Spark2.2.0源码阅读-stage提交

之前介绍了stage的划分，还是从这个地方开始
DAGScheduler

 private[scheduler] def handleMapStageSubmitted(jobId: Int,
      dependency: ShuffleDependency[_, _, _],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties) {
    // Submitting this map stage might still require the creation of some parent stages, so make
    // sure that happens.
    var finalStage: ShuffleMapStage = 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 = getOrCreateShuffleMapStage(dependency, jobId)//获取最后一个stage，里面逻辑之前已经说过了
    } 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 map stage job %s (%s) with %d output partitions".format(
      jobId, callSite.shortForm, dependency.rdd.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.addActiveJob(job)
    val stageIds = jobIdToStageIds(jobId).toArray
    val stageInfos = stageIds.flatMap(id => stageIdToStage.get(id).map(_.latestInfo))
    listenerBus.post(
      SparkListenerJobStart(job.jobId, jobSubmissionTime, stageInfos, properties))
//job启动的信息发送给listenerBus
    submitStage(finalStage)//提交stage

    // If the whole stage has already finished, tell the listener and remove it
    if (finalStage.isAvailable) {
      markMapStageJobAsFinished(job, mapOutputTracker.getStatistics(dependency))
    }
  }

主要看sumitstage 递归的调用submitStage,并且吧当前的stage加入到waiting队列中，直到父Stage如果都是可用的。也就是 missing.isEmpty

/** 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)//如果不在waiting，running或者failde的list里面则获取没有paretnt的stage并且按照stage的id进行排序
        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)
    }
  }

当父stage准备好的时候就开始执行这个stage的task了

 /** Called when stage's parents are available and we can now do its task. */
  private def submitMissingTasks(stage: Stage, jobId: Int) {
    logDebug("submitMissingTasks(" + stage + ")")

    // First figure out the indexes of partition ids to compute.
    val partitionsToCompute: Seq[Int] = stage.findMissingPartitions()

    // Use the scheduling pool, job group, description, etc. from an ActiveJob associated
    // with this Stage
    val properties = jobIdToActiveJob(jobId).properties

    runningStages += stage
    // SparkListenerStageSubmitted should be posted before testing whether tasks are
    // serializable. If tasks are not serializable, a SparkListenerStageCompleted event
    // will be posted, which should always come after a corresponding SparkListenerStageSubmitted
    // event.
    stage match {//并发写hdfs锁相关，暂时没没看懂
      case s: ShuffleMapStage =>
        outputCommitCoordinator.stageStart(stage = s.id, maxPartitionId = s.numPartitions - 1)
      case s: ResultStage =>
        outputCommitCoordinator.stageStart(
          stage = s.id, maxPartitionId = s.rdd.partitions.length - 1)
    }
//获取指定rdd的partition的位置信息
    val taskIdToLocations: Map[Int, Seq[TaskLocation]] = try {
      stage match {
        case s: ShuffleMapStage =>
          partitionsToCompute.map { id => (id, getPreferredLocs(stage.rdd, id))}.toMap
        case s: ResultStage =>
          partitionsToCompute.map { id =>
            val p = s.partitions(id)
            (id, getPreferredLocs(stage.rdd, p))
          }.toMap
      }
    } catch {
      case NonFatal(e) =>
        stage.makeNewStageAttempt(partitionsToCompute.size)
        listenerBus.post(SparkListenerStageSubmitted(stage.latestInfo, properties))
        abortStage(stage, s"Task creation failed: $e\n${Utils.exceptionString(e)}", Some(e))
        runningStages -= stage
        return
    }
var taskBinary: Broadcast[Array[Byte]] = null
    try {
      // For ShuffleMapTask, serialize and broadcast (rdd, shuffleDep).
      // For ResultTask, serialize and broadcast (rdd, func).
      val taskBinaryBytes: Array[Byte] = stage match {
        case stage: ShuffleMapStage =>
          JavaUtils.bufferToArray(
            closureSerializer.serialize((stage.rdd, stage.shuffleDep): AnyRef))
        case stage: ResultStage =>
          JavaUtils.bufferToArray(closureSerializer.serialize((stage.rdd, stage.func): AnyRef))
      }

      taskBinary = sc.broadcast(taskBinaryBytes)
    } catch {
      // In the case of a failure during serialization, abort the stage.
      case e: NotSerializableException =>
        abortStage(stage, "Task not serializable: " + e.toString, Some(e))
        runningStages -= stage

        // Abort execution
        return
      case NonFatal(e) =>
        abortStage(stage, s"Task serialization failed: $e\n${Utils.exceptionString(e)}", Some(e))
        runningStages -= stage
        return
    }
//根据stage的每个partition 创建对应的task，如果是shuffleMapStage 则创建ShuffleMapTask,如果是ResultStage则创建ResultStage。
    val tasks: Seq[Task[_]] = try {
      val serializedTaskMetrics = closureSerializer.serialize(stage.latestInfo.taskMetrics).array()
      stage match {
        case stage: ShuffleMapStage =>
          stage.pendingPartitions.clear()
          partitionsToCompute.map { id =>
            val locs = taskIdToLocations(id)
            val part = stage.rdd.partitions(id)
            stage.pendingPartitions += id
            new ShuffleMapTask(stage.id, stage.latestInfo.attemptId,
              taskBinary, part, locs, properties, serializedTaskMetrics, Option(jobId),
              Option(sc.applicationId), sc.applicationAttemptId)
          }

        case stage: ResultStage =>
          partitionsToCompute.map { id =>
            val p: Int = stage.partitions(id)
            val part = stage.rdd.partitions(p)
            val locs = taskIdToLocations(id)
            new ResultTask(stage.id, stage.latestInfo.attemptId,
              taskBinary, part, locs, id, properties, serializedTaskMetrics,
              Option(jobId), Option(sc.applicationId), sc.applicationAttemptId)
          }
      }
    } catch {
      case NonFatal(e) =>
        abortStage(stage, s"Task creation failed: $e\n${Utils.exceptionString(e)}", Some(e))
        runningStages -= stage
        return
    }

    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)})")
     //taskScheduler 调用sumitTasks 提交task集合 ，这个taskScheduler就是SparkContext在创建的时候初始化的调度器类型，FAIR还是FIFO
      taskScheduler.submitTasks(new TaskSet(
        tasks.toArray, stage.id, stage.latestInfo.attemptId, jobId, properties))
      stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
    } 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)

      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)
  //检查waitin中的stage有哪些是已经可以运行了的，然后重新提交。也就是说如果当前stage的父stage已经完成的时候就会提交当前的stage。
      submitWaitingChildStages(stage)
    }
  }

看下TaskSchedulerImpl 是如何提交的
根据taskSet 创建taskManager,然后将taskManager添加到调度器中，最后 执行backend.reviveOffers向DriverActor发送一个receiveOffsers消息
org.apache.spark.scheduler.TaskSchedulerImpl#submitTasks

  override def submitTasks(taskSet: TaskSet) {
    val tasks = taskSet.tasks
    logInfo("Adding task set " + taskSet.id + " with " + tasks.length + " tasks")
    this.synchronized {
  //创建一个taskManager 主要是用于跟踪task的执行情况
      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(",")}")
      }
    //将taskmanager添加到调度器中
      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()
  }

再看下CoarseGrainedSchedulerBackend 直接执行makeOffers

  override def receive: PartialFunction[Any, Unit] = {
      case StatusUpdate(executorId, taskId, state, data) =>
        scheduler.statusUpdate(taskId, state, data.value)
        if (TaskState.isFinished(state)) {
          executorDataMap.get(executorId) match {
            case Some(executorInfo) =>
              executorInfo.freeCores += scheduler.CPUS_PER_TASK
              makeOffers(executorId)
            case None =>
              // Ignoring the update since we don't know about the executor.
              logWarning(s"Ignored task status update ($taskId state $state) " +
                s"from unknown executor with ID $executorId")
          }
        }

      case ReviveOffers =>
        makeOffers()

      case KillTask(taskId, executorId, interruptThread, reason) =>
        executorDataMap.get(executorId) match {
          case Some(executorInfo) =>
            executorInfo.executorEndpoint.send(
              KillTask(taskId, executorId, interruptThread, reason))
          case None =>
            // Ignoring the task kill since the executor is not registered.
            logWarning(s"Attempted to kill task $taskId for unknown executor $executorId.")
        }

      case KillExecutorsOnHost(host) =>
        scheduler.getExecutorsAliveOnHost(host).foreach { exec =>
          killExecutors(exec.toSeq, replace = true, force = true)
        }
    }

查找过滤所有可用的workers，给task分配执行资源，最后执行任务

 // Make fake resource offers on all executors
    private def makeOffers() {
      // Make sure no executor is killed while some task is launching on it
      val taskDescs = CoarseGrainedSchedulerBackend.this.synchronized {
        // Filter out executors under killing
        val activeExecutors = executorDataMap.filterKeys(executorIsAlive)
        val workOffers = activeExecutors.map { case (id, executorData) =>
          new WorkerOffer(id, executorData.executorHost, executorData.freeCores)
        }.toIndexedSeq

      //给task分配资源，这儿会将资源的分配情况记录在taskManager中报告到driver
        scheduler.resourceOffers(workOffers)
      }
      if (!taskDescs.isEmpty) {
      //启动task任务
        launchTasks(taskDescs)
      }
    }

序列化task发送到executor

 // Launch tasks returned by a set of resource offers
    private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
      for (task <- tasks.flatten) {
        val serializedTask = TaskDescription.encode(task)
        if (serializedTask.limit >= maxRpcMessageSize) {//判断序列化的task任务数量是否超过最大的RPCMessageSize
          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}.")
         //序列化task并发送出去
          executorData.executorEndpoint.send(LaunchTask(new SerializableBuffer(serializedTask)))
        }
      }
    }

至此 task从提交，到任务的分发结束。