Linux Cluster: disturbances of SLURM operation

Dear users of the Linux Cluster,

Since Saturday, February 2, we are observing temporary disruptions of the SLURM services, causing SLURM commands to fail in irregular intervals. We are currently still investigating the precise cause of this, and will keep you updated about the progress via this document.

We urge you to avoid overloading the SLURM infrastructure through mass execution of queries (e.g. squeue, sview, sacct).


Verfasser: R. Bader, J. Pancorbo
veröffentlicht: 2019-02-08