Hi Chris, Christopher Samuel <[email protected]> writes:
> On 04/12/15 00:26, Loris Bennett wrote: > >> where upon some of the jobs which had been pending immediately started. >> >> However, for the other jobs which are still pending the reason >> 'AssocMaxJobsLimit' is still given. >> >> I assume that this is just a bug in the display of 'squeue' (version >> 14.11.8). Can anyone confirm this? > > Fro what I've seen in the past the status of a job is only updated when > the scheduler next tries to run it, so that message will stay there > until then. > > The "hack" to refresh it is to set the partition to down and then up and > it'll go back to pending. :-) > > All the best, > Chris I think I was vaguely aware of this, but didn't know what the update interval was and didn't think to look. It turns out we have the default 60s. It seems like the situation persisted for longer, but then again, maybe I was just being impatient. Thanks for the hint. Loris -- Dr. Loris Bennett (Mr.) ZEDAT, Freie Universität Berlin Email [email protected]
