Re: Is the C3 possible with SMP?

On Mon, 2008-11-03 at 00:43 +0200, Alexander Motin wrote: 
> Alexandre "Sunny" Kovalenko wrote:
> > You would not happen to have USB loaded or built into kernel? If you do,
> 
> At home I have external USB keyboard and mouse, so yes, it is built in. 
> It would be difficult to unload and reload it each time I connect something.
I am not sure, I follow. When my laptop is on my desk (and plugged into
the power supply), I am loading usb modules for all the necessary
devices, including, but not limited to my mouse and keyboard.
At this point, I do not get much of C3:

dev.cpu.0.cx_usage: 0.00% 100.00% 0.00%
dev.cpu.1.cx_usage: 0.00% 99.76% 0.23%

When laptop is moving around with me, all USB modules are unloaded and I
get about 4 hours of battery life with wireless on, admittedly on the
light usage (reading/writing E-mails, browsing web, typing up occasional
document). I consider this good for 4.4lbs (<2kg) laptop.

My Kill-A-Watt device shows miniscule (~4%) even if stable difference
between C3 and no-C3 when plugged into the outlet.
> 
> I have read in ICH8M datasheet about special feature of reducing USB 
> busmaster activity on idle periods to support C3 state. Do you know 
> something about it?
Unfortunately, I do not. 

> 
> > you will practically never go into C3. What does
> > 
> > sysctl dev.cpu | grep cx_usage 
> > 
> > say?
> 
> %sysctl -a | grep cx_
> hw.acpi.cpu.cx_lowest: C2
> dev.cpu.0.cx_supported: C1/1 C2/1 C3/57
> dev.cpu.0.cx_lowest: C2
> dev.cpu.0.cx_usage: 0.00% 100.00% 0.00%
> dev.cpu.1.cx_supported: C1/1 C2/1 C3/57
> dev.cpu.1.cx_lowest: C3
> dev.cpu.1.cx_usage: 0.00% 0.43% 99.56%
> 
OK, so we have C3. Is this the machine you see no difference in power
consumption between C3 and no C3? How did you measure it?

-- 
Alexandre "Sunny" Kovalenko (Олександр Коваленко)