[torqueusers] TORQUE 2.0.0p1 Release

Dave Jackson jacksond at clusterresources.com
Thu Nov 10 10:39:23 MST 2005


Garrick,

  The biggest difference is that it works period.  The original code was
broken in more ways than you would want to know about.  

  We are currently working with a number of partner sites to build on
this capability to enable both load balancing and high availability.  We
would love to continue to grow the community involvement in this process
and get more ideas on community needs and best approaches to do this.  I
am sure this will be a topic at the SC 05 BOF.

Dave

On Thu, 2005-11-10 at 08:29 -0800, Garrick Staples wrote:
> On Thu, Nov 10, 2005 at 09:24:15AM +0000, Steve Traylen alleged:
> >  Do you have some details on 
> > 
> > >   multi-server support allowing mom's to communicate with multiple
> > >     server daemons simultaneously
> > 
> >  which is presumably related to 
> > 
> >  add initial multi-server support for HA (CRI)
> > 
> >  in the CHANGELOG.
> 
> It basicly gets us back to the OpenPBS level of multi-server support,
> except that it works better.
> 
> You can run jobs from multiple pbs_server hosts using the same nodes.
> All servers get state and status updates; and job updates go to the
> correct server.
> 
> 
> _______________________________________________
> torqueusers mailing list
> torqueusers at supercluster.org
> http://www.supercluster.org/mailman/listinfo/torqueusers



More information about the torqueusers mailing list