RE: [Xen-devel] Xen on top of xen

["Petersson, Mats" <Mats.Petersson@xxxxxxx>]

> -----Original Message-----
> From: Koripella Srinivas [mailto:talkwithsrinivas@xxxxxxxxxxx] 
> Sent: 09 May 2007 19:53
> To: Petersson, Mats
> Subject: Re: [Xen-devel] Xen on top of xen
> 
> Can u throw more light on  the non-nestability ?? 

Well, to put it simply, once you set up the SVM/VMX feature, it doesn't
allow another such setup on top of it. It would be technically possible
to support this in a processor designed to do so, but at the moment,
neither of AMD's or Intel's CPU's support this. It is clearly easier to
design a processor that only supports one level of "nesting" of
virtualization[1], and it is also debatable what the REAL benefit of
running nested virtual machines would be - I'm sure if it was a huge
benefit compared to the effort of implementing it[2], at least one of
the two producers of virtualizable x86 processors would have added such
fearures... 

[1] Keeping one set of data for where to return to when the VMExit
happens, for example, is easier than having a "stack" of such. 

[2] On top of the extra effort to design and test such feature, there is
also a potential performance penalty for nesting VM's, since there is
more logic involved. Depending on where that extra logic ends up, it may
be necessary to add a further clock-cycle to some operation. 

--
Mats
> 
> 
> ----- Original Message ----
> From: "Petersson, Mats" <Mats.Petersson@xxxxxxx>
> To: pradeep singh rautela <rautelap@xxxxxxxxx>; Koripella 
> Srinivas <talkwithsrinivas@xxxxxxxxxxx>
> Cc: xen-devel@xxxxxxxxxxxxxxxxxxx; 
> xen-devel-request@xxxxxxxxxxxxxxxxxxx
> Sent: Wednesday, 9 May, 2007 4:33:57 PM
> Subject: RE: [Xen-devel] Xen on top of xen
> 
> 
> 
> 
> > -----Original Message-----
> > From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx 
> > [mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of 
> > pradeep singh rautela
> > Sent: 09 May 2007 10:11
> > To: Koripella Srinivas
> > Cc: xen-devel@xxxxxxxxxxxxxxxxxxx; 
> > xen-devel-request@xxxxxxxxxxxxxxxxxxx
> > Subject: Re: [Xen-devel] Xen on top of xen
> > 
> > 
> > 
> > On 5/9/07, pradeep singh rautela <rautelap@xxxxxxxxx> wrote:
> > 
> > 
> > 
> >     On 5/9/07, Koripella Srinivas < 
> > talkwithsrinivas@xxxxxxxxxxx 
> > <mailto:talkwithsrinivas@xxxxxxxxxxx> > wrote:
> > 
> >         Hi,
> >         Is it possible to run xen in a hvm guest which 
> > itself is running on xen?
> > 
> > 
> >     Yes, you can. 
> > 
> > 
> > Just to add only on hvm guests and not  on pv guests.
> 
> And you can't run HVM guests inside the "xen on top of xen", 
> as the HVM
> feature is not (in current CPU's) nestable. 
> 
> --
> Mats
> > 
> > 
> > 
> >     Thanks 
> >     ~psr
> >     
> > 
> > 
> >         
> >         Thanks
> >         
> > 
> > ________________________________
> > 
> >         Office firewalls, cyber cafes, college labs, 
> > don't allow you to download CHAT? Here's a solution! 
> > <http://us.rd.yahoo.com/mail/in/ymessenger/*http://in.messenge
> > r.yahoo.com/webmessengerpromo.php>  
> > 
> >         _______________________________________________
> >         Xen-devel mailing list
> >         Xen-devel@xxxxxxxxxxxxxxxxxxx 
> > <mailto:Xen-devel@xxxxxxxxxxxxxxxxxxx> 
> >         http://lists.xensource.com/xen-devel
> >         
> >         
> > 
> > 
> > 
> > 
> >     -- 
> >     ---
> >     pradeep singh rautela
> >     
> >     "Genius is 1% inspiration, and 99% perspiration" - not me :) 
> > 
> > 
> > 
> > 
> > -- 
> > ---
> > pradeep singh rautela
> > 
> > "Genius is 1% inspiration, and 99% perspiration" - not me :) 
> > 
> 
> 
> 
> 
> 
> ________________________________
> 
> Office firewalls, cyber cafes, college labs, don't allow you 
> to download CHAT? Here's a solution! 
> <http://us.rd.yahoo.com/mail/in/ymessenger/*http://in.messenge
> r.yahoo.com/webmessengerpromo.php>  
> 



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel