File tree

• .gitignore
• .rat-excludes
• .travis.yml
• NOTICE
• README.md
• assembly
  • pom.xml
• bagel/src
  • main/scala/org/apache/spark/bagel
    • Bagel.scala
  • test/scala/org/apache/spark/bagel
    • BagelSuite.scala
• bin
  • compute-classpath.sh
  • load-spark-env.sh
  • pyspark
  • run-example
  • spark-class2.cmd
  • spark-class
  • spark-shell
  • spark-submit
• conf
  • spark-defaults.conf.template
  • spark-env.sh.template
• core
  • pom.xml
  • src
    • main
      • java/org/apache/spark
        • api/java
          • StorageLevels.java
          • function
            • FlatMapFunction.java
            • FlatMapFunction2.java
        • package-info.java
      • resources/org/apache/spark/ui/static
        • webui.css
      • scala/org/apache/spark
        • Aggregator.scala
        • CacheManager.scala
        • ContextCleaner.scala
        • Dependency.scala
        • FutureAction.scala
        • HttpFileServer.scala
        • HttpServer.scala
        • InterruptibleIterator.scala
        • Logging.scala
        • MapOutputTracker.scala
        • Partition.scala
        • Partitioner.scala
        • SecurityManager.scala
        • SerializableWritable.scala
        • ShuffleFetcher.scala
        • SparkConf.scala
        • SparkContext.scala
        • SparkEnv.scala
        • SparkException.scala
        • SparkHadoopWriter.scala
        • SparkSaslClient.scala
        • SparkSaslServer.scala
        • TaskContext.scala
        • TaskEndReason.scala
        • TestUtils.scala
        • annotation
          • AlphaComponent.java
          • DeveloperApi.java
          • Experimental.java
        • api
          • java
            • JavaDoubleRDD.scala
            • JavaPairRDD.scala
            • JavaRDD.scala
            • JavaRDDLike.scala
            • JavaSparkContext.scala
            • JavaUtils.scala
          • python
            • PythonRDD.scala
        • broadcast
          • Broadcast.scala
          • BroadcastFactory.scala
          • BroadcastManager.scala
          • HttpBroadcast.scala
          • HttpBroadcastFactory.scala
          • TorrentBroadcast.scala
          • TorrentBroadcastFactory.scala
        • deploy
          • ApplicationDescription.scala
          • Client.scala
          • ClientArguments.scala
          • Command.scala
          • DeployMessage.scala
          • FaultToleranceTest.scala
          • JsonProtocol.scala
          • LocalSparkCluster.scala
          • SparkHadoopUtil.scala
          • SparkSubmit.scala
          • SparkSubmitArguments.scala
          • WebUI.scala
          • client
            • TestClient.scala
          • history
            • HistoryPage.scala
            • HistoryServer.scala
            • HistoryServerArguments.scala
          • master
            • ApplicationInfo.scala
            • LeaderElectionAgent.scala
            • Master.scala
            • ZooKeeperPersistenceEngine.scala
            • ui
              • ApplicationPage.scala
              • IndexPage.scala
              • MasterPage.scala
              • MasterWebUI.scala
          • worker
            • CommandUtils.scala
            • DriverRunner.scala
            • ExecutorRunner.scala
            • Worker.scala
            • WorkerArguments.scala
            • ui
              • IndexPage.scala
              • LogPage.scala
              • WorkerPage.scala
              • WorkerWebUI.scala
        • executor
          • CoarseGrainedExecutorBackend.scala
          • Executor.scala
          • ExecutorExitCode.scala
          • ExecutorSource.scala
          • ExecutorURLClassLoader.scala
          • TaskMetrics.scala
        • input
          • WholeTextFileInputFormat.scala
          • WholeTextFileRecordReader.scala
        • io
          • CompressionCodec.scala
        • metrics
          • MetricsConfig.scala
          • sink
            • ConsoleSink.scala
            • CsvSink.scala
            • GraphiteSink.scala
            • JmxSink.scala
            • MetricsServlet.scala
            • Sink.scala
          • source
            • JvmSource.scala
            • Source.scala
        • network
          • Connection.scala
          • ConnectionId.scala
          • ConnectionManager.scala
          • ConnectionManagerTest.scala
          • ReceiverTest.scala
          • SecurityMessage.scala
          • SenderTest.scala
          • netty
            • FileHeader.scala
        • package.scala
        • partial
          • BoundedDouble.scala
          • GroupedCountEvaluator.scala
          • PartialResult.scala
        • rdd
          • AsyncRDDActions.scala
          • CoGroupedRDD.scala
          • CoalescedRDD.scala
          • DoubleRDDFunctions.scala
          • EmptyRDD.scala
          • HadoopRDD.scala
          • JdbcRDD.scala
          • NewHadoopRDD.scala
          • OrderedRDDFunctions.scala
          • PairRDDFunctions.scala
          • PartitionPruningRDD.scala
          • PartitionerAwareUnionRDD.scala
          • PartitionwiseSampledRDD.scala
          • PipedRDD.scala
          • RDD.scala
          • SampledRDD.scala
          • ShuffledRDD.scala
          • SubtractedRDD.scala
          • UnionRDD.scala
          • ZippedPartitionsRDD.scala
          • ZippedRDD.scala
        • scheduler
          • ApplicationEventListener.scala
          • DAGScheduler.scala
          • DAGSchedulerEvent.scala
          • DAGSchedulerSource.scala
          • EventLoggingListener.scala
          • InputFormatInfo.scala
          • JobLogger.scala
          • JobResult.scala
          • JobWaiter.scala
          • LiveListenerBus.scala
          • Pool.scala
          • ReplayListenerBus.scala
          • ResultTask.scala
          • SchedulableBuilder.scala
          • SchedulingMode.scala
          • ShuffleMapTask.scala
          • SparkListener.scala
          • SparkListenerBus.scala
          • SplitInfo.scala
          • StageInfo.scala
          • Task.scala
          • TaskInfo.scala
          • TaskLocality.scala
          • TaskResultGetter.scala
          • TaskSchedulerImpl.scala
          • TaskSetManager.scala
          • cluster
            • CoarseGrainedSchedulerBackend.scala
            • SparkDeploySchedulerBackend.scala
            • mesos
              • CoarseMesosSchedulerBackend.scala
              • MesosSchedulerBackend.scala
        • serializer
          • JavaSerializer.scala
          • KryoSerializer.scala
          • Serializer.scala
          • SerializerManager.scala
        • storage
          • BlockFetcherIterator.scala
          • BlockId.scala
          • BlockManager.scala
          • BlockManagerId.scala
          • BlockManagerMaster.scala
          • BlockManagerMasterActor.scala
          • BlockManagerMessages.scala
          • BlockManagerSlaveActor.scala
          • BlockMessage.scala
          • BlockMessageArray.scala
          • BlockObjectWriter.scala
          • DiskBlockManager.scala
          • FileSegment.scala
          • MemoryStore.scala
          • PutResult.scala
          • ShuffleBlockManager.scala
          • StorageLevel.scala
          • StorageStatusListener.scala
          • StorageUtils.scala
          • TachyonBlockManager.scala
          • TachyonFileSegment.scala
          • TachyonStore.scala
          • ThreadingTest.scala
        • ui
          • JettyUtils.scala
          • Page.scala
          • SparkUI.scala
          • UIUtils.scala
          • WebUI.scala
          • env
            • EnvironmentPage.scala
            • EnvironmentTab.scala
            • EnvironmentUI.scala
          • exec
            • ExecutorsPage.scala
            • ExecutorsTab.scala
            • ExecutorsUI.scala
          • jobs
            • ExecutorSummary.scala
            • ExecutorTable.scala
            • IndexPage.scala
            • JobProgressListener.scala
            • JobProgressPage.scala
            • JobProgressTab.scala
            • JobProgressUI.scala
            • PoolPage.scala
            • PoolTable.scala
            • StagePage.scala
            • StageTable.scala
          • storage
            • BlockManagerUI.scala
            • IndexPage.scala
            • RDDPage.scala
            • StoragePage.scala
            • StorageTab.scala
        • util
          • AkkaUtils.scala
          • BoundedPriorityQueue.scala
          • ClosureCleaner.scala
          • CollectionsUtil.scala
          • Distribution.scala
          • FileLogger.scala
          • IndestructibleActorSystem.scala
          • JsonProtocol.scala
          • MetadataCleaner.scala
          • MutablePair.scala
          • NextIterator.scala
          • ParentClassLoader.scala
          • SizeEstimator.scala
          • StatCounter.scala
          • TimeStampedHashMap.scala
          • TimeStampedHashSet.scala
          • TimeStampedWeakValueHashMap.scala
          • Utils.scala
          • Vector.scala
          • collection
            • AppendOnlyMap.scala
            • BitSet.scala
            • ExternalAppendOnlyMap.scala
            • OpenHashMap.scala
            • OpenHashSet.scala
            • Utils.scala
          • random
            • Pseudorandom.scala
            • RandomSampler.scala
            • XORShiftRandom.scala
    • test
      • java/org/apache/spark
        • JavaAPISuite.java
      • scala/org/apache/spark
        • AccumulatorSuite.scala
        • AkkaUtilsSuite.scala
        • BroadcastSuite.scala
        • CacheManagerSuite.scala
        • CheckpointSuite.scala
        • ConnectionManagerSuite.scala
        • ContextCleanerSuite.scala
        • DriverSuite.scala
        • FailureSuite.scala
        • FileServerSuite.scala
        • FileSuite.scala
        • JobCancellationSuite.scala
        • MapOutputTrackerSuite.scala
        • PartitioningSuite.scala
        • PipedRDDSuite.scala
        • ShuffleSuite.scala
        • SparkContextInfoSuite.scala
        • SparkContextSchedulerCreationSuite.scala
        • deploy
          • JsonProtocolSuite.scala
          • SparkSubmitSuite.scala
          • worker
            • DriverRunnerTest.scala
            • ExecutorRunnerTest.scala
            • WorkerWatcherSuite.scala
        • executor
          • ExecutorURLClassLoaderSuite.scala
        • input
          • WholeTextFileRecordReaderSuite.scala
        • rdd
          • AsyncRDDActionsSuite.scala
          • PairRDDFunctionsSuite.scala
          • ParallelCollectionSplitSuite.scala
          • RDDSuite.scala
        • scheduler
          • DAGSchedulerSuite.scala
          • JobLoggerSuite.scala
          • SparkListenerSuite.scala
          • TaskSchedulerImplSuite.scala
          • TaskSetManagerSuite.scala
        • storage
          • BlockManagerSuite.scala
          • DiskBlockManagerSuite.scala
        • ui
          • UISuite.scala
          • jobs
            • JobProgressListenerSuite.scala
        • util
          • ClosureCleanerSuite.scala
          • JsonProtocolSuite.scala
          • NextIteratorSuite.scala
          • TimeStampedHashMapSuite.scala
          • UtilsSuite.scala
          • collection
            • BitSetSuite.scala
            • ExternalAppendOnlyMapSuite.scala
          • random
            • RandomSamplerSuite.scala
            • XORShiftRandomSuite.scala
• dev
  • audit-release
    • README.md
    • audit_release.py
    • maven_app_core
      • pom.xml
    • sbt_app_core/src/main/scala
      • SparkApp.scala
    • sbt_app_graphx/src/main/scala
      • GraphxApp.scala
    • sbt_app_streaming/src/main/scala
      • StreamingApp.scala
  • check-license
  • create-release
    • create-release.sh
  • merge_spark_pr.py
  • run-tests
  • scalastyle
• docker/spark-test/base
  • Dockerfile
• docs
  • README.md
  • _config.yml
  • _layouts
    • global.html
  • _plugins
    • copy_api_dirs.rb
  • api.md
  • building-with-maven.md
  • cluster-overview.md
  • configuration.md
  • css
    • api-docs.css
  • graphx-programming-guide.md
  • index.md
  • java-programming-guide.md
  • js
    • api-docs.js
    • main.js
  • mllib-basics.md
  • mllib-classification-regression.md
  • mllib-clustering.md
  • mllib-collaborative-filtering.md
  • mllib-decision-tree.md
  • mllib-dimensionality-reduction.md
  • mllib-guide.md
  • mllib-linear-algebra.md
  • mllib-linear-methods.md
  • mllib-naive-bayes.md
  • mllib-optimization.md
  • monitoring.md
  • python-programming-guide.md
  • quick-start.md
  • running-on-yarn.md
  • scala-programming-guide.md
  • spark-standalone.md
  • sql-programming-guide.md
  • streaming-custom-receivers.md
  • streaming-programming-guide.md
  • tuning.md
• ec2
  • spark_ec2.py
• examples
  • pom.xml
  • src/main
    • java/org/apache/spark
      • examples
        • JavaHdfsLR.java
        • JavaKMeans.java
        • JavaLogQuery.java
        • JavaPageRank.java
        • JavaTC.java
        • JavaWordCount.java
        • sql
          • JavaSparkSQL.java
      • mllib/examples
        • JavaALS.java
        • JavaKMeans.java
        • JavaLR.java
    • resources
      • kv1.txt
      • people.txt
    • scala/org/apache/spark
      • examples
        • BroadcastTest.scala
        • CassandraCQLTest.scala
        • CassandraTest.scala
        • ExceptionHandlingTest.scala
        • GroupByTest.scala
        • HBaseTest.scala
        • HdfsTest.scala
        • LocalALS.scala
        • LocalFileLR.scala
        • LocalKMeans.scala
        • LocalLR.scala
        • LocalPi.scala
        • LogQuery.scala
        • MultiBroadcastTest.scala
        • SimpleSkewedGroupByTest.scala
        • SkewedGroupByTest.scala
        • SparkALS.scala
        • SparkHdfsLR.scala
        • SparkKMeans.scala
        • SparkLR.scala
        • SparkPageRank.scala
        • SparkPi.scala
        • SparkTC.scala
        • SparkTachyonHdfsLR.scala
        • SparkTachyonPi.scala
        • bagel
          • WikipediaPageRankStandalone.scala
        • mllib
          • SparkSVD.scala
          • TallSkinnyPCA.scala
          • TallSkinnySVD.scala
      • sql/examples
        • HiveFromSpark.scala
        • RDDRelation.scala
      • streaming/examples
        • ActorWordCount.scala
        • FlumeEventCount.scala
        • HdfsWordCount.scala
        • KafkaWordCount.scala
        • MQTTWordCount.scala
        • NetworkWordCount.scala
        • QueueStream.scala
        • RawNetworkGrep.scala
        • RecoverableNetworkWordCount.scala
        • StatefulNetworkWordCount.scala
        • TwitterAlgebirdCMS.scala
        • TwitterAlgebirdHLL.scala
        • TwitterPopularTags.scala
        • ZeroMQWordCount.scala
        • clickstream
          • PageViewGenerator.scala
          • PageViewStream.scala
• external
  • flume/src