Dear Fram users,
We have to do emergency maintenance on Fram storage system, one of the controller has to be rebooted to eliminate errors, during the maintenance /cluster filesystem speed will be degraded. we will update you here.
11:50 Maintenance is over, controller is rebooted. Filesystem performance is back to normal.
Dear Fram users:
Login prompts hangs on both login nodes on Fram, some of the commands may also cause hang. Slurm jobs are not affected as far as we can see.
We are investigating the hang issue on login nodes, will keep users updated.
There seems to have been a problem with the Fram /cluster file system between 23:50 on Friday and 00:30 on Saturday. Symptoms were error messages like “No space left on device”. Because of this problem lots for compute nodes are drained. we are investigating the problem.
There is an ongoing attack against academic HPC centers in Europe right now, and several clusters and storage systems have been compromised. The attackers have used stolen credentials (passwords and/or SSH keys) to get into systems. We are investigating whether any of our systems are affected. In the mean time we encourage everyone to create new SSH keys. See https://documentation.sigma2.no/getting_started/create_ssh_keys.html for a description of how to create SSH keys. Please do set a passphrase on the keys, so they will be worthless if they should be stolen. Please also remember to remove old SSH keys from your ~/.ssh/authorized_keys file on each system (NIRD, Fram, Saga, Stallo, Vilje), so noone can use the old keys any more.
Dear Fram users,
We still have lustre quota problem on Fram cluster where “dusage” command may give you inaccurate numbers.
To eliminate this issue we need downtime which will take about 4 hours.
Date for downtime is not decided, we will give you an update as soon as we have more information.
Meanwhile if you have any problem related to quota on Fram please contact us.
Dear Fram users:
Fram interconnect network manager crashed yesterday at 15:34, which caused all compute nodes had degraded routing information. This can cause Slurm jobs crash with a communication error.
Interconnect network manager is running again, and all compute nodes have the latest routing information, and communication between the compute nodes are restored.
We apologize for the inconvenience if you have any question please don’t hesitate to contact support.
/cluster filesystem on Saga is crashed, we are working on it. users should expect that their Slurm jobs will crash.
Update, 09:45: The file system is back online now. Only parts of /cluster was unavailable, but we recommend you to check your jobs, some of them will probably have crached.
Dear Saga cluster Users:
We have discovered /cluster filesystem issue on Saga, which can lead to possible data corruption, to be able to examine the problem, we decided to suspend all running jobs on Saga and reserve entire cluster. No new job will be accepted until problem is resolved.
Users can still login to Saga login nodes.
We are sorry for any inconvenience this may have caused.
We will keep you updated as we progress.
Update: We are trying to repair the file system without killing all jobs. It might not work, at least not for all jobs. In the mean time, we have closed access to the login nodes to avoid more damage to the file system.
Update 14:15: Problem resolved, Saga is open again. Please check if you have running jobs, some of the jobs could get crashed.
The source of the problem is related to the underlying filesystem (XFS) and the current kernel that we are running. We scanned the underlying filesystem on our OSS servers to eliminate possible data corruption on /cluster filesystem, and we also updated kernel on OSS’es.
Please don’t hesitate to contact us if you have any questions
One of the fileserver had a problem which caused some of the folders under /cluster is unavailable.
The problem is resolved now.
NIRD storage system was crashed and unavailable for short period of time.
Due to this crash, users logged in to NIRD and Fram experienced problemes.
The problem is resolved, NIRD storage system is online now.
Please contact us if you still encounter problems.
Note: The export of NIRD to FRAM does not work currently