leletan opened a new pull request, #45715:
URL: https://github.com/apache/spark/pull/45715
<!--
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
'common/utils/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.
-->
During spark submit, for K8s cluster mode driver, instead of always
downloading jars and serving it to executors, make it only happen when its url
matches scheme in the configuration.
### 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 K8s cluster mode driver, `SparkSubmit` will download all the jars in the
`spark.jars` to driver and then those jars' urls in `spark.jars` will be
replaced by the driver local paths. Later when driver starts the
`SparkContext`, it will copy all the `spark.jars` to
`spark.app.initial.jar.urls`, start a file server and replace the jars with
driver local paths in `spark.app.initial.jar.urls` with file service urls. When
the executors start, they will download those driver local jars by
`spark.app.initial.jar.urls`.
When jars are big and the spark application requests a lot of executors, the
executors' massive concurrent download of the jars from the driver will cause
network saturation. In this case, the executors jar download will timeout,
causing executors to be terminated. From user point of view, the application is
trapped in the loop of massive executor loss and re-provision, but never gets
enough live executors as requested, leads to SLA breach or sometimes failure.
So instead of letting driver to download the jars and then serve them to
executors, if we just avoid driver from downloading the jars and keeping the
urls in `spark.jars` as they were, the executor will try to directly download
the jars from the urls provided by user. This will avoid the driver download
bottleneck mentioned above, especially when jar urls are with scalable storage
schemes, like s3 or hdfs.
Meanwhile, there are cases jar urls are with schemes of less scalable than
driver file server, e.g. http, ftp, etc, or when the jars are small, or
executor count is small - user may still want to fall back to current solution
and use driver file server to serve the jars.
So in this case, make the driver jars downloading and serving optional by
scheme (similar idea to `FORCE_DOWNLOAD_SCHEMES` in YARN) is a good approach
for the solution.
### 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'.
-->
A configuration `spark.kubernetes.jars.avoidDownloadSchemes` is added
### 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.
-->
- Unit tests added
- Tested with an application running on AWS EKS submitted with a 1GB jar on
s3.
- Before the fix, the application could not scale beyond 1000 live
executors.
- After the fix, the application had no problem to scale 12k live
executors.
### 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.
-->
No
--
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]
