From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754462AbZEIMrl (ORCPT ); Sat, 9 May 2009 08:47:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751553AbZEIMrd (ORCPT ); Sat, 9 May 2009 08:47:33 -0400 Received: from 124x34x33x190.ap124.ftth.ucom.ne.jp ([124.34.33.190]:54024 "EHLO master.linux-sh.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751504AbZEIMrc (ORCPT ); Sat, 9 May 2009 08:47:32 -0400 Date: Sat, 9 May 2009 21:41:56 +0900 From: Paul Mundt To: Andrew Morton Cc: Ron , mingo@elte.hu, a.p.zijlstra@chello.nl, linux-kernel@vger.kernel.org Subject: Re: [PATCH] fix for sched_clock() when using jiffies Message-ID: <20090509124155.GA23191@linux-sh.org> Mail-Followup-To: Paul Mundt , Andrew Morton , Ron , mingo@elte.hu, a.p.zijlstra@chello.nl, linux-kernel@vger.kernel.org References: <20081126150645.GA28153@homer.shelbyville.oz> <1227712598.4454.199.camel@twins> <20081126153152.GB28153@homer.shelbyville.oz> <20081128144039.GG28138@elte.hu> <20090508132449.GV5417@homer.shelbyville.oz> <20090508200444.GA22132@homer.shelbyville.oz> <20090508160142.ad89944f.akpm@linux-foundation.org> <20090509004009.GZ5417@homer.shelbyville.oz> <20090508181559.4750800e.akpm@linux-foundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090508181559.4750800e.akpm@linux-foundation.org> User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, May 08, 2009 at 06:15:59PM -0700, Andrew Morton wrote: > On Sat, 9 May 2009 10:10:09 +0930 Ron wrote: > > This was a resend of a patch that seemed to get a thumbs up, except > > for whitespace damage in what I originally sent, but which apparently > > then didn't get applied. The original context to it was: > > > > I'm in the process of updating a port for an ARM based chip we've been > > working on, from 2.6.22-rc4'ish to the current HEAD of Linus' tree, and > > I started seeing the following: > > > > [ 0.000000] PID hash table entries: 512 (order: 9, 2048 bytes) > > [42949372.970000] Dentry cache hash table entries: 16384 (order: 4, 65536 bytes) > > > > The reason appears to be that printk_clock() has been replaced with a > > call to cpu_clock, which in our case currently falls back to the default > > (weak) implementation of sched_clock() that uses jiffies -- but doesn't > > account for the initial offset of the jiffy count. The following simple > > patch fixes it for me, in line with what printk_clock used to do. > > Removing printk_clock() always seemed a mildly wrong idea to me. > > I'm sure we fixed this printk-timestamping ages and ages ago. Maybe it > came back, or maybe it's somehow specific to your setup? > FWIW, I just ran in to this yesterday on a board with a single timer channel (which is assigned over to clockevents so we can still do tickless), using the jiffies clocksource. With printk_clock() gone, it seems like anything using the jiffies clocksource ought to have this problem.