[GE users] job killed without action from the user

Reuti reuti at staff.uni-marburg.de
Fri Aug 4 09:54:38 BST 2006


Am 04.08.2006 um 09:43 schrieb Benoit MOREL:

> Hello,
> I had a job which have been launched from 30 hours and was suddenly  
> killed without any specific action from the user.
> In the log file of the qmaster, there is the following message :
> Fri Aug  4 06:16:21 2006|qmaster|c2x3025|W|job 122366.1 failed on  
> host c2x3050  assumedly after job because: job 122366.1 died  
> through signal KILL (9)
> The strange thing is that this job didn't run on the host c2x3050.

was it a serial or a parallel job? Any more lines about job 122366.1  
in the messages file? Please also check the messages files of the  
nodes in question: the one where the job supposed to have run, and  
the c2x3050.

-- Reuti

To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net

More information about the gridengine-users mailing list