feat(perf): add per-plan hardware performance counters to EXPLAIN PERF#19493
Merged
zhang2014 merged 5 commits intodatabendlabs:mainfrom Mar 9, 2026
Merged
feat(perf): add per-plan hardware performance counters to EXPLAIN PERF#19493zhang2014 merged 5 commits intodatabendlabs:mainfrom
zhang2014 merged 5 commits intodatabendlabs:mainfrom
Conversation
github-actions
bot
added
the
pr-feature
Contributor
Docker Image for PR
|
- Add PerfEvent hw counters (cycles, instructions, branch misses, cache refs/misses) - Support grouped and standalone perf counter modes with per-event multiplexing info - Propagate PerfConfig through ExecutorSettings and QueryCtxShared - Add DataPacket::QueryPerfCounters flight packet for distributed hw counter collection - Fix distributed EXPLAIN PERF: enable perf on remote nodes, propagate executor to ctx - Fix double profiler start on coordinator node via is_request_server guard - Render per-node hw counter tables in EXPLAIN PERF HTML output Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
dqhl76
added
ci-cloud
Contributor
Docker Image for PR
|
Add missing Software variants (CpuClock, AlignmentFaults, EmulationFaults, BpfOutput, CgroupSwitches) and Cache variant (NodeReadMisses, NodeReadAccesses). Reorder Hardware and Software sections to match perf_event2 declaration order. Add sqllogictest covering all event names.
![chatgpt-codex-connector[bot]](https://avatars.gh.umua.top/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 6282a11ef8
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
zhang2014
approved these changes
Mar 9, 2026
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.
I hereby agree to the terms of the CLA available at: https://docs.databend.com/dev/policies/cla/
Summary
closes #19488
This PR integrates Linux perf_event hardware performance counters into EXPLAIN PERF, providing CPU microarchitecture-level insights per query plan node alongside
the existing flamegraph output.
Extended SQL syntax
The
EXPLAIN PERFsyntax has been extended to support both default and custom hardware event profiling. We introduced a grouping syntax (+) to pair related events, which is necessary for calculating derived metrics like IPC (Instructions Per Cycle) or cache miss rates.default:
group
cycles+instructionsto get IPC to get cache miss rate:not group:
Tests
Type of change
This change is