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

ci: codspeed walltime #2294

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
Draft

ci: codspeed walltime #2294

wants to merge 2 commits into from

Conversation

njzjz
Copy link
Member

@njzjz njzjz commented Oct 31, 2024

See https://docs.codspeed.io/instruments/walltime/#usage-with-github-actions

Summary by CodeRabbit

  • Chores
    • Updated workflow configuration to enhance benchmarking capabilities.
    • Renamed job from "Test with tox" to "Benchmark with codspeed."
    • Changed execution environment to codspeed-macro.
    • Added conditional execution for repository owner 'deepmodeling.'

Copy link

codecov bot commented Oct 31, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 96.19%. Comparing base (18ad1e4) to head (253e6cf).

Additional details and impacted files
@@            Coverage Diff             @@
##           master    #2294      +/-   ##
==========================================
+ Coverage   96.05%   96.19%   +0.14%     
==========================================
  Files          17       17              
  Lines        1418     1418              
==========================================
+ Hits         1362     1364       +2     
+ Misses         56       54       -2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link
Contributor

coderabbitai bot commented Oct 31, 2024

📝 Walkthrough

Walkthrough

The pull request modifies the workflow configuration in .github/workflows/benchmark.yml. It updates the job name from "Test with tox" to "Benchmark with codspeed" and changes the execution environment from ubuntu-latest to codspeed-macro. Additionally, it introduces a conditional execution clause based on the repository owner and adjusts the steps to include the installation of the uv package and the use of CodSpeedHQ/action@v3 for running benchmarks with authentication.

Changes

File Change Summary
.github/workflows/benchmark.yml - Job name changed from "Test with tox" to "Benchmark with codspeed".
- Execution environment changed from ubuntu-latest to codspeed-macro.
- Added conditional execution for repository owner 'deepmodeling'.
- Updated steps to install uv package and run benchmarks using CodSpeedHQ/action@v3.

Possibly related PRs


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 1

🧹 Outside diff range and nitpick comments (1)
.github/workflows/benchmark.yml (1)

Line range hint 24-25: Add descriptive names to the installation steps.

Consider adding names to the installation steps for better workflow visibility.

-    - run: pip install uv
-    - run: uv pip install --system -e .[test]
+    - name: Install uv package manager
+      run: pip install uv
+    - name: Install package dependencies
+      run: uv pip install --system -e .[test]
🧰 Tools
🪛 actionlint

18-18: label "codspeed-macro" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2022", "windows-2019", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-22.04", "ubuntu-20.04", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-14.0", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "macos-13.0", "macos-12-xl", "macos-12-xlarge", "macos-12-large", "macos-12", "macos-12.0", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Reviewing files that changed from the base of the PR and between 18ad1e4 and 253e6cf.

📒 Files selected for processing (1)
  • .github/workflows/benchmark.yml (1 hunks)
🧰 Additional context used
🪛 actionlint
.github/workflows/benchmark.yml

18-18: label "codspeed-macro" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2022", "windows-2019", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-22.04", "ubuntu-20.04", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-14.0", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "macos-13.0", "macos-12-xl", "macos-12-xlarge", "macos-12-large", "macos-12", "macos-12.0", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

🔇 Additional comments (1)
.github/workflows/benchmark.yml (1)

Line range hint 26-29: LGTM! CodSpeed integration is properly configured.

The benchmark setup correctly:

  • Uses the latest CodSpeed action version
  • Includes proper authentication
  • Runs pytest with the required --codspeed flag
🧰 Tools
🪛 actionlint

18-18: label "codspeed-macro" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2022", "windows-2019", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-22.04", "ubuntu-20.04", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-14.0", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "macos-13.0", "macos-12-xl", "macos-12-xlarge", "macos-12-large", "macos-12", "macos-12.0", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

Comment on lines +16 to +18
name: Benchmark with codspeed
if: ${{ github.repository_owner == 'deepmodeling' }}
runs-on: codspeed-macro
Copy link
Contributor

Choose a reason for hiding this comment

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

💡 Codebase verification

Action Required: Configure CODSPEED_TOKEN Repository Secret

The workflow is correctly configured to use CodSpeed's custom runner and token, but the required CODSPEED_TOKEN secret is not set in the repository. This token is necessary for the benchmark workflow to authenticate with CodSpeed's service.

  • Add the CODSPEED_TOKEN secret to your repository settings
  • You can obtain the token from your CodSpeed dashboard
🔗 Analysis chain

LGTM! Job configuration aligns with CodSpeed's requirements.

The changes appropriately:

  • Restrict the benchmark to run only for the main repository
  • Use CodSpeed's custom runner environment

Let's verify the repository configuration:


Let me verify if the CodSpeed token is used in the workflow file:

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Verify repository settings for CodSpeed integration
# Check if CODSPEED_TOKEN secret is configured
gh secret list 2>/dev/null | grep CODSPEED_TOKEN || echo "Warning: CODSPEED_TOKEN secret not found"

Length of output: 129


Script:

#!/bin/bash
# Check if CODSPEED_TOKEN is referenced in the workflow
rg -U "CODSPEED_TOKEN|codspeed/codspeed-benchmark-action" .github/workflows/benchmark.yml

Length of output: 136

🧰 Tools
🪛 actionlint

18-18: label "codspeed-macro" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2022", "windows-2019", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-22.04", "ubuntu-20.04", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-14.0", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "macos-13.0", "macos-12-xl", "macos-12-xlarge", "macos-12-large", "macos-12", "macos-12.0", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant