Github user devaraj-kavali commented on a diff in the pull request:
https://github.com/apache/spark/pull/11996#discussion_r63736986
--- Diff:
core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala ---
@@ -789,6 +791,51 @@ class TaskSetManagerSuite extends SparkFunSuite with
LocalSparkContext with Logg
assert(TaskLocation("executor_host1_3") ===
ExecutorCacheTaskLocation("host1", "3"))
}
+ test("Kill other task attempts when one attempt belonging to the same
task succeeds") {
+ sc = new SparkContext("local", "test")
+ val sched = new FakeTaskScheduler(sc, ("exec1", "host1"), ("exec2",
"host2"))
+ val taskSet = FakeTask.createTaskSet(4)
+ val manager = new TaskSetManager(sched, taskSet, MAX_TASK_FAILURES)
+ val accumUpdatesByTask: Array[Seq[AccumulableInfo]] =
taskSet.tasks.map { task =>
+ task.initialAccumulators.map { a => a.toInfo(Some(0L), None) }
+ }
+ // Offer resources for 4 tasks to start
+ for ((k, v) <- List(
+ "exec1" -> "host1",
+ "exec1" -> "host1",
+ "exec2" -> "host2",
+ "exec2" -> "host2")) {
+ val taskOption = manager.resourceOffer(k, v, NO_PREF)
+ assert(taskOption.isDefined)
+ val task = taskOption.get
+ assert(task.executorId === k)
+ }
+ assert(sched.startedTasks.toSet === Set(0, 1, 2, 3))
+ // Complete the 3 tasks and leave 1 task in running
+ for (id <- Set(0, 1, 2)) {
+ manager.handleSuccessfulTask(id, createTaskResult(id,
accumUpdatesByTask(id)))
+ assert(sched.endedTasks(id) === Success)
+ }
+
+ // Wait for the threshold time to start speculative attempt for the
running task
+ Thread.sleep(100)
+ val speculation = manager.checkSpeculatableTasks
+ assert(speculation === true)
+ // Offer resource to start the speculative attempt for the running task
+ val taskOption5 = manager.resourceOffer("exec1", "host1", NO_PREF)
+ assert(taskOption5.isDefined)
+ val task5 = taskOption5.get
+ assert(task5.taskId === 4)
+ assert(task5.executorId === "exec1")
+ assert(task5.attemptNumber === 1)
+ sched.backend = mock(classOf[SchedulerBackend])
+ // Complete the speculative attempt for the running task
+ manager.handleSuccessfulTask(4, createTaskResult(3,
accumUpdatesByTask(3)))
+ assert(sched.endedTasks(3) === Success)
--- End diff --
Here **sched.backend** is **mock(classOf[SchedulerBackend])** and as part
of **manager.handleSuccessfulTask()**, it issues **sched.backend.killTask()**
for any other attempts. Since it is a mock invocation it only ensures that
other attempts kill invocation is happening. I have added the same in the
comment.
---
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
