[SPARK-XXXXX][CORE] Skip task serialization for local executor backend #49355
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Member
There was a problem hiding this comment.
Could you file a JIRA issue and use its ID, @viirya ?
Member
Author
|
Thanks @dongjoon-hyun. I changed this to draft as some test failures in the CI. I will add a JIRA issue once this is ready. |
Member
Author
|
Looks like Spark in many places replies some tricks during serialization. Skipping serialization will cause errors. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What changes were proposed in this pull request?
This patch removes task serialization when scheduling tasks for local executor backend. The tasks are directly passed to the local executor to run.
Why are the changes needed?
Spark serializes tasks and attaches serialized tasks in task description before submitting tasks to executors. For remote executor backends, this is necessary. But for local executor backend, it runs in same JVM with master. It seems that task serialization for local executor backend is not necessary.
Does this PR introduce any user-facing change?
No
How was this patch tested?
Manual test local mode.
Was this patch authored or co-authored using generative AI tooling?
No