[tinker] Route uvicorn's access log to a plain handler instead of Rich - #11
Closed
avigyabb wants to merge 1 commit into
Closed
[tinker] Route uvicorn's access log to a plain handler instead of Rich#11avigyabb wants to merge 1 commit into
avigyabb wants to merge 1 commit into
Conversation
RichHandler renders every access-log record through a rich Table, about 1.5ms of event-loop CPU per HTTP request. Under rollout load that was 63% of the Tinker API server's CPU: a 4096-sample run spent 12.5s of its 19.9s of server CPU in rich.logging.emit. With a plain StreamHandler for uvicorn.access the same run takes 9.7s and server throughput goes from 337 to 568 samples/s. Startup and error logging keep the Rich handler. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Signed-off-by: Avi Basnet <avigyabb@stanford.edu>
This was referenced Sep 4, 2026
avigyabb
marked this pull request as ready for review
September 4, 2026 00:40
Owner
Author
|
Moved upstream: NovaSky-AI#2160 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack 1/7. Independent of the rest.
RichHandler renders each access-log record through a rich Table, about 1.5 ms of event-loop CPU per HTTP request. Under rollout load that was 63% of the Tinker API server's CPU: profiling a 4096-sample run showed 12.5 s of its 19.9 s of server CPU inside
rich.logging.emit. With a plainStreamHandlerforuvicorn.accessthe same run takes 9.7 s and server throughput goes from 337 to 568 samples/s. Startup and error logging keep the Rich handler.Measured with the load harness in stack 7/7 (
skyrl/benchmarks/load_test_tinker_sampling.py).Stack
🤖 Generated with Claude Code