From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 15920 invoked by alias); 23 Sep 2008 17:33:09 -0000 Received: (qmail 15911 invoked by uid 22791); 23 Sep 2008 17:33:08 -0000 X-Spam-Status: No, hits=-2.6 required=5.0 tests=BAYES_00 X-Spam-Check-By: sourceware.org Received: from www.tglx.de (HELO www.tglx.de) (62.245.132.106) by sourceware.org (qpsmtpd/0.31) with ESMTP; Tue, 23 Sep 2008 17:32:30 +0000 Received: from localhost (www.tglx.de [127.0.0.1]) by www.tglx.de (8.13.8/8.13.8/TGLX-2007100201) with ESMTP id m8NHUeUF016014 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 23 Sep 2008 19:30:46 +0200 Date: Tue, 23 Sep 2008 17:33:00 -0000 From: Thomas Gleixner To: Masami Hiramatsu cc: Linus Torvalds , Mathieu Desnoyers , Martin Bligh , Linux Kernel Mailing List , Steven Rostedt , darren@dvhart.com, "Frank Ch. Eigler" , systemtap-ml Subject: Re: Unified tracing buffer In-Reply-To: <48D921B3.2060809@redhat.com> Message-ID: References: <33307c790809191433w246c0283l55a57c196664ce77@mail.gmail.com> <48D7F5E8.3000705@redhat.com> <33307c790809221313s3532d851g7239c212bc72fe71@mail.gmail.com> <48D81B5F.2030702@redhat.com> <33307c790809221616h5e7410f5gc37c262d83722111@mail.gmail.com> <48D832B6.3010409@redhat.com> <33307c790809221712x4fbd9781u958c98d4585e92a9@mail.gmail.com> <48D901FE.5060604@redhat.com> <20080923150410.GA28341@Krystal> <48D90B84.4030905@redhat.com> <48D921B3.2060809@redhat.com> User-Agent: Alpine 1.10 (LFD 962 2008-03-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Virus-Scanned: ClamAV 0.93.2/8314/Tue Sep 23 02:50:20 2008 on www.tglx.de X-Virus-Status: Clean X-Spam-Checker-Version: SpamAssassin 3.2.4 (2008-01-01) on www.tglx.de Mailing-List: contact systemtap-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org X-SW-Source: 2008-q3/txt/msg00773.txt.bz2 On Tue, 23 Sep 2008, Masami Hiramatsu wrote: > > So if you can test this, try it with > > (a) cpufreq at a fixed _low_ value (to not cause overheating) > > (b) with the spray-can cooling the thing and cpufreq at a fixed high > > value > > and see if the TSC is constant then. > > Hi Linus, > > Thank you for your advice. I tested it again according your advice, > I did: > - service cpuspeed stop > - echo 1000000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed > and checked /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq is > 1000000. > - echo 1 > /proc/acpi/thermal_zone/THM/polling_frequency > - cooling with spray-can :) > - cat /proc/acpi/thermal_zone/THM/temperature > temperature: 39 C > > and ran the test. > --- > p0: c:1107576, ns:990280 ratio:111 > p0: c:1805640, ns:1008787 ratio:178 > p0: c:1998324, ns:1000127 ratio:199 > p0: c:946380, ns:990280 ratio:95 > p0: c:871728, ns:1000267 ratio:87 > p0: c:1807380, ns:1007949 ratio:179 > p0: c:1784808, ns:1000127 ratio:178 > p0: c:1768488, ns:991676 ratio:178 > p0: c:1802292, ns:1008299 ratio:178 > p0: c:1787088, ns:1000406 ratio:178 > p0: c:1999176, ns:1000896 ratio:199 > p0: c:881364, ns:991956 ratio:88 > p0: c:1802712, ns:1008019 ratio:178 > p0: c:1787088, ns:998590 ratio:178 > --- > this seems not so stable yet. :-( > > After test I checked temperature again. > # cat /proc/acpi/thermal_zone/THM/temperature > temperature: 39 C > > Hmm, 39 C is not so high. I wouldn't be surprised even if this > is an individual product bug. Anyway, currently, Linux itself > works well on this laptop with hpet.:-) Do you have C-States enabled on that machine ? ls /sys/devices/system/cpu/cpu0/cpuidle/ has it more than a state0 entry ? If yes, please do: cat /sys/devices/system/cpu/cpu0/cpuidle/stateX/usage where X is the highest number in there. cat /proc/acpi/processor/CPU0/power might be useful as well. Thanks, tglx