VasilyKolpakov commented on a change in pull request #32526:
URL: https://github.com/apache/spark/pull/32526#discussion_r635563994
##########
File path: core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala
##########
@@ -859,6 +847,29 @@ private[spark] class ExecutorAllocationManager(
allocationManager.synchronized {
// Clear unschedulableTaskSets since atleast one task becomes
schedulable now
unschedulableTaskSets.remove(stageAttempt)
+ removeStageFromResourceProfileIfUnused(stageAttempt)
+ }
+ }
+
+ def removeStageFromResourceProfileIfUnused(stageAttempt: StageAttempt):
Unit = {
+ if (!stageAttemptToNumRunningTask.contains(stageAttempt) &&
+ !stageAttemptToNumTasks.contains(stageAttempt) &&
+ !stageAttemptToNumSpeculativeTasks.contains(stageAttempt) &&
+ !stageAttemptToTaskIndices.contains(stageAttempt) &&
+ !stageAttemptToSpeculativeTaskIndices.contains(stageAttempt) &&
+ !unschedulableTaskSets.contains(stageAttempt)
+ ) {
+ val rpForStage = resourceProfileIdToStageAttempt.filter { case (k, v)
=>
+ v.contains(stageAttempt)
+ }.keys
+ if (rpForStage.size == 1) {
+ // be careful about the removal from here due to late tasks, make
sure stage is
+ // really complete and no tasks left
+ resourceProfileIdToStageAttempt(rpForStage.head) -= stageAttempt
+ } else {
+ logWarning(s"Should have exactly one resource profile for stage
$stageAttempt," +
Review comment:
I'm not sure. This behaviour was there before and it is not directly
related to the bug.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
