-
Notifications
You must be signed in to change notification settings - Fork 158
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
Improve decoupled shm handling #337
Conversation
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.
Happy to see a 1-line fix!
Is this the small "growth" (~dozen bytes or so) we saw consistently in this test? Or does it address any other growths or issues as well?
It's the consistent small growth on the decoupled IO test. Might fixed other decoupled issue, but I didn't test for it explicitly. |
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.
Great catch!
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.
It is not really a leak based on the offline conversation so perhaps change the PR title to
"Release received message to avoid shm probe failures".
Related PR: triton-inference-server/server#6803
Free decoupled shm memory as soon as the memory will not be accessed any more.