Spark源码学习笔记8-TaskScheduler

SparkContext中调用伴生对象的方法来创建TaskScheduler对象：

// Create and start the scheduler
    val (sched, ts) = SparkContext.createTaskScheduler(this, master, deployMode)
    _schedulerBackend = sched
    _taskScheduler = ts


/**
 * Create a task scheduler based on a given master URL.
 * Return a 2-tuple of the scheduler backend and the task scheduler.
   */
  private def createTaskScheduler(
      sc: SparkContext,
      master: String,
      deployMode: String): (SchedulerBackend, TaskScheduler) = {
    import SparkMasterRegex._

    // When running locally, don't try to re-execute tasks on failure.
    val MAX_LOCAL_TASK_FAILURES = 1

    master match {
      case "local" =>
        val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
        val backend = new LocalSchedulerBackend(sc.getConf, scheduler, 1)
        scheduler.initialize(backend)
        (backend, scheduler)

      case LOCAL_N_REGEX(threads) =>
        def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
        // local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
        val threadCount = if (threads == "*") localCpuCount else threads.toInt
        if (threadCount <= 0) {
          throw new SparkException(s"Asked to run locally with $threadCount threads")
        }
        val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
        val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
        scheduler.initialize(backend)
        (backend, scheduler)

      case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
        def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
        // local[*, M] means the number of cores on the computer with M failures
        // local[N, M] means exactly N threads with M failures
        val threadCount = if (threads == "*") localCpuCount else threads.toInt
        val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
        val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
        scheduler.initialize(backend)
        (backend, scheduler)

      case SPARK_REGEX(sparkUrl) =>
        val scheduler = new TaskSchedulerImpl(sc)
        val masterUrls = sparkUrl.split(",").map("spark://" + _)
        val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
        scheduler.initialize(backend)
        (backend, scheduler)

      case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
        // Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
        val memoryPerSlaveInt = memoryPerSlave.toInt
        if (sc.executorMemory > memoryPerSlaveInt) {
          throw new SparkException(
            "Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
              memoryPerSlaveInt, sc.executorMemory))
        }

        val scheduler = new TaskSchedulerImpl(sc)
        val localCluster = new LocalSparkCluster(
          numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt, sc.conf)
        val masterUrls = localCluster.start()
        val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
        scheduler.initialize(backend)
        backend.shutdownCallback = (backend: StandaloneSchedulerBackend) => {
          localCluster.stop()
        }
        (backend, scheduler)

      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)
          cm.initialize(scheduler, backend)
          (backend, scheduler)
        } catch {
          case se: SparkException => throw se
          case NonFatal(e) =>
            throw new SparkException("External scheduler cannot be instantiated", e)
        }
    }
  }

• TaskScheduler
  TaskScheduler负责调度向它提交的来自DAGScheduler的task集（DAGScheduler处理stage），按照调度规则将task分发到集群运行，最终向DAGScheduler返回相关事件。TaskScheduler是一个trait，目前由类TaskSchedulerImpl实现。

package org.apache.spark.scheduler
......
/**
 * Low-level task scheduler interface, currently implemented exclusively by
 * [[org.apache.spark.scheduler.TaskSchedulerImpl]].
 * This interface allows plugging in different task schedulers. Each TaskScheduler schedules tasks
 * for a single SparkContext. These schedulers get sets of tasks submitted to them from the
 * DAGScheduler for each stage, and are responsible for sending the tasks to the cluster, running
 * them, retrying if there are failures, and mitigating stragglers. They return events to the
 * DAGScheduler.
 */
private[spark] trait TaskScheduler {

  private val appId = "spark-application-" + System.currentTimeMillis

  def rootPool: Pool

  def schedulingMode: SchedulingMode

  def start(): Unit

  // Invoked after system has successfully initialized (typically in spark context).
  // Yarn uses this to bootstrap allocation of resources based on preferred locations,
  // wait for slave registrations, etc.
  def postStartHook() { }

  // Disconnect from the cluster.
  def stop(): Unit

  // Submit a sequence of tasks to run.
  def submitTasks(taskSet: TaskSet): Unit

  // Cancel a stage.
  def cancelTasks(stageId: Int, interruptThread: Boolean): Unit

  // Set the DAG scheduler for upcalls. This is guaranteed to be set before submitTasks is called.
  def setDAGScheduler(dagScheduler: DAGScheduler): Unit

  // Get the default level of parallelism to use in the cluster, as a hint for sizing jobs.
  def defaultParallelism(): Int

  /**
   * Update metrics for in-progress tasks and let the master know that the BlockManager is still
   * alive. Return true if the driver knows about the given block manager. Otherwise, return false,
   * indicating that the block manager should re-register.
   */
  def executorHeartbeatReceived(
      execId: String,
      accumUpdates: Array[(Long, Seq[AccumulatorV2[_, _]])],
      blockManagerId: BlockManagerId): Boolean

  /**
   * Get an application ID associated with the job.
   *
   * @return An application ID
   */
  def applicationId(): String = appId

  /**
   * Process a lost executor
   */
  def executorLost(executorId: String, reason: ExecutorLossReason): Unit

  /**
   * Get an application's attempt ID associated with the job.
   *
   * @return An application's Attempt ID
   */
  def applicationAttemptId(): Option[String]

}

• TaskSchedulerImpl