On Tue, 30 Jun 2015, Alexis Huxley wrote:
Hi, is there any news regarding cgroup-based enforcement of h_vmem?
I saw that Mark Dixon posted patches against 8.1.1 (details at
http://gridengine.org/pipermail/users/2012-September/004699.html), but
these are not in 8.1.8 nor the 20150129 snapshot.
We would like to use exactly this facility, but on 8.1.8.
Before I try to port Mark's patches, I thought it made sense to ask here
in case "native" support is just around the corner, or somebody else has
already done this porting, or somebody has written their own patches.
Thanks!
Hi Alexis,
cgroup control of memory isn't in soge as far as I know, only control of
process placement.
I've not maintained those patches and got them merged, because I ran into
problems with an interaction between the memory cgroup controller and the
Lustre filesystem on centos6 clients. Essentially, attempts to delete the
cgroup at job end would cause the execd to hang in a call to rmdir.
Perhaps I'll try again and see if centos7+lustre is any better when we get
our next machine.
What's your motivation: is it more accurate measurement of memory usage?
Dave did some work a while back and so the existing soge functionality is
pretty good, with one small modification. If you ditch the bit in
source/daemons/shepherd/setrlimits.c that sets RLIMIT_AS, all memory
control will be based on a realistic measurement by the kernel - but all
enforcement will be done via a periodic poll by the execd. We've been
running like that for ages very happily: I tried to get a patch merged
that drops RLIMIT_AS, but it didn't make the cut.
All the best and good luck,
Mark
_______________________________________________
SGE-discuss mailing list
[email protected]
https://arc.liv.ac.uk/mailman/listinfo/sge-discuss
