From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <petermerhaut@gmail.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 T5hgsbReD1Mi for <dm-crypt@saout.de>;
 Thu, 15 Sep 2011 13:07:52 +0200 (CEST)
Received: from mail-fx0-f50.google.com (mail-fx0-f50.google.com
 [209.85.161.50]) (using TLSv1 with cipher RC4-SHA (128/128 bits))
 (No client certificate requested)
 by mail.saout.de (Postfix) with ESMTPS
 for <dm-crypt@saout.de>; Thu, 15 Sep 2011 13:07:52 +0200 (CEST)
Received: by fxh10 with SMTP id 10so576334fxh.37
 for <dm-crypt@saout.de>; Thu, 15 Sep 2011 04:07:51 -0700 (PDT)
Message-ID: <4E71DC82.7050003@gmail.com>
Date: Thu, 15 Sep 2011 13:07:46 +0200
From: Peter Merhaut <petermerhaut@gmail.com>
MIME-Version: 1.0
References: <4E70B46C.9050304@gmail.com> <20110914150400.GA18107@tansi.org>
 <4E70DAB6.2000107@gmail.com> <4E71CA41.1060808@oldum.net>
 <4E71D754.2050506@redhat.com>
In-Reply-To: <4E71D754.2050506@redhat.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [dm-crypt] slow read performance, but fast writes?
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: dm-crypt@saout.de

Yeah but why is it using one cpu for encryption? I got 6 encrypted block
devices. When writing to them, all cpu cores are used for encryption,
therefor it's fast. When reading, it seems to use 1 cpu for all 6 crypto
threads?

Am 09/15/2011 12:45 PM, schrieb Milan Broz:
> On 09/15/2011 11:49 AM, Nikolay Kichukov wrote:
>> Hi,
>> this query is best suited for md-raid mailing list as what you measure:
>>
>> dd if=/dev/md3 of=/dev/null bs=1M
>>
>> does not involve any decryption. You are reading directly from the md device and there is no matter what is actually there.
> heh. I read that as crypt device and it is MD directly, sorry for confusion.
> Seems my brain is still in different timezone :)
>
> yes, this test has nothing to do with crypt.
>
> Anyway, it is interesting that the problem is there even without crypt,
> perhaps you should ask on linux-raid list then.
>
> for badblock - I guess it just submits all IO from one cpu,
> so only one core is used for encryption in fact. There applies the same what I wrote before.
>
> Milan