def submitJob[T, U](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
partitions: Seq[Int],
callSite: CallSite,
resultHandler: (Int, U) => Unit,
properties: Properties): JobWaiter[U] = {
// Check to make sure we are not launching a task on a partition that does not exist.
val maxPartitions = rdd.partitions.length
partitions.find(p => p >= maxPartitions || p < 0).foreach { p =>
throw new IllegalArgumentException(
"Attempting to access a non-existent partition: " + p + ". " +
"Total number of partitions: " + maxPartitions)
}
val jobId = nextJobId.getAndIncrement()
if (partitions.size == 0) {
// Return immediately if the job is running 0 tasks
return new JobWaiter[U](this, jobId, 0, resultHandler)
}
assert(partitions.size > 0)
val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
//给eventProcessLoop发送JobSubmitted消息
eventProcessLoop.post(JobSubmitted(
jobId, rdd, func2, partitions.toArray, callSite, waiter,
SerializationUtils.clone(properties)))
waiter
}
private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this)
private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
//Job提交
case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)
case MapStageSubmitted(jobId, dependency, callSite, listener, properties) =>
dagScheduler.handleMapStageSubmitted(jobId, dependency, callSite, listener, properties)
case StageCancelled(stageId) =>
dagScheduler.handleStageCancellation(stageId)
case JobCancelled(jobId) =>
dagScheduler.handleJobCancellation(jobId)
case JobGroupCancelled(groupId) =>
dagScheduler.handleJobGroupCancelled(groupId)
case AllJobsCancelled =>
dagScheduler.doCancelAllJobs()
case ExecutorAdded(execId, host) =>
dagScheduler.handleExecutorAdded(execId, host)
case ExecutorLost(execId) =>
dagScheduler.handleExecutorLost(execId, fetchFailed = false)
case BeginEvent(task, taskInfo) =>
dagScheduler.handleBeginEvent(task, taskInfo)
case GettingResultEvent(taskInfo) =>
dagScheduler.handleGetTaskResult(taskInfo)
case completion: CompletionEvent =>
dagScheduler.handleTaskCompletion(completion)
case TaskSetFailed(taskSet, reason, exception) =>
dagScheduler.handleTaskSetFailed(taskSet, reason, exception)
case ResubmitFailedStages =>
dagScheduler.resubmitFailedStages()
}
try {
//创建新stage可能出现异常,比如job运行依赖hdfs文文件被删除
finalStage = newResultStage(finalRDD, func, partitions, jobId, callSite)
} catch {
case e: Exception =>
logWarning("Creating new stage failed due to exception - job: " + jobId, e)
listener.jobFailed(e)
return
}
private def getMissingParentStages(stage: Stage): List[Stage] = {
val missing = new HashSet[Stage] //存储需要返回的父Stage
val visited = new HashSet[RDD[_]] //存储访问过的RDD
//自己建立栈,以免函数的递归调用导致
val waitingForVisit = new Stack[RDD[_]]
def visit(rdd: RDD[_]) {
if (!visited(rdd)) {
visited += rdd
val rddHasUncachedPartitions = getCacheLocs(rdd).contains(Nil)
if (rddHasUncachedPartitions) {
for (dep <- rdd.dependencies) {
dep match {
case shufDep: ShuffleDependency[_, _, _] =>
val mapStage = getShuffleMapStage(shufDep, stage.firstJobId)
if (!mapStage.isAvailable) {
missing += mapStage //遇到宽依赖,加入父stage
}
case narrowDep: NarrowDependency[_] =>
waitingForVisit.push(narrowDep.rdd) //窄依赖入栈,
}
}
}
}
}
//回溯的起始RDD入栈waitingForVisit.push(stage.rdd)
while (waitingForVisit.nonEmpty) {
visit(waitingForVisit.pop())
}
missing.toList
}
private def newOrUsedShuffleStage(
shuffleDep: ShuffleDependency[_, _, _],
firstJobId: Int): ShuffleMapStage = {
val rdd = shuffleDep.rdd
val numTasks = rdd.partitions.length
val stage = newShuffleMapStage(rdd, numTasks, shuffleDep, firstJobId, rdd.creationSite)
if (mapOutputTracker.containsShuffle(shuffleDep.shuffleId)) {
//Stage已经被计算过,从MapOutputTracker中获取计算结果
val serLocs = mapOutputTracker.getSerializedMapOutputStatuses(shuffleDep.shuffleId)
val locs = MapOutputTracker.deserializeMapStatuses(serLocs)
(0 until locs.length).foreach { i =>
if (locs(i) ne null) {
// locs(i) will be null if missing
stage.addOutputLoc(i, locs(i))
}
}
} else {
// Kind of ugly: need to register RDDs with the cache and map output tracker here
// since we can't do it in the RDD constructor because # of partitions is unknown
logInfo("Registering RDD " + rdd.id + " (" + rdd.getCreationSite + ")")
mapOutputTracker.registerShuffle(shuffleDep.shuffleId, rdd.partitions.length)
}
stage
}
/** Submits stage, but first recursively submits any missing parents. */
private def submitStage(stage: Stage) {
val jobId = activeJobForStage(stage)
if (jobId.isDefined) {
logDebug("submitStage(" + stage + ")")
if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
val missing = getMissingParentStages(stage).sortBy(_.id)
logDebug("missing: " + missing)
if (missing.isEmpty) {
logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
//如果没有父stage,则提交当前stage
submitMissingTasks(stage, jobId.get)
} else {
for (parent <- missing) {
//如果有父stage,则递归提交父stage
submitStage(parent)
}
waitingStages += stage
}
}
} else {
abortStage(stage, "No active job for stage " + stage.id, None)
}
}