Skip to content
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

IODEMO: fix progress loop #7662

Merged

Conversation

evgeny-leksikov
Copy link
Contributor

@evgeny-leksikov evgeny-leksikov commented Nov 16, 2021

What

Fix progress loop in io_demo

Why

Fixes a hang in io_demo test over shared memory transport

How

If progress_worker_event() returns false, we don't progress the io message. We have to progress io_msg and worker at least once to avoid the situation when io_msg is completed on previous iteration of worker progress.
The issue is stable reproducible with shared memory transport

@yosefe
Copy link
Contributor

yosefe commented Nov 16, 2021

what failure does it fix?

@evgeny-leksikov
Copy link
Contributor Author

what failure does it fix?

stuck with UCX_TLS=rc_x,shm

@yosefe
Copy link
Contributor

yosefe commented Nov 16, 2021

because progress_worker_event() returns false and we don't progress the io message?

@evgeny-leksikov
Copy link
Contributor Author

because progress_worker_event() returns false and we don't progress the io message?

exactly

Copy link
Contributor

@yosefe yosefe left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pls update PR description with issue symptom

@evgeny-leksikov
Copy link
Contributor Author

pls update PR description with issue symptom

done

@changchengx
Copy link
Contributor

Under shm transports, io_demo works with this PR.

@evgeny-leksikov
Copy link
Contributor Author

/azp run

@azure-pipelines
Copy link

Azure Pipelines successfully started running 3 pipeline(s).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants