[slurm-users] jobs stuck in ReqNodeNotAvail,
anthon at rth.dk
Thu Nov 30 07:41:39 MST 2017
I now realised I probably need some kind of job preemption to make
things work the way I want them to. I'll take a look at how slurm does that.
On 30-11-2017 13:29, Chris Samuel wrote:
> On Thursday, 30 November 2017 9:40:53 PM AEDT Christian Anthon wrote:
>> The queue has a ton of of single-core jobs and somebody submits a high
>> priority multi-core job, will the mulit-core job not run before all
>> single-core jobs are done or will slurm free up a node?
> I can see you are weighting the size of a job, so that should help increase
> its priority and get in front of the other jobs.
> To see how the priorities for waiting jobs are being calculated run "sprio -l"
> and you'll see how those priorities are working out. That will let you
> juggle the weightings to get what you want.
> All the best,
More information about the slurm-users