otterc commented on code in PR #40393:
URL: https://github.com/apache/spark/pull/40393#discussion_r1142475865
##########
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala:
##########
@@ -4595,6 +4595,184 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
}
}
+ test("SPARK-40082: recomputation of shuffle map stage with no pending
partitions" +
+ "should not hang") {
+
+ initPushBasedShuffleConfs(conf)
+ conf.set(config.SHUFFLE_MERGER_LOCATIONS_MIN_STATIC_THRESHOLD, 3)
+ DAGSchedulerSuite.clearMergerLocs()
+ DAGSchedulerSuite.addMergerLocs(Seq("host1", "host2", "host3"))
+
+ val rddA = new MyRDD(sc, 2, Nil)
+ val shuffleDepA = new ShuffleDependency(rddA, new HashPartitioner(2))
+ val shuffleIdA = shuffleDepA.shuffleId
+
+ val rddB = new MyRDD(sc, 2, List(shuffleDepA), tracker = mapOutputTracker)
+ val shuffleDepB = new ShuffleDependency(rddB, new HashPartitioner(2))
+
+ val rddC = new MyRDD(sc, 2, List(shuffleDepB), tracker = mapOutputTracker)
+
+ submit(rddC, Array(0, 1))
+
+ completeShuffleMapStageSuccessfully(0, 0, 2, Seq("hostA", "hostA"))
+
+ // Fetch failed
+ runEvent(makeCompletionEvent(
+ taskSets(1).tasks(0),
+ FetchFailed(makeBlockManagerId("hostC"), shuffleIdA, 0L, 0, 0,
+ "Fetch failure of task: stageId=1, stageAttempt=0, partitionId=0"),
+ result = null))
+
+ // long running task complete
+ completeShuffleMapStageSuccessfully(1, 0, 2, Seq("hostA", "hostA"))
+ assert(!shuffleDepB.shuffleMergeFinalized)
+
+ // stage1`s tasks have all completed
+ val shuffleStage1 =
scheduler.stageIdToStage(1).asInstanceOf[ShuffleMapStage]
+ assert(shuffleStage1.pendingPartitions.isEmpty)
+
+ // resubmit
+ scheduler.resubmitFailedStages()
+
+ // complete parentStage0
+ completeShuffleMapStageSuccessfully(0, 0, 2, Seq("hostA", "hostA"))
+
+ // stage1 should be shuffleMergeFinalized
+ assert(shuffleDepB.shuffleMergeFinalized)
+ }
+
+ for (pushBasedShuffleEnabled <- Seq(true, false)) {
+ test("SPARK-40082: recomputation of shuffle map stage with no pending
partitions should not " +
+ s"hang. pushBasedShuffleEnabled = $pushBasedShuffleEnabled") {
Review Comment:
How do we run just the individual tests?
##########
core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala:
##########
@@ -4595,6 +4595,184 @@ class DAGSchedulerSuite extends SparkFunSuite with
TempLocalSparkContext with Ti
}
}
+ test("SPARK-40082: recomputation of shuffle map stage with no pending
partitions" +
+ "should not hang") {
Review Comment:
nit: missing ` ` between `partitions` and `should`.
Since this test is checking that the stage gets finalized, we should change
the name to "SPARK-40082: re-computation of shuffle map stage with no pending
partitions should finalize the stage"
--
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
