Hi Steve,

Thank you for your feedback.

I figured out a solution for the problem. In my case the root cause lies in
NUMA Topology, the memory slots was not physically split up evenly across
the processors, so i disturbed them accordingly and everything works fine
now.

Thanks again,
Hamza

On 19 April 2016 at 19:37, Steve Gordon <[email protected]> wrote:

> ----- Original Message -----
> > From: "Benyatou Hamza" <[email protected]>
> > To: [email protected]
> >
> > Hi,
> >
> > I established a mapping between virtual CPU to the physical core
> following
> > this Mirantis guide [1], I went through it successfully but the problem I
> > have is that I am only able to launch one instance regardless of the the
> > number of vCPUs specified in the Flavor (2,4,16.....).
> >
> > Have you implemented this option before ?
>
> Hi Hamza,
>
> Do you have debug logging from the scheduling attempt? Output from `virsh
> capabilities` might be of help too.
>
> Thanks,
>
> Steve
>
> > Thank you
> >
> > Hamza
> >
> >
> https://www.mirantis.com/blog/mirantis-openstack-7-0-nfvi-deployment-guide-numacpu-pinning/
>
_______________________________________________
OpenStack-operators mailing list
[email protected]
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators

Reply via email to