[torqueusers] Problems with Torque configuration

Garrick Staples garrick at usc.edu
Thu Nov 29 10:50:56 MST 2007


On Thu, Nov 29, 2007 at 03:39:42PM -0200, Davi Vercillo alleged:
> Hi Garrick,
> 
> Tanks for your halep and sorry about this too. I got the logs that you said
> and I'll send to you in this e-mail. I sow the logs of my nodes and them are
> the same, with teh same error message. So, here they go...
> 
> Nodes - bangu07:
> [root at bangu08 ~]# cat /var/spool/torque/mom_logs/20071123
> 11/23/2007 07:57:58;0002;   pbs_mom;Svr;Log;Log opened
> 11/23/2007 07:57:58;0002;   pbs_mom;n/a;initialize;independent
> 11/23/2007 07:57:58;0002;   pbs_mom;Svr;pbs_mom;Is up
> 11/23/2007 07:57:58;0002;   pbs_mom;Svr;mom_main;MOM executable path and
> mtime at launch: /usr/local/sbin/pbs_mom 1193074779
> 11/23/2007 07:57:58;0002;   pbs_mom;n/a;mom_main;hello sent to server
> bangu00
> 11/23/2007 07:59:28;0002;   pbs_mom;n/a;mom_main;connection to server
> bangu00 timeout

There's your problem.  pbs_mom can't talk to pbs_server.  Standard admin
debugging applies.  Ping check, port filtering, etc.


> The syslog I didn't find here, where would i look for !?

Depends on your OS.  Most Linux systems use /var/log/messages.

 
> Other question: Do I need run the pbs_mom on the server with pbs_server and
> pbs_mom !?

You have 1 pbs_server.  Run pbs_mom where you want to compute.


-------------- 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/20071129/80823fab/attachment.bin


More information about the torqueusers mailing list