Merge pull request #5 from apache/master

merge lastest spark

Author: pzzs

README.md

@@ -85,7 +85,7 @@ storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
 
 Please refer to the build documentation at
-["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-with-maven.html#specifying-the-hadoop-version)
+["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)

assembly/pom.xml

@@ -114,16 +114,6 @@
                 <exclude>META-INF/*.RSA</exclude>
               </excludes>
             </filter>
-            <filter>
-              <!-- Exclude libgfortran, libgcc for license issues -->
-              <artifact>org.jblas:jblas</artifact>
-              <excludes>
-                <!-- Linux amd64 is OK; not statically linked -->
-                <exclude>lib/static/Linux/i386/**</exclude>
-                <exclude>lib/static/Mac OS X/**</exclude>
-                <exclude>lib/static/Windows/**</exclude>
-              </excludes>
-            </filter>
           </filters>
         </configuration>
         <executions>

bin/pyspark

@@ -89,7 +89,6 @@ export PYTHONSTARTUP="$SPARK_HOME/python/pyspark/shell.py"
 if [[ -n "$SPARK_TESTING" ]]; then
   unset YARN_CONF_DIR
   unset HADOOP_CONF_DIR
-  export PYSPARK_SUBMIT_ARGS=pyspark-shell
   if [[ -n "$PYSPARK_DOC_TEST" ]]; then
     exec "$PYSPARK_DRIVER_PYTHON" -m doctest $1
   else

conf/spark-env.sh.template

@@ -15,7 +15,7 @@
 # - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program
 # - SPARK_CLASSPATH, default classpath entries to append
 # - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data
-# - MESOS_NATIVE_LIBRARY, to point to your libmesos.so if you use Mesos
+# - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos
 
 # Options read in YARN client mode
 # - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files

core/pom.xml

@@ -414,7 +414,7 @@
               <overWriteIfNewer>true</overWriteIfNewer>
               <useSubDirectoryPerType>true</useSubDirectoryPerType>
               <includeArtifactIds>
-                guava,jetty-io,jetty-servlet,jetty-continuation,jetty-http,jetty-plus,jetty-util,jetty-server
+                guava,jetty-io,jetty-servlet,jetty-continuation,jetty-http,jetty-plus,jetty-util,jetty-server,jetty-security
               </includeArtifactIds>
               <silent>true</silent>
             </configuration>

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

@@ -145,7 +145,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging {
   }
 
   /** Keep cleaning RDD, shuffle, and broadcast state. */
-  private def keepCleaning(): Unit = Utils.logUncaughtExceptions {
+  private def keepCleaning(): Unit = Utils.tryOrStopSparkContext(sc) {
     while (!stopped) {
       try {
         val reference = Option(referenceQueue.remove(ContextCleaner.REF_QUEUE_POLL_TIMEOUT))

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

@@ -1093,7 +1093,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
   def addFile(path: String, recursive: Boolean): Unit = {
     val uri = new URI(path)
     val schemeCorrectedPath = uri.getScheme match {
-      case null | "local" => "file:" + uri.getPath
+      case null | "local" => new File(path).getCanonicalFile.toURI.toString
       case _              => path
     }
 
@@ -1736,7 +1736,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
         }
     }
 
-    listenerBus.start()
+    listenerBus.start(this)
   }
 
   /** Post the application start event */

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

@@ -46,5 +46,6 @@ private[spark] object TaskState extends Enumeration {
     case MesosTaskState.TASK_FAILED => FAILED
     case MesosTaskState.TASK_KILLED => KILLED
     case MesosTaskState.TASK_LOST => LOST
+    case MesosTaskState.TASK_ERROR => LOST
   }
 }

core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala

@@ -32,7 +32,8 @@ import org.apache.spark.storage.StorageLevel
 import org.apache.spark.util.StatCounter
 import org.apache.spark.util.Utils
 
-class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[JDouble, JavaDoubleRDD] {
+class JavaDoubleRDD(val srdd: RDD[scala.Double])
+  extends AbstractJavaRDDLike[JDouble, JavaDoubleRDD] {
 
   override val classTag: ClassTag[JDouble] = implicitly[ClassTag[JDouble]]
 

core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala

@@ -44,7 +44,7 @@ import org.apache.spark.util.Utils
 
 class JavaPairRDD[K, V](val rdd: RDD[(K, V)])
                        (implicit val kClassTag: ClassTag[K], implicit val vClassTag: ClassTag[V])
-  extends JavaRDDLike[(K, V), JavaPairRDD[K, V]] {
+  extends AbstractJavaRDDLike[(K, V), JavaPairRDD[K, V]] {
 
   override def wrapRDD(rdd: RDD[(K, V)]): JavaPairRDD[K, V] = JavaPairRDD.fromRDD(rdd)