Mailing-List: contact user-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@hbase.apache.org
Received-SPF: neutral (nike.apache.org: local policy)
MIME-Version: 1.0
In-Reply-To: 
 <CAK5mr4o0HVbRN2uvm_AbXD8uhxBV4meCNVv-ZtruWoWM8bjRZw@mail.gmail.com>
References: 
 <CAK5mr4o0HVbRN2uvm_AbXD8uhxBV4meCNVv-ZtruWoWM8bjRZw@mail.gmail.com>
Date: Wed, 11 Jul 2012 06:59:22 -0700
Message-ID: 
 <CAPupAWO7H5qtuvUB=UzWu=StazwbuwN4yfS7_-0Yfa04KM_KPA@mail.gmail.com>
Subject: Re: Does anybody use HBase with petabyte sized data ?
From: David Schnepper <daves@cfotogo.com>
To: user@hbase.apache.org
Content-Type: multipart/alternative; boundary=f46d042f9be00e965d04c48e41df

--f46d042f9be00e965d04c48e41df
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

A project we were doing at Yahoo had 2PB of web crawl data on a 1300 node
HBase cluster.
A presentation we gave at the 2011 Hadoop summit is below
http://www.youtube.com/watch?v=3DbyXGqhz2N5M

Yahoo has since cancelled the project - but not for any technical reason.

Dave Schnepper


On Wed, Jul 11, 2012 at 4:41 AM, =EC=9D=B4=EB=B2=94=EC=84=9D <yolongyi@gmai=
l.com> wrote:

> Hi.
>
> We are planning to make a big storage to save text and binary data
> and considering to use HBase for it.
>
> Most features of HBase are very appropriate for our program and make easy
> to make it.
>
> But the thing is the capacity of HBase.
> ( Nothing I could find about the limit capacity or any experience ... )
> Our data to be stored might be nearly 300TB and still growing bigger.
>
> If you are working with big-sized HBase or know anyone doing..
> plz let me know it.
>
>
>
>
> Thanks.
>

--f46d042f9be00e965d04c48e41df--