[PATCH 00 of 11 v4] NUMA aware credit scheduling

[Dario Faggioli <dario.faggioli@citrix.com>]

Hello,

Round 4 of the NUMA aware scheduling series. Very few going on, actually, as
the comments to v3 where not a big deal... Nevertheless, I, as usual, really
appreciated them a lot, and I think I've addressed them all. The only notable
change is on patch 05/11, where I discovered a small but nasty bug (see the
specific changelog).

I couldn't rerun the full set of my usual benchmarks, but I really don't think
that to be necessary, as practically no functional change is being introduced,
wrt to v3. However, I did run a couple of them, randomly, just to be sure,
and the numbers actually do look almost identical to these ones:

 http://lists.xen.org/archives/html/xen-devel/2013-02/msg00009.html

What I'm now missing is a couple of Ack-s from the relevant people. In fact,
almost all the patches carry more than one Ack, but there are a few of them
which are missing Ack-s from the actual maintainers of the code they touch.
In some more details, and with
  '*'='properly Ack-ed',
  '+'= 'Ack-ed but _not_ by the maintainer',
here it comes the series:

 * 01/11 xen, libxc: rename xenctl_cpumap to xenctl_bitmap
 * 02/11 xen, libxc: introduce xc_nodemap_t
 * 03/11 xen: sched_credit: when picking, make sure we get an idle one, if any
 + 04/11 xen: sched_credit: let the scheduler know about node-affinity
 * 05/11 xen: allow for explicitly specifying node-affinity
 * 06/11 libxc: allow for explicitly specifying node-affinity
 + 07/11 libxl: allow for explicitly specifying node-affinity
 + 08/11 libxl: optimize the calculation of how many VCPUs can run on a candidate
 + 09/11 libxl: automatic placement deals with node-affinity
 + 10/11 xl: add node-affinity to the output of `xl list
 * 11/11 docs: rearrange and update NUMA placement documentation

So, George, if, as you said, you're fine with it, could you explicitly
ack 04/11 ?
Also, IanC and IanJ, could you have a look and ack (if you feel like
so, of course) 07/11, 08/11, 09/11 and 10/11 ?

Thanks a lot and Regads,
Dario

-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)