[torqueusers] PBS unable to execute Job.

Chris Samuel csamuel at vpac.org
Sun Sep 11 18:53:08 MDT 2005


On Mon, 12 Sep 2005 10:41 am, Ashley Wright wrote:

> The error was easy to fix, it was just hard to find the right log file.
> Would it be worth while putting a list of log files in the
> troubleshooting section of the online manual?

I second that idea.

> The way we have set up our cluster is probably a little different from
> the way that is recommended. We have installed torque into /usr/local
> which is a NFS share, however /usr in general is not shared. So we
> copied over the the directories and configuration files needed to start.

Hmm, what you're supposed to do is to use pbs_mkdirs to create them, but on 
our IBM clusters that are managed through CSM I do that by putting the 
directories and post scripts into /cfmroot and cfmupdatenode then creates 
them on install.

good luck!
Chris
-- 
 Christopher Samuel - (03)9925 4751 - VPAC Deputy Systems Manager
 Victorian Partnership for Advanced Computing http://www.vpac.org/
 Bldg 91, 110 Victoria Street, Carlton South, VIC 3053, Australia

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://www.supercluster.org/pipermail/torqueusers/attachments/20050912/43da39ce/attachment.bin


More information about the torqueusers mailing list