On Fri, 01 Sep 2006 14:01:47 +1000, Simon Burge <simonb@NetBSD.org> wrote:


> 
> And blind luck wins!
> 
> I've got a little script that cycles through the frequencies every 2
> seconds, and prints some info gathered from the kernel.  I then started
> a "make -j4" to keep the system busy.  Note here that the MSR_PERF_CTL
> value of 0x613 is the value for the lowest CPU speed (1000MHz).

Let me see if I understand the situation correctly.  If we had good ACPI
support -- and for laptops, there was a lot of progress a few months ago,
though it seems to have stalled; I'm one feature away from being able to
use it on my laptop -- we could read the speed tables directly.  However,
we don't have that, so we need to resort to heuristics to guess what the
speeds should be?  Is that a fair summary?  Or is the data just not
present on the machine in any form?

		--Steven M. Bellovin, http://www.cs.columbia.edu/~smb