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 watcherfr@gmail.com
 designates 74.125.82.44 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAO5xsd0uwTB7v7qLZhQUCyqXSL1b1Yi=mo-N1dNmt4KUycjAFQ@mail.gmail.com>
References: 
 <CAHwsXYkJmaCtOq8EA4sTR=VP3=6E1VDFJYow7iCqMs+3BW6+bQ@mail.gmail.com>
	<CAO5xsd0uwTB7v7qLZhQUCyqXSL1b1Yi=mo-N1dNmt4KUycjAFQ@mail.gmail.com>
Date: Thu, 29 Sep 2011 07:47:38 +0200
Message-ID: 
 <CAHwsXYk0WMbo6pc8xXev+4JBD+Q7cpnvkN1-2KdBKXV82M_dWQ@mail.gmail.com>
Subject: Re: GC for ParNew on 0.8.6
From: Philippe <watcherfr@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=0016367fb998ddb18204ae0e0b71

--0016367fb998ddb18204ae0e0b71
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

No it was an upgrade from 0.8.4 or 0.8.5 depending on the nodes.
No cassandra-env files were changed during the update.
Any other ideas?  The cluster has just been weird ever since running 0.8.6 =
:
has anyone else upgraded and not run into this?
Le 28 sept. 2011 09:32, "Peter Schuller" <peter.schuller@infidyne.com> a
=E9crit :
>> I have changed absolutely nothing and the work load is perhaps even lowe=
r
>> than before upgrading because I have paused most updates to the cluster.
Did
>> a log level change or does this have deeper meaning ?
>
> You don't say which version you upgraded from but I suspect 0.7? JVM
> options like heap size calculations have changed. I am guessing you're
> seeing it in the logs because the young generation was sized
> differently, causing young generation garbage collections to be longer
> than before and thus triggering the logging by the Cassandra
> GCInspector.
>
> --
> / Peter Schuller (@scode on twitter)

--0016367fb998ddb18204ae0e0b71
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<p>No it was an upgrade from 0.8.4 or 0.8.5 depending on the nodes.<br>
No cassandra-env files were changed during the update.<br>
Any other ideas?=A0 The cluster has just been weird ever since running 0.8.=
6 : has anyone else upgraded and not run into this? </p>
<div class=3D"gmail_quote">Le 28 sept. 2011 09:32, &quot;Peter Schuller&quo=
t; &lt;<a href=3D"mailto:peter.schuller@infidyne.com" target=3D"_blank">pet=
er.schuller@infidyne.com</a>&gt; a =E9crit=A0:<br type=3D"attribution">&gt;=
&gt; I have changed absolutely nothing and the work load is perhaps even lo=
wer<br>

&gt;&gt; than before upgrading because I have paused most updates to the cl=
uster. Did<br>&gt;&gt; a log level change or does this have deeper meaning =
?<br>&gt; <br>&gt; You don&#39;t say which version you upgraded from but I =
suspect 0.7? JVM<br>

&gt; options like heap size calculations have changed. I am guessing you=
9;re<br>&gt; seeing it in the logs because the young generation was sized<b=
r>&gt; differently, causing young generation garbage collections to be long=
er<br>

&gt; than before and thus triggering the logging by the Cassandra<br>&gt; G=
CInspector.<br>&gt; <br>&gt; -- <br>&gt; / Peter Schuller (@scode on twitte=
r)<br></div>

--0016367fb998ddb18204ae0e0b71--