From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ted Ts'o Subject: Re: [PATCH 3/3] ext4: update writeback_index based on last page scanned Date: Mon, 25 Oct 2010 17:35:50 -0400 Message-ID: <20101025213550.GK16981@thunk.org> References: <4CC2023A.7060607@redhat.com> <4CC205ED.4090007@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: ext4 development To: Eric Sandeen Return-path: Received: from THUNK.ORG ([69.25.196.29]:54140 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752674Ab0JYVfz (ORCPT ); Mon, 25 Oct 2010 17:35:55 -0400 Content-Disposition: inline In-Reply-To: <4CC205ED.4090007@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Fri, Oct 22, 2010 at 04:45:17PM -0500, Eric Sandeen wrote: > As pointed out in a prior patch, updating the mapping's > writeback_index based on pages written isn't quite right; > what the writeback index is really supposed to reflect is > the next page which should be scanned for writeback during > periodic flush. > > As in write_cache_pages(), write_cache_pages_da() does > this scanning for us as we assemble the mpd for later > writeout. If we keep track of the next page after the > current scan, we can easily update writeback_index without > worrying about pages written vs. pages skipped, etc. > > Without this, an fsync will reset writeback_index to > 0 (its starting index) + however many pages it wrote, which > can mess up the progress of periodic flush. > > Signed-off-by: Eric Sandeen Have you done any benchmarks with and without this patch series? Say, compilebench on a used and mildly fragmented file system? - Ted