Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver1

Author: scwf

LICENSE

@@ -712,18 +712,6 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-========================================================================
-For colt:
-========================================================================
-
-Copyright (c) 1999 CERN - European Organization for Nuclear Research.
-Permission to use, copy, modify, distribute and sell this software and its documentation for any purpose is hereby granted without fee, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation. CERN makes no representations about the suitability of this software for any purpose. It is provided "as is" without expressed or implied warranty.
-
-Packages hep.aida.*
-
-Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, Andreas Pfeiffer, and others. Check the FreeHEP home page for more info. Permission to use and/or redistribute this work is granted under the terms of the LGPL License, with the exception that any usage related to military applications is expressly forbidden. The software and documentation made available under the terms of this license are provided with no warranty.
-
-
 ========================================================================
 For SnapTree:
 ========================================================================

README.md

@@ -84,7 +84,7 @@ 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-spark.html#specifying-the-hadoop-version)
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-with-maven.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

@@ -146,6 +146,10 @@
                     <exclude>com/google/common/base/Present*</exclude>
                   </excludes>
                 </relocation>
+                <relocation>
+                  <pattern>org.apache.commons.math3</pattern>
+                  <shadedPattern>org.spark-project.commons.math3</shadedPattern>
+                </relocation>
               </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />

core/pom.xml

@@ -85,8 +85,6 @@
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-math3</artifactId>
-      <version>3.3</version>
-      <scope>test</scope>
     </dependency>
     <dependency>
       <groupId>com.google.code.findbugs</groupId>
@@ -162,10 +160,6 @@
       <artifactId>json4s-jackson_${scala.binary.version}</artifactId>
       <version>3.2.10</version>
     </dependency>
-    <dependency>
-      <groupId>colt</groupId>
-      <artifactId>colt</artifactId>
-    </dependency>
     <dependency>
       <groupId>org.apache.mesos</groupId>
       <artifactId>mesos</artifactId>
@@ -247,6 +241,11 @@
         </exclusion>
       </exclusions>
     </dependency>
+    <dependency>
+      <groupId>org.seleniumhq.selenium</groupId>
+      <artifactId>selenium-java</artifactId>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>org.scalatest</groupId>
       <artifactId>scalatest_${scala.binary.version}</artifactId>

core/src/main/java/org/apache/spark/JobExecutionStatus.java

@@ -0,0 +1,25 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark;
+
+public enum JobExecutionStatus {
+  RUNNING,
+  SUCCEEDED,
+  FAILED,
+  UNKNOWN
+}

core/src/main/java/org/apache/spark/SparkJobInfo.java

@@ -0,0 +1,30 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark;
+
+/**
+ * Exposes information about Spark Jobs.
+ *
+ * This interface is not designed to be implemented outside of Spark.  We may add additional methods
+ * which may break binary compatibility with outside implementations.
+ */
+public interface SparkJobInfo {
+  int jobId();
+  int[] stageIds();
+  JobExecutionStatus status();
+}

core/src/main/java/org/apache/spark/SparkStageInfo.java

@@ -0,0 +1,34 @@
+/*
+ * 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.
+ */
+
+package org.apache.spark;
+
+/**
+ * Exposes information about Spark Stages.
+ *
+ * This interface is not designed to be implemented outside of Spark.  We may add additional methods
+ * which may break binary compatibility with outside implementations.
+ */
+public interface SparkStageInfo {
+  int stageId();
+  int currentAttemptId();
+  String name();
+  int numTasks();
+  int numActiveTasks();
+  int numCompletedTasks();
+  int numFailedTasks();
+}

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

@@ -71,15 +71,13 @@ static void unset() {
   /**
    * Add a (Java friendly) listener to be executed on task completion.
    * This will be called in all situation - success, failure, or cancellation.
-   * <p/>
    * An example use is for HadoopRDD to register a callback to close the input stream.
    */
   public abstract TaskContext addTaskCompletionListener(TaskCompletionListener listener);
 
   /**
    * Add a listener in the form of a Scala closure to be executed on task completion.
    * This will be called in all situations - success, failure, or cancellation.
-   * <p/>
    * An example use is for HadoopRDD to register a callback to close the input stream.
    */
   public abstract TaskContext addTaskCompletionListener(final Function1<TaskContext, Unit> f);

core/src/main/java/org/apache/spark/api/java/function/PairFunction.java

@@ -22,7 +22,8 @@
 import scala.Tuple2;
 
 /**
- * A function that returns key-value pairs (Tuple2<K, V>), and can be used to construct PairRDDs.
+ * A function that returns key-value pairs (Tuple2&lt;K, V&gt;), and can be used to
+ * construct PairRDDs.
  */
 public interface PairFunction<T, K, V> extends Serializable {
   public Tuple2<K, V> call(T t) throws Exception;

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

@@ -26,7 +26,6 @@ import java.util.concurrent.atomic.AtomicInteger
 import java.util.{Properties, UUID}
 import java.util.UUID.randomUUID
 import scala.collection.{Map, Set}
-import scala.collection.JavaConversions._
 import scala.collection.generic.Growable
 import scala.collection.mutable.HashMap
 import scala.reflect.{ClassTag, classTag}
@@ -51,6 +50,7 @@ import org.apache.spark.scheduler.cluster.mesos.{CoarseMesosSchedulerBackend, Me
 import org.apache.spark.scheduler.local.LocalBackend
 import org.apache.spark.storage._
 import org.apache.spark.ui.SparkUI
+import org.apache.spark.ui.jobs.JobProgressListener
 import org.apache.spark.util.{CallSite, ClosureCleaner, MetadataCleaner, MetadataCleanerType, TimeStampedWeakValueHashMap, Utils}
 
 /**
@@ -61,7 +61,7 @@ import org.apache.spark.util.{CallSite, ClosureCleaner, MetadataCleaner, Metadat
  *   this config overrides the default configs as well as system properties.
  */
 
-class SparkContext(config: SparkConf) extends Logging {
+class SparkContext(config: SparkConf) extends SparkStatusAPI with Logging {
 
   // This is used only by YARN for now, but should be relevant to other cluster types (Mesos,
   // etc) too. This is typically generated from InputFormatInfo.computePreferredLocations. It
@@ -224,10 +224,15 @@ class SparkContext(config: SparkConf) extends Logging {
   private[spark] val metadataCleaner =
     new MetadataCleaner(MetadataCleanerType.SPARK_CONTEXT, this.cleanup, conf)
 
-  // Initialize the Spark UI, registering all associated listeners
+
+  private[spark] val jobProgressListener = new JobProgressListener(conf)
+  listenerBus.addListener(jobProgressListener)
+
+  // Initialize the Spark UI
   private[spark] val ui: Option[SparkUI] =
     if (conf.getBoolean("spark.ui.enabled", true)) {
-      Some(new SparkUI(this))
+      Some(SparkUI.createLiveUI(this, conf, listenerBus, jobProgressListener,
+        env.securityManager,appName))
     } else {
       // For tests, do not enable the UI
       None
@@ -854,69 +859,6 @@ class SparkContext(config: SparkConf) extends Logging {
   /** The version of Spark on which this application is running. */
   def version = SPARK_VERSION
 
-  /**
-   * Return a map from the slave to the max memory available for caching and the remaining
-   * memory available for caching.
-   */
-  def getExecutorMemoryStatus: Map[String, (Long, Long)] = {
-    env.blockManager.master.getMemoryStatus.map { case(blockManagerId, mem) =>
-      (blockManagerId.host + ":" + blockManagerId.port, mem)
-    }
-  }
-
-  /**
-   * :: DeveloperApi ::
-   * Return information about what RDDs are cached, if they are in mem or on disk, how much space
-   * they take, etc.
-   */
-  @DeveloperApi
-  def getRDDStorageInfo: Array[RDDInfo] = {
-    val rddInfos = persistentRdds.values.map(RDDInfo.fromRdd).toArray
-    StorageUtils.updateRddInfo(rddInfos, getExecutorStorageStatus)
-    rddInfos.filter(_.isCached)
-  }
-
-  /**
-   * Returns an immutable map of RDDs that have marked themselves as persistent via cache() call.
-   * Note that this does not necessarily mean the caching or computation was successful.
-   */
-  def getPersistentRDDs: Map[Int, RDD[_]] = persistentRdds.toMap
-
-  /**
-   * :: DeveloperApi ::
-   * Return information about blocks stored in all of the slaves
-   */
-  @DeveloperApi
-  def getExecutorStorageStatus: Array[StorageStatus] = {
-    env.blockManager.master.getStorageStatus
-  }
-
-  /**
-   * :: DeveloperApi ::
-   * Return pools for fair scheduler
-   */
-  @DeveloperApi
-  def getAllPools: Seq[Schedulable] = {
-    // TODO(xiajunluan): We should take nested pools into account
-    taskScheduler.rootPool.schedulableQueue.toSeq
-  }
-
-  /**
-   * :: DeveloperApi ::
-   * Return the pool associated with the given name, if one exists
-   */
-  @DeveloperApi
-  def getPoolForName(pool: String): Option[Schedulable] = {
-    Option(taskScheduler.rootPool.schedulableNameToSchedulable.get(pool))
-  }
-
-  /**
-   * Return current scheduling mode
-   */
-  def getSchedulingMode: SchedulingMode.SchedulingMode = {
-    taskScheduler.schedulingMode
-  }
-
   /**
    * Clear the job's list of files added by `addFile` so that they do not get downloaded to
    * any new nodes.