RE: [Xen-ia64-devel] SMP guest and itc

["Xu, Anthony" <anthony.xu@xxxxxxxxx>]

>Ultimately I think we're going to need to fully virtualize the ITC, but
>I would guess the pre-sync solution will work for a while.  We are
>eventually going to need to run on systems where the ITC may drift
>between processors, we could hide that with a fully virtualized ITC.

Totally agree.

Thanks,
-Anthony 

>-----Original Message-----
>From: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
>[mailto:xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Alex
>Williamson
>Sent: 2006年2月10日 23:11
>To: Tristan Gingold
>Cc: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
>Subject: Re: [Xen-ia64-devel] SMP guest and itc
>
>On Fri, 2006-02-10 at 09:01 +0100, Tristan Gingold wrote:
>> Le Jeudi 09 Février 2006 17:59, Alex Williamson a écrit :
>
>> >    I'm not sure I understand c).  Aren't the ITCs already
>> > pre-synchronized by xen in smp_callin()?   Thanks,
>> Correct, but Linux is not aware of this.
>> After more thoughs, I really think this is the best solution.
>
>   Does that imply the Linux kernel will be somewhat paravirtualized
>with respect to the ITC (ie. knowing that the ITC is pre-synchronized)?
>Ultimately I think we're going to need to fully virtualize the ITC, but
>I would guess the pre-sync solution will work for a while.  We are
>eventually going to need to run on systems where the ITC may drift
>between processors, we could hide that with a fully virtualized ITC.
>Thanks,
>
>       Alex
>
>--
>Alex Williamson                             HP Linux & Open Source Lab
>
>
>_______________________________________________
>Xen-ia64-devel mailing list
>Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
>http://lists.xensource.com/xen-ia64-devel

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel