Re: [Openstack-operators] Passing a flavor's extra_specs to libvirt

Hello Paco - > On 13 Apr 2017, at 11:10, Paco Bernabé wrote: > > Hi, > > The issue is apparently solved; we found a solution here > https://www.stackhpc.com/tripleo-numa-vcpu-pinning.html where libvirt and > qemu-kvm version restrictions where indicated. The CentOS7.3 repo has an > older qe

Re: [Openstack-operators] Passing a flavor's extra_specs to libvirt

Hi, The issue is apparently solved; we found a solution here https://www.stackhpc.com/tripleo-numa-vcpu-pinning.html where libvirt and qemu-kvm version restrictions where indicated. The CentOS7.3 repo has an older qemu-kvm version (1.5.

Re: [Openstack-operators] Passing a flavor's extra_specs to libvirt

Hi, More info; in de log file of the nova-scheduler we see messages like ( is de compute host name): , fails NUMA topology requirements. No host NUMA topology while the instance specified one. host_passes /usr/lib/python2.7/site-packages/nova/scheduler/filters/numa_topology_filter.py:100 Filt

[Openstack-operators] Passing a flavor's extra_specs to libvirt

Hi, After reading the following articles: https://docs.openstack.org/admin-guide/compute-flavors.html http://redhatstackblog.redhat.com/2015/05/05/cpu-pinning-and-numa-topology-awareness-in-openstack-compute/