[GE users] sge_qmaster 6.2u5 daemon: repeating segfaults

beatrubi beat at 0x1b.ch
Fri Apr 16 10:11:26 BST 2010


Hi Marco!

Quoting <marco.donauer at sun.com> (16.04.10 10:42):

> Is it possible to find out what happens short before the crashes?

Typically the end of a scheduler run. I may run the queuemaster with
debugging enabled - feel free to give me the SGE_DEBUG_LEVEL you need to
track down memory management errors.

> Do you have high load
> in your cluster, do you have special configurations? Could you give me
> some information about your configuration?

Nothing special: Mid sized system with ~260 nodes x 8 cores, a job mix of
serial and parallel jobs up to 100 cores. 20-30 jobs on the system, 50-100
waiting in the queue. Less then 100 jobs throughput per day. Nothing which
should drive the Grid Enigne to the limits :-/

Beat

-- 
     \|/                           Beat Rubischon <beat at 0x1b.ch>
   ( 0^0 )                             http://www.0x1b.ch/~beat/
oOO--(_)--OOo---------------------------------------------------
Meine Erlebnisse, Gedanken und Traeume: http://www.0x1b.ch/blog/

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=253640

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list