-
Notifications
You must be signed in to change notification settings - Fork 6.5k
[serve] Handle request with Semaphore #54019
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[serve] Handle request with Semaphore #54019
Conversation
f50a3c0
to
84a4f9e
Compare
Mind adding some description on what's the goal of the PR? |
python/ray/serve/_private/replica.py
Outdated
@@ -354,6 +364,7 @@ def __init__( | |||
self._component_id = self._replica_id.unique_id | |||
self._configure_logger_and_profilers(self._deployment_config.logging_config) | |||
self._event_loop = get_or_create_event_loop() | |||
self._num_queued_requests = 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
self._num_queued_requests
is not required and can be removed.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@abrarsheikh resolved at a035ca3
Signed-off-by: doyoung <doyoung@anyscale.com>
Signed-off-by: doyoung <doyoung@anyscale.com>
ce65881
to
a035ca3
Compare
This PR updates how the logic on determining if the request can be currently handled or not with Semaphore and number of ongoing requests. --------- Signed-off-by: doyoung <doyoung@anyscale.com>
This PR updates how the logic on determining if the request can be currently handled or not with Semaphore and number of ongoing requests.