How/why would dev.cpu.0.freq_levels change??!?

[Nate Lawson]

David Wolfskill wrote:
> My laptop is a Dell Inspiron 8200; I (ab)use it moderately heavily:
> this includes tracking RELENG_6, RELENG_7, & HEAD on it, daily.
> 
> Lately there have been some times when "make buildworld" for RELENG_6
> has taken a lot longer than it used to ... and I noticed that the
> fans were on, even though it was running fairly cool (around 50C;
> during a "make buildworld, around 85C is more common) -- and that
> the machine was typically "topping out" at half speed (1200 MHz).
> 
> During these times, querying dev.cpu.0.freq_levels would yield a list
> that did, ini fact, max out at 1200 MHz, when I know that it has gone up
> to 2400 MHz in the past.

The ACPI spec describes how the _PSS levels can change dynamically at 
runtime.  For instance, if you go off AC, the system might offer a lower 
power state.  I'm guessing you're using the acpi_perf driver.

Usually the system generates a notify when that happens though so I was 
surprised there was no dmesg.  I'm not sure how well we support changing 
levels yet.

-- 
Nate