From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: Re: [PATCH] KVM: emulator: do not needlesly sync registers from emulator ctxt to vcpu Date: Wed, 30 Mar 2011 13:43:33 +0200 Message-ID: <20110330114333.GW7766@redhat.com> References: <20110329120838.GQ7766@redhat.com> <4D93083D.6000806@redhat.com> <20110330104727.GS7766@redhat.com> <4D930B0D.4090809@redhat.com> <20110330112243.GV7766@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: mtosatti@redhat.com, kvm@vger.kernel.org To: Avi Kivity Return-path: Received: from mx1.redhat.com ([209.132.183.28]:20176 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932120Ab1C3Lnf (ORCPT ); Wed, 30 Mar 2011 07:43:35 -0400 Received: from int-mx09.intmail.prod.int.phx2.redhat.com (int-mx09.intmail.prod.int.phx2.redhat.com [10.5.11.22]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id p2UBhZkM016517 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Wed, 30 Mar 2011 07:43:35 -0400 Content-Disposition: inline In-Reply-To: <20110330112243.GV7766@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Wed, Mar 30, 2011 at 01:22:43PM +0200, Gleb Natapov wrote: > On Wed, Mar 30, 2011 at 12:50:53PM +0200, Avi Kivity wrote: > > On 03/30/2011 12:47 PM, Gleb Natapov wrote: > > >On Wed, Mar 30, 2011 at 12:38:53PM +0200, Avi Kivity wrote: > > >> On 03/29/2011 02:08 PM, Gleb Natapov wrote: > > >> >Currently we sync registers back and forth before/after exiting > > >> >to userspace for IO, but during IO device model shouldn't need to > > >> >read/write the registers, so we can as well skip those sync points. The > > >> >only exaception is broken vmware backdor interface. The new code sync > > >> >registers content during IO only if registers are read from/written to > > >> >by userspace in the middle of the IO operation and this almost never > > >> >happens in practise. > > >> > > >> While this is a nice idea, how much does it save in practice? It > > >> does introduce more complexity. > > >> > > > > > >I haven't measured, but can try to do so. It eliminates two copies of > > >all registers on each MMIO/PIO read. I expect this to be measurable in > > >workloads that do many such reads. > > > > > > > I don't, especially if these are mmios to userspace. Perhaps it's > > better to remove the copy on kernel mmio, since it's much faster, if > > the result is simpler (there can be no KVM_SET_REGS in that > > context). > > > > The patch saves copying of 256 bytes on each MMIO/PIO read. It may not > save a lot comparing to time it takes to do one MMIO to userspace, but > do 1 million of those and you saved a lot of CPU cycles. I do not think > we should abandon the optimization so easily. Unfortunately I can't run > perf on 2.6.38 kernel right now. It gives me strange errors and when it > doesn't it makes kernel OOPS. > After reboot perf started to work. I ran modified emulator.flat unit test. It was modified to run test_cmps() in an endless loop. Without patch: 1.71% qemu-system-x86 [kvm] [k] x86_emulate_instruction 1.51% qemu-system-x86 [kvm] [k] x86_emulate_instruction 1.68% qemu-system-x86 [kvm] [k] x86_emulate_instruction With patch: 0.84% qemu-system-x86 [kvm] [k] x86_emulate_instruction 0.96% qemu-system-x86 [kvm] [k] x86_emulate_instruction 0.89% qemu-system-x86 [kvm] [k] x86_emulate_instruction -- Gleb.