From user-return-118-apmail-hadoop-user-archive=hadoop.apache.org@hadoop.apache.org Wed Aug 8 17:06:39 2012 Return-Path: X-Original-To: apmail-hadoop-user-archive@minotaur.apache.org Delivered-To: apmail-hadoop-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 71B22DBA4 for ; Wed, 8 Aug 2012 17:06:39 +0000 (UTC) Received: (qmail 88507 invoked by uid 500); 8 Aug 2012 17:06:34 -0000 Delivered-To: apmail-hadoop-user-archive@hadoop.apache.org Received: (qmail 88281 invoked by uid 500); 8 Aug 2012 17:06:34 -0000 Mailing-List: contact user-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@hadoop.apache.org Delivered-To: mailing list user@hadoop.apache.org Received: (qmail 88272 invoked by uid 99); 8 Aug 2012 17:06:34 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 08 Aug 2012 17:06:34 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of michael_segel@hotmail.com designates 65.55.111.83 as permitted sender) Received: from [65.55.111.83] (HELO blu0-omc2-s8.blu0.hotmail.com) (65.55.111.83) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 08 Aug 2012 17:06:28 +0000 Received: from BLU0-SMTP445 ([65.55.111.72]) by blu0-omc2-s8.blu0.hotmail.com with Microsoft SMTPSVC(6.0.3790.4675); Wed, 8 Aug 2012 10:06:07 -0700 X-Originating-IP: [173.15.87.38] X-Originating-Email: [michael_segel@hotmail.com] Message-ID: Received: from [10.1.10.10] ([173.15.87.38]) by BLU0-SMTP445.phx.gbl over TLS secured channel with Microsoft SMTPSVC(6.0.3790.4675); Wed, 8 Aug 2012 10:06:05 -0700 From: Michael Segel Content-Type: multipart/alternative; boundary="Apple-Mail=_5F6BF5E5-1BAA-4A58-A78D-E6498C12B47A" MIME-Version: 1.0 (Mac OS X Mail 6.0 \(1485\)) Subject: Re: is HDFS RAID "data locality" efficient? Date: Wed, 8 Aug 2012 12:06:04 -0500 References: <00bc01cd7585$4c585550$e508fff0$@com> To: user@hadoop.apache.org In-Reply-To: <00bc01cd7585$4c585550$e508fff0$@com> X-Mailer: Apple Mail (2.1485) X-OriginalArrivalTime: 08 Aug 2012 17:06:05.0993 (UTC) FILETIME=[190D8190:01CD7588] X-Virus-Checked: Checked by ClamAV on apache.org --Apple-Mail=_5F6BF5E5-1BAA-4A58-A78D-E6498C12B47A Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="windows-1252" Just something to think about...=20 There's a company here in Chicago called Cleversafe. I believe they = recently made an announcement concerning Hadoop?=20 The interesting thing about RAID is that you're adding to the disk = latency and depending on which raid you use you could kill performance = on a rebuild of a disk.=20 In terms of uptime of Apache based Hadoop, RAID allows you to actually = hot swap the disks and unless you lose both drives (assuming Raid 1, = mirroring), your DN doesn't know and doesn't have to go down.=20 So there is some value there, however at the expense of storage and = storage costs.=20 You can reduce the replication factor to 2. I don't know that I would go = to anything lower because you still can lose the server...=20 In terms of data locality... maybe you lose a bit, however... because = you're raiding your storage, you now have less data per node. So you end = up with more nodes, right?=20 Just some food for thought.=20 On Aug 8, 2012, at 11:46 AM, Sourygna Luangsay = wrote: > Hi folks! > =20 > I have just read about the HDFS RAID feature that was added to Hadoop = 0.21 or 0.22. and I am quite curious to know if people use it, what kind = of use > they have and what they think about Map/Reduce data locality. > =20 > First big actor of this technology is Facebook, that claims to save = many PB with it (see http://www.slideshare.net/ydn/hdfs-raid-facebook = slides 4 and 5). > =20 > I understand the following advantages with HDFS RAID: > - You can save space > - System tolerates more missing blocks > =20 > Nonetheless, one of the drawback I see is M/R data locality. > As far as I understand, the advantage of having 3 replicas of each = blocks is not only security if one server fails or a block is corrupted, > but also the possibility to have as far as 3 tasktrackers executing = the map task with =93local data=94. > If you consider the 4th slide of the Facebook presentation, such = infrastructure decreases this possibility to only 1 tasktracker. > That means that if this tasktracker is very busy executing other = tasks, you have the following choice: > - Waiting this tasktracker to finish executing (part of) the = current tasks (freeing map slots for instance) > - Executing the map task for this block in another = tasktracker, transferring the information of the block through the = network > In both cases, you=B4ll get a M/R penalty (please, tell me if I am = wrong). > =20 > Has somebody considered such penalty or has some benchmarks to share = with us? > =20 > One of the scenario I can think in order to take advantage of HDFS = RAID without suffering this penalty is: > - Using normal HDFS with default replication=3D3 for my = =93fresh data=94 > - Using HDFS RAID for my historical data (that is barely used = by M/R) > =20 > And you, what are you using HDFS RAID for? > =20 > Regards, > =20 > Sourygna Luangsay --Apple-Mail=_5F6BF5E5-1BAA-4A58-A78D-E6498C12B47A Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset="windows-1252" Just something to think = about... 

There's a company here in Chicago = called Cleversafe. I believe they recently made an announcement = concerning Hadoop? 

The interesting thing = about RAID is that you're adding to the disk latency and depending on = which raid you use you could kill performance on a rebuild of a = disk. 

In terms of uptime of Apache based = Hadoop, RAID allows you to actually hot swap the disks and unless you = lose both drives (assuming Raid 1, mirroring), your DN doesn't know and = doesn't have to go down. 
So there is some value there, = however at the expense of storage and storage = costs. 

You can reduce the replication = factor to 2. I don't know that I would go to anything lower because you = still can lose the server... 

In terms of = data locality... maybe you lose a bit, however... because you're raiding = your storage, you now have less data per node. So you end up with more = nodes, right? 

Just some food for = thought. 

On Aug 8, 2012, at 11:46 AM, = Sourygna Luangsay <sluangsay@pragsis.com> = wrote:

I have just read about the HDFS RAID feature that was = added to Hadoop 0.21 or 0.22. and I am quite curious to know if people = use it, what kind of use
they have and what they think about = Map/Reduce data locality.
 
First big actor of this technology is Facebook, that = claims to save many PB with it (see  

<= /body>= --Apple-Mail=_5F6BF5E5-1BAA-4A58-A78D-E6498C12B47A--