WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

[Xen-devel] RE: Bizarre pv kernel ultra-high frequency rdtsc?!?

To: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>, Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Subject: [Xen-devel] RE: Bizarre pv kernel ultra-high frequency rdtsc?!?
From: Dan Magenheimer <dan.magenheimer@xxxxxxxxxx>
Date: Sat, 21 Nov 2009 14:05:01 -0800 (PST)
Cc: "Xen-Devel \(E-mail\)" <xen-devel@xxxxxxxxxxxxxxxxxxx>
Delivery-date: Sat, 21 Nov 2009 14:07:28 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <C72E0FF4.AFE%keir.fraser@xxxxxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Yes, that does indeed fix it.  Thanks very much!

Now, onward to scaling!  (Necessary when the PV kernel
boots on "tsc safe" hardware but then migrates.)

Thanks again!
Dan

> -----Original Message-----
> From: Keir Fraser [mailto:keir.fraser@xxxxxxxxxxxxx]
> Sent: Saturday, November 21, 2009 2:45 PM
> To: Dan Magenheimer; Jeremy Fitzhardinge
> Cc: Xen-Devel (E-mail)
> Subject: Re: Bizarre pv kernel ultra-high frequency rdtsc?!?
> 
> 
> On 20/11/2009 23:45, "Dan Magenheimer" 
> <dan.magenheimer@xxxxxxxxxx> wrote:
> 
> > -        _u.tsc_timestamp     = t->stime_local_stamp;
> > -        _u.system_time       = t->stime_local_stamp;
> > +        _u.tsc_timestamp     = t->stime_local_stamp - BIG_OFFSET;
> > +        _u.system_time       = t->stime_local_stamp - BIG_OFFSET;
> 
> Ah, the line above is the bug. You should be subtracting 
> BIG_OFFSET from
> _u.tsc_timestamp only. Leave _u.system_time as it is. That'll 
> fix all your
> observed problems.
> 
>  -- Keir
> 
> 
>

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