feat: reduce read syscalls to improve performance #4485
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
lrstewart
force-pushed
the
recv_buffering
branch
from
764b7f4 to
2e4e1d8
Compare
camshaft
reviewed
Apr 3, 2024
goatgoose
reviewed
Apr 3, 2024
goatgoose
approved these changes
Apr 4, 2024
Co-authored-by: Sam Clark <3758302+goatgoose@users.noreply.github.com>
lrstewart
force-pushed
the
recv_buffering
branch
from
1fcac73 to
16436df
Compare
camshaft
approved these changes
Apr 5, 2024
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Outdated suggestions cannot be applied.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.
Description of changes:
If we want to read one TLS record at a time, we need two reads: one to read the fixed-size header, which includes the total record size, and one to use that record size to read the rest of the record.
However, if we're willing to potentially read more than one record at a time, we can just perform a single optimistic read that attempts to read as much data as we can buffer. This reduces the cost of reads, since reading a record now takes <= 1 read syscall rather than 2 read syscalls. The optimization isn't for free though-- applications need to ensure that they can handle the behavior change.
Testing:
New unit tests.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.