dbeer at adaptivecomputing.com
Wed Nov 13 09:40:47 MST 2013
I'm not certain how to get a good value for vmem other than through
empirical use. One possible way to do this would be to set
in the mom's config file and reboot the mom. This parameter makes it so
that the mom will not kill the job for going over the limit. Then you could
see about how much the job uses and make your requests based on that.
On Wed, Nov 13, 2013 at 6:09 AM, Delphine Ramalingom <
delphine.ramalingom at univ-reunion.fr> wrote:
> I have a problem with vmem. How can I know the value I should fix to
> vmem in my script ?
> I put
> #PBS -l nodes=1:ppn=1,mem=28gb,vmem=28gb
> and I have the error message :
> =>> PBS: job killed: vmem 37569708032 exceeded limit 30064771072
> We have Torque + maui installed and configured to cancel job that exceed
> torqueusers mailing list
> torqueusers at supercluster.org
David Beer | Senior Software Engineer
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the torqueusers