[torqueusers] Error adding a node
Lawrence Sorrillo
sorrillo at jlab.org
Wed Feb 7 12:01:25 MST 2007
I just found my jobs. They all ran properly but where sent to
/var/spool/torque/undelivered.
I guess I need to setup stagein and stageout etc.
~Lawrence
_____
From: Kevin Van Workum [mailto:vanw at tticluster.com]
Sent: Wednesday, February 07, 2007 11:58 AM
To: Lawrence Sorrillo
Cc: torqueusers at supercluster.org
Subject: Re: [torqueusers] Error adding a node
did you restart maui?
On 2/7/07, Lawrence Sorrillo <sorrillo at jlab.org> wrote:
Hi:
I have a working version of Maui-3.2.6p19 and torque-2.1.6.
Initially I had one machine running pbs_server and pms_mom. Everything
worked well!
Now I am attempting to add a dual process machine to the list of compute
nodes.
Below is the sequence of events I adhered to:
1. Installed pbs_mom on the compute node.
2. Edit /var/spool/torque/mom_priv/config to include the $clienthost
host_running_pbs_server
3. Start pbs_mom on the compute node.
4. run qmgr -c 'create node compute_node np=2'
5. now pbsnodes -a show both nodes 'free'. However, when I submit jobs
they never run on the newly added machine - even after I set the
first/original node offline to force jobs to run on the added node.
Is this not the correct sequence of events?
What is the meaning/efftect of: qmgr -c 'set queue foo
resources_default.nodes=1'
.
Thanks
_______________________________________________
torqueusers mailing list
torqueusers at supercluster.org
http://www.supercluster.org/mailman/listinfo/torqueusers
--
Kevin Van Workum, Ph.D.
Vice President
Senior System Administrator
www.clusterondemand.com
ONLINE COMPUTER CLUSTERS
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20070207/97c69d25/attachment.html
More information about the torqueusers
mailing list