Github user suyanNone commented on a diff in the pull request: https://github.com/apache/spark/pull/4055#discussion_r32800016 --- Diff: core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala --- @@ -598,6 +598,49 @@ class DAGSchedulerSuite assertDataStructuresEmpty() } + test("run with ShuffleMapStage retry") { + val firstRDD = new MyRDD(sc, 3, Nil) + val firstShuffleDep = new ShuffleDependency(firstRDD, null) + val firstShuffleId = firstShuffleDep.shuffleId + val shuffleMapRdd = new MyRDD(sc, 3, List(firstShuffleDep)) + val shuffleDep = new ShuffleDependency(shuffleMapRdd, null) + val reduceRdd = new MyRDD(sc, 1, List(shuffleDep)) + submit(reduceRdd, Array(0)) + + complete(taskSets(0), Seq( + (Success, makeMapStatus("hostB", shuffleMapRdd.partitions.size)), + (Success, makeMapStatus("hostB", shuffleMapRdd.partitions.size)), + (Success, makeMapStatus("hostC", shuffleMapRdd.partitions.size)) + )) + + complete(taskSets(1), Seq( + (Success, makeMapStatus("hostA", reduceRdd.partitions.size)), + (Success, makeMapStatus("hostB", reduceRdd.partitions.size)) + )) + runEvent(ExecutorLost("exec-hostA")) + // Resubmit already succcessd in hostA task + runEvent(CompletionEvent(taskSets(1).tasks(0), Resubmitted, + null, null, createFakeTaskInfo(), null)) + + // Cause mapOutTracker remove hostA outputs for taskset(0). + // Task that resubmitted will fetch matadata failed. + runEvent(CompletionEvent(taskSets(1).tasks(0), + FetchFailed(null, firstShuffleId, -1, 0, "Fetch matadata failed"), + null, null, createFakeTaskInfo(), null)) + // FetchFailed cause resubmit failed Stages. + scheduler.resubmitFailedStages() + + runEvent(CompletionEvent(taskSets(1).tasks(0), Success, + makeMapStatus("hostC", reduceRdd.partitions.size), null, createFakeTaskInfo(), null)) + runEvent(CompletionEvent(taskSets(1).tasks(2), Success, + makeMapStatus("hostC", reduceRdd.partitions.size), null, createFakeTaskInfo(), null)) --- End diff -- 3ks, I will refine that test... A very long time without updating that patch... so some logical slip from one's memory
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org