From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: RFC: Still TODO for 4.2? xl domain numa memory allocation vs xm/xend Date: Fri, 20 Jan 2012 18:32:48 +0100 Message-ID: <1327080768.2337.65.camel@Abyss> References: <1325694562.25206.304.camel@zakaz.uk.xensource.com> <20120119211430.GT12984@reaktio.net> <1327046368.21391.29.camel@dagon.hellion.org.uk> <1327058562.17599.134.camel@zakaz.uk.xensource.com> <1327059874.2337.38.camel@Abyss> <1327060480.30054.15.camel@zakaz.uk.xensource.com> <1327061083.2337.42.camel@Abyss> <1327062788.30054.31.camel@zakaz.uk.xensource.com> <1327065091.30054.43.camel@zakaz.uk.xensource.com> <1327071976.30054.55.camel@zakaz.uk.xensource.com> <1327075340.2337.50.camel@Abyss> <1327076495.30054.63.camel@zakaz.uk.xensource.com> <1327076924.30054.65.camel@zakaz.uk.xensource.com> <1327077068.23358.97.camel@elijah> <1327077590.30054.71.camel@zakaz.uk.xensource.com> <1327077796.23358.98.camel@elijah> <1327078460.30054.74.camel@zakaz.uk.xensource.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7914952055398166999==" Return-path: In-Reply-To: <1327078460.30054.74.camel@zakaz.uk.xensource.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Ian Campbell Cc: xen-devel , "Keir (Xen.org)" , Stefano Stabellini , George Dunlap , Ian Jackson , Juergen Gross , "Tim (Xen.org)" , George Dunlap , Jan Beulich List-Id: xen-devel@lists.xenproject.org --===============7914952055398166999== Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature"; boundary="=-UWrnpNr439JFMAMhDRvw" --=-UWrnpNr439JFMAMhDRvw Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Fri, 2012-01-20 at 16:54 +0000, Ian Campbell wrote:=20 > I confused myself into thinking that cpupools ~=3D NUMA because I've only > used cpupool-numa-split but I can see that you might also divide your > cpus up some other way. >=20 Yeah, indeed, although the numa-split case looks like the most useful one to me. > Should that same union be used for d->node_affinity though? It seems > like it would make sense. >=20 According to me, it should. Then, at least right now, moving it would probably kill its performances because all its memory will be far away, while right now it's all more "stochastic". Still, I think it should be done, as if you place a domain in a cpupool at its creation, I think the case of moving it away from there would be quite rare. Regards, Dario --=20 <> (Raistlin Majere) ------------------------------------------------------------------- Dario Faggioli, http://retis.sssup.it/people/faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) PhD Candidate, ReTiS Lab, Scuola Superiore Sant'Anna, Pisa (Italy) --=-UWrnpNr439JFMAMhDRvw Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (GNU/Linux) iEYEABECAAYFAk8ZpUAACgkQk4XaBE3IOsT0zQCfXIW1CYXk2evbh5IuRkDP19xI V/0AnRHZzEVbTmsPjP4YMAhTkMiakXtZ =fkwu -----END PGP SIGNATURE----- --=-UWrnpNr439JFMAMhDRvw-- --===============7914952055398166999== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel --===============7914952055398166999==--