akpatnam25 commented on code in PR #36601: URL: https://github.com/apache/spark/pull/36601#discussion_r876437352
########## core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala: ########## @@ -4342,6 +4342,56 @@ class DAGSchedulerSuite extends SparkFunSuite with TempLocalSparkContext with Ti assertDataStructuresEmpty() } + test("SPARK-38987: corrupted shuffle block FetchFailure should unregister merge result") { + 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, + shuffleMergeRegister = 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) + + // Pass in custom bitmap so that the mergeStatus can store + // the correct mapIndex. + val bitmap = new RoaringBitmap() + bitmap.add(-1) + + val shuffleMapStage = scheduler.stageIdToStage(0).asInstanceOf[ShuffleMapStage] + scheduler.handleRegisterMergeStatuses(shuffleMapStage, + Seq((0, MergeStatus(makeBlockManagerId("hostA"), shuffleDep.shuffleMergeId, bitmap, 1000L)))) + scheduler.handleShuffleMergeFinalized(shuffleMapStage, + shuffleMapStage.shuffleDep.shuffleMergeId) + scheduler.handleRegisterMergeStatuses(shuffleMapStage, + Seq((1, MergeStatus(makeBlockManagerId("hostA"), shuffleDep.shuffleMergeId, bitmap, 1000L)))) + Review Comment: Let me know if i am missing something -- 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