Skip to content

Conversation

@typhoonzero
Copy link
Contributor

fix #6978
fix #6893

Copy link
Contributor

@Yancey0623 Yancey0623 left a comment

Choose a reason for hiding this comment

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

I haven't seen the code about how to deal with SIGINT in the send side(trainer), or maybe you have any other idea?

}

virtual ~RecvOp() {
void Stop() override {
Copy link
Contributor

Choose a reason for hiding this comment

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

Maybe we also need the destructor function, and call Stop() in it.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

No. recv_op's Run may run in another thread (in unit test), Stop must be called out side dtor

Copy link
Contributor

Choose a reason for hiding this comment

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

So we also need to add the interface to pybind , maybe we coud do that in another PR.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yep. We can add it later when running in different clusters.

Yancey0623
Yancey0623 previously approved these changes Dec 26, 2017
Copy link
Contributor

@Yancey0623 Yancey0623 left a comment

Choose a reason for hiding this comment

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

LGTM

Copy link
Contributor

@Yancey0623 Yancey0623 left a comment

Choose a reason for hiding this comment

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

LGTM++

@typhoonzero typhoonzero merged commit 4cade60 into PaddlePaddle:develop Dec 26, 2017
@typhoonzero typhoonzero deleted the fix_sendrecv_ut branch December 27, 2017 02:03
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.

send recv unit test failed at develop branch recv_op need graceful shutdown

2 participants