From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933292AbXGYPkX (ORCPT ); Wed, 25 Jul 2007 11:40:23 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1762477AbXGYPkJ (ORCPT ); Wed, 25 Jul 2007 11:40:09 -0400 Received: from ns.suse.de ([195.135.220.2]:37922 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760614AbXGYPkH (ORCPT ); Wed, 25 Jul 2007 11:40:07 -0400 To: Andrew Morton Cc: Ingo Molnar , Jeremy Fitzhardinge , linux-kernel@vger.kernel.org, Linus Torvalds , stable@kernel.org, Greg KH , Chris Wright Subject: Re: [patch] fix the softlockup watchdog to actually work References: <20070717114453.GA8212@elte.hu> <469CCF8F.4010107@goop.org> <20070717154934.GA24231@elte.hu> <20070725014912.35c7e325.akpm@linux-foundation.org> From: Andi Kleen Date: 25 Jul 2007 18:34:54 +0200 In-Reply-To: <20070725014912.35c7e325.akpm@linux-foundation.org> Message-ID: User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Andrew Morton writes: > > One possibility is that sched_clock() is bollixed and (say) it's returning > a 32-bit value. That'll cause the softlockup logic to get a bit sick when > time wraps. FYI, The current ff x86 sched_clock() [which you likely have, it's not mainline] tends to warp backwards by 80-90ms during cpu freq changes on AMD on one of my test systems. I haven't tracked down why it does that yet. Intel or systems with no cpufreq or cpufreq not changing frequencies regularly are not affected -Andi