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 sean.bridges@gmail.com
 designates 209.85.212.172 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:date:message-id:subject:from:to:content-type;
        b=XsLy1N/mWm8sN2zcZEe10P9RxwiossRUzomgXjq6z5rVT1KBlmOERAiWqSvzJmuJJo
         dEw3N2nEakDgGnp6aGnsPDpkkr576/etwe6XHjqDULIszZYMrKgzbEmeNerO5kd925AK
         YxBu30nnQlfEqYcXSrSK/2iy3IS52A2O7+5ao=
MIME-Version: 1.0
Date: Wed, 26 May 2010 09:50:17 -0700
Message-ID: <AANLkTileksl4A6MotaRhGTy1SHMpqQWUg8rmOYirOduZ@mail.gmail.com>
Subject: using more than 50% of disk space
From: Sean Bridges <sean.bridges@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=001636e0aa5e9331300487821163

--001636e0aa5e9331300487821163
Content-Type: text/plain; charset=ISO-8859-1

We're investigating Cassandra, and we are looking for a way to get Cassandra
use more than 50% of it's data disks.  Is this possible?

For major compactions, it looks like we can use more than 50% of the disk if
we use multiple similarly sized column families.  If we had 10 column
families of the same size, we could use 90% of the disk, since a major
compaction would only need as much free space as the largest column family
(in reality we would use less).  Is that right?

For bootstrapping new nodes, it looks like adding a new node will require
that an existing node does anti-compaction.  This anti-compaction could take
nearly 50% of the disk.  Is there a way around this?

Is there anything else that would prevent us from using more than 50% of the
data disk.

Thanks,

Sean

--001636e0aa5e9331300487821163
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

We&#39;re investigating Cassandra, and we are looking for a way to get Cass=
andra use more than 50% of it&#39;s data disks.=A0 Is this possible?=A0 <br=
><br>For major compactions, it looks like we can use more than 50% of the d=
isk if we use multiple similarly sized column families.=A0 If we had 10 col=
umn families of the same size, we could use 90% of the disk, since a major =
compaction would only need as much free space as the largest column family =
(in reality we would use less).=A0 Is that right?<br>
<br>For bootstrapping new nodes, it looks like adding a new node will requi=
re that an existing node does anti-compaction.=A0 This anti-compaction coul=
d take nearly 50% of the disk.=A0 Is there a way around this?<br><br>Is the=
re anything else that would prevent us from using more than 50% of the data=
 disk.<br>
<br>Thanks,<br><br>Sean<br><br>

--001636e0aa5e9331300487821163--