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.

Sign up for GitHub

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

Jump to bottom

Segfault in CUDA support when KNEM not present and CMA is active intra-node RMA transport #2919

Closed
bureddy opened this issue Oct 4, 2018 · 1 comment
Closed

Segfault in CUDA support when KNEM not present and CMA is active intra-node RMA transport #2919

bureddy opened this issue Oct 4, 2018 · 1 comment
Assignees
@bureddy
Labels
Bug
Milestone
v1.5.0

Comments

@bureddy
Copy link
Contributor

bureddy commented Oct 4, 2018

When KNEM is not present, CMA will be selected for RMA for which RKEY is not needed. When RKEY is not needed, it is wrongly selecting CMA lane for cuda mem type rma.

Workarounds:
install KNEM
(or)
Disable CMA (--disable-cma)
(or)
not select cma through UCX_TLS.
@shamisp shamisp added the Bug label Oct 4, 2018
@yosefe yosefe added this to the v1.5.0 milestone Oct 15, 2018
@bureddy
Copy link
Contributor Author

bureddy commented Oct 26, 2018

#2995

@bureddy bureddy mentioned this issue Oct 31, 2018
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@bureddy bureddy

Labels
Bug
Projects
None yet
Milestone
v1.5.0
Development

No branches or pull requests
3 participants
@shamisp @yosefe @bureddy