[libvirt] [PATCH] nodeinfo: Add workaround if kernel reports bogous numa topology.

[George-Cristian Bîrzan]

On Wed, Oct 31, 2012 at 4:50 PM, George-Cristian Bîrzan <gc at birzan.org>wrote:

> on 0.10.2:
>
> [root at host34 libvirt]# virsh nodeinfo
> CPU model:           x86_64
> CPU(s):              24
> CPU frequency:       2200 MHz
> CPU socket(s):       1
> Core(s) per socket:  6
> Thread(s) per core:  1
> NUMA cell(s):        4
> Memory size:         131971020 KiB
>
> and http://birzan.org/capabilities4-newlibvirt.txt
>
> This has made the problem even worse, as we now can only use 6 cores out
> of 24 by default (libvirt pins qemus to the CPUs is sees available, so we
> have to manually taskset them after starting).
>
>
I should check before I let my mouth run. This actually fixed the problem,
we now get all 24 CPUs:

virsh # vcpuinfo 08867271-d458-43dc-8a03-807e83d107b4
VCPU:           0
CPU:            9
State:          running
CPU time:       1.3s
CPU Affinity:   yyyyyyyyyyyyyyyyyyyyyyyy


To give you an example from the 'broken' host (still with 0.10.2):

[root at host29 ~]# virsh vcpuinfo 17db9ebb-691b-47e1-bbf4-c9e3c1388d4f
VCPU:           0
CPU:            3
State:          running
CPU time:       3103.2s
CPU Affinity:   yyyyyyyyyyyy

VCPU:           1
CPU:            1
State:          running
CPU time:       3460.4s
CPU Affinity:   yyyyyyyyyyyy


-- 
George-Cristian Bîrzan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/libvir-list/attachments/20121031/789dd972/attachment-0001.htm>