Github user tgravescs commented on a diff in the pull request:
https://github.com/apache/spark/pull/22288#discussion_r226999715
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala ---
@@ -415,9 +420,54 @@ private[spark] class TaskSchedulerImpl(
launchedAnyTask |= launchedTaskAtCurrentMaxLocality
} while (launchedTaskAtCurrentMaxLocality)
}
+
if (!launchedAnyTask) {
- taskSet.abortIfCompletelyBlacklisted(hostToExecutors)
+ taskSet.getCompletelyBlacklistedTaskIfAny(hostToExecutors) match
{
+ case Some(taskIndex) => // Returns the taskIndex which was
unschedulable
+
+ // If the taskSet is unschedulable we try to find an
existing idle blacklisted
+ // executor. If we cannot find one, we abort immediately.
Else we kill the idle
+ // executor and kick off an abortTimer which if it doesn't
schedule a task within the
+ // the timeout will abort the taskSet if we were unable to
schedule any task from the
+ // taskSet.
+ // Note 1: We keep track of schedulability on a per taskSet
basis rather than on a per
+ // task basis.
+ // Note 2: The taskSet can still be aborted when there are
more than one idle
+ // blacklisted executors and dynamic allocation is on. This
can happen when a killed
+ // idle executor isn't replaced in time by
ExecutorAllocationManager as it relies on
+ // pending tasks and doesn't kill executors on idle
timeouts, resulting in the abort
+ // timer to expire and abort the taskSet.
+ executorIdToRunningTaskIds.find(x => !isExecutorBusy(x._1))
match {
+ case Some (x) =>
+ val executorId = x._1
+ if (!unschedulableTaskSetToExpiryTime.contains(taskSet))
{
+ blacklistTrackerOpt.foreach(blt =>
blt.killBlacklistedIdleExecutor(executorId))
+
+ unschedulableTaskSetToExpiryTime(taskSet) =
clock.getTimeMillis()
+ val timeout =
conf.get(config.UNSCHEDULABLE_TASKSET_TIMEOUT) * 1000
+ logInfo(s"Waiting for $timeout ms for completely "
+ + s"blacklisted task to be schedulable again before
aborting $taskSet.")
+ abortTimer.schedule(getAbortTimer(taskSet, taskIndex,
timeout), timeout)
+ }
+ case _ => // Abort Immediately
+ logInfo("Cannot schedule any task because of complete
blacklisting. No idle" +
+ s" executors can be found to kill. Aborting $taskSet."
)
+ taskSet.abortSinceCompletelyBlacklisted(taskIndex)
+ }
+ case _ => // Do nothing if no tasks completely blacklisted.
+ }
+ } else {
+ // We want to differ killing any taskSets as long as we have a
non blacklisted executor
--- End diff --
s/differ/defer/
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
