[Hpc-notice] Issue with Slurm submitting new jobs

[Casey Mc Laughlin]

Hi HPC Users,

We are currently experiencing an issue with our scheduler software, Slurm. The issue affects submitting jobs. When you run a Slurm job submission command (sbatch or srun), you'll see this error message:

$ sbatch slurm-submit.sh
sbatch: error: Batch job submission failed: Socket timed out on send/recv operation

The Systems Team is investigating right now, and we expect to have a solution shortly.

As far as we are aware, the issue does not affect currently running jobs.

Thanks for your patience while we sort this issue out.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.fsu.edu/pipermail/hpc-notice/attachments/20210412/504ea954/attachment.html>