From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rusty Russell Subject: Re: updated: kvm networking todo wiki Date: Thu, 30 May 2013 14:53:59 +0930 Message-ID: <87r4gpkplc.fsf@rustcorp.com.au> References: <20130523085034.GA16142@redhat.com> <519F35B7.6010408@redhat.com> <20130524113542.GA7046@redhat.com> <8738tctrox.fsf@codemonkey.ws> <20130524140024.GA12024@redhat.com> <87li6yodgq.fsf@rustcorp.com.au> <87k3miq6sw.fsf@codemonkey.ws> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Jason Wang , herbert@gondor.hengli.com.au, kvm@vger.kernel.org, qemu-devel@nongnu.org, netdev@vger.kernel.org, virtualization@lists.linux-foundation.org, Dmitry Fleytman To: Anthony Liguori , "Michael S. Tsirkin" Return-path: Received: from ozlabs.org ([203.10.76.45]:45174 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S967416Ab3E3Fec (ORCPT ); Thu, 30 May 2013 01:34:32 -0400 In-Reply-To: <87k3miq6sw.fsf@codemonkey.ws> Sender: netdev-owner@vger.kernel.org List-ID: Anthony Liguori writes: > Rusty Russell writes: >> On Fri, May 24, 2013 at 08:47:58AM -0500, Anthony Liguori wrote: >>> FWIW, I think what's more interesting is using vhost-net as a networking >>> backend with virtio-net in QEMU being what's guest facing. >>> >>> In theory, this gives you the best of both worlds: QEMU acts as a first >>> line of defense against a malicious guest while still getting the >>> performance advantages of vhost-net (zero-copy). >>> >> It would be an interesting idea if we didn't already have the vhost >> model where we don't need the userspace bounce. > > The model is very interesting for QEMU because then we can use vhost as > a backend for other types of network adapters (like vmxnet3 or even > e1000). > > It also helps for things like fault tolerance where we need to be able > to control packet flow within QEMU. (CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). Then I'm really confused as to what this would look like. A zero copy sendmsg? We should be able to implement that today. On the receive side, what can we do better than readv? If we need to return to userspace to tell the guest that we've got a new packet, we don't win on latency. We might reduce syscall overhead with a multi-dimensional readv to read multiple packets at once? Confused, Rusty. From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:58498) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UhvVY-0005jT-W4 for qemu-devel@nongnu.org; Thu, 30 May 2013 01:34:45 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UhvVU-0007m4-8c for qemu-devel@nongnu.org; Thu, 30 May 2013 01:34:40 -0400 Received: from ozlabs.org ([203.10.76.45]:34467) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UhvVT-0007ke-Ue for qemu-devel@nongnu.org; Thu, 30 May 2013 01:34:36 -0400 From: Rusty Russell In-Reply-To: <87k3miq6sw.fsf@codemonkey.ws> References: <20130523085034.GA16142@redhat.com> <519F35B7.6010408@redhat.com> <20130524113542.GA7046@redhat.com> <8738tctrox.fsf@codemonkey.ws> <20130524140024.GA12024@redhat.com> <87li6yodgq.fsf@rustcorp.com.au> <87k3miq6sw.fsf@codemonkey.ws> Date: Thu, 30 May 2013 14:53:59 +0930 Message-ID: <87r4gpkplc.fsf@rustcorp.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Subject: Re: [Qemu-devel] updated: kvm networking todo wiki List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Anthony Liguori , "Michael S. Tsirkin" Cc: kvm@vger.kernel.org, netdev@vger.kernel.org, Jason Wang , qemu-devel@nongnu.org, virtualization@lists.linux-foundation.org, herbert@gondor.hengli.com.au, Dmitry Fleytman Anthony Liguori writes: > Rusty Russell writes: >> On Fri, May 24, 2013 at 08:47:58AM -0500, Anthony Liguori wrote: >>> FWIW, I think what's more interesting is using vhost-net as a networking >>> backend with virtio-net in QEMU being what's guest facing. >>> >>> In theory, this gives you the best of both worlds: QEMU acts as a first >>> line of defense against a malicious guest while still getting the >>> performance advantages of vhost-net (zero-copy). >>> >> It would be an interesting idea if we didn't already have the vhost >> model where we don't need the userspace bounce. > > The model is very interesting for QEMU because then we can use vhost as > a backend for other types of network adapters (like vmxnet3 or even > e1000). > > It also helps for things like fault tolerance where we need to be able > to control packet flow within QEMU. (CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). Then I'm really confused as to what this would look like. A zero copy sendmsg? We should be able to implement that today. On the receive side, what can we do better than readv? If we need to return to userspace to tell the guest that we've got a new packet, we don't win on latency. We might reduce syscall overhead with a multi-dimensional readv to read multiple packets at once? Confused, Rusty.