[torqueusers] Question about the difference between a node where pbs_server is run and a compute node
Ken Nielson
knielson at adaptivecomputing.com
Fri Apr 30 10:19:11 MDT 2010
On 04/30/2010 09:59 AM, Bas van der Vlies wrote:
> We have not changed anything to the unix sockets code. We have not
> changed anything with pbs_iff as well. We need to get into your system
> to see where the hang up is.
>
> Ken,
>
> There is a simple test.
> * ssh<batch_server_node>
> * put hostname output in /var/spool/torque/server_name.
> *
> {{{
> ipython
> import pbs
> pbs.pbs_connect( pbs.pbs_default() )
> }}}}
> * qstat
>
> We have tested this on several clusters with different linux distribution.
>
> --
> Bas van der Vlies
> basv at sara.nl<mailto:basv at sara.nl>
>
>
I will give this a try and let you know what I find out.
Ken
More information about the torqueusers
mailing list