Repository navigation
Prioritize hot buffers and accelerate paging progress - #14
Merged
Merged
Conversation
nerdrx
changed the title
nerdrx
marked this pull request as ready for review
October 19, 2026 14:55
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Recovery previously chose the oldest eligible nonlocal buffer, and snapshot compression replaced its application-use timestamp. Preserve use history and prioritize eligible buffers by recent known-submission frequency, breaking ties by most recent use. Frequency is bounded and decays; unknown accesses retain conservative recency tracking without inventing popularity. Pressure eviction remains oldest-first.
After committed pressure paging or recovery, the worker yields for 1 ms before continuing; blocked attempts retain slower polling. In-flight, compatibility, quiet-time and budget guards are unchanged.
Validation includes failing-before timestamp/ranking regressions, normal and genuinely hook-enabled CPU tests, an end-to-end mocked worker drain/busy/stop fixture, and frequency decay/deduplication/freeze-preservation checks. The latest-policy bounded native buffer-device-address GPU fixture passed full-byte recovery and zero final tracked resources; the earlier production async live-cap fixture also passed. No game FPS or migration-latency claim.
Prepared as v0.4.29. Five package tests pass. Release/install await final-head CI; no installed change yet.