spark的Task的序列化

Task类型

Spark一共有两种Task，一种是ResultTask，此Task只有job的最后一个stage才会生成，其他stage生成的Task是ShuffleTask。

Task生成

  // 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.
    //每个Task的环境是独立的，相互不影响的。
    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 =>
        //此处将所有Task依赖的都给进行序列化，也会对闭包进行处理。
          closureSerializer.serialize((stage.rdd, stage.shuffleDep): AnyRef).array()
        case stage: ResultStage =>
        //此处将所有Task依赖的都给进行序列化，也会对闭包进行处理。
          closureSerializer.serialize((stage.rdd, stage.func): AnyRef).array()
      }
		
		//将序列化好的对象进行广播
      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
    }

	//生成Task，分两种类型
    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)
    }

Task序列化

  @throws[TaskNotSerializableException]
  def resourceOffer(
      execId: String,
      host: String,
      maxLocality: TaskLocality.TaskLocality)
    : Option[TaskDescription] =
  {
    if (!isZombie) {
      val curTime = clock.getTimeMillis()

      var allowedLocality = maxLocality

      if (maxLocality != TaskLocality.NO_PREF) {
        allowedLocality = getAllowedLocalityLevel(curTime)
        if (allowedLocality > maxLocality) {
          // We're not allowed to search for farther-away tasks
          allowedLocality = maxLocality
        }
      }

      dequeueTask(execId, host, allowedLocality) match {
        case Some((index, taskLocality, speculative)) => {
          // Found a task; do some bookkeeping and return a task description
          //找到一个任务，然后封装task的信息，包括序列化
          val task = tasks(index)
          val taskId = sched.newTaskId()
          // Do various bookkeeping
          copiesRunning(index) += 1
          val attemptNum = taskAttempts(index).size
          val info = new TaskInfo(taskId, index, attemptNum, curTime,
            execId, host, taskLocality, speculative)
          taskInfos(taskId) = info
          taskAttempts(index) = info :: taskAttempts(index)
          // Update our locality level for delay scheduling
          // NO_PREF will not affect the variables related to delay scheduling
          if (maxLocality != TaskLocality.NO_PREF) {
            currentLocalityIndex = getLocalityIndex(taskLocality)
            lastLaunchTime = curTime
          }
          // Serialize and return the task
          val startTime = clock.getTimeMillis()
          //此处将Task进行序列化
          val serializedTask: ByteBuffer = try {
            Task.serializeWithDependencies(task, sched.sc.addedFiles, sched.sc.addedJars, ser)
          } catch {
            // If the task cannot be serialized, then there's no point to re-attempt the task,
            // as it will always fail. So just abort the whole task-set.
            case NonFatal(e) =>
              val msg = s"Failed to serialize task $taskId, not attempting to retry it."
              logError(msg, e)
              abort(s"$msg Exception during serialization: $e")
              throw new TaskNotSerializableException(e)
          }
          //由于Task会有依赖关系，因此检查Task的大小是否超出，如果超出，打印警告
          if (serializedTask.limit > TaskSetManager.TASK_SIZE_TO_WARN_KB * 1024 &&
              !emittedTaskSizeWarning) {
            emittedTaskSizeWarning = true
            logWarning(s"Stage ${task.stageId} contains a task of very large size " +
              s"(${serializedTask.limit / 1024} KB). The maximum recommended task size is " +
              s"${TaskSetManager.TASK_SIZE_TO_WARN_KB} KB.")
          }
          addRunningTask(taskId)

          // We used to log the time it takes to serialize the task, but task size is already
          // a good proxy to task serialization time.
          // val timeTaken = clock.getTime() - startTime
          val taskName = s"task ${info.id} in stage ${taskSet.id}"
          logInfo(s"Starting $taskName (TID $taskId, $host, partition ${task.partitionId}," +
            s"$taskLocality, ${serializedTask.limit} bytes)")

          sched.dagScheduler.taskStarted(task, info)
          return Some(new TaskDescription(taskId = taskId, attemptNumber = attemptNum, execId,
            taskName, index, serializedTask))
        }
        case _ =>
      }
    }
    None
  }

序列化代码

  /**
   * Serialize a task and the current app dependencies (files and JARs added to the SparkContext)
   */
  def serializeWithDependencies(
      task: Task[_],
      currentFiles: HashMap[String, Long],
      currentJars: HashMap[String, Long],
      serializer: SerializerInstance)
    : ByteBuffer = {

    val out = new ByteArrayOutputStream(4096)
    val dataOut = new DataOutputStream(out)

    // Write currentFiles
    dataOut.writeInt(currentFiles.size)
    for ((name, timestamp) <- currentFiles) {
      dataOut.writeUTF(name)
      dataOut.writeLong(timestamp)
    }

    // Write currentJars
    dataOut.writeInt(currentJars.size)
    for ((name, timestamp) <- currentJars) {
      dataOut.writeUTF(name)
      dataOut.writeLong(timestamp)
    }

    // Write the task itself and finish
    dataOut.flush()
    val taskBytes = serializer.serialize(task).array()
    out.write(taskBytes)
    ByteBuffer.wrap(out.toByteArray)
  }

TaskDescription

/**
 * Description of a task that gets passed onto executors to be executed, usually created by
 * [[TaskSetManager.resourceOffer]].
 */
private[spark] class TaskDescription(
    val taskId: Long,
    val attemptNumber: Int,
    val executorId: String,
    val name: String,
    val index: Int,    // Index within this task's TaskSet
    _serializedTask: ByteBuffer)
  extends Serializable {

  // Because ByteBuffers are not serializable, wrap the task in a SerializableBuffer
  private val buffer = new SerializableBuffer(_serializedTask)

  def serializedTask: ByteBuffer = buffer.value

  override def toString: String = "TaskDescription(TID=%d, index=%d)".format(taskId, index)
}

Task最终生成。