yaooqinn opened a new pull request, #43746:
URL: https://github.com/apache/spark/pull/43746
<!--
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 introduces a new configuration,
`spark.scheduler.minResourcesToSurviveRatio`, which works as:
When an application encounters the maximum number of executor failures, if
the scheduler still has sufficient resources, calculated by `live executors >=
max number of executor * ratio`, it will not fail immediately and will give its
best effort to finish what it started. The smaller the ratio is, the more
tolerant the application will be to executor failures. If the value >=1, it
means intolerant at all.
### 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.
-->
The ExecutorFailureTracker is overly sensitive to executor failures and
tends to overreact by terminating the application immediately upon reaching the
threshold, regardless of whether the current resources obtained are sufficient
or not. Since executor allocation depends on various factors such as resource
managers, host environments, and external dependencies, it may become
unavailable for some time. During this period, ExecutorFailureTracker may
accumulate enough failures to mistakenly kill itself.
Here is also an example from our prod,
The application had been running for hours before it suddenly crashed with
`Stage cancelled because SparkContext was shut down` and `Max number of
executor failures (20) reached`. Meanwhile, it still had 90% of maxNumExecutors
and was about to finish. In its final moments(< 10 secs), it only requested one
more executor.
The threshold of ExecutorFailureTracker is inflexible to use. It's
pre-configured by `spark.executor.maxNumFailures` or calculated by `2 * max
number of executor`. It does not consider the actual numbers of live executors.
Thus, `spark.scheduler.minResourcesToSurviveRatio` is introduced to evaluate
whether to terminate itself or leave it behind to the next round.
### 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, new configuation
### 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.
If benchmark tests were added, please run the benchmarks in GitHub Actions
for the consistent environment, and the instructions could accord to:
https://spark.apache.org/developer-tools.html#github-workflow-benchmarks.
-->
tested on yarn manually
### Was this patch authored or co-authored using generative AI tooling?
<!--
If generative AI tooling has been used in the process of authoring this
patch, please include the
phrase: 'Generated-by: ' followed by the name of the tool and its version.
If no, write 'No'.
Please refer to the [ASF Generative Tooling
Guidance](https://www.apache.org/legal/generative-tooling.html) for details.
-->
--
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]
