jiang13021 opened a new pull request, #2611:
URL: https://github.com/apache/celeborn/pull/2611
<!--
Thanks for sending a pull request! Here are some tips for you:
- Make sure the PR title start w/ a JIRA ticket, e.g. '[CELEBORN-XXXX]
Your PR title ...'.
- Be sure to keep the PR description updated to reflect all changes.
- Please write your PR title to summarize what this PR proposes.
- If possible, provide a concise example to reproduce the issue for a
faster review.
-->
### What changes were proposed in this pull request?
Decide whether to reuse the shuffle id based on the appShuffle's
numAvailableOutputs instead of deterministic level
### Why are the changes needed?
In Spark, the DAGScheduler determines whether to reuse task output based on
multiple factors, deterministic level is one of them, but not all. I
constructed a case in the test, where a shuffleId should be regenerated instead
of reused. IMO, celeborn should decide whether to reuse the shuffle id based on
whether the map output is empty, which means to delegating the decision of
reusing previous attempt results to the DAGScheduler.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Add a test:
org.apache.celeborn.tests.spark.CelebornFetchFailureSuite#test("celeborn spark
integration test - resubmit a barrier stage and do not reuse the shuffle id")
--
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]
