[torqueusers] Delayed Job Execution

Mark A. White mawhite at utmb.edu
Fri Nov 19 12:07:58 MST 2010


The only error message I am getting is
 
/var/torque/sched_logs/20101119
11/19/2010 12:13:25;0040; pbs_sched;Job;74324.random;Not enough of the
right type of nodes available


Has anyone else seen this type of problem?  Jobs held in the queue with
unused processors still available?

Thanks,
Mark

PS. Also, I do not have a sched_config in this installation (CentOS 5).
torque-client-2.1.9-1cri
torque-devel-2.1.9-1cri
torque-server-2.1.9-1cri
torque-2.1.9-1cri
torque-scheduler-2.1.9-1cri
torque-head-1.0-1
torque-gui-2.1.9-1cri
torque-docs-2.1.9-1cri

On Tue, 2010-10-05 at 10:28 -0500, "Mgr. Šimon Tóth" wrote:

> > There are no jobs waiting in the queue when these jobs are submitted. 
> > Sometimes they all run, and other times a small fraction are held in the
> > queue, apparently at random and without any obvious reason.
> 
> Try this:
> 
> qmgr -c "set server scheduler_iteration = 10"
> 
> Plus set the scheduler loging to max:
> log_filter: 0 (in sched_config)
> 
> and watch the log with tail -f
> 
> There might be some weird interaction going on.
> 


Yours sincerely,

Mark A. White, Ph.D.
Associate Professor of Biochemistry and Molecular Biology, 
Manager, Sealy Center for Structural Biology and Molecular Biophysics
X-ray Crystallography Laboratory,
Basic Science Building, Room 6.660 C
University of Texas Medical Branch
Galveston, TX 77555-0647
Tel. (409) 747-4747
Cell. (281) 734-3614
Fax. (409) 747-1404
mailto://mawhite@utmb.edu
http://xray.utmb.edu
http://xray.utmb.edu/~white
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20101119/374183a1/attachment.html 


More information about the torqueusers mailing list