[openstack-dev] [nova][NFV][qa][Telco] Testing NUMA, CPU pinning and large pages

Daniel P. Berrange berrange at redhat.com
Mon Jan 12 13:58:50 UTC 2015


On Mon, Jan 12, 2015 at 02:47:19PM +0100, Marc Koderer wrote:
> Hi Vladik,
> 
> I added the [Telco] tag.
> see below.. 
> 
> Am 12.01.2015 um 03:02 schrieb Vladik Romanovsky <vladik.romanovsky at enovance.com>:
> 
> > Hi everyone,
> > 
> > Following Steve Gordon's email [1], regarding CI for NUMA, SR-IOV, and other
> > features, I'd like to start a discussion about the NUMA testing in particular.
> > 
> > Recently we have started a work to test some of these features.
> > The current plan is to use the functional tests, in the Nova tree, to exercise
> > the code paths for NFV use cases. In general, these will contain tests
> > to cover various scenarios regarding NUMA, CPU pinning, large pages and
> > validate a correct placement/scheduling.
> 
> I think we need to determine where these patches are belonging to.
> So IMHO Nova tree makes sense. But I am unsure if Tempest is the right place.
> I would say all tests with a general propose can be located in Tempest
> especially scenario tests.
> 
> Since we are already planning to have a external CI system it would make
> sense to keep them somewhere outside and use the tempest lib (when ready).

NUMA, huge pages & cpu pinning are all general purpose Nova features. While
NFV / Telcos will be a large user of them, they're not the only. As such
these features should be tested in a general Nova test suite, as we would
for any other Nova functionality, not in a telco-specific test suite as
that just re-inforces the impression that this is a niche feature only
useful for a few use cases.

Regards,
Daniel
-- 
|: http://berrange.com      -o-    http://www.flickr.com/photos/dberrange/ :|
|: http://libvirt.org              -o-             http://virt-manager.org :|
|: http://autobuild.org       -o-         http://search.cpan.org/~danberr/ :|
|: http://entangle-photo.org       -o-       http://live.gnome.org/gtk-vnc :|



More information about the OpenStack-dev mailing list