From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754379Ab1LDPRI (ORCPT ); Sun, 4 Dec 2011 10:17:08 -0500 Received: from mx1.redhat.com ([209.132.183.28]:31449 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754087Ab1LDPRF (ORCPT ); Sun, 4 Dec 2011 10:17:05 -0500 Message-ID: <4EDB8EEB.4070309@redhat.com> Date: Sun, 04 Dec 2011 17:16:59 +0200 From: Avi Kivity User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111115 Thunderbird/8.0 MIME-Version: 1.0 To: "Michael S. Tsirkin" CC: Sasha Levin , Rusty Russell , linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, kvm@vger.kernel.org, markmc@redhat.com Subject: Re: [PATCH] virtio-ring: Use threshold for switching to indirect descriptors References: <1322669511.3985.8.camel@lappy> <87wrahrp0u.fsf@rustcorp.com.au> <20111201075847.GA5479@redhat.com> <1322726977.3259.3.camel@lappy> <20111201102640.GB8822@redhat.com> <87zkfbre9x.fsf@rustcorp.com.au> <1322913028.3782.4.camel@lappy> <4EDB5EF0.2010909@redhat.com> <20111204120132.GB18758@redhat.com> <4EDB624A.3030403@redhat.com> <20111204151148.GA21851@redhat.com> In-Reply-To: <20111204151148.GA21851@redhat.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 12/04/2011 05:11 PM, Michael S. Tsirkin wrote: > > There's also the used ring, but that's a > > mistake if you have out of order completion. We should have used copying. > > Seems unrelated... unless you want used to be written into > descriptor ring itself? The avail/used rings are in addition to the regular ring, no? If you copy descriptors, then it goes away. > But, I don't really know why does virtio ring insist on > making the 3 buffers (avail/used/descriptor) > physically contigious. Rusty? Let's drop them instead. > > > 16kB worth of descriptors is 1024 entries. With 4kB buffers, that's 4MB > > worth of data, or 4 ms at 10GbE line speed. With 1500 byte buffers it's > > just 1.5 ms. In any case I think it's sufficient. > > Right. So I think that without indirect, we waste about 3 entries > per packet for virtio header and transport etc headers. That does suck. Are there issues in increasing the ring size? Or making it discontiguous? Can you take a peek at how Xen manages its rings? They have the same problems we do. -- error compiling committee.c: too many arguments to function