venkata91 commented on a change in pull request #30164:
URL: https://github.com/apache/spark/pull/30164#discussion_r518510112
##########
File path: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
##########
@@ -1281,6 +1309,12 @@ private[spark] class DAGScheduler(
stage match {
case s: ShuffleMapStage =>
outputCommitCoordinator.stageStart(stage = s.id, maxPartitionId =
s.numPartitions - 1)
+ // Only generate merger location for a given shuffle dependency once.
This way, even if
+ // this stage gets retried, it would still be merging blocks using the
same set of
+ // shuffle services.
+ if (s.shuffleDep.shuffleMergeEnabled) {
Review comment:
Yes you're right.
----------------------------------------------------------------
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]
