Ngone51 commented on a change in pull request #33896:
URL: https://github.com/apache/spark/pull/33896#discussion_r768410580
##########
File path:
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
##########
@@ -3847,10 +3890,201 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
// Job successful ended.
assert(results === Map(0 -> 11, 1 -> 12))
+ }
+
+ test("SPARK-33701: shuffle adaptive merge finalization") {
+ initPushBasedShuffleConfs(conf)
+ conf.set(config.SHUFFLE_MERGER_LOCATIONS_MIN_STATIC_THRESHOLD, 3)
+ DAGSchedulerSuite.clearMergerLocs
+ DAGSchedulerSuite.addMergerLocs(Seq("host1", "host2", "host3", "host4",
"host5"))
+ val parts = 2
+
+ val shuffleMapRdd1 = new MyRDD(sc, parts, Nil)
+ val shuffleDep1 = new ShuffleDependency(shuffleMapRdd1, new
HashPartitioner(parts))
+ val shuffleMapRdd2 = new MyRDD(sc, parts, Nil)
+ val shuffleDep2 = new ShuffleDependency(shuffleMapRdd2, new
HashPartitioner(parts))
+ val reduceRdd = new MyRDD(sc, parts, List(shuffleDep1, shuffleDep2),
+ tracker = mapOutputTracker)
+
+ // Submit a reduce job that depends which will create a map stage
+ submit(reduceRdd, (0 until parts).toArray)
+
+ val taskResults = taskSets(0).tasks.zipWithIndex.map {
+ case (_, idx) =>
+ (Success, makeMapStatus("host" + ('A' + idx).toChar, parts))
+ }.toSeq
+ // Remove MapStatus on one of the host before the stage ends to trigger
+ // a scenario where stage 0 needs to be resubmitted upon finishing all
tasks.
+ // Merge finalization should be scheduled in this case.
+ for ((result, i) <- taskResults.zipWithIndex) {
+ if (i == taskSets(0).tasks.size - 1) {
+ mapOutputTracker.removeOutputsOnHost("hostA")
+ }
+ runEvent(makeCompletionEvent(taskSets(0).tasks(i), result._1, result._2))
+ }
+ // Shuffle merge finalization should have completed even if some map
outputs
+ // are missing at the end of the stage
+ val shuffleStage1 =
scheduler.stageIdToStage(0).asInstanceOf[ShuffleMapStage]
+ assert(shuffleStage1.shuffleDep.shuffleMergeFinalized)
+ // Successfully completing the retry of stage 0.
+ complete(taskSets(2), taskSets(2).tasks.zipWithIndex.map {
Review comment:
nit: indent is off.
--
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]
