Spark DAG有向无环图任务划分

1.DAG有向无环图
DAG（Directed Acyclic Graph）有向无环图是由点和线组成的拓扑图形，该图形具有方向，不会闭环。例如，DAG记录了RDD的转换过程和任务的阶段。

2）RDD任务切分中间分为：Application、Job、Stage和Task
（1）Application：初始化一个SparkContext即生成一个Application；
（2）Job：一个Action算子就会生成一个Job；
（3）Stage：Stage等于宽依赖的个数加1；
（4）Task：一个Stage阶段中，最后一个RDD的分区个数就是Task的个数。
注意：Application->Job->Stage->Task每一层都是1对n的关系。

private[scheduler] def handleJobSubmitted(jobId: Int,
      finalRDD: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties): Unit = {
    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: BarrierJobSlotsNumberCheckFailed =>
        // If jobId doesn't exist in the map, Scala coverts its value null to 0: Int automatically.
        val numCheckFailures = barrierJobIdToNumTasksCheckFailures.compute(jobId,
          (_: Int, value: Int) => value + 1)

        logWarning(s"Barrier stage in job $jobId requires ${e.requiredConcurrentTasks} slots, " +
          s"but only ${e.maxConcurrentTasks} are available. " +
          s"Will retry up to ${maxFailureNumTasksCheck - numCheckFailures + 1} more times")

        if (numCheckFailures <= maxFailureNumTasksCheck) {
          messageScheduler.schedule(
            new Runnable {
              override def run(): Unit = eventProcessLoop.post(JobSubmitted(jobId, finalRDD, func,
                partitions, callSite, listener, properties))
            },
            timeIntervalNumTasksCheck,
            TimeUnit.SECONDS
          )
          return
        } else {
          // Job failed, clear internal data.
          barrierJobIdToNumTasksCheckFailures.remove(jobId)
          listener.jobFailed(e)
          return
        }

在runjob中有一个createResultStage，创建最终的Stage，这个这个stage中，只有最后一个RDD的action算子才称为ResultStage
由最终的Stage找之前的血缘关系

/**
   * Get or create the list of parent stages for a given RDD.  The new Stages will be created with
   * the provided firstJobId.
   */
  private def getOrCreateParentStages(rdd: RDD[_], firstJobId: Int): List[Stage] = {
    getShuffleDependencies(rdd).map { shuffleDep =>
      getOrCreateShuffleMapStage(shuffleDep, firstJobId)
    }.toList
  }

getOrCreateShuffleMapStage

 /** Find ancestor shuffle dependencies that are not registered in shuffleToMapStage yet */
  private def getMissingAncestorShuffleDependencies(
      rdd: RDD[_]): ListBuffer[ShuffleDependency[_, _, _]] = {
    val ancestors = new ListBuffer[ShuffleDependency[_, _, _]]
    val visited = new HashSet[RDD[_]]
    // We are manually maintaining a stack here to prevent StackOverflowError
    // caused by recursively visiting
    val waitingForVisit = new ListBuffer[RDD[_]]
    waitingForVisit += rdd
    while (waitingForVisit.nonEmpty) {
      val toVisit = waitingForVisit.remove(0)
      if (!visited(toVisit)) {
        visited += toVisit
        getShuffleDependencies(toVisit).foreach { shuffleDep =>
          if (!shuffleIdToMapStage.contains(shuffleDep.shuffleId)) {
            ancestors.prepend(shuffleDep)
            waitingForVisit.prepend(shuffleDep.rdd)
          } // Otherwise, the dependency and its ancestors have already been registered.
        }
      }
    }
    ancestors
  }

getMissingAncestorShuffleDependencies 中获取之前的shuffleDependencies 血缘关系，依照shuffle过程来切分Stage