Hi,
I was about to suggest oneSIS when I saw that Dave was suggesting it. I would
still put my two cents on it, given that we run a small, but very heterogenous
cluster using oneSIS for node management. One of the aspects I like most with
it, is that adding a new node is just a matter of
On 03/10/13 00:00, Dave Love wrote:
Lionel SPINELLI spine...@ciml.univ-mrs.fr writes:
Hello all,
I have a question that is not directly linked to SGE but relates to
the same. Which tool administrators that have to install, manage,
configure and ensure coherence between lot of grid nodes use?
One of our users run heavy jobs, that stuck nodes.
What is the way limit jobs of specific user per node?
I don't want to reduce slots number for other users.
Till now I did this with qsub -l mem_free=10G
___
users mailing list
users@gridengine.org
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 03/10/13 12:26, Semi wrote:
One of our users run heavy jobs, that stuck nodes. What is the way
limit jobs of specific user per node? I don't want to reduce slots
number for other users. Till now I did this with qsub -l
mem_free=10G
Resource
Thanks, this is the way that I used till now.
On 03-Oct-13 15:49, William Hay wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 03/10/13 12:26, Semi wrote:
One of our users run heavy jobs, that stuck nodes. What is the way
limit jobs of specific user per node? I don't want to reduce
On 10/02/2013 07:00 PM, Dave Love wrote:
Lionel SPINELLI spine...@ciml.univ-mrs.fr writes:
Hello all,
I have a question that is not directly linked to SGE but relates to
the same. Which tool administrators that have to install, manage,
configure and ensure coherence between lot of grid nodes
On Thu, Oct 03, 2013 at 10:13:34AM -0400, Prentice Bisbal wrote:
On 10/02/2013 07:00 PM, Dave Love wrote:
Lionel SPINELLI spine...@ciml.univ-mrs.fr writes:
Hello all,
I have a question that is not directly linked to SGE but relates to
the same. Which tool administrators that have to
On 03/10/13 16:09, Gavin W. Burris wrote:
On Thu, Oct 03, 2013 at 10:13:34AM -0400, Prentice Bisbal wrote:
On 10/02/2013 07:00 PM, Dave Love wrote:
Lionel SPINELLI spine...@ciml.univ-mrs.fr writes:
Hello all,
I have a question that is not directly linked to SGE but relates to
the same.
Perceus and Warewulf fit Dave's list very well.
1) Both are free
2) Both use stateless images by default, but instead of an NFS root,
they use a RAM image. You can hybridize the image so that only some
of the image resides in RAM and the rest comes via NFS.
3) You can create different images for
On 10/03/2013 11:52 AM, Tina Friedrich wrote:
On 03/10/13 16:09, Gavin W. Burris wrote:
On Thu, Oct 03, 2013 at 10:13:34AM -0400, Prentice Bisbal wrote:
On 10/02/2013 07:00 PM, Dave Love wrote:
Lionel SPINELLI spine...@ciml.univ-mrs.fr writes:
Hello all,
I have a question that is not
On 10/2/2013 9:54 PM, Joseph Farran wrote:
Thanks Dave and yes, I accidentally sent it non-ascii - I hate it when
that happens.
I want to tackle single jobs first so I'll try DMTCP.
What SGE scripts do you recommend?I found this but not sure if there
are better?
Hi Orion.
I am new to DMTCP and not sure where to start with respect to SGE integration
of DMTCP.
For all I know your scripts are perfect and thanks for making them available.
So you are not using DMTCP any longer? What checkpoint setup if any are you
using now?
Joseph
On 10/3/2013
12 matches
Mail list logo
