Ngone51 opened a new pull request #33451:
URL: https://github.com/apache/spark/pull/33451
<!--
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 PR adds support to diagnose shuffle data corruption. Basically, the
diagnosis mechanism works like this:
The shuffler reader would calculate the checksum (c1) for the corrupted
shuffle block and send it to the server where the block is stored. At the
server, it would read back the checksum (c2) that is stored in the checksum
file and recalculate the checksum (c3) for the corresponding shuffle block.
Then, if c2 != c3, we suspect the corruption is caused by the disk issue.
Otherwise, if c1 != c3, we suspect the corruption is caused by the network
issue. Otherwise, the checksum verifies pass. In any case of the error, the
cause remains unknown.
After the shuffle reader receives the diagnosis response, it'd take the
action bases on the type of cause. Only in case of the network issue, we'd give
a retry. Otherwise, we'd throw the fetch failure directly. Also note that, if
the corruption happens inside BufferReleasingInputStream, the reducer will
throw the fetch failure immediately no matter what the cause is since the data
has been partially consumed by downstream RDDs. If corruption happens again
after retry, the reducer will throw the fetch failure directly this time
without the diagnosis.
Please check out https://github.com/apache/spark/pull/32385 to see the
completed proposal of the shuffle checksum project.
### 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.
-->
Shuffle data corruption is a long-standing issue in Spark. For example, in
SPARK-18105, people continually reports corruption issue. However, data
corruption is difficult to reproduce in most cases and even harder to tell the
root cause. We don't know if it's a Spark issue or not. With the diagnosis
support for the shuffle corruption, Spark itself can at least distinguish the
cause between disk and network, which is very important for users.
### 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, users may know the cause of the shuffle corruption after this 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 tests.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
