From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: vhost net: performance with ping benchmark Date: Tue, 25 Aug 2009 16:34:45 +0300 Message-ID: <20090825133445.GB13949@redhat.com> References: <20090824081240.GA3415@redhat.com> <20090824212137.GA9835@redhat.com> <4A934AF7.2090904@codemonkey.ws> <4A936525.5030300@redhat.com> <20090825064604.GB10429@redhat.com> <4A93E235.5040008@codemonkey.ws> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Avi Kivity , virtualization@lists.linux-foundation.org, kvm@vger.kernel.org, Rusty Russell , Mark McLoughlin To: Anthony Liguori Return-path: Received: from mx1.redhat.com ([209.132.183.28]:58111 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751189AbZHYNhE (ORCPT ); Tue, 25 Aug 2009 09:37:04 -0400 Content-Disposition: inline In-Reply-To: <4A93E235.5040008@codemonkey.ws> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, Aug 25, 2009 at 08:08:05AM -0500, Anthony Liguori wrote: > Michael S. Tsirkin wrote: >>> My preference is ring proxying. Not we'll need ring proxying (or at >>> least event proxying) for non-MSI guests. >>> >> >> Exactly, that's what I meant earlier. That's enough, isn't it, Anthony? >> > > It is if we have a working implementation that demonstrates the > userspace interface is sufficient. The idea is trivial enough to be sure the interface is sufficient: we point kernel at used buffer at address X, and copy stuff from there to guest buffer, then signal guest. I'll post a code snippet to show how it's done if you like. > Once it goes into the upstream > kernel, we need to have backwards compatibility code in QEMU forever > to support that kernel version. Don't worry: kernel needs to handle old userspace as well, and neither I nor Rusty want to have a compatibility mess in kernel. > Regards, > > Anthony Liguori