Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/8887#discussion_r42198578
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala ---
@@ -795,31 +795,40 @@ private[spark] class TaskSetManager(
addPendingTask(index, readding = true)
}
- // Re-enqueue any tasks that ran on the failed executor if this is a
shuffle map stage,
- // and we are not using an external shuffle server which could serve
the shuffle outputs.
- // The reason is the next stage wouldn't be able to fetch the data
from this dead executor
- // so we would need to rerun these tasks on other executors.
- if (tasks(0).isInstanceOf[ShuffleMapTask] &&
!env.blockManager.externalShuffleServiceEnabled) {
- for ((tid, info) <- taskInfos if info.executorId == execId) {
- val index = taskInfos(tid).index
- if (successful(index)) {
- successful(index) = false
- copiesRunning(index) -= 1
- tasksSuccessful -= 1
- addPendingTask(index)
- // Tell the DAGScheduler that this task was resubmitted so that
it doesn't think our
- // stage finishes when a total of tasks.size tasks finish.
- sched.dagScheduler.taskEnded(tasks(index), Resubmitted, null,
null, info, null)
+ reason match {
+ case LossReasonPending =>
+ // Nothing else to do until the actual loss reason is known.
--- End diff --
can you add that we expect `executorLost` to be called a second time with
the real loss reason?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
