Repository navigation
perf(io): read directly into JavaScript file buffers - #2200
Merged
nicolas-abril merged 3 commits intoNov 18, 2026
Merged
Conversation
toprameen
marked this pull request as ready for review
November 17, 2026 19:16
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
JavaScript file reads allocated a temporary view and a one-element array for each host call. Positive reads now fill the existing buffer directly. Zero-byte reads still use
readvSyncso Bun reports OS errors such asEBADFon a write-only handle.For 40,000 50-byte lines on macOS ARM64, the median of seven paired runs went from 979 to 770 ms on Bun and from 1,089 to 1,022 ms on Node. A single 16 MiB read and EOF check stayed within 1 ms of baseline. Repeated zero-byte Bun reads were slower in some stress runs.
The prompt fixture observes the direct read and still fails if the scheduler flush is removed. Local macOS and Linux ARM64 file fixtures preserve baseline results, and the repository gate passes 56/56. The mini-cluster gates did not run.