rmcyang opened a new pull request #33932:
URL: https://github.com/apache/spark/pull/33932
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines:
https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR:
https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g.,
'[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a
faster review.
7. If you want to add a new configuration, please read the guideline first
for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
8. If you want to add or modify an error type or message, please read the
guideline first in
'core/src/main/resources/error/README.md'.
-->
### What changes were proposed in this pull request?
<!--
Please clarify what changes you are proposing. The purpose of this section
is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR. See the examples below.
1. If you refactor some codes with changing classes, showing the class
hierarchy will help reviewers.
2. If you fix some SQL features, you can provide some references of other
DBMSes.
3. If there is design documentation, please add the link.
4. If there is a discussion in the mailing list, please add the link.
-->
This is one of the patches for SPARK-33235: Push-based Shuffle Improvement
Tasks.
At high level, in `MapOutputTrackerWorker`, if serialized `MergeStatuse`
array size is larger than
threshold(`spark.shuffle.push.mergeResult.minSizeForReducedCache`), cache the
much more compact serialized bytes instead and only cache the deserialized
`MergeStatus` objects that are needed (within `startPartitionId` until
`endPartitionId`). Then deserialize the `MergeStatus` array from the cached
serialized bytes again.
### Why are the changes needed?
<!--
Please clarify why the changes are needed. For instance,
1. If you propose a new API, clarify the use case for a new API.
2. If you fix a bug, you can clarify why it is a bug.
-->
For large shuffles with 10s or 100s of thousands of shuffle partitions,
caching the entire deserialized and decompressed MergeStatus array on the
executor side, while perhaps only 0.1% of them are going to be used by the
tasks running in this executor is a huge waste of memory.
This change helps save memory as well as helps with reducing GC pressure on
executor side.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such as
the documentation fix.
If yes, please clarify the previous behavior and the change this PR proposes
- provide the console output, description and/or an example to show the
behavior difference if possible.
If possible, please also clarify if this is a user-facing change compared to
the released Spark versions or within the unreleased branches such as master.
If no, write 'No'.
-->
Yes. This PR introduces a client-side config for push-based
shuffle(`spark.shuffle.push.mergeResult.minSizeForReducedCache`). If push-based
shuffle is turned-off then the users will not see any change.
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some
test cases that check the changes thoroughly including negative and positive
cases if possible.
If it was tested in a way different from regular unit tests, please clarify
how you tested step by step, ideally copy and paste-able, so that other
reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why
it was difficult to add.
-->
Added unit test.
Verified effectiveness with jobs that would fail due to GC issue otherwise.
Ran the benchmark using GitHub Actions and did not observe any performance
penalties. The results are attached in this PR:
```
core/benchmarks/MapStatusesSerDeserBenchmark-jdk11-results.txt
core/benchmarks/MapStatusesSerDeserBenchmark-results.txt
```
Lead-authored-by: Min Shen ms...@linkedin.com
Co-authored-by: Chandni Singh chsi...@linkedin.com
Co-authored-by: Minchu Yang miny...@linkedin.com
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
