Ngone51 commented on code in PR #42950:
URL: https://github.com/apache/spark/pull/42950#discussion_r1335422697
##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -1903,13 +1903,20 @@ private[spark] class DAGScheduler(
case smt: ShuffleMapTask =>
val shuffleStage = stage.asInstanceOf[ShuffleMapStage]
- shuffleStage.pendingPartitions -= task.partitionId
+ // Ignore task completion for old attempt of indeterminate stage
+ val ignoreIndeterminate = stage.isIndeterminate &&
+ task.stageAttemptId < stage.latestInfo.attemptNumber()
+ if (!ignoreIndeterminate) {
+ shuffleStage.pendingPartitions -= task.partitionId
+ }
val status = event.result.asInstanceOf[MapStatus]
val execId = status.location.executorId
logDebug("ShuffleMapTask finished on " + execId)
if (executorFailureEpoch.contains(execId) &&
smt.epoch <= executorFailureEpoch(execId)) {
logInfo(s"Ignoring possibly bogus $smt completion from executor
$execId")
Review Comment:
I also noticed this but seems to be fine since the missing partitions are
defined by `mapOutputTrackerMaster.findMissingPartitions` rather than
`pendingPartitions`.
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
