Modifying priority for jobs requeud after an HPC infrastructure problem

Sorry for not providing any help, but I have the same issue. Moreover, all my running jobs were stopped (ExitCode 1, can’t provide the full log since I can’t access my home ) and they now have to be resubmitted and wait again in the queue - this happened already twice in the last ~1 month.
It would be great to have some insight and to know if there’s a way to take this into account for having a higher priority when resubmitting those jobs. Thanks!

Hi there,

you originally posted at Trouble accessing Yggdrasil today.

This is normal if the analysis could no more read/write data to the Yggdrasil ${HOME} space.

As far as I remember, there were no other BeeGFS issues on Yggdrasil in the last 2 months.

Actually, the latest issue I am aware of on Yggdrasil was the temporary disk space on login1, which dates back to 2021-04-07T22:00:00Z (cf. Current issues on Baobab and Yggdrasil - #41 by Luca.Capello).

After your private request last week, we have discussed internally about this and we are not going to do that, sorry.

Thx, bye,