Github user squito commented on a diff in the pull request: https://github.com/apache/spark/pull/15644#discussion_r86078676 --- Diff: core/src/test/scala/org/apache/spark/scheduler/TaskSchedulerImplSuite.scala --- @@ -282,6 +316,114 @@ class TaskSchedulerImplSuite extends SparkFunSuite with LocalSparkContext with B assert(!failedTaskSet) } + test("scheduled tasks obey task and stage blacklists") { + taskScheduler = setupSchedulerWithMockTsm() + (0 to 2).foreach { stageId => + val taskSet = FakeTask.createTaskSet(numTasks = 2, stageId = stageId, stageAttemptId = 0) + taskScheduler.submitTasks(taskSet) + } + + val offers = IndexedSeq( + new WorkerOffer("executor0", "host0", 1), + new WorkerOffer("executor1", "host1", 1), + new WorkerOffer("executor2", "host1", 1), + new WorkerOffer("executor3", "host2", 10) + ) + + // Setup our mock blacklist: + // * stage 0 is blacklisted on node "host1" + // * stage 1 is blacklisted on executor "executor3" + // * stage 0, part 0 is blacklisted on executor 0 + // Setup some defaults, then override them with particulars. + // (Later stubs take precedence over earlier ones.) + stageToMockTaskSetBlacklist.values.foreach { taskSetBlacklist => + when(taskSetBlacklist.isNodeBlacklistedForTaskSet(anyString())).thenReturn(false) + when(taskSetBlacklist.isExecutorBlacklistedForTaskSet(anyString())).thenReturn(false) + when(taskSetBlacklist.isExecutorBlacklistedForTask(anyString(), anyInt())).thenReturn(false) + when(taskSetBlacklist.isNodeBlacklistedForTask(anyString(), anyInt())).thenReturn(false) + } + when(stageToMockTaskSetBlacklist(0).isNodeBlacklistedForTaskSet("host1")).thenReturn(true) + when(stageToMockTaskSetBlacklist(1).isExecutorBlacklistedForTaskSet("executor3")) + .thenReturn(true) + when(stageToMockTaskSetBlacklist(0).isExecutorBlacklistedForTask("executor0", 0)) + .thenReturn(true) + + val firstTaskAttempts = taskScheduler.resourceOffers(offers).flatten + (0 to 2).foreach { stageId => + verify(stageToMockTaskSetBlacklist(stageId), atLeast(1)) + .isNodeBlacklistedForTaskSet(anyString()) + } + for { + exec <- Seq("executor1", "executor2") + part <- 0 to 1 + } { + // The node blacklist should ensure we never check the task blacklist. This is important + // for performance, otherwise we end up changing an O(1) operation into a + // O(numPendingTasks) one. --- End diff -- I've updated the comment (and re-organized slightly) so hopefully this is more clear. The point is to avoid calling `dequeueTask()` O(numPendingTasks) times inside the scheduler (that's one of the major problems w/ the old blacklisting).
--- 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