[torqueusers] Re: Contents of torqueusers Digest, Vol 13, Issue 13

Jerry Smith jdsmit at sandia.gov
Thu Aug 11 08:42:24 MDT 2005


Susan,  There are logs on the Moms themselves at $PBS_HOME/mom_logs/

You can usually find an error code there, and hunt it down in pbs_error.h (though recent versions of torque have been good about defining errors in the error line itself.


Jerry


------------------------------

Message: 8
Date: Wed, 10 Aug 2005 11:38:22 -0700
From: susan james <sjames at lbl.gov>
Subject: [torqueusers] new torque user
To: torqueusers at supercluster.org
Message-ID: <42FA499E.4070707 at lbl.gov>
Content-Type: text/plain; charset=us-ascii; format=flowed

Hello All

I'm new to torque and have a basic question.

I'm looking for a logging file that will give me information about each 
running or queued job that failed.

server_priv/accounting  has information about running jobs.
tracejob gives me information about any job.

jobs that fail most of the time will give this message:  unable to run 
job, MOM rejected
and, that's the end of the message.  is there any other utility that I 
can run that will tell me why MOM rejected my job?

thanks in advance.
Susan


------------------------------




More information about the torqueusers mailing list