On 5/22/19 6:34 AM, Aravindh Sampathkumar wrote:
Nothing has changed recently, and today, I noticed that the QOS limits
which were working until now has silently stopped working. A user was
able to submit jobs enough to saturate the cluster singlehandedly
annoying other users.
Can you check that the QOS on your jobs is still set?
We have an odd bug where we occasionally see jobs lose their QOS when
restarting slurmctld for reasons that are yet unknown. :-(
All the best,
Chris
--
Chris Samuel : http://www.csamuel.org/ : Berkeley, CA, USA