From mboxrd@z Thu Jan 1 00:00:00 1970 From: George Dunlap Subject: Re: Xen 4.3 development update / winxp AMD performance regression Date: Thu, 25 Apr 2013 15:00:49 +0100 Message-ID: <51793711.3070809@eu.citrix.com> References: <515B186F02000078000CA1A7@nat28.tlf.novell.com> <20130402163440.GB17022@ocelot.phlegethon.org> <515BF5F102000078000CA39C@nat28.tlf.novell.com> <515C0A0D.6020007@eu.citrix.com> <4691AE88-FA92-4826-BF5E-50175BACA5D9@gmail.com> <20130425135152.GQ11427@reaktio.net> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1"; Format="flowed" Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20130425135152.GQ11427@reaktio.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: =?ISO-8859-1?Q?Pasi_K=E4rkk=E4inen?= Cc: "suravee.suthikulpanit@amd.com" , "Tim (Xen.org)" , "xen-devel@lists.xen.org" , Jan Beulich , Andres Lagar-Cavilla , Peter Maloney List-Id: xen-devel@lists.xenproject.org On 04/25/2013 02:51 PM, Pasi K=E4rkk=E4inen wrote: > On Wed, Apr 03, 2013 at 11:34:13AM -0400, Andres Lagar-Cavilla wrote: >> On Apr 3, 2013, at 6:53 AM, George Dunlap = wrote: >> >>> On 03/04/13 08:27, Jan Beulich wrote: >>>>>>> On 02.04.13 at 18:34, Tim Deegan wrote: >>>>> At 16:42 +0100 on 02 Apr (1364920927), Jan Beulich wrote: >>>>>>>>> On 02.04.13 at 16:07, George Dunlap = wrote: >>>>>>> * AMD NPT performance regression after c/s 24770:7f79475d3de7 >>>>>>> owner: ? >>>>>>> Reference: http://marc.info/?l=3Dxen-devel&m=3D135075376805215 >>>>>> This is supposedly fixed with the RTC changes Tim committed the >>>>>> other day. Suravee, is that correct? >>>>> This is a separate problem. IIRC the AMD XP perf issue is caused by = the >>>>> emulation of LAPIC TPR accesses slowing down with Andres's p2m locking >>>>> patches. XP doesn't have 'lazy IRQL' or support for CR8, so it takes= a >>>>> _lot_ of vmexits for IRQL reads and writes. >>>> Ah, okay, sorry for mixing this up. But how is this a regression >>>> then? >>> >>> My sense, when I looked at this back whenever that there was much more = to this. The XP IRQL updating is a problem, but it's made terribly worse b= y the changset in question. It seemed to me like the kind of thing that wo= uld be caused by TLB or caches suddenly becoming much less effective. >> >> The commit in question does not add p2m mutations, so it doesn't nuke th= e NPT/EPT TLBs. It introduces a spin lock in the hot path and that is the p= roblem. Later in the 4.2 cycle we changed the common case to use an rwlock.= Does the same perf degradation occur with tip of 4.2? >> > > Adding Peter to CC who reported the original winxp performance problem/re= gression on AMD. > > Peter: Can you try Xen 4.2.2 please and report if it has the performance = problem or not? Do you want to compare 4.2.2 to 4.2.1, or 4.3? The changeset in question was included in the initial release of 4.2, so = unless you think it's been fixed since, I would expect 4.2 to have this = regression. -George