Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/16867#discussion_r104513453
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala ---
@@ -740,6 +743,7 @@ private[spark] class TaskSetManager(
}
removeRunningTask(tid)
info.markFinished(state)
+ successfulTaskDurations.remove(taskInfos(tid).duration)
--- End diff --
When we have executor failures (or due to pre-emption), this can
essentially cause a large number of sub-optimal (new) speculative tasks to be
executed.
Handling tasks which had not succeeded can be handled by looking at
taskInfo to see if it has completed already ? (Yes, an if condition is required
before remove).
---
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]
