GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — CORE-96: Sempar - Expose Linux core class and maximum frequency by peter-lawrey · Pull Request #210 · OpenHFT/Java-Thread-Affinity

Conversation

@peter-lawrey

@peter-lawrey peter-lawrey commented Nov 11, 2026 •
edited
Loading

Uh oh!

There was an error while loading. Please reload this page.

Copy link
Copy Markdown
Member

During a hybrid-CPU benchmark investigation, the sender was found on CPU 21 while the experiment expected performance-core placement. Operators had to inspect PMU lists and CPU frequencies manually. This change exposes those observations without changing allocation or claiming that a sampled frequency proves performance.

Add immutable CPU capability snapshots, restricted to the caller-supplied mask intersected with online CPUs. Intel hybrid PMU membership supplies coarse PERFORMANCE/EFFICIENCY/UNKNOWN class and source. Optional cpuinfo_max_freq supplies maximum kHz and its separate source; missing values remain unknown. Do not infer class from CPU IDs or MHz, and do not substitute a governor cap for the hardware maximum. Includes corrected README affinity examples and a focused capability guide.

Verification: fresh Linux/Java 21 offline mvn -o -q -f affinity/pom.xml verify: 93 tests, 91 passed, two existing JNIClock skips, zero failures/errors. Fifteen capability/frequency fixture tests cover sparse/restricted/offline CPUs, unknown/malformed/conflicting data, refresh, optional maximum and source semantics. Retained online-mask negative control fails. The updated API also compiles for Java 8. A local observation reported CPU 0/12/21 maxima of 4800000/3800000/2500000 kHz; this is not a benchmark.

Draft conditions: review the public API and source/unknown semantics. The PMU source cannot distinguish E from LP-E, sysfs reads are not atomic with hotplug, and the caller owns the eligibility envelope. Other hosts/platforms and manual acceptance remain open. No automatic placement, performance ranking or speedup is established.

Develop refresh — 11 November 2026

Rebased onto develop e2da74d257f993d08f39a844848bae503fb3a036; incremental PR changes are unchanged. Fresh Linux/Java 21 offline clean verify passed for the full affinity module; the two existing JNIClock skips remain. Previously triaged cross-platform CI failures remain open; this local verification does not establish green TeamCity matrices.

Candidate-owned CI repair — 11 November 2026

Windows CI exposed slash-specific expected source paths. Build the expected paths with the fixture filesystem instead. Production detection is unchanged. Linux/Java 21 offline module verify: 93 tests, zero failures/errors, two existing JNIClock skips. Windows rerun remains required.

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.

All reactions
@peter-lawrey peter-lawrey mentioned this pull request Nov 11, 2026
CORE-96: Sempar - Prefer performance cores and CPU-zero NUMA locality #214
Open
@peter-lawrey
CORE-96: Sempar - Add read-only Linux hybrid core detection
bd8ae79
Expose immutable CPU-class snapshots from kernel PMU lists intersected with online and caller-allowed CPUs. Preserve unknown data and source provenance without changing allocation. E versus LP-E remains unresolved. Validate fixtures, an online-mask mutant and a Java 8 host probe; affinity module verify passes with two existing skipped tests.
@peter-lawrey
peter-lawrey force-pushed the bugfix/core-96-sempar-aff-1 branch from 64cf602 to bd8ae79 Compare November 11, 2026 14:44
@peter-lawrey
CORE-96: Sempar - Use platform paths in capability fixtures
c249c6b
@peter-lawrey peter-lawrey mentioned this pull request Nov 11, 2026
CORE-96: Sempar - Add a read-only CPU capability CLI #213
Open
@peter-lawrey
peter-lawrey marked this pull request as ready for review November 11, 2026 18:12
@peter-lawrey
peter-lawrey requested a review from a team as a code owner November 11, 2026 18:12

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Uh oh!

There was an error while loading. Please reload this page.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Uh oh!

There was an error while loading. Please reload this page.

1 participant

@peter-lawrey
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.
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.