From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933777AbXK3Aaf (ORCPT ); Thu, 29 Nov 2007 19:30:35 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932303AbXK3AaZ (ORCPT ); Thu, 29 Nov 2007 19:30:25 -0500 Received: from hpsmtp-eml15.KPNXCHANGE.COM ([213.75.38.115]:48131 "EHLO hpsmtp-eml15.kpnxchange.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763053AbXK3AaY (ORCPT ); Thu, 29 Nov 2007 19:30:24 -0500 To: Paul Rolland (Witbe.net) Subject: Re: constant_tsc and TSC unstable Cc: linux-kernel@vger.kernel.org, rol@witbe.net In-reply-To: <20071129171142.56c7890a@tux.DEF.witbe.net> References: <20071129171142.56c7890a@tux.DEF.witbe.net> Message-Id: From: Frans Pop Date: Fri, 30 Nov 2007 01:30:22 +0100 X-OriginalArrivalTime: 30 Nov 2007 00:30:22.0320 (UTC) FILETIME=[316EB700:01C832E8] Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Paul Rolland wrote: > Total of 2 processors activated (6919.15 BogoMIPS). > ENABLING IO-APIC IRQs > ..TIMER: vector=0x31 apic1=0 pin1=2 apic2=-1 pin2=-1 > checking TSC synchronization [CPU#0 -> CPU#1]: > Measured 3978592228 cycles TSC warp between CPUs, turning off TSC clock. > Marking TSC unstable due to: check_tsc_sync_source failed. > Brought up 2 CPUs > ... Not sure if this is related, but thought I'd contribute it anyway... I've got a Pentium D system (dual core, single processor) and I on some boots I get "Marking TSC unstable due to check_tsc_sync_source failed" with some cycles warp between CPUs, while most boots are OK. This kind of inconsistency seems more due to a failure in the kernel to deal with differences between boots than with something inherent to the hardware. I conclude that because basically I never have any problems with the system once it has booted and the TSC has passed. >>From my kern.logs since Okt 26, I get the following data: 2.6.23+cfs: 2 passes 2.6.23.1: 1 pass; 1 failure (48 cycles warp) 2.6.24-rc1: 15 passes 2.6.24-rc2: 13 passes; 1 failure (8 cycles warp) 2.6.24-rc3: 5 passes; 3 failures (8, 8 and 16 cycles warp) Note that this is not a new issue. For 2.6.21/2.6.23-RCx kernels I reported similar data in http://lkml.org/lkml/2007/9/16/45. Cheers, FJP