[Trillian-users] One Node, One Proc Per Node Jobs

[James Pringle]

Jimmy --

     Let me push back a little -- it is fine to run 1 core/node if there is
some good reason. My experience with talking to some of the chemist is that
they were not at all IO bound or memory bound, and they could easily get 12
to 14 jobs per node with good efficiency. There are jobs queued and waiting
to run now, while 14 nodes have been running with 1 core for 17 or 72
hours.

     I do not think it is that hard to run multiple jobs per node, and if
there is no reason not to, it should be done.

     I agree, there are a whole lot of legitimate reasons for 1 core jobs.
However, in my experience, when I have asked people, their jobs were often
(not always!) able to be run together on a single core.

Jamie

On Tue, Dec 6, 2016 at 3:16 PM, Raeder, Joachim <j.raeder at unh.edu> wrote:

>
> Core envy!
>
> No, this is perfectly acceptable use.  There is a whole lot of legitimate
> uses for one core jobs.
> We will definitely not micro manage that unless there is some abuse
> suspected.
> I’m a whole lot more worried about people running 50 node jobs for days
> without checking
> properly, and then have to throw away everything (or worse keep it  on the
> disk!), just because
> we are so blessed and it costs nothing.  If anything, we have to change
> that.
>
> —  Jimmy
>
> ------------------------------------------------------------
> --------------------------------------
> Joachim (Jimmy) Raeder
> Professor of Physics, Department of Physics & Space Science Center
> University of New Hampshire
> 245G Morse Hall, 8 College Rd, Durham, NH 03824-3525
> voice: 603-862-3412 <(603)%20862-3412>  mobile: 603-502-9505
> <(603)%20502-9505>  assistant: 603-862-1431 <(603)%20862-1431>
> e-mail: J.Raeder at unh.edu
> WWW: http://mhd.sr.unh.edu/~jraeder/tmp.homepage
> ------------------------------------------------------------
> --------------------------------------
>
> On Dec 6, 2016, at 12:24 PM, Gorby, Matthew <Matthew.Gorby at unh.edu> wrote:
>
> Hello Trillian Users,
>
> I'm seeing a lot of one node, one proc / node jobs running at the moment.
> If this is just the way "qstat -a" displays a type of run I'm not familiar
> then please excuse this email.  If those jobs really are what they appear
> to be then may we have one of the admins chime in on this issue?  I'd like
> to know if that is an acceptable use of Trillian's resources.  If not, it
> would be really great to have the other 31/32 of those procs available.
>
> Thanks,
>
> -Matt
>
>
> _______________________________________________
> Trillian-users mailing list
> Trillian-users at lists.sr.unh.edu
> http://lists.sr.unh.edu/mailman/listinfo/trillian-users
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.sr.unh.edu/pipermail/trillian-users/attachments/20161206/ad43f947/attachment-0001.html>