venkata91 commented on a change in pull request #34122:
URL: https://github.com/apache/spark/pull/34122#discussion_r787352423
##########
File path:
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
##########
@@ -4147,7 +4146,128 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
assert(finalizeTask2.delay == 0 && finalizeTask2.registerMergeResults)
}
- /**
+ test("SPARK-34826: Adaptively fetch shuffle mergers") {
+ initPushBasedShuffleConfs(conf)
+ conf.set(config.SHUFFLE_MERGER_LOCATIONS_MIN_STATIC_THRESHOLD, 6)
+ DAGSchedulerSuite.clearMergerLocs
+ DAGSchedulerSuite.addMergerLocs(Seq("host1", "host2", "host3", "host4",
"host5"))
+ val parts = 7
+
+ 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)
+
+ runEvent(makeCompletionEvent(
+ taskSets(0).tasks(0), Success, makeMapStatus("hostA", parts),
+ Seq.empty, Array.empty, createFakeTaskInfoWithId(0)))
+
+ val shuffleStage1 =
scheduler.stageIdToStage(0).asInstanceOf[ShuffleMapStage]
+ assert(shuffleStage1.shuffleDep.getMergerLocs.isEmpty)
+ assert(mapOutputTracker.getShufflePushMergerLocations(0).isEmpty)
+
+ DAGSchedulerSuite.addMergerLocs(Seq("host6", "host7", "host8"))
+
+ runEvent(makeCompletionEvent(
+ taskSets(0).tasks(1), Success, makeMapStatus("hostA", parts),
+ Seq.empty, Array.empty, createFakeTaskInfoWithId(1)))
+
+ // Dummy executor added event to trigger registering of shuffle merger
locations
+ // as shuffle mergers are tracked separately for test
+ runEvent(ExecutorAdded("dummy", "dummy"))
+
+ // Check if new shuffle merger locations are available for push or not
+ assert(mapOutputTracker.getShufflePushMergerLocations(0).size == 7)
Review comment:
Since the `parts` (numPartitions) is 7 and also we have 8 merger
locations available, it would return 7.
`spark.shuffle.push.mergersMinStaticThreshold` is set to 6 but if we have
`numDesired` (in this case 7) then we would get 7.
--
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]
