Dear users,
the maintenance is now over!
What was done during this maintenance:
- Upgrade Slurm to version 20.11.7
- De activate MIG on A100 card on GPU020
- Enable local private space per job on compute nodes:
/dev/shm,/tmp,/scratch - Re install all the compute nodes with latest bugfix.
- Re installation of all the BeeGFS home servers in CentOS7 and perform a filesystem check
- various fixes
Thanks for your feedback in case you notice something weird or just because you wan to say hello:)
Best regards,
the HPC team