Slurm scheduling issue (22.02.2024)

Since yesterday evening, we are experiencing some problems with the scheduling of jobs in Slurm due to a system issue that requires rebooting a larger number of nodes. Due to this, newly submitted jobs will have a longer pending time than usual.

We are working on resolving this issue as soon as possible and will publish updates on this wiki page.

We are sorry for the inconvenience

Updates

2024-02-22 08:50

We made some configuration changes to Slurm and restarted the batch system to improve the scheduling of jobs

2024-02-22 11:35

The issue is resolved. Jobs are again starting as expected.