Merge pull request #2 from apache/master

merge upstream changes

Author: nchammas

.gitignore

@@ -15,11 +15,10 @@ 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/
@@ -50,7 +49,6 @@ 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 the [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.

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/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/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

core/src/main/scala/org/apache/spark/util/Utils.scala

@@ -530,7 +530,12 @@ private[spark] object Utils extends Logging {
       if (address.isLoopbackAddress) {
         // Address resolves to something like 127.0.1.1, which happens on Debian; try to find
         // a better address using the local network interfaces
-        for (ni <- NetworkInterface.getNetworkInterfaces) {
+        // getNetworkInterfaces returns ifs in reverse order compared to ifconfig output order
+        // on unix-like system. On windows, it returns in index order.
+        // It's more proper to pick ip address following system output order.
+        val activeNetworkIFs = NetworkInterface.getNetworkInterfaces.toList
+        val reOrderedNetworkIFs = if (isWindows) activeNetworkIFs else activeNetworkIFs.reverse
+        for (ni <- reOrderedNetworkIFs) {
           for (addr <- ni.getInetAddresses if !addr.isLinkLocalAddress &&
                !addr.isLoopbackAddress && addr.isInstanceOf[Inet4Address]) {
             // We've found an address that looks reasonable!

core/src/test/scala/org/apache/spark/ui/UISuite.scala

@@ -23,7 +23,6 @@ import javax.servlet.http.HttpServletRequest
 import scala.io.Source
 import scala.util.{Failure, Success, Try}
 
-import org.eclipse.jetty.server.Server
 import org.eclipse.jetty.servlet.ServletContextHandler
 import org.scalatest.FunSuite
 import org.scalatest.concurrent.Eventually._
@@ -108,14 +107,8 @@ class UISuite extends FunSuite {
   }
 
   test("jetty selects different port under contention") {
-    val startPort = 4040
-    val server = new Server(startPort)
-
-    Try { server.start() } match {
-      case Success(s) =>
-      case Failure(e) =>
-      // Either case server port is busy hence setup for test complete
-    }
+    val server = new ServerSocket(0)
+    val startPort = server.getLocalPort
     val serverInfo1 = JettyUtils.startJettyServer(
       "0.0.0.0", startPort, Seq[ServletContextHandler](), new SparkConf)
     val serverInfo2 = JettyUtils.startJettyServer(
@@ -126,6 +119,9 @@ class UISuite extends FunSuite {
     assert(boundPort1 != startPort)
     assert(boundPort2 != startPort)
     assert(boundPort1 != boundPort2)
+    serverInfo1.server.stop()
+    serverInfo2.server.stop()
+    server.close()
   }
 
   test("jetty binds to port 0 correctly") {

dev/mima

@@ -25,11 +25,19 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 cd "$FWDIR"
 
 echo -e "q\n" | sbt/sbt oldDeps/update
+rm -f .generated-mima*
+
+# Generate Mima Ignore is called twice, first with latest built jars 
+# on the classpath and then again with previous version jars on the classpath.
+# Because of a bug in GenerateMIMAIgnore that when old jars are ahead on classpath
+# it did not process the new classes (which are in assembly jar). 
+./bin/spark-class org.apache.spark.tools.GenerateMIMAIgnore
 
 export SPARK_CLASSPATH="`find lib_managed \( -name '*spark*jar' -a -type f \) | tr "\\n" ":"`"
 echo "SPARK_CLASSPATH=$SPARK_CLASSPATH"
 
 ./bin/spark-class org.apache.spark.tools.GenerateMIMAIgnore
+
 echo -e "q\n" | sbt/sbt mima-report-binary-issues | grep -v -e "info.*Resolving"
 ret_val=$?