Spark satge划分

 // 当遇到action算子 ，触发job提交
 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)
    ThreadUtils.awaitReady(waiter.completionFuture, Duration.Inf)
    waiter.completionFuture.value.get match {
      case scala.util.Success(_) =>
        logInfo("Job %d finished: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
      case scala.util.Failure(exception) =>
        logInfo("Job %d failed: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
        // SPARK-8644: Include user stack trace in exceptions coming from DAGScheduler.
        val callerStackTrace = Thread.currentThread().getStackTrace.tail
        exception.setStackTrace(exception.getStackTrace ++ callerStackTrace)
        throw exception
    }
  }
  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] = {
    // Check to make sure we are not launching a task on a partition that does not exist.
    val maxPartitions = rdd.partitions.length
    partitions.find(p => p >= maxPartitions || p < 0).foreach { p =>
      throw new IllegalArgumentException(
        "Attempting to access a non-existent partition: " + p + ". " +
          "Total number of partitions: " + maxPartitions)
    }

    val jobId = nextJobId.getAndIncrement()
    if (partitions.size == 0) {
      // Return immediately if the job is running 0 tasks
      return new JobWaiter[U](this, jobId, 0, resultHandler)
    }

    assert(partitions.size > 0)
    val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
    val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
    /** eventProcessLoop是一个DAGSchedulerEventProcessLoop(this)对象，可以把DAGSchedulerEventProcessLoop
    理解成DAGScheduler的对外的功能接口。它对外隐藏了自己内部实现的细节。无论是内部还是外部消息，DAGScheduler可以共用同一消息处理代码，
    逻辑清晰，处理方式统一。
     eventProcessLoop接收各种消息并进行处理，处理的逻辑在其doOnReceive方法中
     **/
    eventProcessLoop.post(JobSubmitted(
      jobId, rdd, func2, partitions.toArray, callSite, waiter,
      SerializationUtils.clone(properties)))
    waiter
  }
  private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
     // 当提交的是JobSubmitted，便会通过 dagScheduler.handleJobSubmitted处理此事件。
    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)

    case StageCancelled(stageId, reason) =>
      dagScheduler.handleStageCancellation(stageId, reason)

    case JobCancelled(jobId, reason) =>
      dagScheduler.handleJobCancellation(jobId, reason)

    case JobGroupCancelled(groupId) =>
      dagScheduler.handleJobGroupCancelled(groupId)

    case AllJobsCancelled =>
      dagScheduler.doCancelAllJobs()

    case ExecutorAdded(execId, host) =>
      dagScheduler.handleExecutorAdded(execId, host)

    case ExecutorLost(execId, reason) =>
      val workerLost = reason match {
        case SlaveLost(_, true) => true
        case _ => false
      }
      dagScheduler.handleExecutorLost(execId, workerLost)

    case WorkerRemoved(workerId, host, message) =>
      dagScheduler.handleWorkerRemoved(workerId, host, message)
... 略
 /** 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)
    }
  }

 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.
      // Stage划分过程是从最后一个Stage开始往前执行的，最后一个Stage的类型是ResultStage
      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))

    if (isContinuous) {
      // TODO: make "spark.streaming.totalShuffleNumber" as a val string
      val value = properties.getProperty("spark.streaming.totalShuffleNumber")
      assert(value != null && value.nonEmpty, "totalShuffleNumber must be set!")
      // For continuou processing submit, in this case, we submit all stages at once
      // instead of the origin submission in which child stages must be submitted only
      // after parent stages complete success
      submitAllStagesOnce(finalStage)
    } else {
      submitStage(finalStage)
    }
  }

 private def createResultStage(
      rdd: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      jobId: Int,
      callSite: CallSite): ResultStage = {
    val parents = getOrCreateParentStages(rdd, jobId)
    val id = nextStageId.getAndIncrement()
    val stage = new ResultStage(id, rdd, func, partitions, parents, jobId, callSite)
    stageIdToStage(id) = stage
    updateJobIdStageIdMaps(jobId, stage)
    stage
  }
   private def getOrCreateParentStages(rdd: RDD[_], firstJobId: Int): List[Stage] = {
    getShuffleDependencies(rdd).map { shuffleDep =>
      getOrCreateShuffleMapStage(shuffleDep, firstJobId)
    }.toList
  }
  private def getOrCreateShuffleMapStage(
      shuffleDep: ShuffleDependency[_, _, _],
      firstJobId: Int): ShuffleMapStage = {
    shuffleIdToMapStage.get(shuffleDep.shuffleId) match {
      case Some(stage) =>
        stage

      case None =>
        // Create stages for all missing ancestor shuffle dependencies.
        getMissingAncestorShuffleDependencies(shuffleDep.rdd).foreach { dep =>
          // Even though getMissingAncestorShuffleDependencies only returns shuffle dependencies
          // that were not already in shuffleIdToMapStage, it's possible that by the time we
          // get to a particular dependency in the foreach loop, it's been added to
          // shuffleIdToMapStage by the stage creation process for an earlier dependency. See
          // SPARK-13902 for more information.
          if (!shuffleIdToMapStage.contains(dep.shuffleId)) {
            createShuffleMapStage(dep, firstJobId)
          }
        }
        // Finally, create a stage for the given shuffle dependency.
        createShuffleMapStage(shuffleDep, firstJobId)
    }
  }
/** Find ancestor shuffle dependencies that are not registered in shuffleToMapStage yet 

通过给定的RDD返回其依赖的Stage集合。通过RDD每一个依赖进行遍历，遇到窄依赖就继续往前遍历，
遇到ShuffleDependency便通过getShuffleMapStage返回一个ShuffleMapStage对象添加到父Stage列表中。
可见，这里的parentStage是Stage直接依赖的父stages（parentStage也有自己的parentStage），而不是整个DAG的所有stages
*/
  private def getMissingAncestorShuffleDependencies(
      rdd: RDD[_]): ArrayStack[ShuffleDependency[_, _, _]] = {
    val ancestors = new ArrayStack[ShuffleDependency[_, _, _]]
    val visited = new HashSet[RDD[_]]
    // We are manually maintaining a stack here to prevent StackOverflowError
    // caused by recursively visiting
    val waitingForVisit = new ArrayStack[RDD[_]]
    waitingForVisit.push(rdd)
    while (waitingForVisit.nonEmpty) {
      val toVisit = waitingForVisit.pop()
      if (!visited(toVisit)) {
        visited += toVisit
        getShuffleDependencies(toVisit).foreach { shuffleDep =>
          if (!shuffleIdToMapStage.contains(shuffleDep.shuffleId)) {
            ancestors.push(shuffleDep)
            waitingForVisit.push(shuffleDep.rdd)
          } // Otherwise, the dependency and its ancestors have already been registered.
        }
      }
    }
    ancestors
  }