Currently, job processing on CoolMUC-4 is massively disrupted. Multiple jobs show problems with the module system, licences, etc. We are investigating the problem and notify you as soon as it is fixed.
15:02 Outdated certificates have been replaced and nodes seem to behave normal again. We are running a series of test jobs. Note that there still might be some parts to fix in the aftermath of the problem. Not completely fixed yet.
Overnight the cluster has run stably. The problem appears to be fixed. The disruption is resolved.
Zuletzt aktualisiert: Do., 04.09.2025 15:19