Spark-SchedulerPool-Deep-Div.md

title	date	tags	hidden
Spark SchedulerPool Deep Dive	2019-01-13 03:35:42 -0800		true

初始化

在 TaskSchedulerImpl 的initialize 方法里 schedulableBuilder.buildPools初始化了 scheuler pool.其中有两种SchedulingMode[FIFO,FAIR]

/**
 * An interface for schedulable entities.
 * there are two type of Schedulable entities(Pools and TaskSetManagers)
 */
private[spark] trait Schedulable {
  var parent: Pool
  // child queues
  def schedulableQueue: ConcurrentLinkedQueue[Schedulable]
  def schedulingMode: SchedulingMode
  def weight: Int
  def minShare: Int
  def runningTasks: Int
  def priority: Int
  def stageId: Int
  def name: String

  def addSchedulable(schedulable: Schedulable): Unit
  def removeSchedulable(schedulable: Schedulable): Unit
  def getSchedulableByName(name: String): Schedulable
  def executorLost(executorId: String, host: String, reason: ExecutorLossReason): Unit
  def checkSpeculatableTasks(minTimeToSpeculation: Int): Boolean
  def getSortedTaskSetQueue: ArrayBuffer[TaskSetManager]
}

/**
 * An interface for sort algorithm
 * FIFO: FIFO algorithm between TaskSetManagers
 * FS: FS algorithm between Pools, and FIFO or FS within Pools
 */
private[spark] trait SchedulingAlgorithm {
  def comparator(s1: Schedulable, s2: Schedulable): Boolean
}

private[spark] class FIFOSchedulingAlgorithm extends SchedulingAlgorithm {
  override def comparator(s1: Schedulable, s2: Schedulable): Boolean = {
    val priority1 = s1.priority
    val priority2 = s2.priority
    var res = math.signum(priority1 - priority2)
    if (res == 0) {
      val stageId1 = s1.stageId
      val stageId2 = s2.stageId
      res = math.signum(stageId1 - stageId2)
    }
    res < 0
  }
}

private[spark] class FairSchedulingAlgorithm extends SchedulingAlgorithm {
  override def comparator(s1: Schedulable, s2: Schedulable): Boolean = {
    val minShare1 = s1.minShare
    val minShare2 = s2.minShare
    val runningTasks1 = s1.runningTasks
    val runningTasks2 = s2.runningTasks
    val s1Needy = runningTasks1 < minShare1
    val s2Needy = runningTasks2 < minShare2
    val minShareRatio1 = runningTasks1.toDouble / math.max(minShare1, 1.0)
    val minShareRatio2 = runningTasks2.toDouble / math.max(minShare2, 1.0)
    val taskToWeightRatio1 = runningTasks1.toDouble / s1.weight.toDouble
    val taskToWeightRatio2 = runningTasks2.toDouble / s2.weight.toDouble

    var compare = 0
    if (s1Needy && !s2Needy) {
      return true
    } else if (!s1Needy && s2Needy) {
      return false
    } else if (s1Needy && s2Needy) {
      compare = minShareRatio1.compareTo(minShareRatio2)
    } else {
      compare = taskToWeightRatio1.compareTo(taskToWeightRatio2)
    }
    if (compare < 0) {
      true
    } else if (compare > 0) {
      false
    } else {
      s1.name < s2.name
    }
  }
}

Submit 到 pool

每一个 TaskSet 会创建一个TaskSetManager, 然后放到

org.apache.spark.scheduler.TaskSchedulerImpl#submitTasks(taskSet: TaskSet) {
  ...
  val manager = createTaskSetManager(taskSet, maxTaskFailures)
  schedulableBuilder.addTaskSetManager(manager, manager.taskSet.properties)
  ...
}