From owner-freebsd-mobile@FreeBSD.ORG Sat Nov 8 05:19:22 2008 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4F201106564A; Sat, 8 Nov 2008 05:19:22 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id 956A88FC18; Sat, 8 Nov 2008 05:19:21 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 227325505; Sat, 08 Nov 2008 07:19:20 +0200 Message-ID: <49152158.9090207@FreeBSD.org> Date: Sat, 08 Nov 2008 07:19:20 +0200 From: Alexander Motin User-Agent: Thunderbird 2.0.0.17 (X11/20081029) MIME-Version: 1.0 To: Ian Smith References: <491208D3.2050901@FreeBSD.org> <20081107033524.A70117@sola.nimnet.asn.au> <1226065673.1210.9.camel@RabbitsDen> <20081108012859.Y70117@sola.nimnet.asn.au> In-Reply-To: <20081108012859.Y70117@sola.nimnet.asn.au> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Sam Leffler , "Alexandre \"Sunny\" Kovalenko" , freebsd-mobile@freebsd.org Subject: Re: RFC: powerd algorithms enhancements X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 08 Nov 2008 05:19:22 -0000 Ian Smith wrote: > We're now seeing cpus that can vary freq, with absolute and relative > cpufreq drivers enabled, in ratios up to 32:1 or so, so the advice, > apart from 'disable powerd' :), seems to be to at least try setting > cpufreq.lowest to some reasonable speed for workload, maybe 300MHz? I surely should not be the default, but it is reasonable if systems should have some guarantied minimal performance. PS: At any modern SMP/HTT system, even if scheduler is unable to manage this IRQ situation, powerd running on different CPU will rise clock to required level just in second. It is hard to lock-out all CPUs same time. It's surely not solution, but still... -- Alexander Motin