Github user squito commented on a diff in the pull request: https://github.com/apache/spark/pull/5636#discussion_r36260436 --- Diff: core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala --- @@ -473,6 +473,299 @@ 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, reduceParts: Int): Seq[(Success.type, MapStatus)] = { + stageAttempt.tasks.zipWithIndex.map { case (task, idx) => + (Success, makeMapStatus("host" + ('A' + idx).toChar, reduceParts)) + }.toSeq + } + + def setupStageAbortTest(sc: SparkContext) { + sc.listenerBus.addListener(new EndListener()) + ended = false + jobResult = null + } + + // 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 + } + } + + // Helper functions to extract commonly used code in Fetch Failure test cases + /** + * Common code to get the next stage attempt, confirm it's the one we expect, and complete it + * succesfullly. + * + * @param stageId - The current stageId + * @param attemptIdx - The current attempt count + * @param numPartitions - The number of partitions in the next stage + */ + def completeNextShuffleMapSuccesfully(stageId: Int, attemptIdx: Int, numPartitions: Int): Unit = { + val stageAttempt = taskSets.last + checkStageId(stageId, attemptIdx, stageAttempt) + complete(stageAttempt, makeCompletions(stageAttempt, numPartitions)) + } + + /** + * Common code to get the next stage attempt, confirm it's the one we expect, and complete it + * with an intermediate FetchFailure. + * + * @param stageId - The current stageId + * @param attemptIdx - The current attempt count + * @param shuffleId - The shuffleId of the stage with a fetch failure + */ + def completeNextShuffleMapWithFailureAndSuccess(stageId: Int, + attemptIdx: Int, + shuffleId: Int, + numPartitions: Int): Unit = { + val stageAttempt = taskSets.last + checkStageId(stageId, attemptIdx, stageAttempt) + + val stageSuccesses = stageAttempt.tasks.tail.map { _ => (Success, makeMapStatus("hostB", + numPartitions))} + complete(stageAttempt, + Seq((FetchFailed(makeBlockManagerId("hostA"), shuffleId, 0, 0, "ignored"), null)) + ++ stageSuccesses + ) + } + + /** + * Common code to get the next stage attempt, confirm it's the one we expect, and complete it + * with all FetchFailure. + * + * @param stageId - The current stageId + * @param attemptIdx - The current attempt count + * @param shuffleId - The shuffleId of the stage with a fetch failure + */ + def completeNextShuffleMapWithFetchFailure(stageId: Int, + attemptIdx: Int, + shuffleId: Int): Unit = { + val stageAttempt = taskSets.last + checkStageId(stageId, attemptIdx, stageAttempt) + + complete(stageAttempt, stageAttempt.tasks.zipWithIndex.map{ case (task, idx) => + (FetchFailed(makeBlockManagerId("hostA"), shuffleId, 0, idx, "ignored"), null) + }.toSeq) + } + + /** + * Common code to get the next stage attempt, confirm it's the one we expect, and complete it + * with a success where we return 42. + * + * @param stageId - The current stageId + * @param attemptIdx - The current attempt count + */ + def completeNextShuffleMapWithSuccess_42 (stageId: Int, attemptIdx: Int): Unit = { + val stageAttempt = taskSets.last + checkStageId(stageId, attemptIdx, stageAttempt) + complete(stageAttempt, stageAttempt.tasks.zipWithIndex.map(_ => (Success, 42)).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.") { --- End diff -- typo: *job* being aborted
--- 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