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 hosschao@gmail.com designates
 209.85.210.172 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAGg-zQV1qK=VqKQdiYfz_uRM=yw4tYvoEdpCaQAQVhKRMkG3zw@mail.gmail.com>
References: 
 <CAGg-zQV1qK=VqKQdiYfz_uRM=yw4tYvoEdpCaQAQVhKRMkG3zw@mail.gmail.com>
Date: Tue, 24 Apr 2012 18:11:26 +0800
Message-ID: 
 <CAGg-zQWng6d+FVE8P+-_yyMEcYwT3Nst_VMMcvqyr_Mm0WsKRA@mail.gmail.com>
Subject: Re: High latency of cassandra
From: =?GB2312?B?wu2zrA==?= <hosschao@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=bcaec51a76dc47fe1504be69fa6c

--bcaec51a76dc47fe1504be69fa6c
Content-Type: text/plain; charset=GB2312
Content-Transfer-Encoding: quoted-printable

Does any one have idea for this? Thanks~

2012/4/24 =C2=ED=B3=AC <hosschao@gmail.com>

> Hi all,
>
> I have some troubles of cassandra in my production:
>
> I build up a RPC server which using hector client to manipulate the
> cassandra. Wired things happen nowadays: the latency of RPC sometimes
> becames very high (10seconds~70seconds) in several minutes and reduce
> to normal level (30ms in average) after that time. I investigate the
> debug log of cassandra. During high latency time, the cassandra output
> lots of message like:
> "IncomingTcpConnection.java(116) Version is now 3. "
> Seems everything be blocked during that time.
>
> Our settings as following:
> The version of cassandra is 1.0.1 and hector version is 0.7.0 for the
> compatible of thrift version which we use (0.5.0)
> The cluster contains 4 nodes and all of them are seeds. The
> gcgraceseconds is 0 since we needn't delete the data
>
> p.s. It works well for a long time (3 months) but becames crazy these
> days after we push the new RPC server which supports bigger data
> saving (2mb in average). I'm not sure if these is the reason.
>
> Hope getting your replay~~
>
> Thanks,
>
> Chao.
>

--bcaec51a76dc47fe1504be69fa6c
Content-Type: text/html; charset=GB2312
Content-Transfer-Encoding: quoted-printable

<div class=3D"gmail_extra">Does any one have idea for this? Thanks~<br><br>=
<div class=3D"gmail_quote">2012/4/24 =C2=ED=B3=AC <span dir=3D"ltr">&lt;<a =
href=3D"mailto:hosschao@gmail.com" target=3D"_blank">hosschao@gmail.com</a>=
&gt;</span><br><blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex=
;border-left:1px #ccc solid;padding-left:1ex">
<span>Hi all,</span><br><br><span>I have some troubles of cassandra in my p=
roduction:</span><br><br><span>I build up a RPC server which using hector c=
lient to manipulate the</span><br>
<span>cassandra. Wired things happen nowadays: the latency of RPC sometimes=
</span><br><span>becames very high (10seconds~70seconds) in several minutes=
 and reduce</span><br><span>to normal level (30ms in average) after that ti=
me. I investigate the</span><br>

<span>debug log of cassandra. During high latency time, the cassandra outpu=
t</span><br><span>lots of message like:</span><br><span>&quot;IncomingTcpCo=
nnection.java(</span><span>116) Version is now 3. &quot;</span><br>
<span>Seems everything be blocked during that time.</span><br><br><span>Our=
 settings as following:</span><br><span>The version of cassandra is 1.0.1 a=
nd hector version is 0.7.0 for the</span><br>
<span>compatible of thrift version which we use (0.5.0)</span><br><span>The=
 cluster contains 4 nodes and all of them are seeds. The</span><br><span>gc=
graceseconds is 0 since we needn&#39;t delete the data</span><br>
<br><span>p.s. It works well for a long time (3 months) but becames crazy t=
hese</span><br><span>days after we push the new RPC server which supports b=
igger data</span><br><span>saving (2mb in average). I&#39;m not sure if the=
se is the reason.</span><br>

<br><span>Hope getting your replay~~</span><br><br><span>Thanks,</span><br>=
<br><span>Chao.</span><br>
</blockquote></div><br></div>

--bcaec51a76dc47fe1504be69fa6c--