This repository has been archived by the owner on Oct 2, 2024. It is now read-only.
use kernel fast paths for file copying #1742
Merged
Conversation
This file contains 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
shanegoff
approved these changes
Oct 26, 2023
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
ch-imagedoes a lot of file copying. In particular, as of PR #1741, build cache large files that are stored OOB are copied instead of hard-linked.The Linux kernel has two fast paths for copying regular files:
Make a reflink copy, where the destination file gets a new inode but shares all the data extents of the source file in a copy-on-write manner. Some filesystems support this.
Copy data in-kernel without passing through user-space. All filesystems support this.
Python ≥3.8 introduces
os.copy_file_range()that wraps the underlying system callcopy_file_range(2), which does #1 if possible and silently falls back to #2 if not.This PR implements a fast-path copy that calls
os.copy_file_range()if available and the source and destination are on the same filesystem. This should mitigate the performance loss in #1741 to some degree.