due to a necessary maintenance in the cooling infrastructure, an interruption of operation will be necessary on CoolMUC-3 and several housing systems (httf, htus, kcs, kcs_nim, htrp, htce, htfd, lcg, tum_aer). The batch nodes of the system will be taken offline on June 12 at 16:00.
This means that neither scripted batch jobs nor “salloc” style interactive jobs will execute. The interruption is expected to take 2 calendar days.
The login nodes lxlogin[8-9] and kcs-login will be taken offline on June 12 at 16:00, lxlogin[1-4] can be used as a fallback.
The reboot of the cluster is planned for the morning of June 14. We will try to minimize the downtime and start with the reboot as soon as possible.
With best regards, Your LRZ HPC Systems and Services team
System status of LRZ HPC systems: High Performance Computing status page
Zuletzt aktualisiert: Mi., 14.06.2023 14:14