From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH 0/3] qemu-kvm: vhost net support Date: Thu, 20 Aug 2009 16:41:03 +0300 Message-ID: <20090820134103.GC7834@redhat.com> References: <20090810192304.GA16781@redhat.com> <4A808840.70704@codemonkey.ws> <20090812173548.GA29981@redhat.com> <200908201649.48082.rusty@rustcorp.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: virtualization@lists.linux-foundation.org, Anthony Liguori , avi@redhat.com, kvm@vger.kernel.org To: Rusty Russell Return-path: Received: from mx1.redhat.com ([209.132.183.28]:19844 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754513AbZHTNmn (ORCPT ); Thu, 20 Aug 2009 09:42:43 -0400 Content-Disposition: inline In-Reply-To: <200908201649.48082.rusty@rustcorp.com.au> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, Aug 20, 2009 at 04:49:47PM +0930, Rusty Russell wrote: > On Thu, 13 Aug 2009 03:05:48 am Michael S. Tsirkin wrote: > > On Mon, Aug 10, 2009 at 03:51:12PM -0500, Anthony Liguori wrote: > > > Any rough idea on performance? Better or worse than userspace? > > > > Well, I definitely see some gain in latency. > ... > > Part of it might be that tx mitigation does not come into play with vhost. I > > need to disable it in qemu and see. > > A simple test I've found reasonably indicative when looking at base performance (before stuff like TSO get involved) is to do pings. Throughput with "ping -s 1024 -l 120 -c 1000000 -f -q" and latency with "ping -c 1000000 -f -q". > > (You may need to cut -l down if your ring is too small). > > Cheers, > Rusty. OK, will try that. -- MST