Mailing-List: contact user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@hadoop.apache.org
Received-SPF: pass (athena.apache.org: local policy)
DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws;
  s=s1024; d=yahoo.com;
  h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type;
  b=q8UWB5wJMcuADs659mX8JJ/S0joigIAVcBhuHxbH4PykiCpT6Cfk6380B7NxqLBpXRtMlguCM5/yHnZUuJFLvkgWbDz6ficjo4zUHj/yJ7jKJkjSeM+3tq1nxOhFiqi9KZSwvrvwJDtIaNBR9j/SOIVVEot/cJ1n4BHIozLv4/c=;
References: 
 <CAKjW-3KSkHXAEW4DCROU-RfDBA5T_H3KPrXgE7MHdtyPoXWY9w@mail.gmail.com>
Message-ID: <1365544595.11142.YahooMailNeo@web160702.mail.bf1.yahoo.com>
Date: Tue, 9 Apr 2013 14:56:35 -0700 (PDT)
From: Raj Vishwanathan <rajvish@yahoo.com>
Reply-To: Raj Vishwanathan <rajvish@yahoo.com>
Subject: Re: When copying a file to HDFS,
 how to control what nodes that file will reside on?
To: "user@hadoop.apache.org" <user@hadoop.apache.org>
In-Reply-To: 
 <CAKjW-3KSkHXAEW4DCROU-RfDBA5T_H3KPrXgE7MHdtyPoXWY9w@mail.gmail.com>
MIME-Version: 1.0
Content-Type: multipart/alternative;
 boundary="-2130163251-1430606915-1365544595=:11142"

---2130163251-1430606915-1365544595=:11142
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

You could use the following facts.=0A1. Files are stored in blocks. So make=
 your blocksize bigger than the largest file.=0A2, The first split is store=
d on the localnode.=0A=0ARaj=0A=0A=0A=0A>________________________________=
=0A> From: jeremy p <athomewithagroovebox@gmail.com>=0A>To: user@hadoop.apa=
che.org =0A>Sent: Tuesday, April 9, 2013 1:49 PM=0A>Subject: When copying a=
 file to HDFS, how to control what nodes that file will reside on?=0A> =0A>=
=0A>Hey all,=0A>=0A>=0A>I'm dealing with kind of a bizarre use case where I=
 need to make sure that File A is local to Machine A, File B is local to Ma=
chine B, etc. =A0When copying a file to HDFS, is there a way to control whi=
ch machines that file will reside on? =A0I know that any given file will be=
 replicated across three machines, but I need to be able to say "File A wil=
l DEFINITELY exist on Machine A". =A0I don't really care about the other tw=
o machines -- they could be any machines on my cluster.=0A>=0A>=0A>Thank yo=
u.=0A>=0A>
---2130163251-1430606915-1365544595=:11142
Content-Type: text/html; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

<html><body><div style=3D"color:#000; background-color:#fff; font-family:ar=
ial, helvetica, sans-serif;font-size:10pt"><div><span>You could use the fol=
lowing facts.</span></div><div style=3D"color: rgb(0, 0, 0); font-size: 13.=
600000381469727px; font-family: arial, helvetica, sans-serif; background-co=
lor: transparent; font-style: normal;"><span>1. Files are stored in blocks.=
 So make your blocksize bigger than the largest file.</span></div><div styl=
e=3D"color: rgb(0, 0, 0); font-size: 13.600000381469727px; font-family: ari=
al, helvetica, sans-serif; background-color: transparent; font-style: norma=
l;"><span>2, The first split is stored on the localnode.</span></div><div s=
tyle=3D"color: rgb(0, 0, 0); font-size: 13.600000381469727px; font-family: =
arial, helvetica, sans-serif; background-color: transparent; font-style: no=
rmal;"><span><br></span></div><div style=3D"color: rgb(0, 0, 0); font-size:=
 13.600000381469727px; font-family: arial, helvetica, sans-serif;
 background-color: transparent; font-style: normal;">Raj</div><div><br><blo=
ckquote style=3D"border-left: 2px solid rgb(16, 16, 255); margin-left: 5px;=
 margin-top: 5px; padding-left: 5px;">  <div style=3D"font-family: arial, h=
elvetica, sans-serif; font-size: 10pt;"> <div style=3D"font-family: 'times =
new roman', 'new york', times, serif; font-size: 12pt;"> <div dir=3D"ltr"> =
<font size=3D"2" face=3D"Arial"> <hr size=3D"1">  <b><span style=3D"font-we=
ight:bold;">From:</span></b> jeremy p &lt;athomewithagroovebox@gmail.com&gt=
;<br> <b><span style=3D"font-weight: bold;">To:</span></b> user@hadoop.apac=
he.org <br> <b><span style=3D"font-weight: bold;">Sent:</span></b> Tuesday,=
 April 9, 2013 1:49 PM<br> <b><span style=3D"font-weight: bold;">Subject:</=
span></b> When copying a file to HDFS, how to control what nodes that file =
will reside on?<br> </font> </div> <br>=0A<div id=3D"yiv1138273404"><div di=
r=3D"ltr"><div>Hey all,</div><div><br></div><div>I'm dealing with kind of a=
 bizarre use case where I need to make sure that File A is local to Machine=
 A, File B is local to Machine B, etc. &nbsp;When copying a file to HDFS, i=
s there a way to control which machines that file will reside on? &nbsp;I k=
now that any given file will be replicated across three machines, but I nee=
d to be able to say "File A will DEFINITELY exist on Machine A". &nbsp;I do=
n't really care about the other two machines -- they could be any machines =
on my cluster.</div>=0A=0A<div><br></div><div>Thank you.</div></div>=0A</di=
v><br><br> </div> </div> </blockquote></div>   </div></body></html>
---2130163251-1430606915-1365544595=:11142--