[torqueusers] nodes not receiving jobs

Tom Rudwick tomr at intrinsity.com
Sun Sep 14 11:11:22 MDT 2008


For the server you do it in qmgr:
i.e.
set server log_level = 1

For the mom you can do it in the config file or with signals,
do man pbs_mom for the details.

You should be able to bump the log levels up until you can see
the error happening.

Good luck,
Tom

Adrian Sevcenco wrote:
> Tom Rudwick wrote:
>> You probably need to up your log level. The errors you show only
>> mean that someone tried to do a qstat on an invalid/expired job id.
>>
>> Tom
> How can i increase the debug level? Is it an option at the start of
> torque server? i use torque-2.1.8-1 and i don't see and option for
> increasing log verbosity in man page.
> Thank you,
> Adrian
> 
>> Adrian Sevcenco wrote:
>>> Hi! i have a situation in which some nodes with seemingly identical
>>> configuration to all other nodes, don't accept jobs .. the errors that i
>>> see in mom_logs are :
>>> 09/13/2008 12:08:34;0100;   pbs_mom;Req;;Type StatusJob request received
>>> from PBS_Server at alien.local, sock=10
>>> 09/13/2008 12:08:34;0080;   pbs_mom;Req;req_reject;Reject reply
>>> code=15001(Unknown Job Id), aux=0, type=StatusJob, from
>>> PBS_Server at alien.local
>>>
>>> Any idea how can i debug this further?
>>> Thank you,
>>> Best regards,
>>> Adrian
>>>



More information about the torqueusers mailing list