From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gregory Haskins Subject: Re: [RFC PATCH 0/3] generic hypercall support Date: Fri, 08 May 2009 16:01:23 -0400 Message-ID: <4A048F93.1050601@novell.com> References: <4A010927.6020207@novell.com> <20090506072212.GV3036@sequoia.sous-sol.org> <4A018DF2.6010301@novell.com> <20090506160712.GW3036@sequoia.sous-sol.org> <4A031471.7000406@novell.com> <20090507233503.GA9103@amt.cnet> <20090507234311.GA9517@amt.cnet> <4A03E579.8030201@redhat.com> <20090508143507.GA8319@amt.cnet> <4A0445A0.4060104@novell.com> <20090508155109.GA9269@amt.cnet> <4A048E78.6020605@cisco.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig79993F9582203C5C6D4D2250" Cc: Marcelo Tosatti , Avi Kivity , Chris Wright , Gregory Haskins , kvm@vger.kernel.org, Anthony Liguori To: "David S. Ahern" Return-path: Received: from victor.provo.novell.com ([137.65.250.26]:33626 "EHLO victor.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754620AbZEHUB0 (ORCPT ); Fri, 8 May 2009 16:01:26 -0400 In-Reply-To: <4A048E78.6020605@cisco.com> Sender: kvm-owner@vger.kernel.org List-ID: This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig79993F9582203C5C6D4D2250 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable David S. Ahern wrote: > Marcelo Tosatti wrote: > =20 >> On Fri, May 08, 2009 at 10:45:52AM -0400, Gregory Haskins wrote: >> =20 >>> Marcelo Tosatti wrote: >>> =20 >>>> On Fri, May 08, 2009 at 10:55:37AM +0300, Avi Kivity wrote: >>>> =20 >>>> =20 >>>>> Marcelo Tosatti wrote: >>>>> =20 >>>>> =20 >>>>>> Also it would be interesting to see the MMIO comparison with EPT/N= PT, >>>>>> it probably sucks much less than what you're seeing. >>>>>> =20 >>>>>> =20 >>>>>> =20 >>>>> Why would NPT improve mmio? If anything, it would be worse, since = the =20 >>>>> processor has to do the nested walk. >>>>> >>>>> Of course, these are newer machines, so the absolute results as wel= l as =20 >>>>> the difference will be smaller. >>>>> =20 >>>>> =20 >>>> Quad-Core AMD Opteron(tm) Processor 2358 SE 2.4GHz: >>>> >>>> NPT enabled: >>>> test 0: 3088633284634 - 3059375712321 =3D 29257572313 >>>> test 1: 3121754636397 - 3088633419760 =3D 33121216637 >>>> test 2: 3204666462763 - 3121754668573 =3D 82911794190 >>>> >>>> NPT disabled: >>>> test 0: 3638061646250 - 3609416811687 =3D 28644834563 >>>> test 1: 3669413430258 - 3638061771291 =3D 31351658967 >>>> test 2: 3736287253287 - 3669413463506 =3D 66873789781 >>>> >>>> =20 >>>> =20 >>> Thanks for running that. Its interesting to see that NPT was in fact= >>> worse as Avi predicted. >>> >>> Would you mind if I graphed the result and added this data to my wiki= ?=20 >>> If so, could you adjust the tsc result into IOPs using the proper >>> time-base and the test_count you ran with? I can show a graph with = the >>> data as is and the relative differences will properly surface..but it= >>> would be nice to have apples to apples in terms of IOPS units with my= >>> other run. >>> >>> -Greg >>> =20 >> Please, that'll be nice. >> >> Quad-Core AMD Opteron(tm) Processor 2358 SE >> >> host: 2.6.30-rc2 >> guest: 2.6.29.1-102.fc11.x86_64 >> >> test_count=3D1000000, tsc freq=3D2402882804 Hz >> >> NPT disabled: >> >> test 0 =3D 2771200766 >> test 1 =3D 3018726738 >> test 2 =3D 6414705418 >> test 3 =3D 2890332864 >> >> NPT enabled: >> >> test 0 =3D 2908604045 >> test 1 =3D 3174687394 >> test 2 =3D 7912464804 >> test 3 =3D 3046085805 >> >> =20 > > DL380 G6, 1-E5540, 6 GB RAM, SMT enabled: > host: 2.6.30-rc3 > guest: fedora 9, 2.6.27.21-78.2.41.fc9.x86_64 > > with EPT > test 0: 543617607291 - 518146439877 =3D 25471167414 > test 1: 572568176856 - 543617703004 =3D 28950473852 > test 2: 630182158139 - 572568269792 =3D 57613888347 > > > without EPT > test 0: 1383532195307 - 1358052032086 =3D 25480163221 > test 1: 1411587055210 - 1383532318617 =3D 28054736593 > test 2: 1471446356172 - 1411587194600 =3D 59859161572 > > > =20 Thank you kindly, David. -Greg --------------enig79993F9582203C5C6D4D2250 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG/MacGPG2 v2.0.11 (Darwin) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iEYEARECAAYFAkoEj5MACgkQlOSOBdgZUxm9ggCeNlwR6urrslWsCG0X9kUK2qRd vPIAoITZDHqgXxQArYW2B1/JfgYZ1wa5 =oV/o -----END PGP SIGNATURE----- --------------enig79993F9582203C5C6D4D2250--