From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Greear Subject: Re: Kernel splat with debugging on 3.3.6+ kernel. Date: Fri, 18 May 2012 15:46:55 -0700 Message-ID: <4FB6D15F.6020006@candelatech.com> References: <4FB697AB.10809@candelatech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: "linux-wireless@vger.kernel.org" , netdev Return-path: Received: from mail.candelatech.com ([208.74.158.172]:48441 "EHLO ns3.lanforge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S967348Ab2ERWq4 (ORCPT ); Fri, 18 May 2012 18:46:56 -0400 In-Reply-To: <4FB697AB.10809@candelatech.com> Sender: netdev-owner@vger.kernel.org List-ID: On 05/18/2012 11:40 AM, Ben Greear wrote: > This is a patched kernel, but nothing proprietary loaded. > > We're chasing a hard-to-reproduce bug that appears to be stale > memory access related to wifi stations. > > So, I enabled a bunch of debugging (memory debugging, lockdep, etc) > and this lockup occurs every time we try to load our > '400 station' test case. > > I'm going to poke at this some more, try some smaller test > cases and such, but if anyone has any other suggestions I'm interested! I think with the amount of mem debugging I have enabled, I just cannot use this many virtual stations. The problem goes away when we have "only" 100 or so virtual stations enabled... Thanks, Ben -- Ben Greear Candela Technologies Inc http://www.candelatech.com