[GE users] Memory leak in 6.1u2 ?

Richard Ems Richard.Ems at cape-horn-eng.com
Thu Nov 15 13:30:18 GMT 2007


    [ The following text is in the "ISO-8859-1" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]

Andy Schwierskott wrote:
> Hi Richard,
> 
> from what you describe below it seems that NAGIOS somehow seems to monitor
> and manage SGE. That sounds quite interesting. Can you tell more about it?
> 
> Regarding the potential memory leak: do you have the possibility to run the
> SGE qmaster node on a different platform than openSUSE 10.3, ideally a
> somewhat older release? I'm asking because in principle there could be a
> memory leak or memory allocation problem in one of the system libraries as
> well.

No, at least not without taking one computing node from the cluster,
reinstalling it and migrating SGE!

SGE was running fine on openSUSE 10.3 several days, until today. Last
week I could easily reproduce a memory leak enabling queues. since we
had more nodes than licenses some queues where disabled. Every time I
enabled a queue, the scheduler went up to 3/4 GB. But after restarting
it, everything continued normally.

Yesterday I configured qlicserver. Today the scheduler went up to using
the 4 GB, and it keeps going up to 4 GB after each restart.

qlicserver is not running at this moment, but the problem persists.
The other change we did was requesting license=0.25 for a 4
slots/cores/processes parallel run. But license was defined as INT,
could this be a problem?

thanks, Richard

-- 
Richard Ems       mail: Richard.Ems at Cape-Horn-Eng.com

Cape Horn Engineering S.L.
C/ Dr. J.J. Dómine 1, 5? piso
46011 Valencia
Tel : +34 96 3242923 / Fax 924

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