From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753611AbZHRHjV (ORCPT ); Tue, 18 Aug 2009 03:39:21 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751439AbZHRHjH (ORCPT ); Tue, 18 Aug 2009 03:39:07 -0400 Received: from mx2.redhat.com ([66.187.237.31]:38874 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751474AbZHRHjD (ORCPT ); Tue, 18 Aug 2009 03:39:03 -0400 Message-ID: <4A8A5A7F.5050809@redhat.com> Date: Tue, 18 Aug 2009 10:38:39 +0300 From: Avi Kivity User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.1) Gecko/20090814 Fedora/3.0-2.6.b3.fc11 Thunderbird/3.0b3 MIME-Version: 1.0 To: Anthony Liguori CC: Gregory Haskins , Ingo Molnar , Gregory Haskins , kvm@vger.kernel.org, alacrityvm-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, "Michael S. Tsirkin" Subject: Re: [PATCH v3 3/6] vbus: add a "vbus-proxy" bus model for vbus_driver objects References: <20090814154125.26116.70709.stgit@dev.haskins.net> <20090814154308.26116.46980.stgit@dev.haskins.net> <20090815103243.GA26749@elte.hu> <4A870964.9090408@codemonkey.ws> <4A8965E0.8050608@gmail.com> <4A89FF08.30509@codemonkey.ws> In-Reply-To: <4A89FF08.30509@codemonkey.ws> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 08/18/2009 04:08 AM, Anthony Liguori wrote: > I believe strongly that we should avoid putting things in the kernel > unless they absolutely have to be. I'm definitely interested in > playing with vhost to see if there are ways to put even less in the > kernel. In particular, I think it would be a big win to avoid > knowledge of slots in the kernel by doing ring translation in > userspace. This implies a userspace transition in the fast path. > This may or may not be acceptable. I think this is going to be a very > interesting experiment and will ultimately determine whether my > intuition about the cost of dropping to userspace is right or wrong. I believe with a perfectly scaling qemu this should be feasible. Currently qemu is far from scaling perfectly, but inefficient userspace is not a reason to put things into the kernel. Having a translated ring is also a nice solution for migration - userspace can mark the pages dirty while translating the receive ring. Still, in-kernel translation is simple enough that I think we should keep it. -- error compiling committee.c: too many arguments to function