TaskScheduler原理剖析与源码分析

 def resourceOffers(offers: Seq[WorkerOffer]): Seq[Seq[TaskDescription]] = synchronized {
    var newExecAvail = false
    for (o <- offers) {
      executorIdToHost(o.executorId) = o.host
      executorIdToTaskCount.getOrElseUpdate(o.executorId, 0)
      if (!executorsByHost.contains(o.host)) {
        executorsByHost(o.host) = new HashSet[String]()
        executorAdded(o.executorId, o.host)
        newExecAvail = true
      }
      for (rack <- getRackForHost(o.host)) {
        hostsByRack.getOrElseUpdate(rack, new HashSet[String]()) += o.host
      }
    }

 val tasks = shuffledOffers.map(o => new ArrayBuffer[TaskDescription](o.cores))
    val availableCpus = shuffledOffers.map(o => o.cores).toArray

    val sortedTaskSets = rootPool.getSortedTaskSetQueue
    for (taskSet <- sortedTaskSets) {
      logDebug("parentName: %s, name: %s, runningTasks: %s".format(
        taskSet.parent.name, taskSet.name, taskSet.runningTasks))
      if (newExecAvail) {
        taskSet.executorAdded()
      }
    }

    var launchedTask = false
    for (taskSet <- sortedTaskSets; maxLocality <- taskSet.myLocalityLevels) {
      do {

//resourceOfferSingleTaskSet（）方法遍历所有executor，调用manager的resoucerOffer方法，找到合适的本地化级别找到可以启动的task执行task。
       launchedTask = resourceOfferSingleTaskSet(
            taskSet, maxLocality, shuffledOffers, availableCpus, tasks)
      } while (launchedTask)
    }

    if (tasks.size > 0) {
      hasLaunchedTask = true
    }
    return tasks