From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andi Kleen <andi@firstfloor.org>
Subject: Re: How to track down abysmal performance ata - raid1 - crypto - vg/lv - xfs
Date: Wed, 04 Aug 2010 19:43:34 +0200
Message-ID: <87zkx2clyx.fsf@basil.nowhere.org>
References: <20100804073546.GA7494@comet.dominikbrodowski.net>
	<20100804085039.GA11671@infradead.org>
	<20100804091317.GA27779@isilmar-3.linta.de>
	<20100804092122.GA2998@infradead.org>
	<20100804073546.GA7494@comet.dominikbrodowski.net>
	<201008041116.09822@zmi.at>
	<20100804102526.GB13766@isilmar-3.linta.de>
	<20100804111803.GA32643__39273.3621680692$1280923964$gmane$org@infradead.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-raid-owner@vger.kernel.org>
In-Reply-To: <20100804111803.GA32643__39273.3621680692$1280923964$gmane$org@infradead.org>
	(Christoph Hellwig's message of "Wed, 4 Aug 2010 07:18:03 -0400")
Sender: linux-raid-owner@vger.kernel.org
To: Christoph Hellwig <hch@infradead.org>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>, Michael Monnerie <michael.monnerie@is.it-management.at>, linux-raid@vger.kernel.org
List-Id: linux-raid.ids

Christoph Hellwig <hch@infradead.org> writes:

> On Wed, Aug 04, 2010 at 12:25:26PM +0200, Dominik Brodowski wrote:
>> Hey,
>> 
>> many thanks for your feedback. It seems the crypto step is the culprit:
>> 
>> Reading 1.1 GB with dd, iflag=direct, bs=8k:
>> 
>> /dev/sd*                35.3 MB/s       ( 90 %)
>> /dev/md*                39.1 MB/s       (100 %)
>> /dev/mapper/md*_crypt    3.9 MB/s       ( 10 %)
>> /dev/mapper/vg1-*        3.9 MB/s       ( 10 %)
>> 
>> The "good" news: it also happens on my notebook, even though it has a
>> different setup (no raid, disk -> lv/vg -> crypt). On my notebook, I'm
>> more than happy to test out different kernel versions, patches etc.
>> 
>> /dev/sd*                17.7 MB/s       (100 %)
>> /dev/mapper/vg1-*       16.2 MB/s       ( 92 %)
>> /dev/mapper/*_crypt      3.1 MB/s       ( 18 %)
>
> The good news is that you have it tracked down, the bad news is that
> I know very little about dm-crypt.  Maybe the issue is the single
> threaded decryption in dm-crypt?  Can you check how much CPU time
> the dm crypt kernel thread uses?

I fixed this some time ago with

http://linux.derkeiler.com/Mailing-Lists/Kernel/2010-06/msg00181.html

The patch is still somewhere in the DeviceMapper meat-grinder,
that is usually taking longer. 

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only.