From mboxrd@z Thu Jan 1 00:00:00 1970 From: linux-JhLEnvuH02M@public.gmane.org Subject: Re: [ACPI] [PATCHES] ACPI Processor update [idle, throttling, thermal, cpufreq] Date: Wed, 10 Sep 2003 01:29:16 +0200 Sender: cpufreq-bounces-1walMZg8u8rXmaaqVzeoHQ@public.gmane.org Message-ID: <20030909232916.GA9561@brodo.de> References: <20030904222434.GC6350@brodo.de> <20030908132939.GD3944@openzaurus.ucw.cz> <20030909172135.GA4106@brodo.de> <20030909231303.GH211@elf.ucw.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20030909231303.GH211-I/5MKhXcvmPrBKCeMvbIDA@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: cpufreq-bounces-1walMZg8u8rXmaaqVzeoHQ@public.gmane.org To: Pavel Machek Cc: acpi-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org, andrew.grover-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org, cpufreq-1walMZg8u8rXmaaqVzeoHQ@public.gmane.org List-Id: linux-acpi@vger.kernel.org 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