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 adv
On 2/8/19 3:07 PM, Andrea Bolognani wrote:
On Fri, 2019-02-08 at 14:14 +0100, Jiri Denemark wrote:
On Fri, Feb 08, 2019 at 11:03:34 -0200, Daniel Henrique Barboza wrote:
Some devices creates empty (= cpu-less) NUMA nodes to host
its memory. This results in topologies where the following
sani
On Fri, 2019-02-08 at 14:14 +0100, Jiri Denemark wrote:
> On Fri, Feb 08, 2019 at 11:03:34 -0200, Daniel Henrique Barboza wrote:
> > Some devices creates empty (= cpu-less) NUMA nodes to host
> > its memory. This results in topologies where the following
> > sanity rule does not apply as is:
> >
>
On Fri, Feb 08, 2019 at 11:03:34 -0200, Daniel Henrique Barboza wrote:
> Some devices creates empty (= cpu-less) NUMA nodes to host
> its memory. This results in topologies where the following
> sanity rule does not apply as is:
>
> nodes * sockets * cores * threads = total_cpus
>
> As a result,
Some devices creates empty (= cpu-less) NUMA nodes to host
its memory. This results in topologies where the following
sanity rule does not apply as is:
nodes * sockets * cores * threads = total_cpus
As a result, a call to 'virsh nodeinfo' will return the default
value (1) to nodes, sockets and th