1. wordCount程序流程图示

   
   
   rdd.png

2. wordcount程序

sc.textFile("").
   flatMap(_.split("\t")).
    map((_,1)).
    reduceByKey(_+_).
    collect()

2.1 collect函数

  //将所有的结果集以数组的形式返回回来
  //this代表当前rdd，有了rdd其血缘关系就有了
  def collect(): Array[T] = withScope {
    val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray)
    Array.concat(results: _*)
  }

  def runJob[T, U: ClassTag](rdd: RDD[T], func: Iterator[T] => U): Array[U] = {
    //此时就决定rdd的task的数量
    runJob(rdd, func, 0 until rdd.partitions.length)
  }

  def runJob[T, U: ClassTag](
      rdd: RDD[T],
      func: Iterator[T] => U,
      partitions: Seq[Int]): Array[U] = {
    val cleanedFunc = clean(func)
    runJob(rdd, (ctx: TaskContext, it: Iterator[T]) => cleanedFunc(it), partitions)
  }

  def runJob[T, U: ClassTag](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int]): Array[U] = {
    val results = new Array[U](partitions.size)
    //func代表使用的是哪个算子
    //partitions代表多少分区
    runJob[T, U](rdd, func, partitions, (index, res) => results(index) = res)
    results
  } 

  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)
    //开始作业
    logInfo("Starting job: " + callSite.shortForm)
    if (conf.getBoolean("spark.logLineage", false)) {
      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
    }
    //此时dagScheduler和taskScheduler都准备好
    //此时已进入上图的第二阶段
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint()
  }

此时进入DAGScheduler类

  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
    //该方法将rdd、算子、分区等提交上去
    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
    }
  }

//Submit an action job to the scheduler
//提交action作业到scheduler上
  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.
    //分区数量
    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)
    }
    //jobId是什么
    val jobId = nextJobId.getAndIncrement()
    if (partitions.size == 0) {
      // Return immediately if the job is running 0 tasks
      //分区数量为0直接返回
      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.post(JobSubmitted(
      jobId, rdd, func2, partitions.toArray, callSite, waiter,
      SerializationUtils.clone(properties)))
    waiter
  }

private[spark] class JobWaiter[T](
    dagScheduler: DAGScheduler,
    val jobId: Int,
    totalTasks: Int,
    resultHandler: (Int, T) => Unit)
  extends JobListener with Logging{
  //让dagScheduler取消job
  def cancel() {
    dagScheduler.cancelJob(jobId, None)
  }

  //失败job给予提示
  override def jobFailed(exception: Exception): Unit = {
    if (!jobPromise.tryFailure(exception)) {
      logWarning("Ignore failure", exception)
    }
  }
}

根据debug程序可以知道jobSubmitted之后运行handleJobSubmitted

private[scheduler] def handleJobSubmitted(jobId: Int,
      finalRDD: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties) {
    //根据dag图对其拆分成多个stage，因为此时得到的是经过处理的RDD, 
    //所以先得到finalStage，需要从后向前推
    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.
      //根据结果创建stage也就是finalstage
      finalStage = createResultStage(finalRDD, func, partitions, jobId, callSite)
    } catch {
      case e: BarrierJobSlotsNumberCheckFailed =>
        logWarning(s"The job $jobId requires to run a barrier stage that requires more slots " +
          "than the total number of slots in the cluster currently.")
        // If jobId doesn't exist in the map, Scala coverts its value null to 0: Int automatically.
        val numCheckFailures = barrierJobIdToNumTasksCheckFailures.compute(jobId,
          new BiFunction[Int, Int, Int] {
            override def apply(key: Int, value: Int): Int = value + 1
          })
        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
        }
// Job submitted, clear internal data.
    barrierJobIdToNumTasksCheckFailures.remove(jobId)

    val job = new ActiveJob(jobId, finalStage, callSite, listener, properties)
    clearCacheLocs()
// 该行输出为Got job 0 (collect atSparkContextNewApp.scala:10) with 2 output partitions
    logInfo("Got job %s (%s) with %d output partitions".format(
      job.jobId, callSite.shortForm, partitions.length))
//该行输出为DAGScheduler: Final stage: ResultStage 1 (collect at SparkContextNewApp.scala:10)
    logInfo("Final stage: " + finalStage + " (" + finalStage.name + ")")
// 该行输出为Parents of final stage: List(ShuffleMapStage 0)
//得到其父stage
    logInfo("Parents of final stage: " + finalStage.parents)
// 该行输出为Missing parents: List(ShuffleMapStage 0)
    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))
    //提交最后一个stage
    submitStage(finalStage)
  }

    case e: Exception =>
    logWarning("Creating new stage failed due to exception - job: " + jobId, e)
    listener.jobFailed(e)
    return
}

private def submitStage(stage: Stage) {
    val jobId = activeJobForStage(stage)
    if (jobId.isDefined) {
      logDebug("submitStage(" + stage + ")")
      if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
        //查看其有无丢失的父节点
        val missing = getMissingParentStages(stage).sortBy(_.id)
        logDebug("missing: " + missing)
        if (missing.isEmpty) {
          logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
          //提交丢失的task
          submitMissingTasks(stage, jobId.get)
        } else {
          //不为空的话，进行迭代
         //对其父节点依次执行之前的流程
        //一个反向迭代过程
       //就可以将所有的stage都提交了
          for (parent <- missing) {
            submitStage(parent)
          }
          waitingStages += stage
        }
      }
    } else {
      abortStage(stage, "No active job for stage " + stage.id, None)
    }
  }

 private def submitMissingTasks(stage: Stage, jobId: Int){
  if (tasks.size > 0) {
      logInfo(s"Submitting ${tasks.size} missing tasks from $stage (${stage.rdd}) (first 15 " +
        s"tasks are for partitions ${tasks.take(15).map(_.partitionId)})")
    //此时stage已经被封装成一个一个的taskset
    //通过taskScheduler将taskset提交上去
    //对应上图的第二阶段提交到第三阶段  
    taskScheduler.submitTasks(new TaskSet(
        tasks.toArray, stage.id, stage.latestInfo.attemptNumber, jobId, properties))
    } else {
      // Because we posted SparkListenerStageSubmitted earlier, we should mark
      // the stage as completed here in case there are no tasks to run
      markStageAsFinished(stage, None)

      stage match {
        case stage: ShuffleMapStage =>
          logDebug(s"Stage ${stage} is actually done; " +
              s"(available: ${stage.isAvailable}," +
              s"available outputs: ${stage.numAvailableOutputs}," +
              s"partitions: ${stage.numPartitions})")
          markMapStageJobsAsFinished(stage)
        case stage : ResultStage =>
          logDebug(s"Stage ${stage} is actually done; (partitions: ${stage.numPartitions})")
      }
      submitWaitingChildStages(stage)
    }
}

override def submitTasks(taskSet: TaskSet) {
    val tasks = taskSet.tasks
    // 此时输出为Adding task set 0.0 with 2 tasks
    logInfo("Adding task set " + taskSet.id + " with " + tasks.length + " tasks")
    this.synchronized {
      val manager = createTaskSetManager(taskSet, maxTaskFailures)
      val stage = taskSet.stageId
      val stageTaskSets =
        taskSetsByStageIdAndAttempt.getOrElseUpdate(stage, new HashMap[Int, TaskSetManager])
      stageTaskSets(taskSet.stageAttemptId) = manager
      val conflictingTaskSet = stageTaskSets.exists { case (_, ts) =>
        ts.taskSet != taskSet && !ts.isZombie
      }
      if (conflictingTaskSet) {
        throw new IllegalStateException(s"more than one active taskSet for stage $stage:" +
          s" ${stageTaskSets.toSeq.map{_._2.taskSet.id}.mkString(",")}")
      }
      schedulableBuilder.addTaskSetManager(manager, manager.taskSet.properties)

      if (!isLocal && !hasReceivedTask) {
        starvationTimer.scheduleAtFixedRate(new TimerTask() {
          override def run() {
            if (!hasLaunchedTask) {
              logWarning("Initial job has not accepted any resources; " +
                "check your cluster UI to ensure that workers are registered " +
                "and have sufficient resources")
            } else {
              this.cancel()
            }
          }
        }, STARVATION_TIMEOUT_MS, STARVATION_TIMEOUT_MS)
      }
      hasReceivedTask = true
    }
    backend.reviveOffers()
  }