mridulm commented on code in PR #37533:
URL: https://github.com/apache/spark/pull/37533#discussion_r955615397
##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -2259,37 +2259,51 @@ private[spark] class DAGScheduler(
}
override def onShuffleMergeFailure(e: Throwable): Unit = {
+ if (e.isInstanceOf[IOException]) {
+ logInfo(s"Failed to connect external shuffle service "
+
+ s"${shuffleServiceLoc.hostPort}")
+
blockManagerMaster.removeShufflePushMergerLocation(shuffleServiceLoc.host)
+ }
}
})
}
}
}, 0, TimeUnit.SECONDS)
} else {
- stage.shuffleDep.getMergerLocs.zipWithIndex.foreach {
- case (shuffleServiceLoc, index) =>
- // Sends async request to shuffle service to finalize shuffle
merge on that host
- // TODO: SPARK-35536: Cancel finalizeShuffleMerge if the stage is
cancelled
- // TODO: during shuffleMergeFinalizeWaitSec
- shuffleClient.finalizeShuffleMerge(shuffleServiceLoc.host,
- shuffleServiceLoc.port, shuffleId, shuffleMergeId,
- new MergeFinalizerListener {
- override def onShuffleMergeSuccess(statuses: MergeStatuses):
Unit = {
- assert(shuffleId == statuses.shuffleId)
- eventProcessLoop.post(RegisterMergeStatuses(stage,
MergeStatus.
- convertMergeStatusesToMergeStatusArr(statuses,
shuffleServiceLoc)))
- results(index).set(true)
- }
+ shuffleMergeFinalizeScheduler.schedule(new Runnable {
Review Comment:
When either all mergers report success or there is a timeout (whichever is
earlier), we fire `ShuffleMergeFinalized` - at which point, the shuffle is
marked finalized - and all subsequent merge statuses from ESS are ignored.
At this point, sending `FinalizeShuffleMerge` to mergers does not impact the
application once `ShuffleMergeFinalized` is done.
So to answer your question - once there is a timeout, it does not help to
send `FinalizeShuffleMerge`
The current code in master is assuming that sending `FinalizeShuffleMerge`
is really cheap (which would typically be the case if there are no n/w issues
connecting to mergers !) - and so does it as a prefix, before starting to wait
for mergers to complete.
--
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]
