weixiuli commented on a change in pull request #30716:
URL: https://github.com/apache/spark/pull/30716#discussion_r546631296
##########
File path:
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
##########
@@ -2035,6 +2040,107 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
assert(scheduler.activeJobs.isEmpty)
}
+ def reInit(): Unit = {
+ assert(sc != null)
+ val dagOutputTracker = mapOutputTracker
+ val taskSchedulerImpl = new TaskSchedulerImpl(sc) {
+ override def submitTasks(taskSet: TaskSet) = {
+ super.submitTasks(taskSet)
+ taskSet.tasks.foreach(_.epoch = dagOutputTracker.getEpoch)
+ taskSets += taskSet
+ }
+
+ override def cancelTasks(stageId: Int, interruptThread: Boolean) {
+ cancelledStages += stageId
+ }
+ }
+ taskSchedulerImpl.initialize(new FakeSchedulerBackend)
+ scheduler = new DAGScheduler(
+ sc,
+ taskSchedulerImpl,
+ sc.listenerBus,
+ mapOutputTracker,
+ blockManagerMaster,
+ sc.env)
+ dagEventProcessLoopTester = new
DAGSchedulerEventProcessLoopTester(scheduler)
+ }
+
+ test("Test dagScheduler.shouldUnregisterMapOutput with map stage not
running") {
+ reInit()
+ val shuffleMapRdd = new MyRDD(sc, 2, Nil)
+ val shuffleDep = new ShuffleDependency(shuffleMapRdd, new
HashPartitioner(2))
+ val shuffleId = shuffleDep.shuffleId
+ val reduceRdd = new MyRDD(sc, 2, List(shuffleDep), tracker =
mapOutputTracker)
+ submit(reduceRdd, Array(0, 1))
+ complete(taskSets(0), Seq(
+ (Success, makeMapStatus("hostA", reduceRdd.partitions.length)),
+ (Success, makeMapStatus("hostB", reduceRdd.partitions.length))))
+ // The MapOutputTracker should know about both map output locations.
+ assert(mapOutputTracker.getMapSizesByExecutorId(shuffleId,
0).map(_._1.host).toSet ===
+ HashSet("hostA", "hostB"))
+
+ // The first result task fails, with a fetch failure for the output from
the first mapper.
+ runEvent(makeCompletionEvent(
+ taskSets(1).tasks(0),
+ FetchFailed(makeBlockManagerId("hostA"), shuffleId, 0, 0, 0, "ignored"),
+ null))
+ assert(sparkListener.failedStages.contains(1))
+
+ val mapStatuses = mapOutputTracker.shuffleStatuses(shuffleId).mapStatuses
+ // unregisterMapOutput with a fetchFailed.
+ assert(mapStatuses.count(_ != null) === 1)
+ assert(mapStatuses(1).location === makeBlockManagerId("hostB"))
+ }
+
+ test("Test dagScheduler.shouldUnregisterMapOutput with map stage
re-running") {
+ reInit()
+ val shuffleMapRdd = new MyRDD(sc, 3, Nil)
+ val shuffleDep = new ShuffleDependency(shuffleMapRdd, new
HashPartitioner(2))
+ val shuffleId = shuffleDep.shuffleId
+ val reduceRdd = new MyRDD(sc, 2, List(shuffleDep), tracker =
mapOutputTracker)
+ submit(reduceRdd, Array(0, 1))
+ complete(taskSets(0), Seq(
+ (Success, makeMapStatus("hostA", reduceRdd.partitions.length)),
+ (Success, makeMapStatus("hostB", reduceRdd.partitions.length)),
+ (Success, makeMapStatus("hostC", reduceRdd.partitions.length))))
+ // The MapOutputTracker should know about both map output locations.
+ assert(mapOutputTracker.getMapSizesByExecutorId(shuffleId,
0).map(_._1.host).toSet ===
+ HashSet("hostA", "hostB", "hostC"))
+
+ runEvent(makeCompletionEvent(
+ taskSets(1).tasks(0),
+ FetchFailed(makeBlockManagerId("hostA"), shuffleId, 0, 0, 0, "ignored"),
+ null))
+ runEvent(makeCompletionEvent(
+ taskSets(1).tasks(1),
+ FetchFailed(makeBlockManagerId("hostB"), shuffleId, 1, 1, 0, "ignored"),
+ null))
+
+ assert(sparkListener.failedStages.contains(1))
+
+ // Wait for a long time to make sure the map stage was resubmitted.
+ eventually(timeout(1000 milliseconds), interval(10 milliseconds)) {
+ assert(scheduler.runningStages.nonEmpty && taskSets.size == 3)
+ }
+
+ runEvent(makeCompletionEvent(
+ taskSets(2).tasks(0),
+ Success,
+ makeMapStatus("hostA", reduceRdd.partitions.length)))
+
+ runEvent(makeCompletionEvent(
+ taskSets(1).tasks(1),
Review comment:
Oh, I'm sorry,i have update my ut, thanks.
----------------------------------------------------------------
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]
