RDD execute flow

  class BroadcastSuite extends SparkFunSuite with LocalSparkContext {
 
  test("Using TorrentBroadcast locally") {
    sc = new SparkContext("local", "test")
    val list = List[Int](1, 2, 3, 4)
    val broadcast = sc.broadcast(list)
    val results = sc.parallelize(1 to 2).map(x => (x, broadcast.value.sum))
    assert(results.collect().toSet === Set((1, 10), (2, 10)))
  }

  val broadcast = sc.broadcast(list)
 
  def broadcast[T: ClassTag](value: T): Broadcast[T] = {
    assertNotStopped()
    require(!classOf[RDD[_]].isAssignableFrom(classTag[T].runtimeClass),
      "Can not directly broadcast RDDs; instead, call collect() and broadcast the result.")
    val bc = env.broadcastManager.newBroadcast[T](value, isLocal)
    val callSite = getCallSite
    logInfo("Created broadcast " + bc.id + " from " + callSite.shortForm)
    cleaner.foreach(_.registerBroadcastForCleanup(bc))
    bc
  }

  def newBroadcast[T: ClassTag](value_ : T, isLocal: Boolean): Broadcast[T] = {
    broadcastFactory.newBroadcast[T](value_, isLocal, nextBroadcastId.getAndIncrement())
  }

  override def newBroadcast[T: ClassTag](value_ : T, isLocal: Boolean, id: Long): Broadcast[T] = {
    new TorrentBroadcast[T](value_, id)
  }

  //lazy keyword is good for here, transfer the data to block store
  @transient private lazy val _value: T = readBroadcastBlock()
  //read the data from block store
  private val numBlocks: Int = writeBlocks(obj)
 
  override protected def getValue() = {
    _value
  }

  val results = sc.parallelize(1 to 2).map(x => (x, broadcast.value.sum))
 
  def parallelize[T: ClassTag](
      seq: Seq[T],
      numSlices: Int = defaultParallelism): RDD[T] = withScope {
    assertNotStopped()
    new ParallelCollectionRDD[T](this, seq, numSlices, Map[Int, Seq[String]]())
  }
 
  def map[U: ClassTag](f: T => U): RDD[U] = withScope {
    val cleanF = sc.clean(f)
    new MapPartitionsRDD[U, T](this, (context, pid, iter) => iter.map(cleanF))
  }

  results.collect()
 
  //Here is the really area for RDD execute
  def collect(): Array[T] = withScope {
    val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray)
    Array.concat(results: _*)
  }

  /**
   * Run a function on a given set of partitions in an RDD and pass the results to the given
   * handler function. This is the main entry point for all actions in Spark.
   */
  def runJob[T, U: ClassTag](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      resultHandler: (Int, U) => Unit): Unit = {
    if (stopped.get()) {
      throw new IllegalStateException("SparkContext has been shutdown")
    }
    val callSite = getCallSite
    val cleanedFunc = clean(func)
    logInfo("Starting job: " + callSite.shortForm)
    if (conf.getBoolean("spark.logLineage", false)) {
      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
    }
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint()
  }

  def runJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): Unit = {
    val start = System.nanoTime
    val waiter = submitJob(rdd, func, partitions, callSite, resultHandler, properties)

  def submitJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): JobWaiter[U] = {
    //......
    val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
    val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
    //Post a JobSubmitted event to DAGSchedulerEventProcessLoop
    eventProcessLoop.post(JobSubmitted(
      jobId, rdd, func2, partitions.toArray, callSite, waiter,
      SerializationUtils.clone(properties)))
    waiter
  }

private[scheduler] class DAGSchedulerEventProcessLoop(dagScheduler: DAGScheduler)
  extends EventLoop[DAGSchedulerEvent]("dag-scheduler-event-loop") with Logging {
 
  private[this] val timer = dagScheduler.metricsSource.messageProcessingTimer
 
  /**
   * The main event loop of the DAG scheduler.
   */
  override def onReceive(event: DAGSchedulerEvent): Unit = {
    val timerContext = timer.time()
    try {
      doOnReceive(event)
    } finally {
      timerContext.stop()
    }
  }
 
  private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
    case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
      dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)
 
    case MapStageSubmitted(jobId, dependency, callSite, listener, properties) =>
      dagScheduler.handleMapStageSubmitted(jobId, dependency, callSite, listener, properties)

  private[scheduler] def handleJobSubmitted(jobId: Int,
      finalRDD: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties) {
    var finalStage: ResultStage = null
    try {
      // New stage creation may throw an exception if, for example, jobs are run on a
      // HadoopRDD whose underlying HDFS files have been deleted.
      finalStage = createResultStage(finalRDD, func, partitions, jobId, callSite)
    } catch {
      case e: Exception =>
        logWarning("Creating new stage failed due to exception - job: " + jobId, e)
        listener.jobFailed(e)
        return
    }
 
    val job = new ActiveJob(jobId, finalStage, callSite, listener, properties)
    clearCacheLocs()
    logInfo("Got job %s (%s) with %d output partitions".format(
      job.jobId, callSite.shortForm, partitions.length))
    logInfo("Final stage: " + finalStage + " (" + finalStage.name + ")")
    logInfo("Parents of final stage: " + finalStage.parents)
    logInfo("Missing parents: " + getMissingParentStages(finalStage))
 
    val jobSubmissionTime = clock.getTimeMillis()
    jobIdToActiveJob(jobId) = job
    activeJobs += job
    finalStage.setActiveJob(job)
    val stageIds = jobIdToStageIds(jobId).toArray
    val stageInfos = stageIds.flatMap(id => stageIdToStage.get(id).map(_.latestInfo))
    listenerBus.post(
      SparkListenerJobStart(job.jobId, jobSubmissionTime, stageInfos, properties))
    submitStage(finalStage)
  }

  /** Submits stage, but first recursively submits any missing parents. */
  private def submitStage(stage: Stage) {
    val jobId = activeJobForStage(stage)
    if (jobId.isDefined) {
      logDebug("submitStage(" + stage + ")")
      if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
        val missing = getMissingParentStages(stage).sortBy(_.id)
        logDebug("missing: " + missing)
        if (missing.isEmpty) {
          logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
          submitMissingTasks(stage, jobId.get)
        } else {
          for (parent <- missing) {
            submitStage(parent)
          }
          waitingStages += stage
        }
      }
    } else {
      abortStage(stage, "No active job for stage " + stage.id, None)
    }
  }

  /** Called when stage's parents are available and we can now do its task. */
  private def submitMissingTasks(stage: Stage, jobId: Int) {
    logDebug("submitMissingTasks(" + stage + ")")
    // Get our pending tasks and remember them in our pendingTasks entry
    stage.pendingPartitions.clear()
 
    // First figure out the indexes of partition ids to compute.
    val partitionsToCompute: Seq[Int] = stage.findMissingPartitions()
 
    // Use the scheduling pool, job group, description, etc. from an ActiveJob associated
    // with this Stage
    val properties = jobIdToActiveJob(jobId).properties
 
    //......
 
    val tasks: Seq[Task[_]] = try {
      stage match {
        case stage: ShuffleMapStage =>
          partitionsToCompute.map { id =>
            val locs = taskIdToLocations(id)
            val part = stage.rdd.partitions(id)
            new ShuffleMapTask(stage.id, stage.latestInfo.attemptId,
              taskBinary, part, locs, stage.latestInfo.taskMetrics, properties, Option(jobId),
              Option(sc.applicationId), sc.applicationAttemptId)
          }
 
        case stage: ResultStage =>
          partitionsToCompute.map { id =>
            val p: Int = stage.partitions(id)
            val part = stage.rdd.partitions(p)
            val locs = taskIdToLocations(id)
            new ResultTask(stage.id, stage.latestInfo.attemptId,
              taskBinary, part, locs, id, properties, stage.latestInfo.taskMetrics,
              Option(jobId), Option(sc.applicationId), sc.applicationAttemptId)
          }
      }
    } catch {
      case NonFatal(e) =>
        abortStage(stage, s"Task creation failed: $e\n${Utils.exceptionString(e)}", Some(e))
        runningStages -= stage
        return
    }
 
    if (tasks.size > 0) {
      logInfo("Submitting " + tasks.size + " missing tasks from " + stage + " (" + stage.rdd + ")")
      stage.pendingPartitions ++= tasks.map(_.partitionId)
      logDebug("New pending partitions: " + stage.pendingPartitions)
      taskScheduler.submitTasks(new TaskSet(
        tasks.toArray, stage.id, stage.latestInfo.attemptId, jobId, properties))
      stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
    } else {

/**
 * Calls to [[LocalSchedulerBackend]] are all serialized through LocalEndpoint. Using an
 * RpcEndpoint makes the calls on [[LocalSchedulerBackend]] asynchronous, which is necessary
 * to prevent deadlock between [[LocalSchedulerBackend]] and the [[TaskSchedulerImpl]].
 */
private[spark] class LocalEndpoint(
    override val rpcEnv: RpcEnv,
    userClassPath: Seq[URL],
    scheduler: TaskSchedulerImpl,
    executorBackend: LocalSchedulerBackend,
    private val totalCores: Int)
  extends ThreadSafeRpcEndpoint with Logging {
 
  override def receive: PartialFunction[Any, Unit] = {
    case ReviveOffers =>
      reviveOffers()
 
    case StatusUpdate(taskId, state, serializedData) =>
      scheduler.statusUpdate(taskId, state, serializedData)
      if (TaskState.isFinished(state)) {
        freeCores += scheduler.CPUS_PER_TASK
        reviveOffers()
      }
 
    case KillTask(taskId, interruptThread) =>
      executor.killTask(taskId, interruptThread)
  }

 
  def reviveOffers() {
    val offers = IndexedSeq(new WorkerOffer(localExecutorId, localExecutorHostname, freeCores))
    for (task <- scheduler.resourceOffers(offers).flatten) {
      freeCores -= scheduler.CPUS_PER_TASK
      executor.launchTask(executorBackend, taskId = task.taskId, attemptNumber = task.attemptNumber,
        task.name, task.serializedTask)
    }
  }

    override def run(): Unit = {
      val threadMXBean = ManagementFactory.getThreadMXBean
      val taskMemoryManager = new TaskMemoryManager(env.memoryManager, taskId)
      val deserializeStartTime = System.currentTimeMillis()
      val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
        threadMXBean.getCurrentThreadCpuTime
      } else 0L
      Thread.currentThread.setContextClassLoader(replClassLoader)
      val ser = env.closureSerializer.newInstance()
      logInfo(s"Running $taskName (TID $taskId)")
      execBackend.statusUpdate(taskId, TaskState.RUNNING, EMPTY_BYTE_BUFFER)
      var taskStart: Long = 0
      var taskStartCpu: Long = 0
      startGCTime = computeTotalGcTime()
 
      try {
        val (taskFiles, taskJars, taskProps, taskBytes) =
          Task.deserializeWithDependencies(serializedTask)
 
        // Must be set before updateDependencies() is called, in case fetching dependencies
        // requires access to properties contained within (e.g. for access control).
        Executor.taskDeserializationProps.set(taskProps)
 
        updateDependencies(taskFiles, taskJars)
        task = ser.deserialize[Task[Any]](taskBytes, Thread.currentThread.getContextClassLoader)
        task.localProperties = taskProps
        task.setTaskMemoryManager(taskMemoryManager)
 
        // If this task has been killed before we deserialized it, let's quit now. Otherwise,
        // continue executing the task.
        if (killed) {
          // Throw an exception rather than returning, because returning within a try{} block
          // causes a NonLocalReturnControl exception to be thrown. The NonLocalReturnControl
          // exception will be caught by the catch block, leading to an incorrect ExceptionFailure
          // for the task.
          throw new TaskKilledException
        }
 
        logDebug("Task " + taskId + "'s epoch is " + task.epoch)
        env.mapOutputTracker.updateEpoch(task.epoch)
 
        // Run the actual task and measure its runtime.
        taskStart = System.currentTimeMillis()
        taskStartCpu = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
          threadMXBean.getCurrentThreadCpuTime
        } else 0L
        var threwException = true
        val value = try {
          val res = task.run(
            taskAttemptId = taskId,
            attemptNumber = attemptNumber,
            metricsSystem = env.metricsSystem)
          threwException = false
          res

  override def runTask(context: TaskContext): U = {
    // Deserialize the RDD and the func using the broadcast variables.
    val threadMXBean = ManagementFactory.getThreadMXBean
    val deserializeStartTime = System.currentTimeMillis()
    val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
      threadMXBean.getCurrentThreadCpuTime
    } else 0L
    val ser = SparkEnv.get.closureSerializer.newInstance()
    val (rdd, func) = ser.deserialize[(RDD[T], (TaskContext, Iterator[T]) => U)](
      ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
    _executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime
    _executorDeserializeCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
      threadMXBean.getCurrentThreadCpuTime - deserializeStartCpuTime
    } else 0L
 
    func(context, rdd.iterator(partition, context))
  }