Github user squito commented on a diff in the pull request: https://github.com/apache/spark/pull/5636#discussion_r35719989 --- Diff: core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala --- @@ -473,6 +473,322 @@ class DAGSchedulerSuite assertDataStructuresEmpty() } + // Helper function to validate state when creating tests for task failures + def checkStageId(stageId: Int, attempt: Int, stageAttempt: TaskSet) { + assert(stageAttempt.stageId === stageId) + assert(stageAttempt.stageAttemptId == attempt) + } + + def makeCompletions(stageAttempt: TaskSet): Seq[(Success.type, MapStatus)] = { + stageAttempt.tasks.zipWithIndex.map { case (task, idx) => + (Success, makeMapStatus("host" + ('A' + idx).toChar, stageAttempt.tasks.size)) + }.toSeq + } + + /** + * In this test we simulate a job failure where the first stage completes successfully and + * the second stage fails due to a fetch failure. Multiple successive fetch failures of a stage + * trigger an overall stage abort to avoid endless retries. + */ + test("Multiple consecutive stage failures should lead to task being aborted.") { + // Create a new Listener to confirm that the listenerBus sees the JobEnd message + // when we abort the stage. This message will also be consumed by the EventLoggingListener + // so this will propagate up to the user. + var ended = false + var jobResult : JobResult = null + class EndListener extends SparkListener { + override def onJobEnd(jobEnd: SparkListenerJobEnd): Unit = { + jobResult = jobEnd.jobResult + ended = true + } + } + + sc.listenerBus.addListener(new EndListener()) + + val shuffleMapRdd = new MyRDD(sc, 2, Nil) + val shuffleDep = new ShuffleDependency(shuffleMapRdd, null) + val shuffleId = shuffleDep.shuffleId + val reduceRdd = new MyRDD(sc, 2, List(shuffleDep)) + submit(reduceRdd, Array(0, 1)) + + for (attempt <- 0 until Stage.MAX_STAGE_FAILURES) { + // Complete all the tasks for the current attempt of stage 0 successfully + val stage0Attempt = taskSets.last + + // Confirm that this is the next attempt for stage 0 + checkStageId(0, attempt, stage0Attempt) + + // Make each task in stage 0 success + val completions = makeCompletions(stage0Attempt) + + // Run stage 0 + complete(stage0Attempt, completions) --- End diff -- since we've now got a helper function for storing the task comlpetions, I would just inline it. It would save you from making a zillion `completion1_4` vals. So just `complete(stage0Attempt, makeCompletions(stage0Attempt))`.
--- 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