Github user kayousterhout commented on a diff in the pull request: https://github.com/apache/spark/pull/16867#discussion_r104515525 --- 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 -- You mean for shuffle map tasks, where the task completed successfully but then the executor was lost later, so we re-run the task? That case seems OK to leave the task time in, because it's still a valid task completion time.
--- 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