Prefer cooperative compression over offload to blocking pool. #3153
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
mstyura
force-pushed
the
cooperative-compression
branch
from
e5877cb
to
d90883f
Compare
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Outdated suggestions cannot be applied.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.
PR Type
Refactor
PR Checklist
Overview
The current implementation of compression middleware offloads compression of chunks larger than 1024 bytes to a blocking pool. Presumably, this was done to avoid preventing other requests from being served, as no other future can make progress due to the CPU-bound operation that compression is.
Threads from the blocking pool do not provide more computational resources than what is already available to runtime polling futures. Therefore, it makes sense to perform compression in chunks by yielding control from the compression future to other futures, allowing everyone to make progress.
I've also observed uncontrollable thread count growth when benchmarking a real-world application with compression of JSON responses enabled:
