From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757876AbZBMLB2 (ORCPT ); Fri, 13 Feb 2009 06:01:28 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751566AbZBMLBT (ORCPT ); Fri, 13 Feb 2009 06:01:19 -0500 Received: from e23smtp05.au.ibm.com ([202.81.31.147]:43241 "EHLO e23smtp05.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751473AbZBMLBS (ORCPT ); Fri, 13 Feb 2009 06:01:18 -0500 Message-ID: <499552F6.8070101@in.ibm.com> Date: Fri, 13 Feb 2009 16:31:10 +0530 From: Chandru User-Agent: Thunderbird 2.0.0.18 (X11/20081125) MIME-Version: 1.0 To: Dave Hansen CC: Benjamin Herrenschmidt , linux-kernel@vger.kernel.org, mm-commits@vger.kernel.org, chandru@linux.vnet.ibm.com, paulus@samba.org, akpm@linux-foundation.org, Johannes Weiner , "Jon M. Tollefson [imap]" Subject: Re: + powerpc-fix-code-for-reserved-memory-spanning-across-nodes.patch added to -mm tree References: <200812250806.mBP86LPQ018399@imap1.linux-foundation.org> <20090208204725.GA5514@cmpxchg.org> <1234139464.31963.79.camel@pasglop> <1234288310.30155.27.camel@nimitz> <4991C71E.9060509@in.ibm.com> In-Reply-To: <4991C71E.9060509@in.ibm.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Chandru wrote: > Dave Hansen wrote: >> On Mon, 2009-02-09 at 11:31 +1100, Benjamin Herrenschmidt wrote: >> >> >>> (BTW. On another note, do you still have pending bug fixes that didn't >>> got in .29 ?) >>> >> >> No, I don't think so. There were some distro fixes but I couldn't >> reproduce the bugs on mainline. >> >> -- Dave >> >> > Dave, > > If I remember, the first mail that I sent on this subject said > 2.6.28-rc9 panics. Unless something has changed in the way > lmb's are added or are reserved, this should be also > reproducible with the mainline kernel on the machines that > had exhibited this problem earlier. I will verify your patch > on these machines again and let you know the results. > > Thanks, > Chandru This still occurs with 2.6.29.rc4 on one of the machines that had shown this problem earlier and Dave's patch solves the issue here. The system comes up with two nodes... NUMA associativity depth for CPU/Memory: 3 Node 0 Memory: 0x0-0x40000000 Node 1 Memory: 0x40000000-0x80000000 I had to increase the crashkernel memory size to beyond 1G and hence used crashkernel=1280M@32M. This caused the kernel to hit the bug as with earlier kernels. -Chandru