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

Slurm does not clean cgroupv2 #6

Open
rezib opened this issue Nov 6, 2024 · 0 comments
Open

Slurm does not clean cgroupv2 #6

rezib opened this issue Nov 6, 2024 · 0 comments
Labels
bug Something isn't working

Comments

@rezib
Copy link
Contributor

rezib commented Nov 6, 2024

For an unknown reason, Slurm does not properly clean cgroupv2 hierarchy and it ends up being full and fail with no space left in cgroup virtual filesystem.

A workaround is to clean empty cgroups on compute nodes, with:

On Debian:

# clush -bw cn[1-4] 'find /sys/fs/cgroup/system.slice/cn?_slurmstepd.scope -depth -type d -exec rmdir {} +'

On Rocky:

$ clush -bw cn[1-4] 'find /sys/fs/cgroup/system.slice/slurmstepd.scope -depth -type d -exec rmdir {} +
@rezib rezib added the bug Something isn't working label Nov 6, 2024
@rezib rezib added this to the v1.2.0 milestone Nov 8, 2024
@rezib rezib removed this from the v1.2.0 milestone Dec 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant