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 edlinuxguru@gmail.com
 designates 209.85.212.172 as permitted sender)
MIME-Version: 1.0
In-Reply-To: <CD6484E2.22D1D%Dean.Hiller@nrel.gov>
References: <CD6484E2.22D1D%Dean.Hiller@nrel.gov>
Date: Tue, 12 Mar 2013 17:29:26 -0400
Message-ID: 
 <CAENxBwxfuQKoGkkUxhgSY+HXQJXoDRzQdrfj611sG0PjX1W1Zw@mail.gmail.com>
Subject: Re: word of caution to those switching to LCS from SizeTieredStrategy
From: Edward Capriolo <edlinuxguru@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=f46d0444e97fe0056e04d7c0fbd1

--f46d0444e97fe0056e04d7c0fbd1
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable

yes LCS has its own compacting thing. It does not honor min compaction, max
compaction, and no-ops major compaction. The issue is that at the moment
you change your system moves all your sized data to L0 and then starts a
huge compaction grid to level it.

It would be great to just make this change to one server and see
read/write.

Check out the write sampling mode.

Edward

On Tue, Mar 12, 2013 at 9:08 AM, Hiller, Dean <Dean.Hiller@nrel.gov> wrote:

> We tested it in QA, but in production it brought our cluster to a halt
> even though we setcompactionthroughput to 1, we were severely limited.
>  Nodetool stop compaction did not seem to have any impact either.  We end=
ed
> up increasing memory on one node to help alleviate some issue(cranked it =
up
> to 16G and we hope to put it back down to 8 G later).
>
> Just be careful if you are trying to make the switch.  Also, I added this
> jira ticket which would be extremely nice to turn on LCS for a CF/node an=
d
> do a node by node switch=85
>
> https://issues.apache.org/jira/browse/CASSANDRA-5335
>
>
> Dean
>

--f46d0444e97fe0056e04d7c0fbd1
Content-Type: text/html; charset=windows-1252
Content-Transfer-Encoding: quoted-printable

<div>yes LCS has its own compacting thing. It does not honor min compaction=
, max compaction, and no-ops major compaction. The issue is that at the mom=
ent you change your system moves all your sized data to L0 and then starts =
a huge compaction grid to level it.=A0<br>
</div><div><br></div><div>It would be great to just make this change to one=
 server and see read/write.=A0</div><div><br></div><div>Check out the write=
 sampling mode.</div><div><br></div><div>Edward</div><br><div class=3D"gmai=
l_quote">
On Tue, Mar 12, 2013 at 9:08 AM, Hiller, Dean <span dir=3D"ltr">&lt;<a href=
=3D"mailto:Dean.Hiller@nrel.gov" target=3D"_blank">Dean.Hiller@nrel.gov</a>=
&gt;</span> wrote:<br><blockquote class=3D"gmail_quote" style=3D"margin:0 0=
 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
We tested it in QA, but in production it brought our cluster to a halt even=
 though we setcompactionthroughput to 1, we were severely limited. =A0Nodet=
ool stop compaction did not seem to have any impact either. =A0We ended up =
increasing memory on one node to help alleviate some issue(cranked it up to=
 16G and we hope to put it back down to 8 G later).<br>

<br>
Just be careful if you are trying to make the switch. =A0Also, I added this=
 jira ticket which would be extremely nice to turn on LCS for a CF/node and=
 do a node by node switch=85<br>
<br>
<a href=3D"https://issues.apache.org/jira/browse/CASSANDRA-5335" target=3D"=
_blank">https://issues.apache.org/jira/browse/CASSANDRA-5335</a><br>
<span class=3D"HOEnZb"><font color=3D"#888888"><br>
<br>
Dean<br>
</font></span></blockquote></div><br>

--f46d0444e97fe0056e04d7c0fbd1--