Hello,
I'm starting to evaluate slurm and I'm coming from a torque/moab background. On
our clusters we operate a single user policy. That is, a compute node can only
be used by a single user - only they can put jobs on to that node once it's
allocated. I would like to do the same thing in
com>
Subject: [slurm-dev] Re: Implementing a single node policy with slurm
Hi David -
When you define your partition you can state SHARED=exclusive, so when a node
is allocated only that user will have access to it.
Kelly
On 02/09/16, Baker D.J.<d.j.ba...@soton.ac.uk<mailto:d.j.ba...
Hello Jeff,
Thank you for your reply. I've noticed that sacct and scontrol appear to be
slow to update. For the moment I have added a small delay in my epilog script
and that appears to help to a degree. I'll see how this goes -- especially with
users coming on board soon. In this respect your
Hello,
Could someone in the slurm community please advise me on outputting data (job
stats) at the end of a job. I'm currently using the Epilog (slurm.epilog.clean)
to print out a report at the end of each slurm job. This works, however it is
far from ideal. The slurm.epilog.clean can be
Hello,
This is essentially a follow up question to my previous posting re "using the
epilog scripts to print out job stats". I'm currently printing out the job
stats using the slurm.epilog.clean script. When testing out array jobs on the
cluster I see that job stats are printed out for all the
