From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756058Ab1HERBp (ORCPT ); Fri, 5 Aug 2011 13:01:45 -0400 Received: from smtp102.prem.mail.ac4.yahoo.com ([76.13.13.41]:32309 "HELO smtp102.prem.mail.ac4.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751190Ab1HERBm (ORCPT ); Fri, 5 Aug 2011 13:01:42 -0400 X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: nYEaQ3IVM1k_wI0FdObhYzbBNCJx8ixWi9mPgTbYJ9wO0FO WqxEtuJqfQFLWD0PM53n00wxWUSPV.TYS8sLtY.xjRtHMHd9aMvrUlJT_Xgl a6jTUtM977MZBxdTHmdnOHuLbdcD4aAHisQza_baGgcQZllz3yHP14oyIRtl ewo0w0yjJLqtpqVjpkm5miSl743mYzzBPm75ppgfwAJeb.bvuUjUEHTakWTD 6luwgnv5wHyf9sPJwVZjJJ4VpevoXg0x8BrkePtqfe_y.GK3mphHx.y.J05I HrrK0Eelz_vsVdOObihQ1Lx2QxOmH.z3Fur9Ss1MqPaXcf7d9UjAMvYtSFJB NjRrrt6222UGa_q38LC_cZC4xCLn9zZX5JapT..9gP5oGH0ceLjGj5UVOqee k2tMu7wnKPd7h.U42c0tTmg-- X-Yahoo-SMTP: _Dag8S.swBC1p4FJKLCXbs8NQzyse1SYSgnAbY0- Date: Fri, 5 Aug 2011 12:01:38 -0500 (CDT) From: Christoph Lameter X-X-Sender: cl@router.home To: Dave Jones cc: Pekka Enberg , Markus Trippelsdorf , Linux Kernel , Linus Torvalds , Andrew Morton , Jens Axboe Subject: Re: list corruption in the last few days. (block ? crypto ?) In-Reply-To: <20110805165119.GA11593@redhat.com> Message-ID: References: <20110805010038.GA18148@redhat.com> <20110805084614.GA1588@x4.trippels.de> <20110805163948.GA11113@redhat.com> <20110805165119.GA11593@redhat.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 5 Aug 2011, Dave Jones wrote: > On Fri, Aug 05, 2011 at 11:47:56AM -0500, Christoph Lameter wrote: > > On Fri, 5 Aug 2011, Dave Jones wrote: > > > > > Not sure if you were addressing my original report (quoted above), or the networking > > > related report in this part of the thread. But anyway, I had it turned on (as well as just about > > > every other debugging option). I didn't see anything output from it though, > > > just the LIST_DEBUG warnings. > > > > But CONFIG_SLUB_DEBUG_ON was off? If slab debugging was on then this could > > be an issue with full slab list management instead of partial lists. > > $ grep SLUB_DEBUG_ON .config > CONFIG_SLUB_DEBUG_ON=y Argh another debugging code issue. Anyone who sees this please verify that it also occurs with debugging off. I ran this code for 9 months in various configs but only sporadically with debugging support since that switches the lockless stuff. With the lockless ops on we cannot establish a stable state of the object as needed for regular inspection and verification of operations.