From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jan Kara Subject: Re: [PATCH 0/2] radix-tree: fix writeback livelock avoidance code Date: Fri, 20 Aug 2010 15:51:41 +0200 Message-ID: <20100820135141.GC5716@quack.suse.cz> References: <1282281727-15088-1-git-send-email-david@fromorbit.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, jack@suse.cz, npiggin@kernel.dk To: Dave Chinner Return-path: Received: from cantor2.suse.de ([195.135.220.15]:47825 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751642Ab0HTNw0 (ORCPT ); Fri, 20 Aug 2010 09:52:26 -0400 Content-Disposition: inline In-Reply-To: <1282281727-15088-1-git-send-email-david@fromorbit.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Fri 20-08-10 15:22:05, Dave Chinner wrote: > The following two patches fix bugs in the new radix tree functionality used to > implement the writeback livelock avoidance code. Both bugs manifest themselves > as stray PAGECACHE_TAG_TOWRITE tags in the mapping->page_tree radix tree > resulting in livelocks during tag lookups. More subtly, they also appear to > result in writeback tree walks occasionally terminating early and so not > actually writing all the pages they are supposed to. Really, how that early termination could happen? I'm just wondering because I don't see that.. The code just mindlessly copies tags regardless of how target flags are set so that's why I'd think that any stale copied flags just don't matter... Honza -- Jan Kara SUSE Labs, CR