[SPIP][POC] Driver scaling: parallel schedulers#40077
Closed
ozhembr wants to merge 1 commit intoapache:branch-3.1from
Closed
[SPIP][POC] Driver scaling: parallel schedulers#40077ozhembr wants to merge 1 commit intoapache:branch-3.1from
ozhembr wants to merge 1 commit intoapache:branch-3.1from
Conversation
Contributor
|
Before we try to use multiple task schedulers, why not fix the parallelism issues in the existing one. Moving from a locking everywhere approach, to an event loop should yield quite a throughput improvement. |
Author
|
@hvanhovell it won't be enough, we still need to scale communication with executors |
|
We're closing this PR because it hasn't been updated in a while. This isn't a judgement on the merit of the PR in any way. It's just a way of keeping the PR queue manageable. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
SPIP: https://docs.google.com/document/d/1_MVEpGxz6U_CNqKArR1M1l2oP-3I7O67grfwPtniLaA/edit?usp=sharing
POC of scaling Spark Driver via parallel schedulers.
Uses multiple groups of
CoarseGrainedSchedulerBackend, TaskSchedulerImplWhy are the changes needed?
Low performance of Spark Driver with multiple large jobs.
Does this PR introduce any user-facing change?
Configs for enabling parallel schedulers:
spark.driver.schedulers.parallelism- number of parallel schedulers, no value or <= 1 will disable parallelismHow was this patch tested?
Comparison tests with spark-sql processes of same parallelism level