Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

lightning: replace grpc gzip compressor with klauspost/compress/gzip #41974

Merged
merged 6 commits into from
Mar 7, 2023

Conversation

sleepymole
Copy link
Contributor

@sleepymole sleepymole commented Mar 7, 2023

What problem does this PR solve?

Issue Number: close #41970

Problem Summary:

The default gzip library has poor performance. See the issue for more details.

What is changed and how it works?

Replace gzip compressor implementation with klauspost/compress/gzip. Test the same 562GiB data in the issue, with compression enabled, the time cost reduced to 50m7s, which is a big improvement.

Also in unit test, we can see that our custom GzipCompressor is better than the default grpc.GzipCompressor.

> go test -bench "^Benchmar.*(Compressor|Decompressor)$" -run "^$"
goos: linux
goarch: amd64
pkg: github.com/pingcap/tidb/br/pkg/lightning/backend/local
cpu: AMD Ryzen 7 3700X 8-Core Processor             
BenchmarkGzipCompressor-16                  2149            698146 ns/op
BenchmarkGrpcGzipCompressor-16                60          20362977 ns/op
BenchmarkGzipDecompressor-16                1005           1107029 ns/op
BenchmarkGrpcGzipDecompressor-16             986           1122713 ns/op
PASS
ok      github.com/pingcap/tidb/br/pkg/lightning/backend/local  6.545s

Check List

Tests

  • Unit test
  • Integration test
  • Manual test (add detailed scripts or steps below)
  • No code

Side effects

  • Performance regression: Consumes more CPU
  • Performance regression: Consumes more Memory
  • Breaking backward compatibility

Documentation

  • Affects user behaviors
  • Contains syntax changes
  • Contains variable changes
  • Contains experimental features
  • Changes MySQL compatibility

Release note

Please refer to Release Notes Language Style Guide to write a quality release note.

None

@ti-chi-bot
Copy link
Member

ti-chi-bot commented Mar 7, 2023

[REVIEW NOTIFICATION]

This pull request has been approved by:

  • lance6716
  • lichunzhu

To complete the pull request process, please ask the reviewers in the list to review by filling /cc @reviewer in the comment.
After your PR has acquired the required number of LGTMs, you can assign this pull request to the committer in the list by filling /assign @committer in the comment to help you merge this pull request.

The full list of commands accepted by this bot can be found here.

Reviewer can indicate their review by submitting an approval review.
Reviewer can cancel approval by submitting a request changes review.

@ti-chi-bot
Copy link
Member

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

@ti-chi-bot ti-chi-bot added release-note-none Denotes a PR that doesn't merit a release note. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. labels Mar 7, 2023
@sleepymole sleepymole added the component/lightning This issue is related to Lightning of TiDB. label Mar 7, 2023
@sleepymole sleepymole marked this pull request as ready for review March 7, 2023 04:11
@ti-chi-bot ti-chi-bot removed the do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. label Mar 7, 2023
@sleepymole
Copy link
Contributor Author

/retest

case config.CompressionGzip:
opts = append(opts, grpc.WithDefaultCallOptions(grpc.UseCompressor(gzip.Name)))
// Use custom compressor/decompressor to speed up compression/decompression.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe we can register our gzip Compressor with the name "gzip2" or something? Not important, we can postpone it when upstream remove this API

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No, we can't. The name will be sent to the server. The server can't recognize gzip2.

@ti-chi-bot ti-chi-bot added the status/LGT1 Indicates that a PR has LGTM 1. label Mar 7, 2023
Copy link
Contributor

@lichunzhu lichunzhu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ti-chi-bot ti-chi-bot added status/LGT2 Indicates that a PR has LGTM 2. and removed status/LGT1 Indicates that a PR has LGTM 1. labels Mar 7, 2023
@sleepymole
Copy link
Contributor Author

/merge

@ti-chi-bot
Copy link
Member

This pull request has been accepted and is ready to merge.

Commit hash: ed58668

@ti-chi-bot ti-chi-bot added the status/can-merge Indicates a PR has been approved by a committer. label Mar 7, 2023
@ti-chi-bot ti-chi-bot merged commit 7d7350f into pingcap:master Mar 7, 2023
@sleepymole sleepymole deleted the issue-41970 branch March 7, 2023 07:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component/lightning This issue is related to Lightning of TiDB. release-note-none Denotes a PR that doesn't merit a release note. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. status/can-merge Indicates a PR has been approved by a committer. status/LGT2 Indicates that a PR has LGTM 2.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

lightning: optimize the performance of compression when sending kv pairs to tikv
4 participants