From: Andreas Dilger Subject: Re: [PATCH 01/11 RESEND] libe2p: Add new function get_fragment_score() Date: Sat, 18 Jun 2011 11:15:31 -0600 Message-ID: References: <4DF8522F.2020304@sx.jp.nec.com> <20110617031814.GA31884@thunk.org> <4DFB62C7.5070008@redhat.com> Mime-Version: 1.0 (iPhone Mail 8J2) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8BIT Cc: Eric Sandeen , Ted Ts'o , Kazuya Mio , ext4 To: Greg Freemyer Return-path: Received: from shawmail.shawcable.com ([64.59.128.220]:5474 "EHLO mail.shawcable.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750776Ab1FRRPP convert rfc822-to-8bit (ORCPT ); Sat, 18 Jun 2011 13:15:15 -0400 In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: On 2011-06-18, at 11:00 AM, Greg Freemyer wrote: > On Sat, Jun 18, 2011 at 3:19 AM, Andreas Dilger wrote: >> I was thinking about this, and am wondering if it makes sense to have an absolute score for fragmentation instead of a relative one? >> >> By absolute I mean something like fragments per MB or similar. A bad score might be anything > 1. For files smaller than 1 MB in size it would scale the ratio to the equivalent if the file was 1MB in size (e.g. a 16kB file with 4 fragments would have a score of 256, which is clearly bad). Large files can have a score much less than 1, which is good. >> >> Cheers, Andreas > > Shouldn't be based on fragments per max extent size for ext4? > > And I think the max extent size for a 4KB page is 128 MB, right? I was thinking about that, but in most cases it is unrealistic that all files have 128MB extents except on empty test filesystems, and I don't think that files with "only" 32MB extents should be considered that badly off. I don't particularly care what the exact scale is, but I like the idea of an absolute measure instead of a relative measure (i.e. 33% fragmented). Cheers, Andreas