RE: [Xen-devel] RE: rdtsc strangeness on upstream kernel

[Dan Magenheimer <dan.magenheimer@xxxxxxxxxx>]

> On 07/19/2010 04:55 PM, Dan Magenheimer wrote:
> >> With vcpus=2, timer0 goes up to about 2000 irq/sec on CPU0
> >> and timer1 on CPU1 is the same while rdtsc/sec is about 20000.
> >>
> > No, wait, correct that...timer0 and timer1 are 1000 irq/sec.
> > (I was using "watch -d" which defaults to updating every
> > two seconds, not every second.)
> >
> >
> >> Is it possible that the timer interrupt is using rdtsc
> >> five times each interrupt?
> >>
> > TEN times each interrupt.
> >
> 
> Do you have any other debugging/tracing enabled?  CONFIG_XEN_DEBUG_FS
> for example?
> 
> 10 sounds a little high, but not necessarily completely unreasonable,
> especially if there's tracing/debugging on.

Yes, CONFIG_XEN_DEBUG_FS is on.  I dug up some instrumentation
I used in the hypervisor last fall which should identify the
kernel locations of the rdtsc's.  I'll plug that in and
post the results tomorrow.

Dan

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