spark taskset submit and running

spark taskset submit and running

spark RDD 在执行一个action 的时候就会trigger sparkcontext 的RunJob 接口， (SparkContext 在初始化的时候会创建 DAGSchedule) 这个就会直接去invoke DAGSchedule.run--> submit, 然后会直接进入DAGSchedulerEventProcessLoop 的 doOnReceive， Code 如下：

  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)

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

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

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

    case AllJobsCancelled =>
      dagScheduler.doCancelAllJobs()

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

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

    case BeginEvent(task, taskInfo) =>
      dagScheduler.handleBeginEvent(task, taskInfo)

    case GettingResultEvent(taskInfo) =>
      dagScheduler.handleGetTaskResult(taskInfo)

    case completion: CompletionEvent =>
      dagScheduler.handleTaskCompletion(completion)

    case TaskSetFailed(taskSet, reason, exception) =>
      dagScheduler.handleTaskSetFailed(taskSet, reason, exception)

    case ResubmitFailedStages =>
      dagScheduler.resubmitFailedStages()
  }

显然submit task 的时候进入doOnReceive 时候会invoke JobSubmitted, 从而invoke 到 handleJobSubmitted，然后进入 submitStage, 这个DAGScheduler 就开始做我们熟悉的所谓“有向无环图”计算划分stage, 划分完成之后就会recursively submitMissTasks. 从而让TaskSchedulerImpl 来submit task 给相应的Executor 来run. 现在我们来看看怎么submit 和running taskset 的.

1. TaskSchedulerImpl 的submitTasks
为每一个taskset 创建一个 TaskSetManager, 这个TaskSetManager 来跟踪taskset 的状态等等, 随后将这个TasksetManager 插入到SchedulableBuilder的rootPool 中, 最后invoke SchedulerBackend 的reviveOffers, code 如下：

  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()
  }

2. SchedulerBackend 中的reviveOffers
schedulerBackend reviveOffers 其实去调用了EndPoint 中的reviveOffers, 这个时候reviveOffers 就会调用一个Executor 来 launchTask 去run 一个taskset 代码如下 (yarn mode)：

    private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
      for (task <- tasks.flatten) {
        val serializedTask = ser.serialize(task)
        if (serializedTask.limit >= maxRpcMessageSize) {
          scheduler.taskIdToTaskSetManager.get(task.taskId).foreach { taskSetMgr =>
            try {
              var msg = "Serialized task %s:%d was %d bytes, which exceeds max allowed: " +
                "spark.rpc.message.maxSize (%d bytes). Consider increasing " +
                "spark.rpc.message.maxSize or using broadcast variables for large values."
              msg = msg.format(task.taskId, task.index, serializedTask.limit, maxRpcMessageSize)
              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

          logDebug(s"Launching task ${task.taskId} on executor id: ${task.executorId} hostname: " +
            s"${executorData.executorHost}.")

          executorData.executorEndpoint.send(LaunchTask(new SerializableBuffer(serializedTask)))
        }
      }

从代码中我们可以看出， 其实我们还是从TaskSchedulerImpl 中 resourceOffers得到一个task 来run task. 对于SchedulerBackend 和 TaskScheduler 是在sparkContext 的创建的时候就把这个两个实例化了， 以/yarn 为例代码是：

        case masterUrl =>
        val cm = getClusterManager(masterUrl) match {
          case Some(clusterMgr) => clusterMgr
          case None => throw new SparkException("Could not parse Master URL: '" + master + "'")
        }
        try {
          val scheduler = cm.createTaskScheduler(sc, masterUrl)
          val backend = cm.createSchedulerBackend(sc, masterUrl, scheduler)    ==> YarnClusterSchedulerBackend.scala
          cm.initialize(scheduler, backend)
          (backend, scheduler)
        } catch {
          case se: SparkException => throw se
          case NonFatal(e) =>
            throw new SparkException("External scheduler cannot be instantiated", e)
        }

上面的cm 创建的schedulerBackend 对于yarn 来说，是在 YarnClusterSchedulerBackend.scala 中code

接下来我们将来分析task 的状态是如何 monitor 的。