$SCALA_VERSION/spark-hive-assembly-*.jar ]; then
-
-  # Datanucleus jars do not work if only included in the uberjar as plugin.xml metadata is lost.
-  DATANUCLEUSJARS=$(JARS=("$FWDIR/lib_managed/jars"/datanucleus-*.jar); IFS=:; echo "${JARS[*]}")
-  CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
-
-  ASSEMBLY_DIR="$FWDIR/sql/hive/target/scala-$SCALA_VERSION/"
-else
-  ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION/"
-fi
+ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
 
 # First check if we have a dependencies jar. If so, include binary classes with the deps jar
 if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
@@ -59,7 +45,7 @@ if [ -f "$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"
 
-  DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*-deps.jar`
+  DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar`
   CLASSPATH="$CLASSPATH:$DEPS_ASSEMBLY_JAR"
 else
   # Else use spark-assembly jar from either RELEASE or assembly directory
@@ -71,6 +57,23 @@ else
   CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
 fi
 
+# When Hive support is needed, Datanucleus jars must be included on the classpath.
+# Datanucleus jars do not work if only included in the  uber jar as plugin.xml metadata is lost.
+# Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is
+# built with Hive, so first check if the datanucleus jars exist, and then ensure the current Spark
+# assembly is built for Hive, before actually populating the CLASSPATH with the jars.
+# Note that this check order is faster (by up to half a second) in the case where Hive is not used.
+num_datanucleus_jars=$(ls "$FWDIR"/lib_managed/jars/ | grep "datanucleus-.*\\.jar" | wc -l)
+if [ $num_datanucleus_jars -gt 0 ]; then
+  AN_ASSEMBLY_JAR=${ASSEMBLY_JAR:-$DEPS_ASSEMBLY_JAR}
+  num_hive_files=$(jar tvf "$AN_ASSEMBLY_JAR" org/apache/hadoop/hive/ql/exec 2>/dev/null | wc -l)
+  if [ $num_hive_files -gt 0 ]; then
+    echo "Spark assembly has been built with Hive, including Datanucleus jars on classpath" 1>&2
+    DATANUCLEUSJARS=$(echo "$FWDIR/lib_managed/jars"/datanucleus-*.jar | tr " " :)
+    CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
+  fi
+fi
+
 # 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"

diff --git a/bin/load-spark-env.sh b/bin/load-spark-env.sh
@@ -30,6 +30,9 @@ if [ -z "$SPARK_ENV_LOADED" ]; then
   use_conf_dir=${SPARK_CONF_DIR:-"$parent_dir/conf"}
 
   if [ -f "${use_conf_dir}/spark-env.sh" ]; then
+    # Promote all variable declarations to environment (exported) variables
+    set -a
     . "${use_conf_dir}/spark-env.sh"
+    set +a
   fi
 fi
diff --git a/bin/spark-class b/bin/spark-class
@@ -154,5 +154,3 @@ if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
 fi
 
 exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
-
-
diff --git a/bin/spark-shell b/bin/spark-shell
@@ -34,7 +34,7 @@ set -o posix
 FWDIR="$(cd `dirname $0`/..; pwd)"
 
 SPARK_REPL_OPTS="${SPARK_REPL_OPTS:-""}"
-DEFAULT_MASTER="local"
+DEFAULT_MASTER="local[*]"
 MASTER=${MASTER:-""}
 
 info_log=0
@@ -64,7 +64,7 @@ ${txtbld}OPTIONS${txtrst}:
                               is followed by m for megabytes or g for gigabytes, e.g. "1g".
     -dm --driver-memory     : The memory used by the Spark Shell, the number is followed 
                               by m for megabytes or g for gigabytes, e.g. "1g".
-    -m  --master            : A full string that describes the Spark Master, defaults to "local"
+    -m  --master            : A full string that describes the Spark Master, defaults to "local[*]"
                               e.g. "spark://localhost:7077".
     --log-conf              : Enables logging of the supplied SparkConf as INFO at start of the
                               Spark Context.
@@ -127,7 +127,7 @@ function set_spark_log_conf(){
 
 function set_spark_master(){
     if ! [[ "$1" =~ $ARG_FLAG_PATTERN ]]; then
-        MASTER="$1"
+        export MASTER="$1"
     else
         out_error "wrong format for $2"
     fi
@@ -145,7 +145,7 @@ function resolve_spark_master(){
     fi
 
     if [ -z "$MASTER" ]; then
-        MASTER="$DEFAULT_MASTER"
+        export MASTER="$DEFAULT_MASTER"
     fi
 
 }

diff --git a/core/pom.xml b/core/pom.xml
@@ -117,12 +117,10 @@
     <dependency>
       <groupId>com.twitter</groupId>
       <artifactId>chill_${scala.binary.version}</artifactId>
-      <version>0.3.1</version>
     </dependency>
     <dependency>
       <groupId>com.twitter</groupId>
       <artifactId>chill-java</artifactId>
-      <version>0.3.1</version>
     </dependency>
     <dependency>
       <groupId>commons-net</groupId>
@@ -200,6 +198,53 @@
       <artifactId>derby</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.tachyonproject</groupId>
+      <artifactId>tachyon</artifactId>
+      <version>0.4.1-thrift</version>
+      <exclusions>
+        <exclusion>
+          <groupId>org.apache.hadoop</groupId>
+          <artifactId>hadoop-client</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.curator</groupId>
+          <artifactId>curator-recipes</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-jsp</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-webapp</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-server</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-servlet</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>junit</groupId>
+          <artifactId>junit</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.powermock</groupId>
+          <artifactId>powermock-module-junit4</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.powermock</groupId>
+          <artifactId>powermock-api-mockito</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.curator</groupId>
+          <artifactId>curator-test</artifactId>
+        </exclusion>
+      </exclusions>
+    </dependency>
     <dependency>
       <groupId>org.scalatest</groupId>
       <artifactId>scalatest_${scala.binary.version}</artifactId>

diff --git a/core/src/main/java/org/apache/spark/api/java/StorageLevels.java b/core/src/main/java/org/apache/spark/api/java/StorageLevels.java
@@ -23,17 +23,18 @@
  * Expose some commonly useful storage level constants.
  */
 public class StorageLevels {
-  public static final StorageLevel NONE = create(false, false, false, 1);
-  public static final StorageLevel DISK_ONLY = create(true, false, false, 1);
-  public static final StorageLevel DISK_ONLY_2 = create(true, false, false, 2);
-  public static final StorageLevel MEMORY_ONLY = create(false, true, true, 1);
-  public static final StorageLevel MEMORY_ONLY_2 = create(false, true, true, 2);
-  public static final StorageLevel MEMORY_ONLY_SER = create(false, true, false, 1);
-  public static final StorageLevel MEMORY_ONLY_SER_2 = create(false, true, false, 2);
-  public static final StorageLevel MEMORY_AND_DISK = create(true, true, true, 1);
-  public static final StorageLevel MEMORY_AND_DISK_2 = create(true, true, true, 2);
-  public static final StorageLevel MEMORY_AND_DISK_SER = create(true, true, false, 1);
-  public static final StorageLevel MEMORY_AND_DISK_SER_2 = create(true, true, false, 2);
+  public static final StorageLevel NONE = create(false, false, false, false, 1);
+  public static final StorageLevel DISK_ONLY = create(true, false, false, false, 1);
+  public static final StorageLevel DISK_ONLY_2 = create(true, false, false, false, 2);
+  public static final StorageLevel MEMORY_ONLY = create(false, true, false, true, 1);
+  public static final StorageLevel MEMORY_ONLY_2 = create(false, true, false, true, 2);
+  public static final StorageLevel MEMORY_ONLY_SER = create(false, true, false, false, 1);
+  public static final StorageLevel MEMORY_ONLY_SER_2 = create(false, true, false, false, 2);
+  public static final StorageLevel MEMORY_AND_DISK = create(true, true, false, true, 1);
+  public static final StorageLevel MEMORY_AND_DISK_2 = create(true, true, false, true, 2);
+  public static final StorageLevel MEMORY_AND_DISK_SER = create(true, true, false, false, 1);
+  public static final StorageLevel MEMORY_AND_DISK_SER_2 = create(true, true, false, false, 2);
+  public static final StorageLevel OFF_HEAP = create(false, false, true, false, 1);
 
   /**
    * Create a new StorageLevel object.
@@ -42,7 +43,26 @@ public class StorageLevels {
    * @param deserialized saved as deserialized objects, if true
    * @param replication replication factor
    */
-  public static StorageLevel create(boolean useDisk, boolean useMemory, boolean deserialized, int replication) {
-    return StorageLevel.apply(useDisk, useMemory, deserialized, replication);
+  @Deprecated
+  public static StorageLevel create(boolean useDisk, boolean useMemory, boolean deserialized,
+      int replication) {
+    return StorageLevel.apply(useDisk, useMemory, false, deserialized, replication);
+  }
+
+  /**
+   * Create a new StorageLevel object.
+   * @param useDisk saved to disk, if true
+   * @param useMemory saved to memory, if true
+   * @param useOffHeap saved to Tachyon, if true
+   * @param deserialized saved as deserialized objects, if true
+   * @param replication replication factor
+   */
+  public static StorageLevel create(
+    boolean useDisk,
+    boolean useMemory,
+    boolean useOffHeap,
+    boolean deserialized,
+    int replication) {
+    return StorageLevel.apply(useDisk, useMemory, useOffHeap, deserialized, replication);
   }
 }
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -19,14 +19,13 @@ package org.apache.spark
 
 import java.io._
 import java.net.URI
-import java.util.{Properties, UUID}
 import java.util.concurrent.atomic.AtomicInteger
-
+import java.util.{Properties, UUID}
+import java.util.UUID.randomUUID
 import scala.collection.{Map, Set}
 import scala.collection.generic.Growable
 import scala.collection.mutable.{ArrayBuffer, HashMap}
 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}
@@ -37,6 +36,7 @@ import org.apache.mesos.MesosNativeLibrary
 
 import org.apache.spark.broadcast.Broadcast
 import org.apache.spark.deploy.{LocalSparkCluster, SparkHadoopUtil}
+import org.apache.spark.input.WholeTextFileInputFormat
 import org.apache.spark.partial.{ApproximateEvaluator, PartialResult}
 import org.apache.spark.rdd._
 import org.apache.spark.scheduler._
@@ -129,6 +129,11 @@ class SparkContext(
   val master = conf.get("spark.master")
   val appName = conf.get("spark.app.name")
 
+  // Generate the random name for a temp folder in Tachyon
+  // Add a timestamp as the suffix here to make it more safe
+  val tachyonFolderName = "spark-" + randomUUID.toString()
+  conf.set("spark.tachyonStore.folderName", tachyonFolderName)
+
   val isLocal = (master == "local" || master.startsWith("local["))
 
   if (master == "yarn-client") System.setProperty("SPARK_YARN_MODE", "true")
@@ -378,6 +383,39 @@ class SparkContext(
       minSplits).map(pair => pair._2.toString)
   }
 
+  /**
+   * Read a directory of text files from HDFS, a local file system (available on all nodes), or any
+   * Hadoop-supported file system URI. Each file is read as a single record and returned in a
+   * key-value pair, where the key is the path of each file, the value is the content of each file.
+   *
+   * <p> For example, if you have the following files:
+   * {{{
+   *   hdfs://a-hdfs-path/part-00000
+   *   hdfs://a-hdfs-path/part-00001
+   *   ...
+   *   hdfs://a-hdfs-path/part-nnnnn
+   * }}}
+   *
+   * Do `val rdd = sparkContext.wholeTextFile("hdfs://a-hdfs-path")`,
+   *
+   * <p> then `rdd` contains
+   * {{{
+   *   (a-hdfs-path/part-00000, its content)
+   *   (a-hdfs-path/part-00001, its content)
+   *   ...
+   *   (a-hdfs-path/part-nnnnn, its content)
+   * }}}
+   *
+   * @note Small files are preferred, as each file will be loaded fully in memory.
+   */
+  def wholeTextFiles(path: String): RDD[(String, String)] = {
+    newAPIHadoopFile(
+      path,
+      classOf[WholeTextFileInputFormat],
+      classOf[String],
+      classOf[String])
+  }
+
   /**
    * Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf given its InputFormat and other
    * necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable),
@@ -704,10 +742,6 @@ class SparkContext(
    */
   def getPersistentRDDs: Map[Int, RDD[_]] = persistentRdds.toMap
 
-  def getStageInfo: Map[Stage, StageInfo] = {
-    dagScheduler.stageToInfos
-  }
-
   /**
    * Return information about blocks stored in all of the slaves
    */
@@ -1262,8 +1296,8 @@ object SparkContext extends Logging {
 
   /** Creates a task scheduler based on a given master URL. Extracted for testing. */
   private def createTaskScheduler(sc: SparkContext, master: String): TaskScheduler = {
-    // Regular expression used for local[N] master format
-    val LOCAL_N_REGEX = """local\[([0-9]+)\]""".r
+    // Regular expression used for local[N] and local[*] master formats
+    val LOCAL_N_REGEX = """local\[([0-9\*]+)\]""".r
     // Regular expression for local[N, maxRetries], used in tests with failing tasks
     val LOCAL_N_FAILURES_REGEX = """local\[([0-9]+)\s*,\s*([0-9]+)\]""".r
     // Regular expression for simulating a Spark cluster of [N, cores, memory] locally
@@ -1286,8 +1320,11 @@ object SparkContext extends Logging {
         scheduler
 
       case LOCAL_N_REGEX(threads) =>
+        def localCpuCount = Runtime.getRuntime.availableProcessors()
+        // local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
+        val threadCount = if (threads == "*") localCpuCount else threads.toInt
         val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
-        val backend = new LocalBackend(scheduler, threads.toInt)
+        val backend = new LocalBackend(scheduler, threadCount)
         scheduler.initialize(backend)
         scheduler
-Original file line number
+Diff line change
@@ Expand Up / @@ -39,3 +39,4 @@ work @@
     .*\.q
     golden
     test.out/*
+    .*iml
Original file line number	Diff line number	Diff line change
Expand Up		@@ -154,5 +154,3 @@ if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
		fi

		exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"