From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: Virt overehead with HT [was: Re: Xen 4.5 development update] Date: Tue, 15 Jul 2014 04:30:36 +0200 Message-ID: <1405391436.5333.33.camel@Solace> References: <20140701164347.61662A7843@laptop.dumpdata.com> <1405354372.29306.687.camel@Solace> <53C4062A.3040403@bobich.net> <1405356283.7341.5.camel@Abyss> <53C40B91.7080006@eu.citrix.com> <1405358537.7341.19.camel@Abyss> <53C421F4.9070501@bobich.net> <1405377850.5333.17.camel@Solace> <53C47161.1060008@bobich.net> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0031174416655012699==" Return-path: Received: from mail6.bemta3.messagelabs.com ([195.245.230.39]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1X6sVv-0005DK-HB for xen-devel@lists.xenproject.org; Tue, 15 Jul 2014 02:30:43 +0000 In-Reply-To: <53C47161.1060008@bobich.net> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Gordan Bobic Cc: Lars Kurth , George Dunlap , George Dunlap , Ross Lagerwall , "stefano.stabellini@citrix.com" , "xen-devel@lists.xenproject.org" List-Id: xen-devel@lists.xenproject.org --===============0031174416655012699== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-jPBM0pUHrfXj8Pe2okUo" --=-jPBM0pUHrfXj8Pe2okUo Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On mar, 2014-07-15 at 01:10 +0100, Gordan Bobic wrote: > On 07/14/2014 11:44 PM, Dario Faggioli wrote: > > If you pin VCPU#1 to PCPU#1 and VCPU#2 to PCPU#2, with PCPU#1 and PCPU#= 2 > > being HT siblings, what prevents Linux (in the guest) to run two of the > > four build jobs on VCPU#1 and VCPU#2 (i.e., on siblings PCPUs!!) for al= l > > the length of the benchmark? Nothing, I think. >=20 > That would imply that Xen can somehow make a better decision that the=20 > domU's kernel scheduler, something that doesn't seem that likely. > Well, as far as SMT load balancing is concerned, that is _exactly_ the case. The reason is simple: Xen knows the hw topology, and hence knows whether the sibling of an idle core is idle or busy. The guest kernel sees nothing about this, it just treat all its (V)CPUs as full cores, so it most likely will do a bad job in this case. > > And in fact, pinning would also result in good (near to native, > > perhaps?) performance, if we were exposing the SMT topology details to > > guests as, in that case, Linux would do the balancing properly. However= , > > that's not the case either. :-( >=20 > I see, so you are referring specifically to the HT case.=20 > Yeah, well, that's what this benchmarks where all about :-) > I can see how=20 > that could cause a problem. Does pinning improve the performance with HT= =20 > disabled? >=20 HT disabled had pretty goo perf. already. Anyhow, I tried: Average Half load -j 2 Run (std deviation): Elapsed Time 56.462 (0.109179) Average Optimal load -j 4 Run (std deviation): Elapsed Time 31.526 (0.224789) Average Maximal load -j Run (std deviation): Elapsed Time 33.04 (0.439147) So a lot similar to the no-HT unpinned case, which on it's turn was a lot similar to baremetal without HT. Daio --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-jPBM0pUHrfXj8Pe2okUo 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 v2 iEYEABECAAYFAlPEkkwACgkQk4XaBE3IOsTy1ACfffFvGK1U8vAZItwxVhqIX3aC B1oAoJJ5XN0M1VwkXdGONUnu6zz1Uz7l =AndV -----END PGP SIGNATURE----- --=-jPBM0pUHrfXj8Pe2okUo-- --===============0031174416655012699== 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 --===============0031174416655012699==--