[libvirt] [PATCH v1 1/1] virhostcpu.c: consider empty NUMA nodes in topology validation

[Andrea Bolognani]

On Fri, 2019-02-08 at 15:09 -0200, Daniel Henrique Barboza wrote:
> On 2/8/19 3:07 PM, Andrea Bolognani wrote:
> > On Fri, 2019-02-08 at 14:14 +0100, Jiri Denemark wrote:
> > > Anyway, the virNodeInfo structure is just not flexible enough to deal
> > > with all possible topologies and users are advised to look at the host
> > > capabilities XML to get a proper view of the host CPU topology.
> > 
> > Correct, and it's even documented as such:
> > 
> >    https://libvirt.org/html/libvirt-libvirt-host.html#virNodeInfo
> > 
> > So, as long as the number of CPUs is reported correctly (which it
> > seems to be) and 'virsh capabilities' doesn't report incorrect
> > information in the <topology> element, then there's nothing to be
> > fixed - except for applications that still use virNodeInfo ;)
> 
> Fair enough. Guess it's better to leave this one alone then.
> 
> 
> ps: is virNodeInfo somewhat deprecated for showing CPU topology then?

Yeah, you should really use the capabilities XML instead.

-- 
Andrea Bolognani / Red Hat / Virtualization