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

kv/client: use region based rate limiter and decouple it from event handler (#3118) #3131

Merged

Conversation

ti-chi-bot
Copy link
Member

This is an automated cherry-pick of #3118

What problem does this PR solve?

To fix part of #3110

If blocking happens in region worker because of rate limit, the receiving buffer of gRPC connection could be full and cause congestion in a gRPC channel, which would lead to back pressure in TiKV and slow incremental scan.

What is changed and how it works?

  • Use a standalone rate limiter for each region, put the rate limiter in kv client error handler, instead of event handler. With this optimization, we can reduce blocking time in core event handling path to accelerate consuming data from gRPC buffer.
  • Use channel mechanism when waiting all events are processed instead of polling mechanism to decrease latency.
  • Reset some metrics counter after region worker exits

After this PR

latency_after

cdc_memory_after

Before this PR

latency_before

cdc_memory_before

Check List

Tests

  • Unit test
  • Integration test

Existing unit tests have covered the functional of change, the performance benchmark is launched manuall.

Release note

Optimize the rate limit control when TiKV reloads and fix the congestion in gPRC, which may cause slow initialization phase.

@ti-chi-bot
Copy link
Member Author

[REVIEW NOTIFICATION]

This pull request has not been approved.

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 ti-chi-bot added release-note Denotes a PR that will be considered when it comes time to generate release notes. do-not-merge/cherry-pick-not-approved labels Oct 25, 2021
@ti-chi-bot ti-chi-bot added component/kv-client TiKV kv log client component. size/L Denotes a PR that changes 100-499 lines, ignoring generated files. status/LGT2 Indicates that a PR has LGTM 2. subject/performance Denotes an issue or pull request is related to replication performance. type/cherry-pick-for-release-4.0 This PR is cherry-picked to release-4.0 from a source PR. labels Oct 25, 2021
@ti-chi-bot ti-chi-bot added size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. and removed size/L Denotes a PR that changes 100-499 lines, ignoring generated files. labels Oct 25, 2021
@nongfushanquan nongfushanquan added cherry-pick-approved Cherry pick PR approved by release team. and removed do-not-merge/cherry-pick-not-approved labels Oct 26, 2021
@ti-chi-bot ti-chi-bot added the needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. label Oct 26, 2021
@amyangfei amyangfei added this to the v4.0.16 milestone Oct 26, 2021
@ti-chi-bot ti-chi-bot added size/L Denotes a PR that changes 100-499 lines, ignoring generated files. and removed needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files. labels Oct 26, 2021
@amyangfei
Copy link
Contributor

/merge

@ti-chi-bot
Copy link
Member Author

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

Commit hash: 28b1779

@ti-chi-bot ti-chi-bot added the status/can-merge Indicates a PR has been approved by a committer. label Oct 26, 2021
@amyangfei
Copy link
Contributor

/run-integration-tests

3 similar comments
@amyangfei
Copy link
Contributor

/run-integration-tests

@amyangfei
Copy link
Contributor

/run-integration-tests

@amyangfei
Copy link
Contributor

/run-integration-tests

@codecov-commenter
Copy link

Codecov Report

Merging #3131 (28b1779) into release-4.0 (753073a) will increase coverage by 3.5641%.
The diff coverage is 67.2092%.

@@                 Coverage Diff                 @@
##           release-4.0      #3131        +/-   ##
===================================================
+ Coverage      53.7661%   57.3302%   +3.5641%     
===================================================
  Files              153        164        +11     
  Lines            15958      19515      +3557     
===================================================
+ Hits              8580      11188      +2608     
- Misses            6475       7265       +790     
- Partials           903       1062       +159     

@ti-chi-bot ti-chi-bot merged commit d7bfe6c into pingcap:release-4.0 Oct 26, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cherry-pick-approved Cherry pick PR approved by release team. component/kv-client TiKV kv log client component. release-note Denotes a PR that will be considered when it comes time to generate release notes. 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. subject/performance Denotes an issue or pull request is related to replication performance. type/cherry-pick-for-release-4.0 This PR is cherry-picked to release-4.0 from a source PR.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants