Spark源码系列之Spark内核——Job提交

在介绍Job提交之前，我们先看下Job提交的过程：

看完上图之后，大家应该会有一个比较直观的了解，同时也便于对整个流程的把握。

DAGScheduler

在RDD触发Action算子时，会调用sc.runJob()，以count算子为例：

def count(): Long = sc.runJob(this, Utils.getIteratorSize _).sum

在SparkContext的runJob()中，会调用DAGScheduler.runJob()（由于源代码比较多，我多会有省略的形式，只贴出关键部分的代码）：

def runJob[T, U: ClassTag](
  rdd: RDD[T],
  func: (TaskContext, Iterator[T]) => U,
  partitions: Seq[Int],
  resultHandler: (Int, U) => Unit): Unit = {
…………
	dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
	progressBar.foreach(_.finishAll())
	rdd.doCheckpoint()
}

DAGScheduler在SparkContext中被创建，并通过调用runJob()函数启动。然后runJob()函数，调用submitJob()对Job的执行进行判断。

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)
…………	
}

submitJob()会对Job的执行情况用模式匹配进行判断，Job的执行情况放在DAGSchedulerEvent中。然后，会用DAGSchedulerEventProcessLoop根据Job执行情况进行选择性处理。

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 waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
	eventProcessLoop.post(JobSubmitted(
	  jobId, rdd, func2, partitions.toArray, callSite, waiter,
	  SerializationUtils.clone(properties)))
	waiter
}

DAGSchedulerEventProcessLoop根据接收的event进行选择处理，当event是JobSubmitted时，调用DAGScheduler的handleJobSubmitted()函数。

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)
…………
}

在DAGScheduler的handleJobSubmitted()函数中，根据finalRDD计算出finalStage，并把finalStage交给submitStage()函数处理。

private[scheduler] def handleJobSubmitted(jobId: Int,
  finalRDD: RDD[_],
  func: (TaskContext, Iterator[_]) => _,
  partitions: Array[Int],
  callSite: CallSite,
  listener: JobListener,
  properties: Properties) {
	var finalStage: ResultStage = null

	if (finalStage != null) {
	  val job = new ActiveJob(jobId, finalStage, func, partitions, callSite, listener, properties)
	  …………
	  val jobSubmissionTime = clock.getTimeMillis()
	  jobIdToActiveJob(jobId) = job
	  activeJobs += job
	  finalStage.resultOfJob = Some(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)
	}
	submitWaitingStages()
}

DAGScheduler的submitStage()函数会根据finalStage，进行回溯解析DAG图。但是，第一次迭代地提交一些missing parent stage。

/** 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)
	}
}

为了得到missing parent stage，submitStage()函数会调用submitMissingTasks()函数。在submitMissingTasks()函数中，会把解析得到的tasks包装成TaskSet，提交给TaskScheduler。

private def submitMissingTasks(stage: Stage, jobId: Int) {
…………
	if (tasks.size > 0) {
      stage.pendingTasks ++= tasks
      logDebug("New pending tasks: " + stage.pendingTasks)
      taskScheduler.submitTasks(new TaskSet(
        tasks.toArray, stage.id, stage.latestInfo.attemptId, stage.firstJobId, properties))
      stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
    } else {
      markStageAsFinished(stage, None)

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

TaskScheduler
TaskScheduler的实现类TaskSchedulerImple的submitTasks()函数，会把接收到的TaskSet集合发到Worker节点上。

override def submitTasks(taskSet: TaskSet) {
	val tasks = taskSet.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()
}

Worker Node
CoarseGrainedSchedulerBackend的receive()函数，会根据接收的信息类别选择处理，信息类别都放在CoarseGrainedClusterMessage里。当接收信息类别是ReviveOffers时，调用makeOffers()函数。

override def receive: PartialFunction[Any, Unit] = {
…………
	case ReviveOffers =>
        makeOffers()
…………
}

CoarseGrainedSchedulerBackend的makeOffers()会在所有的Executor上，制造fake resource offers。然后启动Tasks。

// Make fake resource offers on all executors
private def makeOffers() {
  // Filter out executors under killing
  val activeExecutors = executorDataMap.filterKeys(!executorsPendingToRemove.contains(_))
  val workOffers = activeExecutors.map { case (id, executorData) =>
	new WorkerOffer(id, executorData.executorHost, executorData.freeCores)
  }.toSeq
  launchTasks(scheduler.resourceOffers(workOffers))
}
CoarseGrainedSchedulerBackend的launchTasks()启动所有的Tasks。
// Launch tasks returned by a set of resource offers
private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
  for (task <- tasks.flatten) {
	val serializedTask = ser.serialize(task)
	if (serializedTask.limit >= akkaFrameSize - AkkaUtils.reservedSizeBytes) {
	  scheduler.taskIdToTaskSetManager.get(task.taskId).foreach { taskSetMgr =>
		try {
		  var msg = "Serialized task %s:%d was %d bytes, which exceeds max allowed: " +
			"spark.akka.frameSize (%d bytes) - reserved (%d bytes). Consider increasing " +
			"spark.akka.frameSize or using broadcast variables for large values."
		  msg = msg.format(task.taskId, task.index, serializedTask.limit, akkaFrameSize,
			AkkaUtils.reservedSizeBytes)
		  taskSetMgr.abort(msg)
		} catch {
		  case e: Exception => logError("Exception in error callback", e)
		}
	  }
	}
	else {
	  val executorData = executorDataMap(task.executorId)
	  executorData.freeCores -= scheduler.CPUS_PER_TASK
	  executorData.executorEndpoint.send(LaunchTask(new SerializableBuffer(serializedTask)))
	}
  }
}

当CoarseGrainedExecutorBackend收到Task执行情况时，会选择性处理。当Task执行情况是LaunchTasks时，调用Executor.launchTask()开始启动Task。

override def receive: PartialFunction[Any, Unit] = {
…………
	case LaunchTask(data) =>
      if (executor == null) {
        logError("Received LaunchTask command but executor was null")
        System.exit(1)
      } else {
        val taskDesc = ser.deserialize[TaskDescription](data.value)
        logInfo("Got assigned task " + taskDesc.taskId)
        executor.launchTask(this, taskId = taskDesc.taskId, attemptNumber = taskDesc.attemptNumber,
          taskDesc.name, taskDesc.serializedTask)
      }
…………
}

Executor将Task包装成TaskRunner，并从线程池中抽取一个空闲线程运行Task。一个CoarseGrainedExecutorBackend进行有且仅有一个Executor对象。

def launchTask(
  context: ExecutorBackend,
  taskId: Long,
  attemptNumber: Int,
  taskName: String,
  serializedTask: ByteBuffer): Unit = {
	val tr = new TaskRunner(context, taskId = taskId, attemptNumber = attemptNumber, taskName,
	  serializedTask)
	runningTasks.put(taskId, tr)
	threadPool.execute(tr)
}

PS：欢迎大家指出其中落下的部分，因为我觉得有些细节，我还没考虑全面。