Re: [Xen-devel] [RFC PATCH 2/2] xen: tmem: make tmem aware of NUMA affinity

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 20.03.14 at 12:59, Bob Liu <bob.liu@xxxxxxxxxx> wrote:
> On 03/20/2014 05:26 PM, Jan Beulich wrote:
>>>>> On 19.03.14 at 18:12, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx> 
>>>>> wrote:
>>> Would you perhaps reconsider reviewing the code that Bob
>>> posted and ignore the committing part of it until a later time
>>> (when tmem has gotten throught the security audit).
>> 
>> The code looked reasonable, albeit I'm not certain it's to the
>> point: Aren't certain types of pages sharable between domains?
> 
> Yes.
> 
>> For those, setting the affinity based on the domain for which
>> the allocation gets done doesn't seem ideal. Plus the domain
> 
> The ideal situation for tmem is try to allocate pages from nodes in
> domain's node_affinity, if there isn't enough memory on those nodes then
> fall back to other online nodes.
> 
> Do you have any suggestion how to implement this?

Nothing beyond what your wording already says.

>> heap use of tmem was found to be broken anyway, and hence
> 
> Yes, but I think it's still better if tmem prefers nodes in
> domain->node_affinity rather than all online nodes.

But that comment of yours relates to the earlier aspect, not
the last comment I made. If you don't recall what I'm referring
to, just go check xen/arch/x86/setup.c for the condition of
tmem getting forcibly disabled.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel