Return-Path: Delivered-To: apmail-hadoop-hdfs-user-archive@minotaur.apache.org Received: (qmail 89344 invoked from network); 13 May 2010 02:58:20 -0000 Received: from unknown (HELO mail.apache.org) (140.211.11.3) by 140.211.11.9 with SMTP; 13 May 2010 02:58:20 -0000 Received: (qmail 27613 invoked by uid 500); 13 May 2010 02:58:20 -0000 Delivered-To: apmail-hadoop-hdfs-user-archive@hadoop.apache.org Received: (qmail 27468 invoked by uid 500); 13 May 2010 02:58:20 -0000 Mailing-List: contact hdfs-user-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hdfs-user@hadoop.apache.org Delivered-To: mailing list hdfs-user@hadoop.apache.org Received: (qmail 27460 invoked by uid 99); 13 May 2010 02:58:20 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 13 May 2010 02:58:20 +0000 X-ASF-Spam-Status: No, hits=1.3 required=10.0 tests=AWL,FREEMAIL_FROM,HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS,T_TO_NO_BRKTS_FREEMAIL X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of srbh.grwl@gmail.com designates 209.85.160.48 as permitted sender) Received: from [209.85.160.48] (HELO mail-pw0-f48.google.com) (209.85.160.48) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 13 May 2010 02:58:14 +0000 Received: by pwi6 with SMTP id 6so499836pwi.35 for ; Wed, 12 May 2010 19:57:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:content-type; bh=2rKSDSY6a/mM6bnUWJ5sFqrUfz6q9hJXWzyXxCftDYo=; b=EjXdnS4gbAP3kovptp/pMf77LMU9ObU4AutKtpRrH8HCH4sOKTv5IFWRdjZd3Wn5qQ HElkmZJ3c/+ArC+H2D47CXXps8MJh4OYSd0oVbHSU5tsbF6/Ypa/WpeMJlhnf+rtus3N oL+L9b3I8i7TJlUelszILjf/gQFWw0fPRd32A= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type; b=akGrQk3co0TKrPiDpZjLcomszzIlrwl7Vb82RpXmN8qPuhif91KfQNWKo5qVEvlbb8 pq5lULGZ5JBUG0kvIzLL+a6NQgOK5lrgaHMNZjyvdvsU3VhtBQcwcxrwMz0iUtUz+zZG S0OBrTXToJYKg0frY7Q47MqqRuMdfcAdIfiRE= MIME-Version: 1.0 Received: by 10.143.128.6 with SMTP id f6mr5732111wfn.88.1273719474473; Wed, 12 May 2010 19:57:54 -0700 (PDT) Received: by 10.143.163.6 with HTTP; Wed, 12 May 2010 19:57:54 -0700 (PDT) In-Reply-To: References: Date: Thu, 13 May 2010 08:27:54 +0530 Message-ID: Subject: Re: HDFS on raw device From: Saurabh Agarwal To: hdfs-user@hadoop.apache.org Content-Type: multipart/alternative; boundary=000e0cd6081ed1ccc3048670ec41 --000e0cd6081ed1ccc3048670ec41 Content-Type: text/plain; charset=ISO-8859-1 Ok Thanks !! Saurabh Agarwal On Wed, May 12, 2010 at 11:52 PM, Eric Sammer wrote: > You can, but you'll lose all of the features and functionality such as > data locality, replication, and so on. Things get tricky if you don't > use HDFS. It's worth reading some of the docs at > http://hadoop.apache.org and the map reduce paper prior to deviating > from the common case. The Hadoop - the Definitive Guide book (Tom > White, O'Reilly) is an excellent reference as well. > > On Wed, May 12, 2010 at 1:34 PM, Saurabh Agarwal > wrote: > > thanks eric > > also can i use bypass hdfs as a datastore and instead use ext3 > > Saurabh Agarwal > > > > > > On Wed, May 12, 2010 at 10:40 PM, Eric Sammer > wrote: > >> > >> No. HDFS always stores data on a OS file system (e.g. ext3 on Linux). > >> > >> On Wed, May 12, 2010 at 7:58 AM, Saurabh Agarwal > >> wrote: > >> > Hii > >> > Can HDFS be give path of raw device, say can I set dfs.data.dir to > >> > /dev/sda3 > >> > or something like that > >> > > >> > > >> > Thanks and regards > >> > Saurabh Agarwal > >> > > >> > >> > >> > >> -- > >> Eric Sammer > >> phone: +1-917-287-2675 > >> twitter: esammer > >> data: www.cloudera.com > > > > > > > > -- > Eric Sammer > phone: +1-917-287-2675 > twitter: esammer > data: www.cloudera.com > --000e0cd6081ed1ccc3048670ec41 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Ok Thanks !!

Saurabh Agarwal


On Wed, May 12, 2010 at 11:52 PM, Eric S= ammer <esammer= @cloudera.com> wrote:
You can, but you'll lose all of the features and functionality such as<= br> data locality, replication, and so on. Things get tricky if you don't use HDFS. It's worth reading some of the docs at
http://hadoop.apache= .org and the map reduce paper prior to deviating
from the common case. The Hadoop - the Definitive Guide book (Tom
White, O'Reilly) is an excellent reference as well.

On Wed, May 12, 2010 at 1:34 PM, Saurabh Agarwal <srbh.grwl@gmail.com> wrote:
> thanks eric
> also can i use bypass hdfs as a datastore and instead use ext3
> Saurabh Agarwal
>
>
> On Wed, May 12, 2010 at 10:40 PM, Eric Sammer <esammer@cloudera.com> wrote:
>>
>> No. HDFS always stores data on a OS file system (e.g. ext3 on Linu= x).
>>
>> On Wed, May 12, 2010 at 7:58 AM, Saurabh Agarwal <srbh.grwl@gmail.com>
>> wrote:
>> > Hii
>> > Can HDFS be give path of raw device, say can I set=A0dfs.data= .dir to
>> > /dev/sda3
>> > or something like that
>> >
>> >
>> > Thanks and regards
>> > Saurabh Agarwal
>> >
>>
>>
>>
>> --
>> Eric Sammer
>> phone: +1-917-287-2675
>> twitter: esammer
>> data: www.cl= oudera.com
>
>



--
Eric Sammer
phone: +1-917-287-2675
twitter: esammer
data: www.cloudera.co= m

--000e0cd6081ed1ccc3048670ec41--