Am 08.10.2013 um 09:47 schrieb Edrisse Chermak:

> Hi All,
> 
> Thanks a lot for your valuable suggestions. I just solved the problem by
> limiting h_vmem value on qconf -mq.

Great.

Just note, that this setting in the queue definition is a limit per job and not 
per exechost - unless you made the complex h_vmem consumable and added a 
feasible value to each machine via `qconf -me node001` as outlines in the 
provided link.

-- Reuti


> Best,
> Edrisse
> 
> 
> On 10/07/2013 07:43 PM, Gavin W. Burris wrote:
>> Hi, All.
>> 
>> When you enable h_vmem, make sure to watch out for h_stack, too.
>> Otherwise, your programs may fail to start, particularly Matlab and
>> Python for me.
>> 
>> $ qsub -l h_vmem=2G -l h_stack=128M myjob.sh
>> 
>> Cheers.
>> 
>> On Mon, Oct 07, 2013 at 04:50:05PM +0200, Nicolás Serrano Martínez-Santos 
>> wrote:
>>> As far as I know, you have to define a memory consumable in each host, and
>>> reserve it when submit a process to SGE, e.g. qsub -l h_vmem=2G.  Otherwise,
>>> machines memory could start swapping and then crash the machine. Also, this
>>> way, the server also kills those process than consume more memory than
>>> was reserved.
>>> 
>>> More info:
>>> 
>>> http://serverfault.com/questions/241813/sun-grid-engine-set-memory-requirements-per-jobs
>>> 
>>> Best regards,
>>> 
>>> NiCo
>>> 
>>> Excerpts from Edrisse Chermak's message of 2013-10-07 16:25:48 +0200:
>>>> Dear Grid Engine developers and users,
>>>> 
>>>> I would like to prevent jobs running when node memory is almost filled.
>>>> Here is the typical situation I have:
>>>> 
>>>> 'qhost':
>>>> ================================================================
>>>> HOSTNAME                ARCH         NCPU  LOAD  MEMTOT  MEMUSE
>>>> ----------------------------------------------------------------
>>>> global                  -               -     -       -       -
>>>> node1                  linux-x64      64  12.00  52.4G    42.8G
>>>> node2                  linux-x64      64  24.00  52.4G    12.8G
>>>> ===============================================================
>>>> 
>>>> The memory on node1 is almost filled, so I would like the new job I'll
>>>> launch to go on node2. (provided that the job I want to launch requires
>>>> 2 CPUs and that I configured np_load_avg=0.80, so that CPU load doesn't
>>>> matter here).
>>>> 
>>>> note : I'm using ge2011.1
>>>> 
>>>> Thanks in advance,
>>>> Best Regards,
>>>> Edrisse
>>>> 
>>> 
>>> --
>>> NiCo
>>> _______________________________________________
>>> users mailing list
>>> [email protected]
>>> https://gridengine.org/mailman/listinfo/users
>> 
> 
> ________________________________
> 
> This message and its contents including attachments are intended solely for 
> the original recipient. If you are not the intended recipient or have 
> received this message in error, please notify me immediately and delete this 
> message from your computer system. Any unauthorized use or distribution is 
> prohibited. Please consider the environment before printing this email.
> 
> _______________________________________________
> users mailing list
> [email protected]
> https://gridengine.org/mailman/listinfo/users
> 


_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users

Reply via email to