Github user tgravescs commented on a diff in the pull request:
https://github.com/apache/spark/pull/22288#discussion_r222816923
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala ---
@@ -414,9 +425,48 @@ private[spark] class TaskSchedulerImpl(
launchedAnyTask |= launchedTaskAtCurrentMaxLocality
} while (launchedTaskAtCurrentMaxLocality)
}
+
if (!launchedAnyTask) {
- taskSet.abortIfCompletelyBlacklisted(hostToExecutors)
- }
+ taskSet.getCompletelyBlacklistedTaskIfAny(hostToExecutors) match
{
+ case taskIndex: Some[Int] => // Returns the taskIndex which
was unschedulable
+
+ // If the taskSet is unschedulable we kill an existing
blacklisted executor/s and
+ // kick off an abortTimer which after waiting will abort the
taskSet if we were
+ // unable to schedule any task from the taskSet.
+ // Note: We keep a track of schedulability on a per taskSet
basis rather than on a
+ // per task basis.
+ val executor =
hostToExecutors.valuesIterator.next().iterator.next()
+ logDebug("Killing executor because of task unschedulability:
" + executor)
+ blacklistTrackerOpt.foreach(blt =>
blt.killBlacklistedExecutor(executor))
+
+ if (!unschedulableTaskSetToExpiryTime.contains(taskSet)) {
+ unschedulableTaskSetToExpiryTime(taskSet) =
clock.getTimeMillis()
+ abortTimer.schedule(new TimerTask() {
+ override def run() {
+ if
(unschedulableTaskSetToExpiryTime.contains(taskSet) &&
+ (unschedulableTaskSetToExpiryTime(taskSet)
+ + UNSCHEDULABLE_TASKSET_TIMEOUT_MS)
+ <= clock.getTimeMillis()
+ ) {
+ logInfo("Cannot schedule any task because of
complete blacklisting. " +
+ "Wait time for scheduling expired. Aborting the
application.")
+
taskSet.abortSinceCompletelyBlacklisted(taskIndex.get)
+ } else {
+ this.cancel()
+ }
+ }
+ }, UNSCHEDULABLE_TASKSET_TIMEOUT_MS)
+ }
+ case _ => // Do nothing.
+ }
+ } else {
+ // If a task was scheduled, we clear the expiry time for the
taskSet. The abort timer
+ // checks this entry to decide if we want to abort the taskSet.
+ if (unschedulableTaskSetToExpiryTime.contains(taskSet)) {
--- End diff --
just calling the remove sounds like a good idea.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
