From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dominik Brodowski Subject: Re: Feature request Date: Thu, 28 Aug 2003 15:50:36 +0200 Sender: cpufreq-bounces+glkc-cpufreq=gmane.org@www.linux.org.uk Message-ID: <20030828135036.GA17216@brodo.de> References: <000001c3694b$6b4eb5d0$0200a8c0@informatik.domaene> <3F473898.4020101@gotiao.com> <3F4746DB.9080303@gotiao.com> <20030826231001.GB31977@brodo.de> <3F4CE772.9090605@gotiao.com> Mime-Version: 1.0 Return-path: Content-Disposition: inline In-Reply-To: <3F4CE772.9090605@gotiao.com> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: cpufreq-bounces+glkc-cpufreq=gmane.org@www.linux.org.uk Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Viktor Radnai Cc: cpufreq@www.linux.org.uk On Thu, Aug 28, 2003 at 03:16:34AM +1000, Viktor Radnai wrote: > Dominik Brodowski wrote: > >Oh well, so users want to use 150 MHz instead of 1600 MHz now... > My laptop is still quite responsive at 150MHz and anything that lets me > conserve battery power when the performance isn't needed is worth > trying. After all, this is the very purpose of frequency scaling. It > doesn't really matter how fast the kernel executes idle loops ;) Well, does your computer do some real "idling" - e.g. ACPI C-States [C2 and above] or APM "halt"? If so, then you don't need any throttling - it saves approximately the same amount of energy. > >worthy of discussion for 2.7. > That would be great, too bad that it won't happen sooner. In the > meantime, do you think that the method described below is an acceptable > way of saving power or do you foresee any potential problems / > instability as a result of this? > > If you think that this is a workable method then I might hack one of the > userspace frequency scaling utilities to support this method. As most systems support either ACPI-C-States or APM "halt" and these methods are as "good" for power saving, I don't see a reason to implement this at the moment. Dominik