From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756409AbYDPWMa (ORCPT ); Wed, 16 Apr 2008 18:12:30 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752966AbYDPWMU (ORCPT ); Wed, 16 Apr 2008 18:12:20 -0400 Received: from fmmailgate09.web.de ([217.72.192.184]:44775 "EHLO fmmailgate09.web.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751507AbYDPWMT (ORCPT ); Wed, 16 Apr 2008 18:12:19 -0400 Date: Thu, 17 Apr 2008 00:12:16 +0200 Message-Id: <242011325@web.de> MIME-Version: 1.0 From: devzero@web.de To: johnstul@us.ibm.com Cc: linux-kernel@vger.kernel.org Subject: Re: Clock has stopped (time/date looping over 5 seconds), things Organization: http://freemail.web.de/ X-Provags-Id: V01U2FsdGVkX1/BUUAasXp4pQZJ2InDcSKH8aoFKcZtiwTihZOdQS+ln+qEH HHE8ozw4oKMY8CA5GdWJ39TzeZNBDCHqYbfrgU8cblnV9iT+qQ= Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >The looping ~5seconds sounds like nanosecond overflows. Might it be >that vmware isn't delivering timer interrupts? seems so - at least i don`t see LOC (local timer interrupts) increase in /proc/interrupts - the only value increasing there is 1: IO-APIC-EDGE i8042 >Could this be an interaction w/ hrt or no_hz? don`t know - not sure what hrt or no_hz is all about in detail, so please you may tell me what i can check - i will happily deliver all input you need or do any test for you. btw - since i thought that problem was vmware only, i didn`t put it in bugzilla - but we have at least two reports that similar behaviour has also also been seen on real hardware, so i have created a bugzilla entry at http://bugzilla.kernel.org/show_bug.cgi?id=10446 regards roland List: linux-kernel Subject: Re: Clock has stopped (time/date looping over 5 secon From: "john stultz" Date: 2008-04-16 17:20:25 Message-ID: 1f1b08da0804161020x7335e58qae9a237da83cb93b () mail ! gmail ! com [Download message RAW] On Tue, Apr 8, 2008 at 2:47 PM, Roland wrote: > > It _appears_ that there is a race in the kernel that can be triggered by > > any number of hardware issues. There's another thread by Gregory Stark > > with the same symptoms - he thinks his was fixed by replacing a bad > > DIMM. > > > > i`d like to mention that we may have a repro-case (if it`s the same issue i > hit within vmware): > > see http://communities.vmware.com/message/909403 The looping ~5seconds sounds like nanosecond overflows. Might it be that vmware isn't delivering timer interrupts? Could this be an interaction w/ hrt or no_hz? thanks -john _____________________________________________________________________ Der WEB.DE SmartSurfer hilft bis zu 70% Ihrer Onlinekosten zu sparen! http://smartsurfer.web.de/?mc=100071&distributionid=000000000066