[gridengine users] Requesting h_vmem or memfree
Mark Dixon
m.c.dixon at leeds.ac.uk
Mon May 28 08:40:56 UTC 2012
On Fri, 25 May 2012, Prentice Bisbal wrote:
...
> 1. Make whatever complex I choose to use requestable
> 2. Set a default value.
> 3. Profit.
>
>
> It's step 2 that worries me. Must I set a default? My assumption is that
> if I do, that default will be used for ALL jobs. Is that correct? I'm
> worried because something tells me that no matter what default I use,
> it's going to break something, somewhere for someone. Is it possible to
> set default = NONE?
We normally set the "requestable" column for h_rt to "FORCED", to avoid
the need to set a default. Perhaps this would also work for h_vmem?
(Although we're not using it for that for some reason - and I cannot
remember why).
If "-w e" is added to your $SGE_ROOT/$SGE_CELL/common/sge_request file,
all jobs with invalid requests should be rejected at submission time.
However, "-w e" recently had a bug fixed in the open source Univa repo, so
do check that whatever version of GE you're running has the/a patch (see
https://arc.liv.ac.uk/trac/SGE/ticket/716 ). Otherwise, your best bet is
to use a JSV to reject jobs without a memory request.
> Second question, is which resource is the best to use for this? h_vmem,
> s_vmem, or mem_free. I know mem_free is more of a "hint", and doesn't
> guarantee anything, and h_vmem will kill a job submitter guesses wrong.
> I've never seen anyone even mention s_vmem for this. Is there a reason
> for that?
...
I won't repeat the good stuff that other people have already written about
what you can do today but, if you haven't already, you might want to
skim-read the ongoing cgroups thread that describes a much better approach
that should be available in the future.
All the best,
Mark
--
-----------------------------------------------------------------
Mark Dixon Email : m.c.dixon at leeds.ac.uk
HPC/Grid Systems Support Tel (int): 35429
Information Systems Services Tel (ext): +44(0)113 343 5429
University of Leeds, LS2 9JT, UK
-----------------------------------------------------------------
More information about the users
mailing list