From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [Qemu-devel] [RFC PATCH 1/1] ceph/rbd block driver for qemu-kvm Date: Tue, 25 May 2010 12:22:14 +0300 Message-ID: <4BFB96C6.8030006@redhat.com> References: <20100519192222.GD61706@ncolin.muc.de> <4BF5A9D2.5080609@codemonkey.ws> <4BF91937.2070801@redhat.com> <4BFA5D07.8030309@redhat.com> <4BFAD146.9090708@codemonkey.ws> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Stefan Hajnoczi , Christian Brunner , Blue Swirl , kvm@vger.kernel.org, qemu-devel@nongnu.org, ceph-devel@vger.kernel.org To: Anthony Liguori Return-path: Received: from mx1.redhat.com ([209.132.183.28]:24852 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756408Ab0EYJW2 (ORCPT ); Tue, 25 May 2010 05:22:28 -0400 In-Reply-To: <4BFAD146.9090708@codemonkey.ws> Sender: kvm-owner@vger.kernel.org List-ID: On 05/24/2010 10:19 PM, Anthony Liguori wrote: > On 05/24/2010 06:03 AM, Avi Kivity wrote: >> On 05/24/2010 11:27 AM, Stefan Hajnoczi wrote: >>> On Sun, May 23, 2010 at 1:01 PM, Avi Kivity wrote: >>>> On 05/21/2010 12:29 AM, Anthony Liguori wrote: >>>>> I'd be more interested in enabling people to build these types of >>>>> storage >>>>> systems without touching qemu. >>>>> >>>>> Both sheepdog and ceph ultimately transmit I/O over a socket to a >>>>> central >>>>> daemon, right? >>>> That incurs an extra copy. >>> Besides a shared memory approach, I wonder if the splice() family of >>> syscalls could be used to send/receive data through a storage daemon >>> without the daemon looking at or copying the data? >> >> Excellent idea. > > splice() eventually requires a copy. You cannot splice() to linux-aio > so you'd have to splice() to a temporary buffer and then call into > linux-aio. With shared memory, you can avoid ever bringing the data > into memory via O_DIRECT and linux-aio. If the final destination is a socket, then you end up queuing guest memory as an skbuff. In theory we could do an aio splice to block devices but I don't think that's realistic given our experience with aio changes. -- error compiling committee.c: too many arguments to function