From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261434AbVFBXZr (ORCPT ); Thu, 2 Jun 2005 19:25:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261505AbVFBXZq (ORCPT ); Thu, 2 Jun 2005 19:25:46 -0400 Received: from e35.co.us.ibm.com ([32.97.110.133]:49607 "EHLO e35.co.us.ibm.com") by vger.kernel.org with ESMTP id S261434AbVFBXVA (ORCPT ); Thu, 2 Jun 2005 19:21:00 -0400 Subject: Re: [PATCH 3/4] new timeofday x86-64 arch specific changes (v. B1) From: john stultz To: Parag Warudkar Cc: Nishanth Aravamudan , Andi Kleen , lkml , Tim Schmielau , George Anzinger , albert@users.sourceforge.net, Ulrich Windl , Christoph Lameter , Dominik Brodowski , David Mosberger , Andrew Morton , paulus@samba.org, schwidefsky@de.ibm.com, keith maanthey , Chris McDermott , Max Asbock , mahuja@us.ibm.com, Darren Hart , "Darrick J. Wong" , Anton Blanchard , donf@us.ibm.com, mpm@selenic.com, benh@kernel.crashing.org In-Reply-To: <200506021905.08274.kernel-stuff@comcast.net> References: <060220051827.15835.429F4FA6000DF9D700003DDB220588617200009A9B9CD3040A029D0A05@comcast.net> <20050602183904.GC2636@us.ibm.com> <200506021905.08274.kernel-stuff@comcast.net> Content-Type: text/plain Date: Thu, 02 Jun 2005 16:20:53 -0700 Message-Id: <1117754453.17804.51.camel@cog.beaverton.ibm.com> Mime-Version: 1.0 X-Mailer: Evolution 2.0.4 (2.0.4-4) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2005-06-02 at 19:05 -0400, Parag Warudkar wrote: > On Thursday 02 June 2005 14:39, Nishanth Aravamudan wrote: > > Which timesource is being used? > > > > cat /sys/devices/system/timesource/timesource0/timesource > > tux-gentoo parag # cat /sys/devices/system/timesource/timesource0/timesource > jiffies tsc tsc-interp *acpi_pm You can change the timesource at runtime by doing something like: echo "tsc" > /sys/devices/system/timesource/timesource0/timesource The "*" denotes the current timesource, so you'll see it move the next time you cat the timesource sysfs file. Could you see if the slowness you're feeling is correlated to the acpi_pm timesource? It is quite a bit slower to access then the TSC, but I'd be surprised if you can actually feel the difference. This is on an x86-64 system, correct? thanks -john