wankunde commented on code in PR #37533:
URL: https://github.com/apache/spark/pull/37533#discussion_r960777861


##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -2242,60 +2251,57 @@ private[spark] class DAGScheduler(
     val numMergers = stage.shuffleDep.getMergerLocs.length
     val results = (0 until numMergers).map(_ => 
SettableFuture.create[Boolean]())
     externalShuffleClient.foreach { shuffleClient =>
-      if (!registerMergeResults) {
-        results.foreach(_.set(true))
-        // Finalize in separate thread as shuffle merge is a no-op in this case
-        shuffleMergeFinalizeScheduler.schedule(new Runnable {
-          override def run(): Unit = {
-            stage.shuffleDep.getMergerLocs.foreach {
-              case shuffleServiceLoc =>
-                // Sends async request to shuffle service to finalize shuffle 
merge on that host.
-                // Since merge statuses will not be registered in this case,
-                // we pass a no-op listener.
-                shuffleClient.finalizeShuffleMerge(shuffleServiceLoc.host,
-                  shuffleServiceLoc.port, shuffleId, shuffleMergeId,
-                  new MergeFinalizerListener {
-                    override def onShuffleMergeSuccess(statuses: 
MergeStatuses): Unit = {
-                    }
+      val scheduledFutures = stage.shuffleDep.getMergerLocs.zipWithIndex.map {
+        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
+          shuffleSendFinalizeRPCExecutor.submit(new Runnable() {
+            override def run(): Unit = {
+              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)
+                  }

Review Comment:
   Thanks for your explanation,  I have updated the PR.



-- 
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

Reply via email to