[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH 3/5] x86: widen NUMA nodes to be allocated from

>>> On 27.02.15 at 14:46, <ian.campbell@xxxxxxxxxx> wrote:
> On Fri, 2015-02-27 at 13:27 +0000, Dario Faggioli wrote:
>> On Thu, 2015-02-26 at 13:54 +0000, Jan Beulich wrote:
>> > Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
>> > 
>> Reviewed-by: Dario Faggioli <dario.faggioli@xxxxxxxxxx>
>> One question (a genuine one, i.e., I'm really not sure what I'm saying
>> is correct).
>> After this series, vcpu_to_node() (defined in xen/include/xen/numa.h) is
>> left with only one use, in xen/arch/arm/domain.c, besides of course
>> being used to implement domain_to_node() (still in
>> xen/include/xen/numa.h).
>> So, provided ARM people (and I'm Cc-ing them) can get rid of that,
> Happy to do so if you have advise on what to replace it with, just 0?
> We don't do NUMA yet on ARM so that would be fine, but eventually we'd
> want the vcpu stack to be allocated in some sort of "sensible relative
> to vcpu affinity" location...

That would require vNUMA information to be set by the tool stack
already by that time. What we have currently (using the node of
the CPU the vCPU starts on) is pretty meaningless unless the vCPU
is meant to only ever run on a single node.


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.