spark 1.6.0 core源码分析9 从简单例子看action

这一节以reduce为例讲解action操作
首先看submitJob方法，它将我们reduce中写的处理函数随JobSubmitted消息传递出去，因为每个分区都需要调用它进行计算；

而resultHandler是指最后合并的方法，在每个task完成后，需要调用resultHandler将最终结果合并。所以它不需要随JobSubmitted消息传递，而是保存在JobWaiter中

org.apache.spark.rdd.RDD

/**
   * Reduces the elements of this RDD using the specified commutative and
   * associative binary operator.
   */
  def reduce(f: (T, T) => T): T = withScope {
    val cleanF = sc.clean(f)
    val reducePartition: Iterator[T] => Option[T] = iter => {
      if (iter.hasNext) {
        Some(iter.reduceLeft(cleanF))
      } else {
        None
      }
    }
    var jobResult: Option[T] = None
    val mergeResult = (index: Int, taskResult: Option[T]) => {
      if (taskResult.isDefined) {
        jobResult = jobResult match {
          case Some(value) => Some(f(value, taskResult.get))
          case None => taskResult
        }
      }
    }
    sc.runJob(this, reducePartition, mergeResult)
    // Get the final result out of our Option, or throw an exception if the RDD was empty
    jobResult.getOrElse(throw new UnsupportedOperationException("empty collection"))
  }

SparkContext.scala

/**
   * Run a function on a given set of partitions in an RDD and pass the results to the given
   * handler function. This is the main entry point for all actions in Spark.
   */
  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)
    logInfo("Starting job: " + callSite.shortForm)
    if (conf.getBoolean("spark.logLineage", false)) {
      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
    }
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint()
  }

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)
    waiter.awaitResult() match {
      case JobSucceeded =>
        logInfo("Job %d finished: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
      case JobFailed(exception: 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
    }
  }

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.
    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)
    }

    val jobId = nextJobId.getAndIncrement()
    if (partitions.size == 0) {
      // Return immediately if the job is running 0 tasks
      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[scheduler] def handleJobSubmitted(jobId: Int,
      finalRDD: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      callSite: CallSite,
      listener: JobListener,
      properties: Properties) {
    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 = newResultStage(finalRDD, func, partitions, jobId, callSite)
    } 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 job %s (%s) with %d output partitions".format(
      job.jobId, callSite.shortForm, 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.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))
    submitStage(finalStage)

    submitWaitingStages()
  }

private def newResultStage(
      rdd: RDD[_],
      func: (TaskContext, Iterator[_]) => _,
      partitions: Array[Int],
      jobId: Int,
      callSite: CallSite): ResultStage = {
    val (parentStages: List[Stage], id: Int) = getParentStagesAndId(rdd, jobId)
    val stage = new ResultStage(id, rdd, func, partitions, parentStages, jobId, callSite)
    stageIdToStage(id) = stage
    updateJobIdStageIdMaps(jobId, stage)
    stage
  }

getParentStagesAndId内部的处理逻辑：从finalRDD开始，查找它的所有依赖中的shuffle依赖，如果是普通依赖，则继续往前找，直到找到shuffle依赖为止。这样，就能获取到与finalRDD相邻的所有shuffle依赖。在上图中，即是groupBy和join两个操作产生的依赖。

得到这些shuffle依赖之后，再往前获取整个job所有shuffle依赖，并以shuffle依赖为边界创建ShuffleMapStage，将每个shuffleId注册到mapOutputTracker中，它是跟踪每个shuffleMapStage输出的位置等信息。
在newResultStage方法中，getParentStagesAndId只返回与finalRDD最近的stage
之后再通过父stages，分区数目，stageId，finalRDD，jobId等构建ResultStage。将jobId保存到所有stage的jobIds成员中。一个stage还能有多个jobId？？？
至此，finalStage的建设就完成了。
接着创建了ActiveJob，它只是将那些参数信息封装起来，并有一个成员记录每个partition是否完成。

最后就是调用submitStage将finalStage提交

 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) {//如果没有父stage未完成，则提交本身的stage  
          logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
          submitMissingTasks(stage, jobId.get)
        } else {
          for (parent <- missing) {//如果还有未完成的父stage，则递归调用submitStage，先提交父stage，把自己放进waitingStages中
            submitStage(parent)
          }
          waitingStages += stage
        }
      }
    } else {
      abortStage(stage, "No active job for stage " + stage.id, None)
    }
  }

/** Called when stage's parents are available and we can now do its task. */
  private def submitMissingTasks(stage: Stage, jobId: Int) {
    logDebug("submitMissingTasks(" + stage + ")")
    // Get our pending tasks and remember them in our pendingTasks entry
    stage.pendingPartitions.clear()

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

    // Create internal accumulators if the stage has no accumulators initialized.
    // Reset internal accumulators only if this stage is not partially submitted
    // Otherwise, we may override existing accumulator values from some tasks
    if (stage.internalAccumulators.isEmpty || stage.numPartitions == partitionsToCompute.size) {
      stage.resetInternalAccumulators()
    }

    // 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 {
      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)
    }
    val taskIdToLocations: Map[Int, Seq[TaskLocation]] = try {
      stage match {
        case s: ShuffleMapStage =>
          partitionsToCompute.map { id => (id, getPreferredLocs(stage.rdd, id))}.toMap
        case s: ResultStage =>
          val job = s.activeJob.get
          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: $e\n${e.getStackTraceString}", Some(e))
        runningStages -= stage
        return
    }

    stage.makeNewStageAttempt(partitionsToCompute.size, taskIdToLocations.values.toSeq)
    listenerBus.post(SparkListenerStageSubmitted(stage.latestInfo, properties))

    // TODO: Maybe we can keep the taskBinary in Stage to avoid serializing it multiple times.
    // Broadcasted binary for the task, used to dispatch tasks to executors. Note that we broadcast
    // the serialized copy of the RDD and for each task we will deserialize it, which means each
    // task gets a different copy of the RDD. This provides stronger isolation between tasks that
    // might modify state of objects referenced in their closures. This is necessary in Hadoop
    // where the JobConf/Configuration object is not thread-safe.
    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 =>
          closureSerializer.serialize((stage.rdd, stage.shuffleDep): AnyRef).array()
        case stage: ResultStage =>
          closureSerializer.serialize((stage.rdd, stage.func): AnyRef).array()
      }

      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: $e\n${e.getStackTraceString}", Some(e))
        runningStages -= stage
        return
    }

    val tasks: Seq[Task[_]] = try {
      stage match {
        case stage: ShuffleMapStage =>
          partitionsToCompute.map { id =>
            val locs = taskIdToLocations(id)
            val part = stage.rdd.partitions(id)
            new ShuffleMapTask(stage.id, stage.latestInfo.attemptId,
              taskBinary, part, locs, stage.internalAccumulators)
          }

        case stage: ResultStage =>
          val job = stage.activeJob.get
          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, stage.internalAccumulators)
          }
      }
    } catch {
      case NonFatal(e) =>
        abortStage(stage, s"Task creation failed: $e\n${e.getStackTraceString}", Some(e))
        runningStages -= stage
        return
    }

    if (tasks.size > 0) {
      logInfo("Submitting " + tasks.size + " missing tasks from " + stage + " (" + stage.rdd + ")")
      stage.pendingPartitions ++= tasks.map(_.partitionId)
      logDebug("New pending partitions: " + stage.pendingPartitions)
      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)
    }
  }

  /** Merge updates from a task to our local accumulator values */
  private def updateAccumulators(event: CompletionEvent): Unit = {
    val task = event.task
    val stage = stageIdToStage(task.stageId)
    if (event.accumUpdates != null) {
      try {
        Accumulators.add(event.accumUpdates)

        event.accumUpdates.foreach { case (id, partialValue) =>
          // In this instance, although the reference in Accumulators.originals is a WeakRef,
          // it's guaranteed to exist since the event.accumUpdates Map exists

          val acc = Accumulators.originals(id).get match {
            case Some(accum) => accum.asInstanceOf[Accumulable[Any, Any]]
            case None => throw new NullPointerException("Non-existent reference to Accumulator")
          }

          // To avoid UI cruft, ignore cases where value wasn't updated
          if (acc.name.isDefined && partialValue != acc.zero) {
            val name = acc.name.get
            val value = s"${acc.value}"
            stage.latestInfo.accumulables(id) =
              new AccumulableInfo(id, name, None, value, acc.isInternal)
            event.taskInfo.accumulables +=
              new AccumulableInfo(id, name, Some(s"$partialValue"), value, acc.isInternal)
          }
        }
      } catch {
        // If we see an exception during accumulator update, just log the
        // error and move on.
        case e: Exception =>
          logError(s"Failed to update accumulators for $task", e)
      }
    }
  }

taskSchedulerImpl的submitTasks方法

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()
  }

调用了reviveOffers，实际最终还是调用了CoarseGrainedSchedulerBackend的makeOffers方法

// Make fake resource offers on all executors
    private def makeOffers() {
      // Filter out executors under killing
      val activeExecutors = executorDataMap.filterKeys(executorIsAlive)
      val workOffers = activeExecutors.map { case (id, executorData) =>
        new WorkerOffer(id, executorData.executorHost, executorData.freeCores)
      }.toSeq
      launchTasks(scheduler.resourceOffers(workOffers))
    }

org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend

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)))
        }
      }
    }

Executor.scala

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)
  }