[feat][cp] Adds shuffle compression support#346
Open
Weixin-Xu wants to merge 1 commit intobytedance:mainfrom
Open
[feat][cp] Adds shuffle compression support#346Weixin-Xu wants to merge 1 commit intobytedance:mainfrom
Weixin-Xu wants to merge 1 commit intobytedance:mainfrom
Conversation
cp from facebookincubator/velox#11914 Summary: Adds per query shuffle compression support. Currently we configure compression kind in partition output buffer manager which enforces all the queries use the same compression kind and assume all the workers having the same compression kind which is not flexible not align with Presto java as well. This change removes the compression kind from partition output buffer manager and instead configure it through query config. Also the shuffle operators report the compression kind. The followup is to integrate with Prestissimo work by setting LZ4 compression kind if the shuffle compression session property is set. Note Presto java doesn't allow to configure compression kind to use. With Meta internal workloads, LZ4 compression kind can reduce e2e execution time by 20% with half of shuffle data volume reduction
Collaborator
|
@zhangxffff can you review this to see any conflict with the existing Spark shuffle compression? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
cp from facebookincubator/velox#11914
Summary:
Adds per query shuffle compression support. Currently we configure compression kind in partition output buffer manager which enforces all the queries use the same compression kind and assume all the workers having the same compression kind which is not flexible not align with Presto java as well. This change removes the compression kind from partition output buffer manager and instead configure it through query config. Also the shuffle operators report the compression kind.
The followup is to integrate with Prestissimo work by setting LZ4 compression kind if the shuffle compression session property is set. Note Presto java doesn't allow to configure compression kind to use.
With Meta internal workloads, LZ4 compression kind can reduce e2e execution time by 20% with half of shuffle data volume reduction
What problem does this PR solve?
Issue Number: close #xxx
Type of Change
Description
Describe your changes in detail.
For complex logic, explain the "Why" and "How".
Performance Impact
No Impact: This change does not affect the critical path (e.g., build system, doc, error handling).
Positive Impact: I have run benchmarks.
Click to view Benchmark Results
Negative Impact: Explained below (e.g., trade-off for correctness).
Release Note
Please describe the changes in this PR
Release Note:
Checklist (For Author)
Breaking Changes
No
Yes (Description: ...)
Click to view Breaking Changes