perf: read and write runs of consecutive sectors in one go - #85
Open
francisdb wants to merge 1 commit into
Open
Conversation
Chains went through the underlying reader or writer one sector per call. Consecutive sectors are now read or written in a single call.
francisdb
force-pushed
the
perf/contiguous-sector-io
branch
from
September 8, 2026 08:41
8875d61 to
561e03c
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A chain read or wrote one sector per call to the underlying reader or writer. Sectors of a chain are almost always consecutive in the file, so a chain now reads and writes through as many consecutive sectors as the buffer covers in one call (
Sectors::read_contiguous/write_contiguous,Chain::run_len), and a write past the end of the chain adds all the sectors it needs before writing.Writing 50 streams of 1 MiB to memory: 14.4 ms to 11.0 ms. File-backed writes barely move yet, because growing a chain still costs two FAT entry writes and a zero fill per sector; batching that allocation is a follow-up PR built on this one.
Tests cover multi-sector writes whose sectors are and are not consecutive (reused free sectors), appends starting inside an existing sector, chains that outgrow a FAT sector, and reads spanning runs.