Return-Path: 
 <user-return-1804-apmail-hadoop-mapreduce-user-archive=hadoop.apache.org@hadoop.apache.org>
X-Original-To: apmail-hadoop-mapreduce-user-archive@minotaur.apache.org
Delivered-To: apmail-hadoop-mapreduce-user-archive@minotaur.apache.org
Received: from mail.apache.org (hermes.apache.org [140.211.11.3])
	by minotaur.apache.org (Postfix) with SMTP id A5ADCDBB8
	for <apmail-hadoop-mapreduce-user-archive@minotaur.apache.org>;
 Wed,  3 Oct 2012 23:56:08 +0000 (UTC)
Received: (qmail 60210 invoked by uid 500); 3 Oct 2012 23:56:04 -0000
Delivered-To: apmail-hadoop-mapreduce-user-archive@hadoop.apache.org
Received: (qmail 60114 invoked by uid 500); 3 Oct 2012 23:56:04 -0000
Mailing-List: contact user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
List-Help: <mailto:user-help@hadoop.apache.org>
List-Unsubscribe: <mailto:user-unsubscribe@hadoop.apache.org>
List-Post: <mailto:user@hadoop.apache.org>
List-Id: <user.hadoop.apache.org>
Reply-To: user@hadoop.apache.org
Delivered-To: mailing list user@hadoop.apache.org
Received: (qmail 60103 invoked by uid 99); 3 Oct 2012 23:56:04 -0000
Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230)
    by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 03 Oct 2012 23:56:04 +0000
X-ASF-Spam-Status: No, hits=-0.7 required=5.0
	tests=RCVD_IN_DNSWL_LOW,SPF_PASS
X-Spam-Check-By: apache.org
Received-SPF: pass (nike.apache.org: domain of adi@cloudera.com designates
 209.85.223.176 as permitted sender)
Received: from [209.85.223.176] (HELO mail-ie0-f176.google.com)
 (209.85.223.176)
    by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 03 Oct 2012 23:55:56 +0000
Received: by ieak11 with SMTP id k11so22609705iea.35
        for <user@hadoop.apache.org>; Wed, 03 Oct 2012 16:55:35 -0700 (PDT)
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=google.com; s=20120113;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :content-type:x-gm-message-state;
        bh=CDt7sTJX4FqQSWURSIuOjlh6GwwhJk3+psmR/vXqPQQ=;
        b=CloG7AZTsICRAxDikkvUEwZeY1ECsOSre7DyOsYpjeZLIMFDzhlnZ868psgzOXSnX1
         c+g/ceNtaDPEmE41l3T59erwLFlgCCjtGlx3TRq2MZ6E82YBJFi3LkwBtoDBC55TMio1
         +XNO1yyfXrB//XXUYE/I3mwlItC7INcLjHuelx0KD50Ov0Sk/EwcLWe1jlKGw8UhJMo4
         NLgYUlh6pfKqxw+LLiQtTN2ddv1jDZJQpShT/vX2pr7xxAYa39luRnpf2ga7EQx/tpZH
         d1gqqZQVQPr1fxfd6P6c9DE1UemXRG2I6J84IhlviRSPvNksO2fVKBZOXHb6p1Cj2Bk2
         4oKg==
MIME-Version: 1.0
Received: by 10.50.40.133 with SMTP id x5mr13432929igk.32.1349308535564; Wed,
 03 Oct 2012 16:55:35 -0700 (PDT)
Received: by 10.64.126.68 with HTTP; Wed, 3 Oct 2012 16:55:35 -0700 (PDT)
In-Reply-To: 
 <CAGyVJ6JMrnMOW1LXX-ovPL7YaDCqgUGGKVfRyhCua27ejVqSNw@mail.gmail.com>
References: 
 <CAGyVJ6JMrnMOW1LXX-ovPL7YaDCqgUGGKVfRyhCua27ejVqSNw@mail.gmail.com>
Date: Wed, 3 Oct 2012 16:55:35 -0700
Message-ID: 
 <CAE_FxDjU_qFyWDUhQGnxpCJh4Ego_sfS1cW=qrD1e13NhjS3mQ@mail.gmail.com>
Subject: Re: hadoop disk selection
From: Andy Isaacson <adi@cloudera.com>
To: beatls@gmail.com, user@hadoop.apache.org
Content-Type: text/plain; charset=ISO-8859-1
X-Gm-Message-State: 
 ALoCoQk7lzUzfwEQRFstdoddXOXNxkmtXs5GOyJPLHW+Nwd6rk0aKaEtY6/ByxpxKnRCPzhpHv7t

Moving this to user@ since it's not appropriate for general@.

On Fri, Sep 28, 2012 at 11:16 PM, Xiang Hua <beatls@gmail.com> wrote:
> Hi,
>   i want to  select 4(600G) local disks combined with  3*800G disks form
> diskarray  in one datanode.
>   is there any problem? performance ?

The recommended configuration would be to partition and format each
disk with ext4, then set dfs.datanode.data.dir to point to the
mountpoints of each disk:

  <property>
     <name>dfs.datanode.data.dir</name>
     <value>/data/1/datadir,/data/2/datadir,/data/3/datadir</value>
  </property>

You may also want to set dfs.datanode.du.reserved to 1GB or thereabouts.

With this configuration your DN will fill all 7 datadir at the same
rate pseudorandomly, until the 600G disks are nearly full, then it
will write any further blocks to the 800G disks. Performance will be
OK except that you will see performance hot-spots on the larger disks
when writing past the 600GB mark. See
https://issues.apache.org/jira/browse/HDFS-1564 for one missing
feature in this area.

I would not recommend using RAID-0 for datadir because if you
experience a disk failure with independent filesystems, only the
blocks on one datadir are lost and need to be rereplicated. If you
experience a disk failure with RAID-0, all blocks stored on that DN
are lost and need to be rereplicated. Also, RAID results in
performance lockstep; a single slow disk will slow down access to all
blocks on that DN, while with independent filesystems a single slow
disk slows down only a fraction of the blocks on that DN.

-andy