[torqueusers] simulating pbs/torque
Paul D Marshall
Paul.Marshall at Colorado.EDU
Tue Jun 23 09:58:43 MDT 2009
Yes, I'd definitely be interested in this.
Ken Nielson wrote:
> We have developed a torque which will allow multiple moms to run on the
> same node similar to what you have described. It is built on the 2.3.7
> code base for testing purposes. Would you be interested in trying out
> what we have?
> Ken Nielson
> Cluster Resources, Inc.
> Paul D Marshall wrote:
>> I was wondering if someone would be able to point me in the right direction.
>> I'm working with Torque 2.3.6 and I've been adding and removing machines
>> from my cluster dynamically (just via the qmgr command and starting or
>> killing pbs_mom processes on the workers).
>> I only have so many machines I can actually work with and so I've begun
>> to look into simulating the pbs_mom process. The problem that I
>> encountered with this is that there seem to be a variety of reasonably
>> complicated messages exchanged between the pbs_mom and server. So before
>> I dug myself too deep, I thought I'd check with others.
>> Does anyone know of another project or person who has simulated torque
>> on *some level*?
>> If not, can anyone provide suggestions as to where might be an
>> appropriate point to simulate the dispatching, running, and reporting of
>> jobs on pbs workers?
>> torqueusers mailing list
>> torqueusers at supercluster.org
> torqueusers mailing list
> torqueusers at supercluster.org
More information about the torqueusers