Dear IANVS users, the cluster is back online. There has been no data loss on the /home or /scratch partitions. The issue happened because today, on 2025-01-30 08:30, an error during repairs to the ITZ’s power infrastructure led to a voltage spike on one of our two power lanes. The ITZ’s systems have redundant power […]
Patrice Peterson
Alle Artikel von Patrice Peterson
30. Jan 2025
IANVS: Unplanned downtime, job loss
Dear IANVS users, we regret to inform you that the IANVS cluster is currently experiencing total system failure. Currently running jobs have been lost. We will do our best to keep data on the /home partition safe. We are investigating the cause and will update you as soon as we have more information. Best regards, […]
12. Sep 2024
IANVS: Back online
Dear IANVS users, the cluster is back online. The issue happened because yesterday, on 2024-09-11 15:50, an error during repairs to the ITZ’s cooling infrastructure led to a short building-wide power outage on one of our two power lanes. The ITZ’s systems have redundant power supplies and were mostly not affected. While IANVS has redundant […]
11. Sep 2024
IANVS: Unplanned downtime, job loss, data loss on /scratch
Dear IANVS users, we regret to inform you that the IANVS cluster is currently experiencing total system failure. We expect the downtime to last at least until tomorrow noon (2024-09-12 12:00). Both running jobs and jobs still in the queue have been lost. There will probably be data loss on the /scratch partition. We will […]
4. Apr 2024
IANVS: Downtime due to GPFS issues
Update 2024-04-04 16:25: The issues have been resolved. The cluster is back online. Dear IANVS users, the cluster is currently offline due to filesystem issues. We will notify you once the issues have been resolved. The data itself should not be impacted. We apologize for the inconvenience. Please contact us if you have any questions: […]
22. Mrz 2024
HPC: Default module version policy change
Dear HPC users, we have decided to implement a policy change during the maintenance window on April 2nd: When a user loads a module without specifying a version, they will get the newest installed version of the software instead of the oldest. During the maintenance window, all software installed on the cluster will be switched […]
15. Mrz 2024
IANVS: Maintenance window on 2024-04-02 09:00 to 17:00
Update 2024-04-02 18:14: The maintenance window is over. Updates have been successfully applied.
19. Feb 2024
IANVS: Deprecation of the Anaconda module
Dear IANVS users, we are deprecating the Anaconda module and replacing it with Micromamba, a small, fast alternative implementation of Anaconda’s package manager, Conda. We have also added a short tutorial on how to use Micromamba environments. Why?
17. Mrz 2023
IANVS: Higher quality of service for test jobs
When you are still testing out your submit scripts, having to wait for a long time only to find your job has quit with an error can be very frustrating. In order to help with this, we have set up a new Quality of Service (QOS) category for jobs, called test. The test QOS is intended to be used for high-priority, high-turnaround jobs that are small, short-lived, and don’t use a lot of resources.
21. Jun 2022
HPC: License server migration on 2022-06-23 15:00
Dear HPC users, the license servers liz.itz.uni-halle.de, liz2.itz.uni-halle.de, and liz3.itz.uni-halle.de will be migrated to new infrastructure on Thursday, 2022-06-23 15:00. This will result in a short amount of downtime (minutes) for these servers. As a consequence, the following software will not be able to check out licenses from these license servers during the maintenance window: Avizo Fire QuantumATK […]