On 11/14/10 11:43 PM, Bjoern A. Zeeb wrote:
On Sun, 14 Nov 2010, Julian Elischer wrote:


this sort of dovetails into something I've been thinking about for a while,
which is NUMA support.

really good thoughts, but bad timing and wrong target audience I

I don't think the thought was seep enough to warrant a larger audience :-)

1) first of all you want the basic underlying OS support all sort of
   things and as we know people are working on things here and there
   and it's not only NUMA.

Well yes, of course but it's interesting how various different parts of what are until now completely separate projects might some day come together in a larger picture.

2) before 1) is rock solid I will not even think about how to leverage
   it for VIMAGE.  It would really just be a waste of time; it will
   however be a good idea to make sure that the proposals people come
   up with in 1) will scale for VIMAGE as well, but that's a different
story. I am at least trying to keep an eye on the network stack side.

3) Before VIMAGE is NOT stable we MUST NOT introduce more complexity.

agreed. My only thought at the moment is to try and keep an eye on the
bigger picture when changing the smaller parts.

So if you are eager to work on this I am all for it and you should get
in touch with the folks doing 1).


freebsd-virtualization@freebsd.org mailing list
To unsubscribe, send any mail to 

Reply via email to