Hi all,
one of my "users" is using clover-mp.
This process take up to 8 cpu cores. But just one sge slot.
I would like to know if there is a configuration/tip or something else to tell
sge to limit cpu usage of this process.
Thanks for your help.
_
Hi,
Am 07.03.2011 um 09:38 schrieb Mauro Donadello:
> one of my "users" is using clover-mp.
> This process take up to 8 cpu cores. But just one sge slot.
> I would like to know if there is a configuration/tip or something else to
> tell sge to limit cpu usage of this process.
although it's j
Hi,
Am 07.03.2011 um 08:31 schrieb Bharanidharan Narayanaswamy:
> Thank you for the reply.
>
> The UI is needed - because the application which is computing pops up a
> terminal or console once the job is submitted.
>
> I tried suppressing the output and also tried to redirect it to NULL, both
Since December I got 6 new ones - where to enter them? At Github as it will be
filled at one point with the former Issuezilla entries? At Son of GridEngine?
-- Reuti
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/use
Hi Richard and Reuti,
Thanks a ton for your valuable inputs. I used the Xvfb to redirect the X output
to the Virtual framebuffer and it is working fine.
Cheers,
Thanks a lot again.
--- On Mon, 7/3/11, Reuti wrote:
From: Reuti
Subject: Re: [gridengine users] (no subject)
To: "Bharanidharan N
Hi List,
is anyone using the core binding feature on AMD Magny-Cours? If so, how do you
do it? For me, loadcheck mis-reads the topology as (SCTTCTTCTTCTTCTTCTT)*4
rather than (S)*4. As far as I can tell, there are two problems:
- the kernel (2.6.18-194.26.1.el5) only exposes core_id
My suggestion is enter them in Github. The Grid Engine team is actively
working on that codebase (you can see that from the commits). Internally we
are using JIRA and maybe we can use that as well for submitting issues on the
github repository. GitHub has issue tracking but it is very minimal
Am 07.03.2011 um 14:42 schrieb Esztermann, Ansgar:
> Hi List,
>
> is anyone using the core binding feature on AMD Magny-Cours? If so, how do
> you do it? For me, loadcheck mis-reads the topology as
> (SCTTCTTCTTCTTCTTCTT)*4 rather than (S)*4. As far as I can tell,
> there are two p
Hi,
There is a single queue available to the users. Now a user has submitted a job
which is going to take a long time to compute. Another users who has a job in
queue is much simpler and will complete in few minutes.
what would be the best / effective method to send the second job in place of
th
On Mar 7, 2011, at 15:09 , Reuti wrote:
> Am 07.03.2011 um 14:42 schrieb Esztermann, Ansgar:
>
>> Hi List,
>>
>> is anyone using the core binding feature on AMD Magny-Cours? If so, how do
>> you do it? For me, loadcheck mis-reads the topology as
>> (SCTTCTTCTTCTTCTTCTT)*4 rather than (SCC
Hi All,
I remember a question like this posted on the old mailing lists, but I'm having
problems setting up qlicserver. Essentially, I have one FLEXlm server serving
licences for two applications (with separate vendor daemons). When I run
./qlicserver -n, I'm getting double the number of lice
Am 07.03.2011 um 15:26 schrieb Esztermann, Ansgar:
> On Mar 7, 2011, at 15:09 , Reuti wrote:
>
>> Am 07.03.2011 um 14:42 schrieb Esztermann, Ansgar:
>>
>>> Hi List,
>>>
>>> is anyone using the core binding feature on AMD Magny-Cours? If so, how do
>>> you do it? For me, loadcheck mis-reads the
On Mar 7, 2011, at 15:44 , Reuti wrote:
> It's the physical ID which is changing for each socket. Magny-Cours just
> output doubles for "physical id" and "core id" entries. But the "apicid" and
> "initial apicid" are changing. But I don't know what's happening for Intel
> CPUs for these entries
On 03/07/2011 03:33 PM, Chris Jewell wrote:
> Hi All,
>
> I remember a question like this posted on the old mailing lists, but I'm
> having problems setting up qlicserver. Essentially, I have one FLEXlm server
> serving licences for two applications (with separate vendor daemons). When I
> ru
Hi,
Am 07.03.2011 um 15:15 schrieb Bharanidharan Narayanaswamy:
> There is a single queue available to the users. Now a user has submitted a
> job which is going to take a long time to compute. Another users who has a
> job in queue is much simpler and will complete in few minutes.
>
> what wo
Hi Reuti,
Thank you so much for that elaborate explanation as always :)
This method works brilliant
Thanks a ton,
Cheers.
--- On Mon, 7/3/11, Reuti wrote:
From: Reuti
Subject: Re: [gridengine users] pausing or holding a job and computing the next
job
To: "Bharanidharan Narayanaswamy"
Cc:
16 matches
Mail list logo