From mboxrd@z Thu Jan 1 00:00:00 1970 From: George Dunlap Subject: Re: Hypervisor Migration Date: Wed, 17 Jul 2013 14:51:09 +0100 Message-ID: <51E6A14D.4070801@eu.citrix.com> References: <51E69850.1070706@amazon.de> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4769673209951230607==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: emdel Cc: "Egger, Christoph" , "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org --===============4769673209951230607== Content-Type: multipart/alternative; boundary="------------000608090005010106010900" --------------000608090005010106010900 Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 7bit On 17/07/13 14:23, emdel wrote: > On Wed, Jul 17, 2013 at 3:12 PM, Egger, Christoph > wrote: > > So let me draw a picture. If it is correct then that means on > machine n > hypervisor i must support nested virtualization. > > > Exactly. The hypervisor i must support nested virtualization. > Your picture is exactly what I mean. Do you mean you want to migrate the guests from m.h to n.i.h? Or do you mean you want to migrate the hypervisor itself from running on bare metal to running in a VM? I think the Intel guys have been looking at the first (migrating a VM running on Xen-on-metal to Xen-on-Xen). Not sure about AMD. I don't think anyone has tried the second even with a normal operating system, much less a hypervisor with things running on top of it. -G --------------000608090005010106010900 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: 8bit

On 17/07/13 14:23, emdel wrote:

On Wed, Jul 17, 2013 at 3:12 PM, Egger, Christoph <chegger@amazon.de> wrote:

So let me draw a picture. If it is correct then that means on machine n
hypervisor i must support nested virtualization.

Exactly. The hypervisor i must support nested virtualization.

Your picture is exactly what I mean.

Do you mean you want to migrate the guests from m.h to n.i.h? Or do you mean you want to migrate the hypervisor itself from running on bare metal to running in a VM?

I think the Intel guys have been looking at the first (migrating a VM running on Xen-on-metal to Xen-on-Xen). Not sure about AMD.

I don't think anyone has tried the second even with a normal operating system, much less a hypervisor with things running on top of it.

-G
--------------000608090005010106010900-- --===============4769673209951230607== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============4769673209951230607==--