[Berzelius-users] Berzelius downtime on the 4th and 5th of April

[Filip Polbratt]

Dear Berzelius Users,

Fixes have been applied to the filesystem and the compute nodes can 
mount the filesystem again. It is now possible to run jobs again.

Final fix to resolve the underlying issues will require a separate 
downtime when we receive those patches.

Best regards,
Filip Polbratt
NSC

On 4/14/25 10:27, Filip Polbratt wrote:
> Dear Berzelius Users,
> 
> Berzelius is still in maintenance mode due to issues with mounting the 
> filesystem on the compute nodes.
> 
> Our storage vendor believe that the issues can be resolved with a full 
> filesystem restart. All IO will be stopped during the restart. This will 
> likely be done with very short notice or no notice.
> 
> We still have a case with our storage vendor's R&D to make sure that all 
> issues encountered in the last week and a half will be solved.
> 
> Best regards,
> Filip Polbratt
> NSC
> 
> On 4/9/25 17:09, Filip Polbratt wrote:
>> Dear Berzelius Users,
>>
>> Berzelius is still in maintenance mode due to issues with mounting the 
>> filesystem on the compute nodes.
>>
>> However, the filesystem is mounted and usable on the login nodes. 
>> Because of this we have re-enabled logins, but it will not be possible 
>> to run jobs for the foreseeable future.
>>
>> There is currently no estimate on when it will be possible to run jobs 
>> again. Do not expect this to be solved this week.
>>
>> Our case with the storage vendor has been escalated to their R&D.
>>
>> Best regards,
>> Filip Polbratt
>> NSC
>>
>> On 4/7/25 09:23, Filip Polbratt wrote:
>>> Dear Berzelius Users,
>>>
>>> Berzelius is still in maintenance mode for the filesystem check. 
>>> Progress on the filesystem check has stalled after it encountered 
>>> unexpected issues on two of the servers.
>>>
>>> Currently we do not have an estimate on when Berzelius will be 
>>> available again.
>>>
>>> We are in contact with the storage vendor.
>>>
>>> Best regards,
>>> Filip Polbratt
>>> NSC
>>>
>>> On 3/25/25 16:12, Filip Polbratt wrote:
>>>> Dear Berzelius Users,
>>>>
>>>> on Friday the 4th of April we will start a maintenance window for 
>>>> several tasks that require significant downtime of the cluster. The 
>>>> primary task determining the length of the downtime is a filesystem 
>>>> check of the project storage. Berzelius will not be available until 
>>>> this task is complete.
>>>>
>>>> We are scheduling this maintenance window to start on the 4th at 
>>>> 09:00 and to last at least 48 hours.
>>>>
>>>> Best regards,
>>>> Filip Polbratt
>>>> NSC
>>>> _______________________________________________
>>>> Berzelius-users mailing list
>>>> Berzelius-users at lists.nsc.liu.se
>>>> https://lists.nsc.liu.se/mailman/listinfo/berzelius-users
>>>
>>> _______________________________________________
>>> Berzelius-users mailing list
>>> Berzelius-users at lists.nsc.liu.se
>>> https://lists.nsc.liu.se/mailman/listinfo/berzelius-users
>>
>> _______________________________________________
>> Berzelius-users mailing list
>> Berzelius-users at lists.nsc.liu.se
>> https://lists.nsc.liu.se/mailman/listinfo/berzelius-users
> 
> _______________________________________________
> Berzelius-users mailing list
> Berzelius-users at lists.nsc.liu.se
> https://lists.nsc.liu.se/mailman/listinfo/berzelius-users