executor: reduce overhead of copystack in idxlookup workers

[zyguan]

also refine the worker pool

What problem does this PR solve?

Issue Number: ref #56649

Problem Summary: copystack in index lookup workers consume a lot of cpu resources.

What changed and how does it work?

Growing the stack at the beginning of the worker goroutine. Also refine the implementation of the worker pool.

And here are some benchmark results.

Workload	Threads	TPS (this PR)	TPS (baseline)	Diff
idxlookup	32	2797.99	2708.88	3.3%
idxlookup	64	3292.84	3123.35	5.4%

Check List

Tests

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

  • I checked and no code files have been changed.

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

[tiprow]

Hi @zyguan. Thanks for your PR.

PRs from untrusted users cannot be marked as trusted with /ok-to-test in this repo meaning untrusted PR authors can never trigger tests themselves. Collaborators can still trigger tests on the PR using /test all.

I understand the commands that are listed here.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

[zyguan]

/ok-to-test

[codecov]

Codecov Report

Attention: Patch coverage is 85.00000% with 3 lines in your changes missing coverage. Please review.

Project coverage is 74.0355%. Comparing base (e79d22f) to head (dba0f17).
Report is 44 commits behind head on master.

Additional details and impacted files

@@               Coverage Diff                @@
##             master     #58705        +/-   ##
================================================
+ Coverage   73.1071%   74.0355%   +0.9284%     
================================================
  Files          1677       1679         +2     
  Lines        463662     477734     +14072     
================================================
+ Hits         338970     353693     +14723     
+ Misses       103866     102681      -1185     
- Partials      20826      21360       +534     

Flag	Coverage Δ
integration	42.9040% <75.0000%> (?)
unit	72.4304% <85.0000%> (+0.1465%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Components	Coverage Δ
dumpling	52.6910% <ø> (ø)
parser	∅ <ø> (∅)
br	45.7539% <ø> (+0.0448%)	⬆️

[ti-chi-bot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: cfzjywxk, crazycs520

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

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [cfzjywxk,crazycs520]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[ti-chi-bot]

[LGTM Timeline notifier]

Timeline:

• 2025-01-13 02:46:39.730115281 +0000 UTC m=+753743.018946984: ☑️ agreed by crazycs520.
• 2025-01-13 03:05:33.976814247 +0000 UTC m=+754877.265645952: ☑️ agreed by cfzjywxk.

[zimulala]

This feels like 8K. Is that a mistake or something else?

[zyguan]

Not a mistake, allocating a 8K var on stack requires 16K stack size.