Dear NIRD users. We need to conduct some small maintenance along with DDN(vendor) on a small part of NIRD-TRD today at around 11:00.
According to the vendor this operation should not affect the availability of the system.
Update: After a meeting with the vendor we have to postpone this until next week.
There is currently a problem with accessing files below /cluster on Saga. As a consequence Saga does not function properly.
We are working on the issue. Sorry for the inconvenience.
Update 27 September @ 13:15
The issue has been resolved and you can use Saga and /cluster normally again. We are looking for an underling problem.
We need to power cycle a small part of NIRD-TRD storage tomorrow 27.09.22
This will be done in production and according to DDN(hw manufactor) This should not affect your work. Regardless we want to tell you that we need to conduct some work on NIRD-TRD and if you experience any issues or problems please let us know.
Best Regards
Infrastructure team.
There is currently a problem with accessing files below /cluster on Saga. As a consequence Saga does not function properly.
We are working on the issue. Sorry for the inconvenience.
Update 26.09 @ 9:10:
The filesystem issue is resolved and Saga is functioning properly again.
We have updated the version of the “pmix” RPM on Saga. This is used internally by OpenMPI. There should for most parts be no visible change from this, but some instances of OpenMPI’s “mpirun” that used to crash with a “segmentation fault” error will now work.
We are currently experiencing issues with the filesystem on Betzy.
The problem affects mainly /cluster/work area.
We are trying to fix this as quickly as possible.
[UPDATE: 17:00] Problem with filesystem persists. Login nodes are now offline. We have contacted the vendor.
[UPDATE: 19:30] login nodes are back online.
We are currently experiencing a problem with accessing some of the services running on TOS-NIRD and are working on it. Sorry for the inconvenience.
Update 24-08 @ 12.30:
Services should be accessible again. Please contact us if you still experience problems.
Dear NIRD Toolkit and NIRD Service Platform user,
We have the pleasure to announce out-rolling of new authentication system for enhanced user experience, as well an upgraded and clean look front-end for the NIRD Toolkit this upcoming Friday.
The upgrade process will start at 09:00 on the 26th of August. Please note that the upgrade process might lead to service interruption.
Thank you for your understanding!
We are going to conduct a file system check on Fram file system. This might lead to degraded performance while the scan is ongoing.
We are diagnosing reports of filesystem errors on Betzy. Subsequently diagnostics might make the filesystem unstable for a couple of hours. Hopefully users will not notice.
Update 11.08 @ 13:55:
We are running fsck as well as rebuilding some internal metadata. This process can result in performance degradation of filesystem operations in submitted jobs. Due to the nature of these checks, it is expected to last until tomorrow.
Update 12.08 @ 10:45:
Work on the filesystem is still ongoing and potential disruptions could still occur during the day.
Update 15.08 @ 10:55:
The filesystem issue is resolved and Betzy fs is working. If you should experience any problems please contact support.