ine, how do I add
>>
>> ENABLE_ADDGRP_KILL=TRUE
>>
>>
>> To config via console? I would like to apply this to all the queues.
>>
>> Regards,
>> Guillermo
>>
>>
>>
>> On 04/30/2017 10:49 AM, Reuti wrote:
>>
>> -BEGIN
I see this with processes that spawn another processes, when you kill the
parent the children go free.
On 29 April 2017 at 20:37, Reuti wrote:
> Hi,
>
> Am 28.04.2017 um 08:57 schrieb Guillermo Marco Puche:
>
> > I'm expecting a weird behavior when I reschedule any job on my work
> cluster.
> >
having there breaks.
On Mon, Mar 10, 2014 at 5:45 PM, Ben De Luca wrote:
> You hit this with reservation + parallel jobs.
>
>
> On Mon, Mar 10, 2014 at 5:17 PM, Joshua Baker-LePain wrote:
>
>> On Sat, 8 Mar 2014 at 11:50am, Ben De Luca wrote
>>
>>
>> Yes I h
You hit this with reservation + parallel jobs.
On Mon, Mar 10, 2014 at 5:17 PM, Joshua Baker-LePain wrote:
> On Sat, 8 Mar 2014 at 11:50am, Ben De Luca wrote
>
>
> Yes I have hit this, reservation needs to be off for all jobs.
>>
>
> Ouch. So any jobs using reservati
Yes I have hit this, reservation needs to be off for all jobs.
I found the section of the code allocating the memory and as far as I Can
tell commenting it does nothing. If you look through the past emails on the
list you will see me writing about it this time (almost exactly + 2 weeks)
2 years ag
aah, I just saw it has no effect.
I use that flag on our systems.
On Fri, Nov 15, 2013 at 12:49 AM, Ben De Luca wrote:
> Can you do this with the submit flags? -pty y[es]/n[o]
>
>
>
>
> On Tue, Nov 12, 2013 at 5:46 PM, Reuti wrote:
>
>> Am 12.11.2013 um 17:
Can you do this with the submit flags? -pty y[es]/n[o]
On Tue, Nov 12, 2013 at 5:46 PM, Reuti wrote:
> Am 12.11.2013 um 17:15 schrieb Mechanic, Daniel:
>
> > Ugh.
> >
> > You are correct, I spoke to soon. I should have said 'my planned
> workaround'
> >
> > This workaround does NOT work.
> >
Does anyone have a sensible and automated method for copying configuration
data between grid versions?
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
Hi all,
I just tried this same test on OGS/GE 2011.11p1 and it works
perfectly.
On Wed, Feb 6, 2013 at 6:28 PM, Ben De Luca wrote:
> I have a 8.0.0c cluster in production and an 8.0.0e running for testing.
>
> No one has noticed it, though I have seen it before
> Oh, I jus
.
On Wed, Feb 6, 2013 at 2:05 PM, Orlando Richards
wrote:
> Hi Ben,
>
>
> On 06/02/13 13:12, Ben De Luca wrote:
>
>> Im fairly sure we are affected by this bug too, I am happy to help in
>> the hunt and I have looked through the code more than once.
>>
>>
> A
Im fairly sure we are affected by this bug too, I am happy to help in the
hunt and I have looked through the code more than once.
Which version of grid are you trying to fix? I havn't been following grid
dev too closely do we still have multiple forks?
On Wed, Feb 6, 2013 at 12:07 PM, Mark Dixo
I was wondering, how people deal with oom conditions on there cluster.
We constantly have machines that die because the oom killer takes out
critical system services.
Has any experiance with the oom_adj proc value, or a patch to grid to
support it?
/proc/[pid]/oom_adj (since Linux 2.6.11)
Ron and Dave.
I appreciate the work that both of you have done. But can you both please stop.
I would appreciate that too.
Thanks
-Ben
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
Hi all,
I am trying to debug an issue with our scheduler at the moment
and I am aware that the values in the debug environment variable,
SGE_DEBUG_LEVEL. At one point I was aware what each of the values
refer to but that was long in the past. I cant seem to find any thing
in the man pages
http://gridscheduler.sourceforge.net/htmlman/htmlman5/queue_conf.html
terminate_method
looks like it might be simplest.
On Tue, Jan 31, 2012 at 9:51 PM, Ben De Luca wrote:
> Strangely im pondering this issue at the moment. If a python process
> is killed any process started with subp
Strangely im pondering this issue at the moment. If a python process
is killed any process started with subprocess does not die.
The two methods im following,
1. a reaper, the grid job starts a python process (parent) that starts
two other jobs, the task, and the reaper.
A. The task is the proces
a whole machine but mantra I'd run more than one.
> That's only going to become more common as we move to machines with
> piles of cores in them. Some things scale across the cores but some
> don't and you're better off running two frames simultaneously.
>
>
Sure :) Those are all relatively new products, or new licensing schemes.
Is it generally sensible to run multiple instances of any of those
packages (possibly excluding rvio)?
On Sun, Jan 15, 2012 at 6:50 PM, Hugh Macdonald
wrote:
> On 15/01/12 17:39, Ben De Luca wrote:
>
> I think
I think you will find that per host licensing is the exception rather
than the rule.
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
I know there are a few forks now, sge, univa, ogs.
But is there an upstream? who do I contribute to? or is everyone going
their separate ways?
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
Hi,
I wonder if I am miss remembering, but is there a way to
configure a queue to have the same number of slots as there are NCOR
(or even NCPU) as per machine. I seem to remember doing this though I
may have set this with hostlist some how? I am running SGE 8.0.0e
(son of gridengine)
If people can say? what software are you running?
On Thu, Dec 29, 2011 at 7:39 PM, Ciaran Wills wrote:
> I think in my case I can just set up a queue with a number of instances equal
> to the number of licenses I have. I'm not so much worried about maximum
> efficiency as avoiding having job
Heres a code snippet I wrote yesterday to handle the parsing of xml
from the latest son of ge.
from xml.etree import cElementTree as ElementTree
cmd = "qstat -ext -xml -u \*"
proc = subprocess.Popen(cmd,
stdout = subprocess.PIPE,
std
Hi All,
I know there are a lot of science types on here, but I
occasionally see the old animation/vfx person. I wondered how many of
you out there might be on that side of things?
___
users mailing list
users@gridengine.org
https://gridengine.org/ma
Hi David,
What platform are you building for ?
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
I have this scenario.
I have:
a low priority job A that requires a consumable resource called license.
a high priority job B that requires the same consumable resource
called license.
A has checkpoint configuration, where it will checkpoint on job suspend.
I on each computer I have two que
I appreciate the bug fixes :)
___
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
27 matches
Mail list logo