Merge remote-tracking branch 'upstream/master' into pyspark-inputformats

Author: MLnick

conf/spark-env.sh.template

@@ -5,6 +5,7 @@
 
 # Options read when launching programs locally with 
 # ./bin/run-example or ./bin/spark-submit
+# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
 # - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
 # - SPARK_PUBLIC_DNS, to set the public dns name of the driver program
 # - SPARK_CLASSPATH, default classpath entries to append
@@ -17,6 +18,7 @@
 # - MESOS_NATIVE_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
 # - SPARK_EXECUTOR_INSTANCES, Number of workers to start (Default: 2)
 # - SPARK_EXECUTOR_CORES, Number of cores for the workers (Default: 1).
 # - SPARK_EXECUTOR_MEMORY, Memory per Worker (e.g. 1000M, 2G) (Default: 1G)

core/pom.xml

@@ -269,7 +269,7 @@
     <dependency>
       <groupId>org.spark-project</groupId>
       <artifactId>pyrolite</artifactId>
-      <version>2.0</version>
+      <version>2.0.1</version>
     </dependency>
   </dependencies>
   <build>

core/src/main/java/org/apache/spark/package-info.java

@@ -0,0 +1,23 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * Core Spark classes in Scala. A few classes here, such as {@link org.apache.spark.Accumulator}
+ * and {@link org.apache.spark.storage.StorageLevel}, are also used in Java, but the
+ * {@link org.apache.spark.api.java} package contains the main Java API.
+ */
+package org.apache.spark;

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

@@ -1110,6 +1110,7 @@ class SparkContext(config: SparkConf) extends Logging {
   }
 
   /**
+   * :: Experimental ::
    * Submit a job for execution and return a FutureJob holding the result.
    */
   @Experimental
@@ -1345,19 +1346,19 @@ object SparkContext extends Logging {
    * Find the JAR from which a given class was loaded, to make it easy for users to pass
    * their JARs to SparkContext.
    */
-  def jarOfClass(cls: Class[_]): Seq[String] = {
+  def jarOfClass(cls: Class[_]): Option[String] = {
     val uri = cls.getResource("/" + cls.getName.replace('.', '/') + ".class")
     if (uri != null) {
       val uriStr = uri.toString
       if (uriStr.startsWith("jar:file:")) {
         // URI will be of the form "jar:file:/path/foo.jar!/package/cls.class",
         // so pull out the /path/foo.jar
-        List(uriStr.substring("jar:file:".length, uriStr.indexOf('!')))
+        Some(uriStr.substring("jar:file:".length, uriStr.indexOf('!')))
       } else {
-        Nil
+        None
       }
     } else {
-      Nil
+      None
     }
   }
 
@@ -1366,7 +1367,7 @@ object SparkContext extends Logging {
    * to pass their JARs to SparkContext. In most cases you can call jarOfObject(this) in
    * your driver program.
    */
-  def jarOfObject(obj: AnyRef): Seq[String] = jarOfClass(obj.getClass)
+  def jarOfObject(obj: AnyRef): Option[String] = jarOfClass(obj.getClass)
 
   /**
    * Creates a modified version of a SparkConf with the parameters that can be passed separately

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

@@ -33,7 +33,7 @@ class TaskContext(
   val attemptId: Long,
   val runningLocally: Boolean = false,
   @volatile var interrupted: Boolean = false,
-  private[spark] val taskMetrics: TaskMetrics = TaskMetrics.empty()
+  private[spark] val taskMetrics: TaskMetrics = TaskMetrics.empty
 ) extends Serializable {
 
   @deprecated("use partitionId", "0.8.1")

core/src/main/scala/org/apache/spark/annotation/AlphaComponent.java

@@ -19,7 +19,14 @@
 
 import java.lang.annotation.*;
 
-/** A new component of Spark which may have unstable API's. */
+/**
+ * A new component of Spark which may have unstable API's.
+ *
+ * NOTE: If there exists a Scaladoc comment that immediately precedes this annotation, the first
+ * line of the comment must be ":: AlphaComponent ::" with no trailing blank line. This is because
+ * of the known issue that Scaladoc displays only either the annotation or the comment, whichever
+ * comes first.
+ */
 @Retention(RetentionPolicy.RUNTIME)
 @Target({ElementType.TYPE, ElementType.FIELD, ElementType.METHOD, ElementType.PARAMETER,
         ElementType.CONSTRUCTOR, ElementType.LOCAL_VARIABLE, ElementType.PACKAGE})

core/src/main/scala/org/apache/spark/annotation/DeveloperApi.java

@@ -23,6 +23,11 @@
  * A lower-level, unstable API intended for developers.
  *
  * Developer API's might change or be removed in minor versions of Spark.
+ *
+ * NOTE: If there exists a Scaladoc comment that immediately precedes this annotation, the first
+ * line of the comment must be ":: DeveloperApi ::" with no trailing blank line. This is because
+ * of the known issue that Scaladoc displays only either the annotation or the comment, whichever
+ * comes first.
  */
 @Retention(RetentionPolicy.RUNTIME)
 @Target({ElementType.TYPE, ElementType.FIELD, ElementType.METHOD, ElementType.PARAMETER,

core/src/main/scala/org/apache/spark/annotation/Experimental.java

@@ -24,6 +24,11 @@
  *
  * Experimental API's might change or be removed in minor versions of Spark, or be adopted as
  * first-class Spark API's.
+ *
+ * NOTE: If there exists a Scaladoc comment that immediately precedes this annotation, the first
+ * line of the comment must be ":: Experimental ::" with no trailing blank line. This is because
+ * of the known issue that Scaladoc displays only either the annotation or the comment, whichever
+ * comes first.
  */
 @Retention(RetentionPolicy.RUNTIME)
 @Target({ElementType.TYPE, ElementType.FIELD, ElementType.METHOD, ElementType.PARAMETER,

core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala

@@ -196,7 +196,7 @@ object SparkSubmit {
         childArgs ++= appArgs.childArgs
       } else if (clusterManager == YARN) {
         for (arg <- appArgs.childArgs) {
-          childArgs += ("--args", arg)
+          childArgs += ("--arg", arg)
         }
       }
     }

core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala

@@ -116,6 +116,15 @@ private[spark] class SparkSubmitArguments(args: Array[String]) {
     if (args.length == 0) printUsageAndExit(-1)
     if (primaryResource == null) SparkSubmit.printErrorAndExit("Must specify a primary resource")
     if (mainClass == null) SparkSubmit.printErrorAndExit("Must specify a main class with --class")
+
+    if (master.startsWith("yarn")) {
+      val hasHadoopEnv = sys.env.contains("HADOOP_CONF_DIR") || sys.env.contains("YARN_CONF_DIR")
+      val testing = sys.env.contains("SPARK_TESTING")
+      if (!hasHadoopEnv && !testing) {
+        throw new Exception(s"When running with master '$master' " +
+          "either HADOOP_CONF_DIR or YARN_CONF_DIR must be set in the environment.")
+      }
+    }
   }
 
   override def toString =  {