1 Return-Path: <racin@free.fr>
\r
2 X-Original-To: notmuch@notmuchmail.org
\r
3 Delivered-To: notmuch@notmuchmail.org
\r
4 Received: from localhost (localhost [127.0.0.1])
\r
5 by olra.theworths.org (Postfix) with ESMTP id 84ACF4196F2
\r
6 for <notmuch@notmuchmail.org>; Mon, 12 Apr 2010 07:41:31 -0700 (PDT)
\r
7 X-Virus-Scanned: Debian amavisd-new at olra.theworths.org
\r
11 X-Spam-Status: No, score=0.501 tagged_above=-999 required=5
\r
12 tests=[BAYES_05=-0.5, FREEMAIL_FROM=0.001, HK_NAME_FREE=1,
\r
13 RCVD_IN_DNSWL_NONE=-0.0001] autolearn=no
\r
14 Received: from olra.theworths.org ([127.0.0.1])
\r
15 by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024)
\r
16 with ESMTP id mF-fVNFlLIWO for <notmuch@notmuchmail.org>;
\r
17 Mon, 12 Apr 2010 07:41:30 -0700 (PDT)
\r
18 Received: from smtp5-g21.free.fr (smtp5-g21.free.fr [212.27.42.5])
\r
19 by olra.theworths.org (Postfix) with ESMTP id 84F7A431FC1
\r
20 for <notmuch@notmuchmail.org>; Mon, 12 Apr 2010 07:41:28 -0700 (PDT)
\r
21 Received: from smtp5-g21.free.fr (localhost [127.0.0.1])
\r
22 by smtp5-g21.free.fr (Postfix) with ESMTP id F3A61D48154;
\r
23 Mon, 12 Apr 2010 16:41:24 +0200 (CEST)
\r
24 Received: from zimbra1-e1.priv.proxad.net (zimbra1-e1.priv.proxad.net
\r
26 by smtp5-g21.free.fr (Postfix) with ESMTP id CA50DD48158;
\r
27 Mon, 12 Apr 2010 16:41:21 +0200 (CEST)
\r
28 Date: Mon, 12 Apr 2010 16:41:21 +0200 (CEST)
\r
30 To: Jameson Rollins <jrollins@finestructure.net>
\r
32 <457171623.7414151271083281537.JavaMail.root@zimbra1-e1.priv.proxad.net>
\r
33 In-Reply-To: <87tyrgeopc.fsf@servo.finestructure.net>
\r
34 Subject: Re: please eat my data!
\r
36 Content-Type: text/plain; charset=utf-8
\r
37 Content-Transfer-Encoding: quoted-printable
\r
38 X-Originating-IP: [132.166.135.72]
\r
39 X-Mailer: Zimbra 5.0 (ZimbraWebClient - FF3.0
\r
40 (Linux)/5.0.15_GA_2815.UBUNTU8_64)
\r
41 X-Authenticated-User: racin@free.fr
\r
42 Cc: Notmuch list <notmuch@notmuchmail.org>
\r
43 X-BeenThere: notmuch@notmuchmail.org
\r
44 X-Mailman-Version: 2.1.13
\r
46 List-Id: "Use and development of the notmuch mail system."
\r
47 <notmuch.notmuchmail.org>
\r
48 List-Unsubscribe: <http://notmuchmail.org/mailman/options/notmuch>,
\r
49 <mailto:notmuch-request@notmuchmail.org?subject=unsubscribe>
\r
50 List-Archive: <http://notmuchmail.org/pipermail/notmuch>
\r
51 List-Post: <mailto:notmuch@notmuchmail.org>
\r
52 List-Help: <mailto:notmuch-request@notmuchmail.org?subject=help>
\r
53 List-Subscribe: <http://notmuchmail.org/mailman/listinfo/notmuch>,
\r
54 <mailto:notmuch-request@notmuchmail.org?subject=subscribe>
\r
55 X-List-Received-Date: Mon, 12 Apr 2010 14:41:31 -0000
\r
58 ----- "Jameson Rollins" <jrollins@finestructure.net> a =C3=A9crit :
\r
60 > On Mon, 12 Apr 2010 15:33:35 +0200, "Sebastian Spaeth"
\r
61 > <Sebastian@SSpaeth.de> wrote:
\r
62 > > fsync is really killing xapian (and notmuch). What suffers, are the
\r
63 > > boolean prefixes (tag, id, and thread). Using libeatmydata (which
\r
64 > > disables fsync) shows a 10x speedup for tagging. The speedup is
\r
66 > > factor 2 for e.g. from: searches. This is ext4 on recent stock
\r
67 > > Ubuntu. Given that search by tag and thread are performed really
\r
69 > > (each time I advance a thread, for example), that really hurts.
\r
71 > Wow, this is really interesting, Sebastian. For those of us not in
\r
73 > know, can you explain what libeatmydata is and how it's used? It
\r
75 > like something I would *not* want to use! So you didn't have to
\r
76 > recompile here, and only had to set LD_PRELOAD=3D./libeatmydata.so? Is
\r
77 > there any drawback to what you're doing here?
\r
82 It seems like it is a small library that implements fsync as no-op. Using L=
\r
84 allows to overloads the libc's fsync definition by libeatmydata's one. Maki=
\r
86 but no longer crash-safe.
\r