GitHub user jinxing64 opened a pull request:
https://github.com/apache/spark/pull/18239
[SPARK-19462] fix bug in Exchange--pass in a tmp "newPartitioning" in
"prepareShuffleDependency"
When `spark.sql.adaptive.enabled` is true, any rerunning of ancestors of
`ShuffledRowRDD` will fail. It can be triggered by `FetchFailed` or killing
some executors, which can lead to rerunning of the tasks. This is because the
`newPartitioning` is set to be `UnknownPartitioning` after the post shuffleRDD
is prepared.
This pr proposes pass in a tmp "newPartitioning" in
"prepareShuffleDependency". Thus we can rerun the ancestor tasks.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/jinxing64/spark SPARK-19462
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/18239.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #18239
----
commit debd107c845e40504feb37a34665318b1885bf71
Author: jinxing <[email protected]>
Date: 2017-06-08T08:57:23Z
[SPARK-19462] fix bug in Exchange--pass in a tmp "newPartitioning" in
"prepareShuffleDependency"
----
---
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]
