From: Christoph Lameter Subject: Re: No, really, stop trying to delete slab until you've finished making slub perform as well Date: Thu, 14 Aug 2008 10:06:33 -0500 Message-ID: <48A449F9.8010903@linux-foundation.org> References: <20080805210125.A897.KOSAKI.MOTOHIRO@jp.fujitsu.com> <48986AC6.5030406@linux-foundation.org> <20080813194222.E77F.KOSAKI.MOTOHIRO@jp.fujitsu.com> <48A2DD2C.3090602@linux-foundation.org> <48A3DBAC.6010109@cs.helsinki.fi> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: KOSAKI Motohiro , KOSAKI Motohiro , Matthew Wilcox , akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, Mel Gorman , andi@firstfloor.org, Rik van Riel To: Pekka Enberg Return-path: Received: from smtp1.linux-foundation.org ([140.211.169.13]:35042 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751518AbYHNPHl (ORCPT ); Thu, 14 Aug 2008 11:07:41 -0400 In-Reply-To: <48A3DBAC.6010109@cs.helsinki.fi> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Pekka Enberg wrote: > > This patch hard locks on my 2-way 64-bit x86 machine (sysrq doesn't > respond) when I run hackbench. At that point we take the listlock and then the slab lock which is a lock inversion if we do not use a trylock here. Crap. Hmmm.. The code already goes to the next slab if an earlier one is already locked. So I do not see how the large partial lists could be generated.