Hi,
Am 16.08.2012 um 22:51 schrieb Jake Carroll:
> I'm currently assessing different job scheduling technologies for a sizeable
> compute/HPC project I'm working on.
>
> One of the things various vendors seem to always throw out there as a "value
> add" in their respective scheduler is their a
Hi all.
I'm currently assessing different job scheduling technologies for a sizeable
compute/HPC project I'm working on.
One of the things various vendors seem to always throw out there as a "value
add" in their respective scheduler is their ability to "drive up utilisation"
of the HPC cluster
Thanks Dave.
This is helpful as I was not sure of the step sequence.
On 08/16/2012 10:21 AM, Dave Love wrote:
In case it's not clear, the upgrade procedure should be: stop the execds; stop the qmaster; install the new binaries; restart the master; restart the execds.
Reuti,
The PEs will stay because we've found the configuration to be incredibly
convenient and easy to support (handles just about all known parallel
implementations). My PE support questions have virtually disappeared
since we deployed this configuration. I know each queue instance has to
Am 16.08.2012 um 18:07 schrieb Brian Smith:
> I know that in a lot of scheduling environments, queues are used such as
> short, long, etc. to differentiate different classes of jobs. In our
> environment, we're doing very much the same thing and using fancy pe_list
> syntax to differentiate ou
Reuti writes:
> Am 15.08.2012 um 15:10 schrieb Dave Love:
>
>> Reuti writes:
>>
>>> If nothing is requested, the default duration defined in `qconf -ssconf` in
>>> the line "default_duration" is used. important to note is, that SGE judges
>>> INIFINITY being smaller than INIFINITY and as a re
Joseph Farran writes:
> I am seeing some weird errors which may be related to this?
>
> 8/15/2012 14:47:01|listen|hpc|W|denied: client (login-1-1.local/execd/2808)
> uses old GDI version 6.2u5 while qmaster uses newer version 8.1.1
I assume that was an old execd, which should have failed to sta
Joseph Farran writes:
> This was working under GE2011.11 which I cannot get it to work with sge-8.1.1
> or maybe I have it set wrong?
>
> Here is the info:
>
> $ id -g
> 200
>
> $ cat /etc/group | grep 200
> staff:x:200:
>
> $ qconf -sq space1 | fgrep user
> user_listsstaff
> xuser_
I know that in a lot of scheduling environments, queues are used such as
short, long, etc. to differentiate different classes of jobs. In our
environment, we're doing very much the same thing and using fancy
pe_list syntax to differentiate our various clusters. It occurred to
me, however, tha
