From owner-freebsd-acpi@FreeBSD.ORG Sun Jun 28 20:58:01 2009 Return-Path: Delivered-To: freebsd-acpi@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D46A7106566C; Sun, 28 Jun 2009 20:58:01 +0000 (UTC) (envelope-from oberman@es.net) Received: from mailgw.es.net (mail2.es.net [IPv6:2001:400:107:1::2]) by mx1.freebsd.org (Postfix) with ESMTP id B6A038FC18; Sun, 28 Jun 2009 20:58:01 +0000 (UTC) (envelope-from oberman@es.net) Received: from ptavv.es.net (ptavv.es.net [IPv6:2001:400:910::29]) by mailgw.es.net (8.14.3/8.14.3) with ESMTP id n5SKw0Yp027197 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT); Sun, 28 Jun 2009 13:58:01 -0700 Received: from ptavv.es.net (ptavv.es.net [127.0.0.1]) by ptavv.es.net (Tachyon Server) with ESMTP id DF09A1CC09; Sun, 28 Jun 2009 13:58:00 -0700 (PDT) To: Alexander Motin In-reply-to: Your message of "Sun, 28 Jun 2009 23:42:48 +0300." <4A47D5C8.4090701@FreeBSD.org> Date: Sun, 28 Jun 2009 13:58:00 -0700 From: "Kevin Oberman" Message-Id: <20090628205800.DF09A1CC09@ptavv.es.net> X-Proofpoint-Virus-Version: vendor=fsecure engine=1.12.8161:2.4.5, 1.2.40, 4.0.166 definitions=2009-06-28_01:2009-06-25, 2009-06-28, 2009-06-26 signatures=0 Cc: freebsd-acpi@freebsd.org Subject: Re: acpi/cpu scaling probs? Dell D820 FreeBSD current X-BeenThere: freebsd-acpi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: ACPI and power management development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 28 Jun 2009 20:58:02 -0000 > Date: Sun, 28 Jun 2009 23:42:48 +0300 > From: Alexander Motin > > Kevin Oberman wrote: > >> Date: Sun, 28 Jun 2009 21:55:48 +0300 > >> From: Alexander Motin > >> Sender: owner-freebsd-acpi@freebsd.org > >> > >> Ron Freidel wrote: > >>> I hope I am posting to the correct list... > >>> > >>> I have updated to FreeBSD current to try out acpi sleep, which works great > >>> by the way, and the improvements to wifi and the addition of sleep are > >>> enough to keep current on the laptop. > >>> > >>> Here's the problem, the cpu is maxed out, no scaling at all. > >>> > >>> Here's the output of powerd -v > >>> > >>> load 108%, current freq 2000 MHz ( 0), wanted freq 4000 MHz > >>> load 109%, current freq 2000 MHz ( 0), wanted freq 4000 MHz > >>> load 102%, current freq 2000 MHz ( 0), wanted freq 4000 MHz > >>> load 124%, current freq 2000 MHz ( 0), wanted freq 4000 MHz > >>> load 108%, current freq 2000 MHz ( 0), wanted freq 4000 MHz > >>> > >> ^^^ > >> This is the reason. powerd sees that one of your CPUs is constantly > >> busy. You should investigate why and what that CPU does. > > > > Agreed, but that still does not explain why it keeps trying to set the > > clock to 4 GHz on a 2 GHz system. Not too surprising that it does not > > work. :-) > > It is not a bug, but feature. It is specific of the "hiadaptive" mode. > It means that CPU is too busy now and should not drop frequency > immediately after load drops to not loose system interactivity and > performance. Thanks! This makes excellent sense. I think I need to switch mine to hiadaptive, at least on AC. Now, it Ron can get his CPU under control, I think things will be normal on his system. -- R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 Key fingerprint:059B 2DDF 031C 9BA3 14A4 EADA 927D EBB3 987B 3751