RE: [Xen-users] a new server for Xen

["Ryan Burke" <burke@xxxxxxxxxxxxxxxxx>]

>
>
>> -----Original Message-----
>> From: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
>> [mailto:xen-users-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of
>> Jan Albrecht
>> Sent: 01 March 2007 05:16
>> To: xin
>> Cc: xen-users@xxxxxxxxxxxxxxxxxxx
>> Subject: Re: [Xen-users] a new server for Xen
>>
>> xin wrote:
>> > Thanks for that. What about a VT-supported cpu to do the
>> para-virtualization
>> > instead of full-virtualization? which one is better.
>> I've AMD PV and Intel VT here and from my point of view the
>> VT are much
>> better (and that's no matter if they're AMD, Intel or from Mars...),
>> because you can install an OS "out-of-box" to that server.
>> With PV you're limited to Linux and to special kernels.  And the
>> arguments Mats brought up may be right, but as long as you do normal
>> daily business on such a server (file-server, webserver, etc...) at VT
>> machine would always be the better choice.
>
> Sure, with VT (in my view obviously preferrably from AMD ;-) ) you have
> ALL the possibilites, rather than just half of them. I should have said
> so in my post.
>
> --
> Mats


I guess now I'm confused. I thought that AMD PV and Intel VT did basically
the same thing. They allowed unmodified OS's to work with a hypervisor to
support full vitrualization. From that Jan said it sounds like there is a
draw back of PV vs VT? I haven't heard anything about that. Can someone
explain (I personally prefer AMD)??

Thanks,
Ryan

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