[torqueusers] problems receiving output files from jobs
garrick at clusterresources.com
Tue Mar 13 09:06:14 MDT 2007
On Mon, Mar 12, 2007 at 09:05:36PM +0100, Thomas Blum alleged:
> we experience problems with torque-2.1.7(with maui-3.2.6p17) when
> submitting 200 jobs in a for loop and getting back the output/error
> files for that jobs. The job only does date, hostname and uptime. From
> submitted 200 jobs e.g. we get back 198 e and 196 o files. We tried
> using scp and rcp but both have the same effects. The missing files
> stuck on the clients in the undelivered directories and the server log says:
> Post job file processing error
> Does anybody has an idea what we can do?
The actual error message would have been emailed to the user. Also, I'd
check syslog for errors.
The first thing off the top of my head is "MaxStartups" in sshd_config.
More information about the torqueusers