venkata91 commented on a change in pull request #34122:
URL: https://github.com/apache/spark/pull/34122#discussion_r779745813
##########
File path: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
##########
@@ -1371,19 +1371,33 @@ private[spark] class DAGScheduler(
private def prepareShuffleServicesForShuffleMapStage(stage:
ShuffleMapStage): Unit = {
assert(stage.shuffleDep.shuffleMergeEnabled &&
!stage.shuffleDep.shuffleMergeFinalized)
if (stage.shuffleDep.getMergerLocs.isEmpty) {
+ getAndSetShufflePushMergerLocations(stage)
+ }
+
+ if (stage.shuffleDep.shuffleMergeEnabled) {
+ logInfo(("Shuffle merge enabled before starting the stage for %s (%s)
with %d" +
+ " merger locations").format(stage, stage.name,
stage.shuffleDep.getMergerLocs.size))
+ } else {
+ logInfo(("Shuffle merge disabled for %s (%s), but can get enabled later"
+
+ " adaptively once enough mergers are available").format(stage,
stage.name))
Review comment:
Yes, above are the only cases when it should be invoked.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
