On 10/02/2010 23:09, "Jeremy Fitzhardinge" <jeremy@xxxxxxxx> wrote:
> There is one big difference between the Xen clock and the CMOS clock,
> which is that the Xen clock is being concurrently accessed by other
> domains. If it is being updated periodically, then there will be
> discontinuities in time which may affect other domains. But since
> there's no time-warp ABI to Xen, I don't think this can really be
> avoided; anyone reading periodically the Xen clock needs to be able to
> deal with any discontinuities. pvops kernels only inspect it at boot
> time, and so won't see any subsequent time adjustments anyway.
A Xen ABI for adjtime()-alike warping of Xen system time is something we
should add at some point, as that's the logical thing for ntp in dom0 to
affect, keeping the system's 'nanosecond ticker' in sync with the wider
world. That'd keep all domU clocks in sync, all except for fixed wallclock
offsets. But it doesn't currently exist, so instead it gets bunged in with
Xen's existing settimeofday()-alike interface: hence domUs either can see
discontinuities, or don't get the automatic benefits of ntp sync at all,
because they only read the wallclock offset at boot time.
 -- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel