Re: [ACPI] [PATCHES] ACPI Processor update [idle, throttling, thermal, cpufreq]

[linux@brodo.de]

Hi,

[powernow-k8 see separate e-mail]

On Wed, Sep 10, 2003 at 01:13:03AM +0200, Pavel Machek wrote:
> > On Mon, Sep 08, 2003 at 03:29:40PM +0200, Pavel Machek wrote:
> > > http://www.brodo.de/cpufreq_tmp/acpi-2.6.0-test4-processor_thermal_throttling
> > > > 	Move throttling into its own submodule, and register it with the new
> > > > 	passive cooling module. Also, the now-useless "limit" interface is
> > > > 	removed.
> > > > 
> > > 
> > > Actually I liked to be able to echo 0:7 > limit and conserve battery/
> > > make sure machine does not overheat  with it...
> > 
> > echo 7 > throttling should do the same thing. 
> 
> Will not first change in thermal system unthrottle it for me, behind
> my back?

Well yes, it might, if the temperature had been higher than the passive
cooling trip point. If you want me to, I'll change the behaviour so that the
/proc/acpi/.../throttling input is consistent (minimum limit) until the user 
choses a different throttling level.

> > However, don't expect any
> > battey conservation if ACPI C2 throttling works, and to set custom levels
> > against "overheating" there's a write access to
> > /proc/acpi/thermal/*/trip_points too...
> 
> I'd should not expect battery conservation *when cpu is idle*. If I'm
> moving windows in X, 0:7 limit will actually help.

depends if you see it relative to the time or relative to the energy...

> And it should allow
> battery to be drained further by limiting maximum amps eaten by
> CPU. [Ok, that's little evil, but being able to run for 30 minutes+ on
> 0% battery is nice ;-)].

Well yes, for this case, setting throttling to 0:7 might indeed make
sense...

	Dominik