Run CI tests with max processes#7254

ShaharNaveh

Recently our CI has started to take around an hour, this will make it faster at the cost of stability. I want to see how faster / stable this effect the CI

Summary by CodeRabbit

Chores
- CI now detects available CPU cores and runs most CPython tests in parallel for faster execution.
- A large platform-independent test allowlist was replaced with a smaller set of known-flaky multiprocessing tests.
Tests
- Flaky multiprocessing tests are executed separately, single-threaded, to improve reliability and avoid interfering with parallel runs.

coderabbitai

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 3ba46c64-cd6c-4fcb-b689-a20a7f18ce76

📥 Commits

Reviewing files that changed from the base of the PR and between 04274b4 and 954b0be.

📒 Files selected for processing (1)

.github/workflows/ci.yaml

🚧 Files skipped from review as they are similar to previous changes (1)

.github/workflows/ci.yaml

📝 Walkthrough

Walkthrough

Replaces a large platform-independent test allowlist with a smaller FLAKY_MP_TESTS, adds a step to detect CPU cores, runs the main CPython test suite in parallel using detected cores while excluding flaky MP tests, and runs flaky multiprocessing tests separately at -j 1.

Changes

Cohort / File(s)	Summary
CI Test Execution Restructuring `\.github/workflows/ci.yaml`	Removed `PLATFORM_INDEPENDENT_TESTS`; added `FLAKY_MP_TESTS` (multiprocessing tests + `test_eintr`); added "Detect available cores" step exporting `steps.cores.outputs.cores`; updated main CPython test step to `-j ${{ steps.cores.outputs.cores }}` and exclude `FLAKY_MP_TESTS`; added dedicated `-j 1` step to run `FLAKY_MP_TESTS`.

Sequence Diagram(s)

sequenceDiagram
    participant Workflow as GitHub Actions Workflow
    participant Runner as CI Runner
    participant CoreDetect as Core Detection Step
    participant RustPy as rustpython -m test

    Workflow->>Runner: start job
    Runner->>CoreDetect: execute core detection (os.process_cpu_count)
    CoreDetect-->>Workflow: outputs.cores
    Workflow->>RustPy: run CPython tests (-j ${{steps.cores.outputs.cores}}, -x FLAKY_MP_TESTS, matrix args/skips)
    RustPy-->>Workflow: report parallel test results
    Workflow->>RustPy: run FLAKY_MP_TESTS (-j 1, matrix args/skips)
    RustPy-->>Workflow: report flaky-mp test results

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

Cleanup ci.yaml matrix usage #7260: Similar modifications to .github/workflows/ci.yaml around allowlists and test invocation.
Restructure CI with matrix approach and multi-feature support #7376: CI workflow changes and test invocation restructuring overlapping this area.
Remove macos skips #5794: Adjusts CI test workflow skips/allowlists and touches related exclusion logic.

Suggested reviewers

youknowone

Poem

🐰 I hopped through CI lines so spry,
I counted cores beneath the sky,
Flaky hops now run one by one,
The rest bound fast when cores say run,
A rabbit cheers — the tests go by! 🎉

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title directly describes the main change: updating CI to run tests with maximum processes instead of previous sequential/limited parallelism approaches.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

📝 Coding Plan

Generate coding plan for human review comments

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

youknowone

Whats the option cpython is using?

ShaharNaveh

Whats the option cpython is using?

CPython uses max processes for their CI (from what I can tell)

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In @.github/workflows/ci.yaml:
- Around line 243-249: The "Detect available cores" step is calling a
non-existent Python function os.process_cpu_count(); update the step (id: cores)
to avoid Python and use bash instead: detect CPU count with a POSIX-safe command
such as nproc or getconf _NPROCESSORS_ONLN (falling back to 2 if detection
fails), assign the result to the cores variable and then echo "cores=${cores}"
>> $GITHUB_OUTPUT; ensure the step retains shell: bash and preserves the output
key name and id (cores) so downstream jobs still read the value.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 23cc4bdc-425b-4286-9c21-25706e3ebe20

📥 Commits

Reviewing files that changed from the base of the PR and between 3148024 and ccb66b1.

📒 Files selected for processing (1)

.github/workflows/ci.yaml

coderabbitai

Actionable comments posted: 1

♻️ Duplicate comments (1)

.github/workflows/ci.yaml (1)

244-249: ⚠️ Potential issue | 🟠 Major

Fix os.process_cpu_count() None handling and quote $GITHUB_OUTPUT.

Line 248 calls os.process_cpu_count(), which returns None in Python 3.14 when the usable CPU count cannot be determined. This causes the step to emit cores=None, which will fail downstream when passed to -j. Additionally, $GITHUB_OUTPUT on line 249 is unquoted, triggering shellcheck SC2086.

🛠️ Proposed fix

       - name: Detect available cores
         id: cores
         shell: bash
         run: |
-          cores=$(python -c 'print(__import__("os").process_cpu_count())')
-          echo "cores=${cores}" >> $GITHUB_OUTPUT
+          cores="$(python -c 'import os; print(os.process_cpu_count() or 1)')"
+          echo "cores=${cores}" >> "$GITHUB_OUTPUT"

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In @.github/workflows/ci.yaml around lines 244 - 249, The GitHub Actions step
named "Detect available cores" (id: cores) uses python to call
os.process_cpu_count(), which can return None in Python 3.14 and writes unquoted
$GITHUB_OUTPUT; update the python snippet to coerce a safe integer fallback
(e.g., use os.cpu_count() or process_cpu_count() or default to 1 when None) and
ensure you echo the output with quoted variable expansion (use "$GITHUB_OUTPUT")
so downstream `-j` receives a numeric value and shellcheck SC2086 is avoided.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In @.github/workflows/ci.yaml:
- Around line 251-254: The workflow change altered which tests run while also
changing parallelism; revert the test invocation in the "Run CPython tests" step
so the matrix-driven test split is preserved and only the -j value is varied:
keep the original joins/skip logic (the use of matrix.skips and
matrix.extra_test_args) exactly as before and do not narrow the suite to only
exclude FLAKY_MP_TESTS here; instead only change the -j argument coming from
steps.cores.outputs.cores so this PR isolates the max-process (‑j) experiment
without changing the test coverage shape.

---

Duplicate comments:
In @.github/workflows/ci.yaml:
- Around line 244-249: The GitHub Actions step named "Detect available cores"
(id: cores) uses python to call os.process_cpu_count(), which can return None in
Python 3.14 and writes unquoted $GITHUB_OUTPUT; update the python snippet to
coerce a safe integer fallback (e.g., use os.cpu_count() or process_cpu_count()
or default to 1 when None) and ensure you echo the output with quoted variable
expansion (use "$GITHUB_OUTPUT") so downstream `-j` receives a numeric value and
shellcheck SC2086 is avoided.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 5a9c912e-53d8-468b-84c8-c54d18ad90ad

📥 Commits

Reviewing files that changed from the base of the PR and between b641625 and 04274b4.

📒 Files selected for processing (1)

.github/workflows/ci.yaml

* Run CI witb max cores * Step for flaky MP tests * Add `test_class` to flkay mp tests

fanninpm reviewed Feb 27, 2026

View reviewed changes

ShaharNaveh force-pushed the parallel-ci branch from 6117934 to 802c499 Compare March 1, 2026 09:04

ShaharNaveh changed the title ~~Run CI tests with 4 processes~~ Mar 1, 2026

Run CI witb max cores

7f1ca40

ShaharNaveh force-pushed the parallel-ci branch from 9ad8f9f to 7f1ca40 Compare March 17, 2026 12:16

ShaharNaveh commented Mar 17, 2026

View reviewed changes

Step for flaky MP tests

ea0d06e

ShaharNaveh force-pushed the parallel-ci branch from 314686f to ea0d06e Compare March 17, 2026 13:49

ShaharNaveh mentioned this pull request Mar 17, 2026

Remove some tests from PLATFORM_INDEPENDENT_TESTS #7459

Merged

Merge remote-tracking branch 'upstream/main' into parallel-ci

ccb66b1

ShaharNaveh marked this pull request as ready for review March 18, 2026 13:45

coderabbitai Bot reviewed Mar 18, 2026

View reviewed changes

ShaharNaveh added 3 commits March 19, 2026 14:55

Merge remote-tracking branch 'upstream/main' into parallel-ci

b641625

Merge remote-tracking branch 'upstream/main' into parallel-ci

4cf7973

Add test_class to flkay mp tests

04274b4

coderabbitai Bot reviewed Mar 19, 2026

View reviewed changes

ShaharNaveh requested review from fanninpm and youknowone March 20, 2026 08:45

Merge remote-tracking branch 'upstream/main' into parallel-ci

954b0be

youknowone approved these changes Mar 20, 2026

View reviewed changes

youknowone pushed a commit to youknowone/RustPython that referenced this pull request Mar 22, 2026

Run CI tests with max processes (RustPython#7254) …

0983522

* Run CI witb max cores * Step for flaky MP tests * Add `test_class` to flkay mp tests

Copilot AI pushed a commit that referenced this pull request Mar 25, 2026

Run CI tests with max processes (#7254) …

820bb32

* Run CI witb max cores * Step for flaky MP tests * Add `test_class` to flkay mp tests

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Run CI tests with max processes#7254