Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/186#discussion_r11918307
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -1152,13 +1003,160 @@ class DAGScheduler(
}
def stop() {
- if (eventProcessActor != null) {
- eventProcessActor ! StopDAGScheduler
- }
+ logInfo("Stopping DAGScheduler")
+ dagSchedulerActorSupervisor ! PoisonPill
taskScheduler.stop()
}
}
+private[scheduler] class DAGSchedulerActorSupervisor(dagScheduler:
DAGScheduler)
+ extends Actor with Logging {
+
+ override val supervisorStrategy =
+ OneForOneStrategy() {
+ case x: Exception =>
+ logError("eventProcesserActor failed due to the error %s; shutting
down SparkContext"
+ .format(x.getMessage))
+ dagScheduler.doCancelAllJobs()
+ dagScheduler.sc.stop()
+ Stop
+ }
+
+ def receive = {
+ case p: Props => sender ! context.actorOf(p)
+ case _ => logWarning("received unknown message in
DAGSchedulerActorSupervisor")
+ }
+
+ dagScheduler.eventProcessActor = context.actorOf(
+ Props(new DAGSchedulerEventProcessActor(dagScheduler)))
+}
+
+private[scheduler] class DAGSchedulerEventProcessActor(dagScheduler:
DAGScheduler)
+ extends Actor with Logging {
+
+ override def preStart() {
+ // set DAGScheduler for taskScheduler to ensure eventProcessActor is
always
+ // valid when the messages arrive
+ dagScheduler.taskScheduler.setDAGScheduler(dagScheduler)
+ }
+
+ /**
+ * The main event loop of the DAG scheduler.
+ */
+ def receive = {
+ case JobSubmitted(jobId, rdd, func, partitions, allowLocal, callSite,
listener, properties) =>
+ var finalStage: Stage = null
+ try {
+ // New stage creation may throw an exception if, for example, jobs
are run on a
+ // HadoopRDD whose underlying HDFS files have been deleted.
+ finalStage = dagScheduler.newStage(rdd, partitions.size, None,
jobId, Some(callSite))
+ } catch {
+ case e: Exception =>
+ logWarning("Creating new stage failed due to exception - job: "
+ jobId, e)
+ listener.jobFailed(e)
+ }
+ val job = new ActiveJob(jobId, finalStage, func, partitions,
callSite, listener, properties)
+ dagScheduler.clearCacheLocs()
+ logInfo("Got job %s (%s) with %d output partitions (allowLocal=%s)".
+ format(job.jobId, callSite, partitions.length, allowLocal))
+ logInfo("Final stage: " + finalStage + "(" + finalStage.name + ")")
+ logInfo("Parents of final stage: " + finalStage.parents)
+ logInfo("Missing parents: " +
dagScheduler.getMissingParentStages(finalStage))
+ if (allowLocal && finalStage.parents.size == 0 && partitions.length
== 1) {
+ // Compute very short actions like first() or take() with no
parent stages locally.
+ dagScheduler.listenerBus.post(SparkListenerJobStart(job.jobId,
Array[Int](), properties))
+ dagScheduler.runLocally(job)
+ } else {
+ dagScheduler.jobIdToActiveJob(jobId) = job
+ dagScheduler.activeJobs += job
+ dagScheduler.resultStageToJob(finalStage) = job
+ dagScheduler.listenerBus.post(
+ SparkListenerJobStart(job.jobId,
dagScheduler.jobIdToStageIds(jobId).toArray,
+ properties))
+ dagScheduler.submitStage(finalStage)
+ }
+
+ case StageCancelled(stageId) =>
+ dagScheduler.handleStageCancellation(stageId)
+
+ case JobCancelled(jobId) =>
+ dagScheduler.handleJobCancellation(jobId)
+
+ case JobGroupCancelled(groupId) =>
+ // Cancel all jobs belonging to this job group.
+ // First finds all active jobs with this group id, and then kill
stages for them.
+ val activeInGroup = dagScheduler.activeJobs.filter(activeJob =>
+ groupId ==
activeJob.properties.get(SparkContext.SPARK_JOB_GROUP_ID))
+ val jobIds = activeInGroup.map(_.jobId)
+ jobIds.foreach(dagScheduler.handleJobCancellation(_, "part of cancel
job group"))
+
+ case AllJobsCancelled =>
+ dagScheduler.doCancelAllJobs()
+
+ case ExecutorAdded(execId, host) =>
+ dagScheduler.handleExecutorAdded(execId, host)
+
+ case ExecutorLost(execId) =>
+ dagScheduler.handleExecutorLost(execId)
+
+ case BeginEvent(task, taskInfo) =>
+ for (
+ job <- dagScheduler.jobIdToActiveJob.get(task.stageId);
+ stage <- dagScheduler.stageIdToStage.get(task.stageId);
+ stageInfo <- dagScheduler.stageToInfos.get(stage)
+ ) {
+ if (taskInfo.serializedSize > DAGScheduler.TASK_SIZE_TO_WARN *
1024 &&
+ !stageInfo.emittedTaskSizeWarning) {
+ stageInfo.emittedTaskSizeWarning = true
+ logWarning(("Stage %d (%s) contains a task of very large " +
+ "size (%d KB). The maximum recommended task size is %d
KB.").format(
+ task.stageId, stageInfo.name, taskInfo.serializedSize / 1024,
+ DAGScheduler.TASK_SIZE_TO_WARN))
+ }
+ }
+ dagScheduler.listenerBus.post(SparkListenerTaskStart(task.stageId,
taskInfo))
+
+ case GettingResultEvent(task, taskInfo) =>
+
dagScheduler.listenerBus.post(SparkListenerTaskGettingResult(taskInfo))
+
+ case completion @ CompletionEvent(task, reason, _, _, taskInfo,
taskMetrics) =>
+ val stageId = task.stageId
+ val taskType = Utils.getFormattedClassName(task)
+ dagScheduler.listenerBus.post(SparkListenerTaskEnd(stageId,
taskType, reason, taskInfo,
+ taskMetrics))
+ dagScheduler.handleTaskCompletion(completion)
+
+ case TaskSetFailed(taskSet, reason) =>
+ dagScheduler.stageIdToStage.get(taskSet.stageId).foreach {
+ dagScheduler.abortStage(_, reason) }
+
+ case ResubmitFailedStages =>
+ if (dagScheduler.failedStages.size > 0) {
+ // Failed stages may be removed by job cancellation, so failed
might be empty even if
+ // the ResubmitFailedStages event has been scheduled.
+ dagScheduler.resubmitFailedStages()
+ }
--- End diff --
Move the if statement into dagScheduler.resubmitFailedStages perhaps since
it accesses fields of dagScheduler
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
