xuanyuanking commented on a change in pull request #25620: [SPARK-25341][Core]
Support rolling back a shuffle map stage and re-generate the shuffle files
URL: https://github.com/apache/spark/pull/25620#discussion_r321556517
##########
File path: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
##########
@@ -1105,7 +1105,16 @@ private[spark] class DAGScheduler(
private def submitMissingTasks(stage: Stage, jobId: Int) {
logDebug("submitMissingTasks(" + stage + ")")
- // First figure out the indexes of partition ids to compute.
+ // Before find missing partition, do the intermediate state clean work
first.
+ // The operation here can make sure for the intermediate stage,
`findMissingPartitions()`
+ // returns all partitions every time.
+ stage match {
Review comment:
That's for the scenario of ExecutorLost. While executor lost happened,
there's possible for the indeterminate stage rerun triggered by
`submitParentStage`.
So if we only unregister during failure handling, only fetch failed stage
and its parent stage do unregister, that logic would not cover the scenario of
its parent's parent stage is indeterminate and have missing tasks.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
