Repository navigation
issues: what #1129's wake-affinity rule measured before it closed - #1158
Merged
Merged
Conversation
ab10 on the AMD bench separated the rule from its plumbing with an arm that names and counts every waker but never moves a task. The rule's gain is real; the plumbing costs mem.munmap_touched_remote.4k about 5% in every boot that carries it, with or without the moves, and the pre-set decision rule closes #1129 on that and on rows the bench's bimodal modes make unreadable. The track keeps the design, its numbers and the constraints a successor must not re-derive. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Records in
issues/placement-has-no-migration-cost-or-wake-affinity.mdwhat #1129's wake-affinity rule measured, as #1129 closes.Problem
#1129 built the near half of the track's "wake-affine vs spread": a woken task moves to its waker's LLC after 8 parked wakes in a row from it. Its final A/B, ab10, ran 12 AMD boots including an arm with all of #1129's plumbing and no moves. By the decision rule fixed before the run, it is not landable:
mem.munmap_touched_remote.4kabout +5%, consistently since ab5; the mechanism is not found.The orchestrator's consolidation rule closes it on this result, with its findings kept in the track.
Resulting behaviour
None: issues only. The track keeps the design, the gain and the cost with their numbers, and the constraints a successor would otherwise re-derive.
Evidence: ab10 judgment.
Checks
None run: one Markdown file.
🤖 Generated with Claude Code