[GE users] Memory quotas

davidecittaro davide.cittaro at ifom-ieo-campus.it
Tue Feb 10 13:03:47 GMT 2009


Hi again,

On Feb 10, 2009, at 1:11 PM, reuti wrote:
>>
>> Ok, I see... and should it be set as complex value in execution
>> host configuration?
>
> this can be set either per exechost as you suggest, or in another RQS:
>
> limit hosts {*} to h_vmem=64GB
>

Mmm... interesting, I'll give a try for sure.

>>
>> Talking about this, I've noticed that if a user sends qlogin,
>> qquota says that he is using 5 Gb RAM (I'm using qlogin_wrapper to
>> sshd). I wonder why this is happening...
>
> Is there any default defined in `qconf -sc`?
>

Nope. And this happens only for qlogin sessions...

>> Just a doubt: suppose I set h_vmem to 40 Gb, will a job be killed
>> if it goes over 40 Gb or every job is killed as the 40 Gb is reached?
>
> h_vmem limited in an RQS won't be enforced. It has to be requested
> per job (or the default from `qconf -mc`applies) and this individual
> resource request (per job) will be enforced.


So, to summarize, you suggest to
- set h_vmem as consumable in qconf -mc
- set a RQS for hosts to a certain amount of RAM (less than 64 Gb, as  
some daemons are running allocating ~10Gb per host)
- set a default for h_vmem (say 2 Gb) that can be overridden by, say,   
"-l h_vmem=10G"

In this way one can run any number of job (RQS on slots apply, of  
course) and if a job drains more than the h_vmem available it is  
killed. Is this right?

Thanks

d

Davide Cittaro
davide.cittaro at ifom-ieo-campus.it

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=103185

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



More information about the gridengine-users mailing list