Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
Received-SPF: pass (athena.apache.org: domain of jeremy.jongsma@barchart.com
 designates 209.85.216.175 as permitted sender)
MIME-Version: 1.0
Date: Tue, 19 Aug 2014 10:56:34 -0500
Message-ID: 
 <CADDd+5Qjq9xOC0YjBmv=ONRxShz0B_DpnA4zbXdKQowcaGrPrw@mail.gmail.com>
Subject: EC2 SSD cluster costs
From: Jeremy Jongsma <jeremy@barchart.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=089e014933e829e8510500fd88e5

--089e014933e829e8510500fd88e5
Content-Type: text/plain; charset=UTF-8

The latest consensus around the web for running Cassandra on EC2 seems to
be "use new SSD instances." I've not seen any mention of the elephant in
the room - using the new SSD instances significantly raises the cluster
cost per TB. With Cassandra's strength being linear scalability to many
terabytes of data, it strikes me as odd that everyone is recommending such
a large storage cost hike almost without reservation.

Monthly cost comparison for a 100TB cluster (non-reserved instances):

m1.xlarge (2x420 non-SSD): $30,000 (120 nodes)
m3.xlarge (2x40 SSD): $250,000 (1250 nodes! Clearly not an option)
i2.xlarge (1x800 SSD): $76,000 (125 nodes)

Best case, the cost goes up 150%. How are others approaching these new
instances? Have you migrated and eaten the costs, or are you staying on
previous generation until prices come down?

--089e014933e829e8510500fd88e5
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">The latest consensus around the web for running Cassandra =
on EC2 seems to be &quot;use new SSD instances.&quot; I&#39;ve not seen any=
 mention of the elephant in the room - using the new SSD instances signific=
antly raises the cluster cost per TB. With Cassandra&#39;s strength being l=
inear scalability to many terabytes of data, it strikes me as odd that ever=
yone is recommending such a large storage cost hike almost without reservat=
ion.<div>
<br></div><div>Monthly cost comparison for a 100TB cluster (non-reserved in=
stances):</div><div><br></div><div>m1.xlarge (2x420 non-SSD): $30,000 (120 =
nodes)</div><div>m3.xlarge (2x40 SSD): $250,000 (1250 nodes! Clearly not an=
 option)</div>
<div>i2.xlarge (1x800 SSD): $76,000 (125 nodes)<br></div><div><br></div><di=
v>Best case, the cost goes up 150%. How are others approaching these new in=
stances? Have you migrated and eaten the costs, or are you staying on previ=
ous generation until prices come down?</div>
</div>

--089e014933e829e8510500fd88e5--