mridulm commented on code in PR #36601:
URL: https://github.com/apache/spark/pull/36601#discussion_r883258132
##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -2449,7 +2458,15 @@ private[spark] class DAGScheduler(
val currentEpoch = maybeEpoch.getOrElse(mapOutputTracker.getEpoch)
logDebug(s"Considering removal of executor $execId; " +
s"fileLost: $fileLost, currentEpoch: $currentEpoch")
- if (!executorFailureEpoch.contains(execId) || executorFailureEpoch(execId)
< currentEpoch) {
+ // Check if the execId is a shuffle push merger. We do not remove the
executor if it is,
+ // and only remove the outputs on the host.
+ val isShuffleMerger =
execId.equals(BlockManagerId.SHUFFLE_MERGER_IDENTIFIER)
+ if (isShuffleMerger && pushBasedShuffleEnabled) {
+ hostToUnregisterOutputs.foreach(
+ host => blockManagerMaster.removeShufflePushMergerLocation(host))
+ }
+ if ((!executorFailureEpoch.contains(execId) ||
executorFailureEpoch(execId) < currentEpoch)
+ && !isShuffleMerger) {
Review Comment:
nit: invert the condition - do !isShuffleMerger before the others.
--
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]
