From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <mbroz@redhat.com>
Received: from mail.saout.de ([127.0.0.1])
 by localhost (mail.saout.de [127.0.0.1]) (amavisd-new, port 10024)
 with ESMTP id OekJYMRbbOwE for <dm-crypt@saout.de>;
 Tue, 24 Jul 2012 17:19:50 +0200 (CEST)
Received: from mx1.redhat.com (mx1.redhat.com [209.132.183.28])
 by mail.saout.de (Postfix) with ESMTP
 for <dm-crypt@saout.de>; Tue, 24 Jul 2012 17:19:49 +0200 (CEST)
Message-ID: <500EBCFE.1020208@redhat.com>
Date: Tue, 24 Jul 2012 17:19:26 +0200
From: Milan Broz <mbroz@redhat.com>
MIME-Version: 1.0
References: <20120722203929.GB3925@merlins.org>
 <20120722214757.GA16793@tansi.org> <20120723062850.GA6931@merlins.org>
 <20120723081407.GA872@tansi.org> <20120723161242.GB27727@merlins.org>
 <500D86AC.7090100@redhat.com> <20120723175129.GA15867@merlins.org>
 <500DC2B0.8060409@redhat.com> <20120724055722.GA15507@merlins.org>
 <20120724062518.GB1517@fancy-poultry.org>
 <20120724150247.GA14273@merlins.org>
In-Reply-To: <20120724150247.GA14273@merlins.org>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [dm-crypt] aes-xts-plain with aes_x86_64 makes my SSD 5x slower
 than my encrypted HD
List-Id: <dm-crypt.saout.de>
List-Unsubscribe: <http://www.saout.de/mailman/options/dm-crypt>,
 <mailto:dm-crypt-request@saout.de?subject=unsubscribe>
List-Archive: <http://www.saout.de/pipermail/dm-crypt>
List-Post: <mailto:dm-crypt@saout.de>
List-Help: <mailto:dm-crypt-request@saout.de?subject=help>
List-Subscribe: <http://www.saout.de/mailman/listinfo/dm-crypt>,
 <mailto:dm-crypt-request@saout.de?subject=subscribe>
To: Marc MERLIN <marc@merlins.org>
Cc: dm-crypt@saout.de, Yves-Alexis Perez <corsac@debian.org>

On 07/24/2012 05:02 PM, Marc MERLIN wrote:
> On Tue, Jul 24, 2012 at 08:25:18AM +0200, Heinz Diehl wrote:
>> Please correct me if I should be wrong, but your drive should report
>> 512/4096 here, so it lies about the real blocksize it uses (4k).
>> This raises the question if you have created your filesystem on top of
>> the encrypted partition with e.g. "-b 4096".
> 
> I'm using btrfs, which defaults to 4K blocks. Also, I was I seeing 270MB/s
> reading a big file with btrfs on top of cryptroot.
> 
> On Tue, Jul 24, 2012 at 10:44:36AM +0200, Milan Broz wrote:
>> Seems I am running out of ideas :)
>> (I just read the mails again and I think I am missing something
>> obvious. Whatever, I will return to it later.)
> 
> I wanted to command you for not giving up, you definitely went the extra
> mile :)

:)

So seems elevator completely misbehaves for SSD in some situations.

I have no time to check it today but this must be fixed. Read-ahead
is just stupid workaround...

# echo "0">/sys/block/sdc/queue/rotational 
# hdparm -t /dev/mapper/sdc_null_crypt 
 Timing buffered disk reads:  220 MB in  3.01 seconds =  73.07 MB/sec

# echo "1">/sys/block/sdc/queue/rotational 
# hdparm -t /dev/mapper/sdc_null_crypt 
 Timing buffered disk reads:  652 MB in  3.01 seconds = 216.75 MB/sec

This SSD is quicker if set to rotational mode!
(So it merges requests in fact.)

Milan