spark 笔记 11: SchedulingAlgorithm 两种调度算法的优先级比较

调度算法的最基本工作之一，就是比较两个可执行的task的优先级。spark提供的FIFO和FAIR的优先级比较在SchedulingAlgorithm这个接口体现。 

FIFO:

1. --计算优先级的差。注意，在程序中，大部分时候是优先级的数字越小，它优先级越高
   
2. --如果优先级相同，那么stage编号越靠前，优先级越高
   
3. --如果优先级字段和stage id都相同，那么s2比s1更优先。（有这种情况？）
   

FAIR:

1. --没有达到最小资源的task比已经达到最小资源的task优先级高
   
2. --如果两个task都没达到最小资源，那么比较它们占用最小资源的比例。比例越小越优先
   
3. --否则比较占用权重资源的比例，比例越小越优先
   
4. --如果所有上述的比较都相同，那么名字小的优先（哈哈，名字很重要）；
   
5. --名字相同，则s2优先级高。
   

/**
 * 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)  --计算优先级的差。注意，在程序中，大部分时候是优先级的数字越小，它优先级越高

 

  if (res == 0) {
      val stageId1 = s1.stageId
      val stageId2 = s2.stageId
      res = math.signum(stageId1 - stageId2)  --如果优先级相同，那么stage编号越靠前，优先级越高。
    }
    if (res < 0) {
      true
    } else {
      false   ---如果优先级字段和stage id都相同，那么s2比s1更优先。（有这种情况？）
    }
  }
}



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).toDouble
    val minShareRatio2 = runningTasks2.toDouble / math.max(minShare2, 1.0).toDouble
    val taskToWeightRatio1 = runningTasks1.toDouble / s1.weight.toDouble
    val taskToWeightRatio2 = runningTasks2.toDouble / s2.weight.toDouble
    var compare:Int = 0

    if (s1Needy && !s2Needy) {     ----没有达到最小资源的task比已经达到最小资源的task优先级高
      return true
    } else if (!s1Needy && s2Needy) {   ----没有达到最小资源的task比已经达到最小资源的task优先级高
      return false
    } else if (s1Needy && s2Needy) {   ---如果两个task都没达到最小资源，那么比较它们占用最小资源的比例。比例越小越优先
      compare = minShareRatio1.compareTo(minShareRatio2)
    } else {   ---否则比较占用权重资源的比例，比例越小越优先
      compare = taskToWeightRatio1.compareTo(taskToWeightRatio2)  
    }

    if (compare < 0) {
      true
    } else if (compare > 0) {
      false
    } else {----如果所有上述的比较都相同，那么名字小的优先（哈哈，名字很重要）；名字相同，则s2优先级高。
      s1.name < s2.name
    }
  }
}

来自为知笔记(Wiz)