Mihal K wrote:
> Jose Rodriguez wrote:
>>>> I installed 2.6.24 and everything seems OK except that my CPU
>>>> spends about 75% of its time in C2 [snip ipw2200 problem]So to recap, 
>>>> 2.6.24
>> compiled from source as well as from Debian repos (hpet=force) do 
>> show a behavior not seen before with 2.6.22 with the mentioned patches.

The patches are i)HPET force and 
ii)http://www.lesswatts.org/projects/powertop/patches/kernel-2.6.22-rc1.patch

>>From http://www.lesswatts.org/projects/powertop/faq.php
> 
> Why did my power usage increase with dynticks? Why do I never reach
> sleep states deeper than C2?
> 
> The current ACPI sleep function requires wakeups to reach deeper sleep
> states. Certain drivers, such as ipw2200, limit the initial sleep state
> to C2 due to DMA activity. With dynticks, which tries to sleep as long
> as possible, this means that your processor will, most of the time, only
> reach C2 and thus waste power compared to a non-dynticks kernel if it is
> mostly idle. This will be solved by an upcoming cpuidle patch. Until
> this hits mainline, you should compare your power usage with and without
> dynticks (and maybe with different HZ values) to figure out which is
> currently the best for your workload.
> ------------------------------------------------
> Though it looks like exactly the opposite has happened - 2.6.22 (without
> cpuidle) had no problems and 2.6.24 (with cpuidle) has trouble going to
> the sleep states deeper than C2.

OK, I'm a little bit confused with all these dynticks, tickless 
kernel, HPET, cpuidle and friends. What is it new now that is 
causing the problem? Is there any configuration option in 2.6.24 I 
can play with to recompile it to obtain the nice behaviour I had 
with 2.6.22 regarding ipw2200? This is, not being stuck at C2 when 
the wifi radio is on?

Thanks

_______________________________________________
Power mailing list
[email protected]
http://www.bughost.org/mailman/listinfo/power

Reply via email to