From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752264AbXCHFkX (ORCPT ); Thu, 8 Mar 2007 00:40:23 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932113AbXCHFkX (ORCPT ); Thu, 8 Mar 2007 00:40:23 -0500 Received: from mail22.syd.optusnet.com.au ([211.29.133.160]:45659 "EHLO mail22.syd.optusnet.com.au" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752227AbXCHFkW (ORCPT ); Thu, 8 Mar 2007 00:40:22 -0500 From: Con Kolivas To: Andrew Morton Subject: Re: [PATCH] [RSDL-mm 0/6] RSDL cpu scheduler for -mm Date: Thu, 8 Mar 2007 16:25:05 +1100 User-Agent: KMail/1.9.5 Cc: linux-kernel@vger.kernel.org, ck@vds.kolivas.org References: <200703071226.43238.kernel@kolivas.org> <20070307185430.31fb48b8.akpm@linux-foundation.org> <20070307201502.4e93c5d5.akpm@linux-foundation.org> In-Reply-To: <20070307201502.4e93c5d5.akpm@linux-foundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200703081625.06383.kernel@kolivas.org> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thursday 08 March 2007 15:15, Andrew Morton wrote: > On Wed, 7 Mar 2007 18:54:30 -0800 Andrew Morton wrote: > > On Wed, 7 Mar 2007 17:43:45 -0800 Andrew Morton wrote: > > > On Wed, 7 Mar 2007 12:26:42 +1100 > > > > > > Con Kolivas wrote: > > > > What follows is the same patch series that constitutes the RDSL > > > > "Rotating Staircase DeadLine" cpu scheduler resynced for > > > > 2.6.21-rc2-mm2. > > > > > > Big oops early in boot on x86_64 SMP, in rq_bitmap_error+0x97/0x9f. > > > > > > I stubbed it out with a `return MAX_RT_PRIO;' (I think) but it then > > > oopsed differently. Before netconsole had come up, no serial console, > > > no digital camera. > > > > > > There's stuff in http://userweb.kernel.org/~akpm/ck/ - you can probably > > > boot that kernel on your own machine. > > > > > > I need to do rc3-mm1 now. I might find some time to poke at this > > > further after that, but I have to leave for a week in .jp and it'll be > > > squeezy, sorry. > > > > well it boots os dual pIII and quad powerpc. > > It also boots OK on a very similar but somewhat older Nocona machine. > Perhaps due to config changes: > http://userweb.kernel.org/~akpm/ck/config-ok.txt Ok I just remembered that not only did I expect the cpu task to never be scheduled and it _might_ be scheduled on sched_init, it is actually _consciously_ scheduled on hotplug cpu which I have no way of handling at the moment. On both your configs I noticed you had hotplug cpu enabled, but perhaps it isn't really being used on the more conservative config. So this is something I already know I need to handle. Did your ppc that had the "bitmap error" have hotplug cpu enabled? It might be an unrelated bug^Wphenomenon. -- -ck