Merge branch 'master' of git://git.apache.org/spark into emacs-metafiles-ignore

Author: sarutak

.gitignore

@@ -17,11 +17,10 @@ out/
 third_party/libmesos.so
 third_party/libmesos.dylib
 conf/java-opts
-conf/spark-env.sh
-conf/streaming-env.sh
-conf/log4j.properties
-conf/spark-defaults.conf
-conf/hive-site.xml
+conf/*.sh
+conf/*.properties
+conf/*.conf
+conf/*.xml
 docs/_site
 docs/api
 target/
@@ -52,7 +51,6 @@ unit-tests.log
 /lib/
 rat-results.txt
 scalastyle.txt
-conf/*.conf
 scalastyle-output.xml
 
 # For Hive

CONTRIBUTING.md

@@ -0,0 +1,12 @@
+## Contributing to Spark
+
+Contributions via GitHub pull requests are gladly accepted from their original
+author. Along with any pull requests, please state that the contribution is
+your original work and that you license the work to the project under the
+project's open source license. Whether or not you state this explicitly, by
+submitting any copyrighted material via pull request, email, or other means
+you agree to license the material under the project's open source license and
+warrant that you have the legal authority to do so.
+
+Please see [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
+for more information.

README.md

@@ -13,16 +13,19 @@ and Spark Streaming for stream processing.
 ## Online Documentation
 
 You can find the latest Spark documentation, including a programming
-guide, on the project webpage at <http://spark.apache.org/documentation.html>.
+guide, on the [project web page](http://spark.apache.org/documentation.html).
 This README file only contains basic setup instructions.
 
 ## Building Spark
 
-Spark is built on Scala 2.10. To build Spark and its example programs, run:
+Spark is built using [Apache Maven](http://maven.apache.org/).
+To build Spark and its example programs, run:
 
-    ./sbt/sbt assembly
+    mvn -DskipTests clean package
 
 (You do not need to do this if you downloaded a pre-built package.)
+More detailed documentation is available from the project site, at
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 
@@ -71,73 +74,24 @@ can be run using:
 
     ./dev/run-tests
 
+Please see the guidance on how to 
+[run all automated tests](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-AutomatedTesting).
+
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting `-Dhadoop.version` when building Spark.
-
-For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
-versions without YARN, use:
-
-    # Apache Hadoop 1.2.1
-    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v1
-    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
-
-For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
-with YARN, also set `-Pyarn`:
-
-    # Apache Hadoop 2.0.5-alpha
-    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v2
-    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
-
-    # Apache Hadoop 2.2.X and newer
-    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
-
-When developing a Spark application, specify the Hadoop version by adding the
-"hadoop-client" artifact to your project's dependencies. For example, if you're
-using Hadoop 1.2.1 and build your application using SBT, add this entry to
-`libraryDependencies`:
-
-    "org.apache.hadoop" % "hadoop-client" % "1.2.1"
 
-If your project is built with Maven, add this to your POM file's `<dependencies>` section:
-
-    <dependency>
-      <groupId>org.apache.hadoop</groupId>
-      <artifactId>hadoop-client</artifactId>
-      <version>1.2.1</version>
-    </dependency>
-
-
-## A Note About Thrift JDBC server and CLI for Spark SQL
-
-Spark SQL supports Thrift JDBC server and CLI.
-See sql-programming-guide.md for more information about using the JDBC server and CLI.
-You can use those features by setting `-Phive` when building Spark as follows.
-
-    $ sbt/sbt -Phive  assembly
+Please refer to the build documentation at
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+for detailed guidance on building for a particular distribution of Hadoop, including
+building for particular Hive and Hive Thriftserver distributions. See also
+["Third Party Hadoop Distributions"](http://spark.apache.org/docs/latest/hadoop-third-party-distributions.html)
+for guidance on building a Spark application that works with a particular
+distribution.
 
 ## Configuration
 
 Please refer to the [Configuration guide](http://spark.apache.org/docs/latest/configuration.html)
 in the online documentation for an overview on how to configure Spark.
-
-
-## Contributing to Spark
-
-Contributions via GitHub pull requests are gladly accepted from their original
-author. Along with any pull requests, please state that the contribution is
-your original work and that you license the work to the project under the
-project's open source license. Whether or not you state this explicitly, by
-submitting any copyrighted material via pull request, email, or other means
-you agree to license the material under the project's open source license and
-warrant that you have the legal authority to do so.
-
-Please see [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
-for more information.

bin/spark-class

@@ -105,7 +105,7 @@ else
     exit 1
   fi
 fi
-JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/java version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
+JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/.* version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 if [ "$JAVA_VERSION" -ge 18 ]; then

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

@@ -1072,11 +1072,8 @@ class SparkContext(config: SparkConf) extends Logging {
     val callSite = getCallSite
     val cleanedFunc = clean(func)
     logInfo("Starting job: " + callSite.shortForm)
-    val start = System.nanoTime
     dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, allowLocal,
       resultHandler, localProperties.get)
-    logInfo(
-      "Job finished: " + callSite.shortForm + ", took " + (System.nanoTime - start) / 1e9 + " s")
     rdd.doCheckpoint()
   }
 

core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala

@@ -776,7 +776,7 @@ private[spark] object PythonRDD extends Logging {
   }
 
   /**
-   * Convert and RDD of Java objects to and RDD of serialized Python objects, that is usable by
+   * Convert an RDD of Java objects to an RDD of serialized Python objects, that is usable by
    * PySpark.
    */
   def javaToPython(jRDD: JavaRDD[Any]): JavaRDD[Array[Byte]] = {

core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala

@@ -17,6 +17,8 @@
 
 package org.apache.spark.api.python
 
+import java.nio.ByteOrder
+
 import scala.collection.JavaConversions._
 import scala.util.Failure
 import scala.util.Try
@@ -28,6 +30,55 @@ import org.apache.spark.rdd.RDD
 
 /** Utilities for serialization / deserialization between Python and Java, using Pickle. */
 private[python] object SerDeUtil extends Logging {
+  // Unpickle array.array generated by Python 2.6
+  class ArrayConstructor extends net.razorvine.pickle.objects.ArrayConstructor {
+    //  /* Description of types */
+    //  static struct arraydescr descriptors[] = {
+    //    {'c', sizeof(char), c_getitem, c_setitem},
+    //    {'b', sizeof(char), b_getitem, b_setitem},
+    //    {'B', sizeof(char), BB_getitem, BB_setitem},
+    //    #ifdef Py_USING_UNICODE
+    //      {'u', sizeof(Py_UNICODE), u_getitem, u_setitem},
+    //    #endif
+    //    {'h', sizeof(short), h_getitem, h_setitem},
+    //    {'H', sizeof(short), HH_getitem, HH_setitem},
+    //    {'i', sizeof(int), i_getitem, i_setitem},
+    //    {'I', sizeof(int), II_getitem, II_setitem},
+    //    {'l', sizeof(long), l_getitem, l_setitem},
+    //    {'L', sizeof(long), LL_getitem, LL_setitem},
+    //    {'f', sizeof(float), f_getitem, f_setitem},
+    //    {'d', sizeof(double), d_getitem, d_setitem},
+    //    {'\0', 0, 0, 0} /* Sentinel */
+    //  };
+    // TODO: support Py_UNICODE with 2 bytes
+    // FIXME: unpickle array of float is wrong in Pyrolite, so we reverse the
+    // machine code for float/double here to workaround it.
+    // we should fix this after Pyrolite fix them
+    val machineCodes: Map[Char, Int] = if (ByteOrder.nativeOrder().equals(ByteOrder.BIG_ENDIAN)) {
+      Map('c' -> 1, 'B' -> 0, 'b' -> 1, 'H' -> 3, 'h' -> 5, 'I' -> 7, 'i' -> 9,
+        'L' -> 11, 'l' -> 13, 'f' -> 14, 'd' -> 16, 'u' -> 21
+      )
+    } else {
+      Map('c' -> 1, 'B' -> 0, 'b' -> 1, 'H' -> 2, 'h' -> 4, 'I' -> 6, 'i' -> 8,
+        'L' -> 10, 'l' -> 12, 'f' -> 15, 'd' -> 17, 'u' -> 20
+      )
+    }
+    override def construct(args: Array[Object]): Object = {
+      if (args.length == 1) {
+        construct(args ++ Array(""))
+      } else if (args.length == 2 && args(1).isInstanceOf[String]) {
+        val typecode = args(0).asInstanceOf[String].charAt(0)
+        val data: String = args(1).asInstanceOf[String]
+        construct(typecode, machineCodes(typecode), data.getBytes("ISO-8859-1"))
+      } else {
+        super.construct(args)
+      }
+    }
+  }
+
+  def initialize() = {
+    Unpickler.registerConstructor("array", "array", new ArrayConstructor())
+  }
 
   private def checkPickle(t: (Any, Any)): (Boolean, Boolean) = {
     val pickle = new Pickler

core/src/main/scala/org/apache/spark/network/ManagedBuffer.scala

@@ -19,6 +19,7 @@ package org.apache.spark.network
 
 import java.io.{FileInputStream, RandomAccessFile, File, InputStream}
 import java.nio.ByteBuffer
+import java.nio.channels.FileChannel
 import java.nio.channels.FileChannel.MapMode
 
 import com.google.common.io.ByteStreams
@@ -66,8 +67,15 @@ final class FileSegmentManagedBuffer(val file: File, val offset: Long, val lengt
   override def size: Long = length
 
   override def nioByteBuffer(): ByteBuffer = {
-    val channel = new RandomAccessFile(file, "r").getChannel
-    channel.map(MapMode.READ_ONLY, offset, length)
+    var channel: FileChannel = null
+    try {
+      channel = new RandomAccessFile(file, "r").getChannel
+      channel.map(MapMode.READ_ONLY, offset, length)
+    } finally {
+      if (channel != null) {
+        channel.close()
+      }
+    }
   }
 
   override def inputStream(): InputStream = {

core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala

@@ -507,11 +507,16 @@ class DAGScheduler(
       resultHandler: (Int, U) => Unit,
       properties: Properties = null)
   {
+    val start = System.nanoTime
     val waiter = submitJob(rdd, func, partitions, callSite, allowLocal, resultHandler, properties)
     waiter.awaitResult() match {
-      case JobSucceeded => {}
+      case JobSucceeded => {
+        logInfo("Job %d finished: %s, took %f s".format
+          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
+      }
       case JobFailed(exception: Exception) =>
-        logInfo("Failed to run " + callSite.shortForm)
+        logInfo("Job %d failed: %s, took %f s".format
+          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
         throw exception
     }
   }

core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala

@@ -23,7 +23,7 @@ import scala.collection.mutable.ArrayBuffer
 import scala.collection.mutable.HashSet
 import scala.collection.mutable.Queue
 
-import org.apache.spark.{TaskContext, Logging, SparkException}
+import org.apache.spark.{TaskContext, Logging}
 import org.apache.spark.network.{ManagedBuffer, BlockFetchingListener, BlockTransferService}
 import org.apache.spark.serializer.Serializer
 import org.apache.spark.util.Utils