From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:53973) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1XOBLS-0003ov-3Y for qemu-devel@nongnu.org; Sun, 31 Aug 2014 16:03:32 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1XOBLL-00053n-Uh for qemu-devel@nongnu.org; Sun, 31 Aug 2014 16:03:26 -0400 Received: from mx1.redhat.com ([209.132.183.28]:15877) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1XOBLL-00053L-OD for qemu-devel@nongnu.org; Sun, 31 Aug 2014 16:03:19 -0400 Message-ID: <54037F82.9050209@redhat.com> Date: Sun, 31 Aug 2014 13:03:14 -0700 From: Andy Grover MIME-Version: 1.0 References: <20140829172218.GD16755@irqsave.net> <20140830144641.GM14001@redhat.com> <20140830155343.GA2212@irqsave.net> <20140830160212.GH1302@redhat.com> In-Reply-To: <20140830160212.GH1302@redhat.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] tcmu-runner and QEMU List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Richard W.M. Jones" , =?ISO-8859-1?Q?Beno=EEt_C?= =?ISO-8859-1?Q?anet?= Cc: kwolf@redhat.com, pbonzini@redhat.com, qemu-devel@nongnu.org, stefanha@redhat.com On 08/30/2014 09:02 AM, Richard W.M. Jones wrote: > On Sat, Aug 30, 2014 at 05:53:43PM +0200, Beno=EEt Canet wrote: >> If the cloud provider want to be able to boot QCOW2 or QED images on >> bare metal machines he will need to export QCOW2 or QED images on >> the network. >> >> So far only qemu-nbd allows to do this and it is neither well >> performing nor really convenient to boot on a bare metal machine. > > So I think what you want is a `qemu-iscsi'? ie. the same as qemu-nbd, > but with an iSCSI frontend (to replace the NBD server). You want qemu to be able to issue SCSI commands over iSCSI? I thought=20 qemu used libiscsi for this, to be the initiator. What Benoit and I have=20 been discussing is the other side, enabling qemu to configure LIO to=20 handle requests from other initiators (either VMs or iron) over iSCSI or=20 FCoE, but backed by qcow2 disk images. The problem being LIO doesn't=20 speak qcow2 yet. > I guess so. Are you planning to integrate bits of LIO into qemu, or > bits of qemu into LIO? My current thinking is 1) enable qemu to configure the LIO kernel target=20 (it's all straightforward via configfs, but add a nice library to qemu=20 to hide the details) and 2) enable LIO to use qcow2 and other formats=20 besides raw images to back exported LUNs. This is where the LIO=20 userspace passthrough and tcmu-runner come in, because we want to do=20 this in userspace, not as kernel code, so we have to pass SCSI commands=20 up to a userspace helper daemon. > The latter has been tried various times, without much success. See > the many examples of people trying to make the qemu block driver code > into a separate library, and failing. What's been the sticking point? Regards -- Andy