Mailing-List: contact common-user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: common-user@hadoop.apache.org
Received-SPF: neutral (athena.apache.org: local policy)
DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws;
  s=s1024; d=yahoo.co.in;
  h=X-YMail-OSG:Received:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type;
  b=nnl1Xfi+tXeprV5OJG3lVT+nb+vq7uqmiMrRgks/2ekyDMPgftJbqvtYAy4qpv7RK94GkQjLSGjPaSs+9LJE1cPQ7JgXDcFzxEaCDeBo1DUdedZHhafY3LULlEzm8SDuTk6yI39fwDGmw6iBEmXmXMyqLKZn5NE0h89N5xajWg8=;
References: <1312963096.55212.YahooMailNeo@web95906.mail.in.yahoo.com>
Message-ID: <1312996037.34735.YahooMailNeo@web95902.mail.in.yahoo.com>
Date: Wed, 10 Aug 2011 22:37:17 +0530 (IST)
From: jagaran das <jagaran_das@yahoo.co.in>
Reply-To: jagaran das <jagaran_das@yahoo.co.in>
Subject: Re: Namenode Scalability
To: "common-user@hadoop.apache.org" <common-user@hadoop.apache.org>,
  jagaran das <jagaran_das@yahoo.co.in>
In-Reply-To: <1312963096.55212.YahooMailNeo@web95906.mail.in.yahoo.com>
MIME-Version: 1.0
Content-Type: multipart/alternative; boundary="0-2096955307-1312996037=:34735"

--0-2096955307-1312996037=:34735
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

To be precise, the projected data is around 1 PB.=0ABut the publishing rate=
 is also around 1GBPS.=0A=0APlease suggest.=0A=0A=0A_______________________=
_________=0AFrom: jagaran das <jagaran_das@yahoo.co.in>=0ATo: "common-user@=
hadoop.apache.org" <common-user@hadoop.apache.org>=0ASent: Wednesday, 10 Au=
gust 2011 12:58 AM=0ASubject: Namenode Scalability=0A=0AIn my current proje=
ct we =A0are planning to streams of data to Namenode (20 Node Cluster).=0AD=
ata Volume would be around 1 PB per day.=0ABut there are application which =
can publish data at 1GBPS.=0A=0AFew queries:=0A=0A1. Can a single Namenode =
handle such high speed writes? Or it becomes unresponsive when GC cycle kic=
ks in.=0A2. Can we have multiple=A0federated=A0Name nodes=A0=A0sharing the =
same slaves and then we can distribute the writes accordingly.=0A3. Can mul=
tiple region servers of HBase help us ??=0A=0APlease suggest how we can des=
ign the streaming part to handle such scale of data.=A0=0A=0ARegards,=0AJag=
aran Das=A0
--0-2096955307-1312996037=:34735--