From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-2?Q?Rafa=B3_Bilski?= Subject: Re: [PATCH] Longhaul - Need timer tick Date: Mon, 05 Mar 2007 23:42:56 +0100 Message-ID: <45EC9CF0.7@interia.pl> References: <45E89FAA.7050008@interia.pl> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <45E89FAA.7050008@interia.pl> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=m.gmane.org+glkc-cpufreq=m.gmane.org@lists.linux.org.uk Content-Type: text/plain; charset="iso-8859-9" To: Dave Jones Cc: cpufreq@lists.linux.org.uk > There is no support for dynamic ticks in Longhaul.=20 > Current code is assuming that timer tick is present and=20 > constant. Please ignore this patch. Somehow NO_HZ option don't change=20 anything. Average tick frequency is reduced to 20% for me=20 (uptime / interrupt 0 count), but somehow when Longhaul=20 is changing CPU frequency it is always equal to value set=20 by "Timer frequency" option. Probably this is how NO_HZ=20 author want it to work. Anyway, tested (with help of ACPI=20 PM timer) and even if help for this option may sound scary=20 for me, there is no change in transition latency. At least=20 on my system. Sorry Rafa=B3 ---------------------------------------------------------------------- Oficjalne konto pocztowe europejskich internautow!=20 >>> http://link.interia.pl/f19e8