From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [PATCH 00 of 10 v2] NUMA aware credit scheduling Date: Thu, 20 Dec 2012 00:16:32 +0100 Message-ID: <1355958992.28419.5.camel@Abyss> References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4923731902198407065==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: xen-devel@lists.xen.org Cc: Marcus Granado , Dan Magenheimer , Ian Campbell , Anil Madhavapeddy , George Dunlap , Andrew Cooper , Juergen Gross , Ian Jackson , Jan Beulich , Daniel De Graaf , Matt Wilson List-Id: xen-devel@lists.xenproject.org --===============4923731902198407065== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-2DmLg/YH2Vcbtlue8HIa" --=-2DmLg/YH2Vcbtlue8HIa Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Wed, 2012-12-19 at 20:07 +0100, Dario Faggioli wrote:=20 > Which, reasoning in terms of %-performances increase/decrease, means NUMA= aware > scheduling does as follows, as compared to no affinity at all and to pinn= ing: >=20 > ---------------------------------- > | SpecJBB2005 (throughput) | > ---------------------------------- > | #VMs | No affinity | Pinning | > | 2 | +14.36% | -0.36% | > | 6 | +14.72% | -0.26% | > | 10 | +11.88% | -2.44% | > ---------------------------------- > | Sysbench memory (throughput) | > ---------------------------------- > | #VMs | No affinity | Pinning | > | 2 | +14.12% | +0.09% | > | 6 | +11.12% | +2.14% | > | 10 | +11.81% | +5.06% | > ---------------------------------- > | LMBench proc (latency) | > ---------------------------------- > | #VMs | No affinity | Pinning | > ---------------------------------- > | 2 | +10.02% | +1.07% | > | 6 | +3.45% | +1.02% | > | 10 | +2.94% | +4.53% | > ---------------------------------- >=20 Just to be sure, as I may have not picked up the perfect wording, in the table above a +xx.yy% means NUMA aware scheduling (i.e., with this patch series fully applied) performs xx.yy% _better_ than either 'No affinity' or 'Pinning'. Conversely, a -zz.ww% means it performs zz.ww% worse. Sorry but the different combination and the presence of both throughput values (which are better if high) and latency values (which are better if low) made things a little bit tricky to present effectively. :-) Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://retis.sssup.it/people/faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-2DmLg/YH2Vcbtlue8HIa 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 v1.4.12 (GNU/Linux) iEYEABECAAYFAlDSStAACgkQk4XaBE3IOsRHigCffv7N/X53wokDYQQBeC+/Cmmy mfoAoKjrUWIKqV6XraDuDx5hy/gF6qVb =Yu33 -----END PGP SIGNATURE----- --=-2DmLg/YH2Vcbtlue8HIa-- --===============4923731902198407065== 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.xen.org http://lists.xen.org/xen-devel --===============4923731902198407065==--