From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gerd Hoffmann Subject: Re: [RFC] VMX CR3 cache Date: Wed, 30 Jan 2008 13:05:55 +0100 Message-ID: <47A06823.7090104@redhat.com> References: <20080128160444.GA3821@dmt> <479EE9C3.8000007@redhat.com> <479EFFB0.1000700@redhat.com> <20080129123355.GA11587@dmt> <47A034CD.9010708@redhat.com> <47A040E3.7000207@redhat.com> <47A04D1C.4090505@qumranet.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Marcelo Tosatti , kvm-devel To: Avi Kivity Return-path: In-Reply-To: <47A04D1C.4090505-atKUWr5tajBWk0Htik3J/w@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org Errors-To: kvm-devel-bounces-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org List-Id: kvm.vger.kernel.org Avi Kivity wrote: > [fairly amazing results. how do they compare to xen?] Didn't benchmark it side-by-side yet. Most likely xenner is still noticeable slower on 64bit (32bit should be roughly comparable). I also wouldn't surprised if you see different results on different workloads. xen mangles page table flags alot to make guests run fast despite the frequent cr3 switches. It sets the global flag for userspace mappings (which are identical in kernel/userspace page table tree) to avoid them being flushed from tlb on every syscall enter/exit. I havn't tried to do similar things in xenner because I don't track page tables in the first place. I hope to get it to speed comparable to xen using virtualization hardware features instead. cheers, Gerd -- http://kraxel.fedorapeople.org/xenner/ ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/