[libvirt-users] VMs fail to start with NUMA configuration

Osier Yang jyang at redhat.com
Thu Jan 24 05:02:18 UTC 2013


On 2013年01月24日 12:11, Doug Goldstein wrote:
> On Wed, Jan 23, 2013 at 3:45 PM, Doug Goldstein<cardoe at gentoo.org>  wrote:
>> I am using libvirt 0.10.2.2 and qemu-kvm 1.2.2 (qemu-kvm 1.2.0 + qemu
>> 1.2.2 applied on top plus a number of stability patches). Having issue
>> where my VMs fail to start with the following message:
>>
>> kvm_init_vcpu failed: Cannot allocate memory

Smell likes we have problem on setting the NUMA policy (perhaps
caused by the incorrect host NUMA topology), given that the system
still has enough memory. Or numad (if it's installed) is doing
something wrong.

Can you see if there is something about the Nodeset used to set
the policy in debug log?

E.g.

% cat libvirtd.debug | grep Nodeset
% cat /var/log/libvirt/qemu/$guest.log

On the other hand, I'm wondering if there is a chance to see the
full error msg kernel throws out.

>
> I've tried libvirt-1.0.1 on this machine and had the same results. The
> capabilities have been fixed on that machine however and now display:
>
>        <topology sockets='1' cores='64' threads='1'/>
>
> I also forgot to mention that LIBVIRT_DEBUG=1 and running the daemon
> with --verbose didn't have more details than what I originally posted.
>




More information about the libvirt-users mailing list