mridulm commented on a change in pull request #30691:
URL: https://github.com/apache/spark/pull/30691#discussion_r641497690
##########
File path:
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
##########
@@ -3641,6 +3658,92 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
assertDataStructuresEmpty()
}
+ test("SPARK-32920: Merge results should be unregistered if the running stage
is cancelled" +
+ " before shuffle merge is finalized") {
+ initPushBasedShuffleConfs(conf)
+ DAGSchedulerSuite.clearMergerLocs
+ DAGSchedulerSuite.addMergerLocs(Seq("host1", "host2", "host3", "host4",
"host5"))
+ scheduler = new MyDAGScheduler(
+ sc,
+ taskScheduler,
+ sc.listenerBus,
+ mapOutputTracker,
+ blockManagerMaster,
+ sc.env,
+ shuffleMergeFinalize = false)
+ dagEventProcessLoopTester = new
DAGSchedulerEventProcessLoopTester(scheduler)
+
+ val parts = 2
+ val shuffleMapRdd = new MyRDD(sc, parts, Nil)
+ val shuffleDep = new ShuffleDependency(shuffleMapRdd, new
HashPartitioner(parts))
+ val reduceRdd = new MyRDD(sc, parts, List(shuffleDep), tracker =
mapOutputTracker)
+
+ // Submit a reduce job that depends which will create a map stage
+ submit(reduceRdd, (0 until parts).toArray)
+ // Complete shuffle map stage successfully on hostA
+ complete(taskSets(0), taskSets(0).tasks.zipWithIndex.map {
+ case (task, _) =>
+ (Success, makeMapStatus("hostA", parts))
+ }.toSeq)
Review comment:
Add a check here to ensure merge results were registered.
`assert(mapOutputTracker.getNumAvailableMergeResults(shuffleDep.shuffleId)
== parts.size)`
--
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]
