Urgent! Gaia server reboot!
Piotr Bartosiewicz
pbartosi at andrew.cmu.edu
Thu Aug 27 17:33:09 EDT 2026
Update:
Gaia is back online.
You should be able to ssh to the auton cluster if you haven't managed to
get yourself banned by trying too many times in the last hour.
I know you have deadlines now/soon but consider placing your main work
directory on zfsauton/scratch in near future.
Right now scratch can hold high load better than home directory.
Piotr.
On Thu, Aug 27, 2026 at 3:16 PM Piotr Bartosiewicz <pbartosi at andrew.cmu.edu>
wrote:
> Greetings!
>
> Gaia is a file server hosting our home directories and it is having
> serious issues.
> I'm unable to restart local services so the server has to be rebooted.
> It will affect all slurm jobs and most likely will corrupt your data.
> To minimize that risk, in 30 minutes all jobs will be canceled then the
> server will be rebooted.
> In other words: you have 30 minutes to stop your jobs and save what you
> can.
>
> Piotr.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20260827/4f0ea461/attachment.html>
More information about the Autonlab-users
mailing list