Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756381AbYKQCSf (ORCPT ); Sun, 16 Nov 2008 21:18:35 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754776AbYKQCS1 (ORCPT ); Sun, 16 Nov 2008 21:18:27 -0500 Received: from cpsmtpo-eml06.KPNXCHANGE.COM ([213.75.38.155]:30910 "EHLO cpsmtpo-eml06.kpnxchange.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754664AbYKQCS0 (ORCPT ); Sun, 16 Nov 2008 21:18:26 -0500 From: Frans Pop To: Thomas Gleixner Subject: Re: [2.6.28-rc5] TSC sync error and high hrtimer_start (was: Bootup time regression from 2.6.27 to 2.6.28-rc3+) Date: Mon, 17 Nov 2008 03:18:22 +0100 User-Agent: KMail/1.9.9 Cc: Arjan van de Ven , Lukas Hejtmanek , "Rafael J. Wysocki" , Marcin Slusarz , linux-kernel@vger.kernel.org, torvalds@linux-foundation.org, corsac@debian.org References: <20081104173300.GF6134@ics.muni.cz> <200811140245.40505.elendil@planet.nl> <200811162027.44988.elendil@planet.nl> In-Reply-To: <200811162027.44988.elendil@planet.nl> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200811170318.23640.elendil@planet.nl> X-OriginalArrivalTime: 17 Nov 2008 02:18:24.0793 (UTC) FILETIME=[C51B5890:01C9485A] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1722 Lines: 36 On Sunday 16 November 2008, Frans Pop wrote: > Possibly this may be related to this diff in the boot messages: > -checking TSC synchronization [CPU#0 -> CPU#1]: passed. > +checking TSC synchronization [CPU#0 -> CPU#1]: > +Measured 696 cycles TSC warp between CPUs, turning off TSC clock. > +Marking TSC unstable due to check_tsc_sync_source failed > > With .27.4 TSC _always_ passed. Now, with .28-rc5 I get this warp. I've > done two boots so far, for the other one the warp was 680 cycles. Maybe this extra context a bit earlier in dmesg is relevant here: -Calibrating delay loop (skipped), value calculated using timer frequency.. 6399.76 BogoMIPS (lpj=12799520) +HPET: 3 timers in total, 0 timers will be used for per-cpu timer +Calibrating delay loop (skipped), value calculated using timer frequency.. 6399.73 BogoMIPS (lpj=12799476) [...] -ACPI: Core revision 20080609 +ACPI: Core revision 20080926 +Setting APIC routing to flat ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1 CPU0: Intel(R) Pentium(R) D CPU 3.20GHz stepping 07 -Using local APIC timer interrupts. -APIC timer calibration result 12499520 -Detected 12.499 MHz APIC timer. -Booting processor 1/1 ip 6000 +Booting processor 1 APIC 0x1 ip 0x6000 Initializing CPU#1 -Calibrating delay using timer specific routine.. 6399.94 BogoMIPS (lpj=12799898) +Calibrating delay using timer specific routine.. 6198.05 BogoMIPS (lpj=12396107) Note the rather large difference in BogoMIPS between core 0 and 1. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/