Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
MIME-Version: 1.0
In-Reply-To: 
 <CA+4UHyPL_YxU1TA8uWuE=8zRH5EAMmfXw1zX_t4Qb7EfMkBL=A@mail.gmail.com>
References: 
 <CA+4UHyPL_YxU1TA8uWuE=8zRH5EAMmfXw1zX_t4Qb7EfMkBL=A@mail.gmail.com>
Date: Fri, 15 Jan 2016 16:34:48 -0500
Message-ID: 
 <CA+4UHyPD9o4O90-bt1f6odkiTq1rQKvPPavF23-kzd-B5hwbpA@mail.gmail.com>
Subject: Re: compaction throughput
From: Kai Wang <depend@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=001a114a9bbe339fc90529662cf5

--001a114a9bbe339fc90529662cf5
Content-Type: text/plain; charset=UTF-8

I forget to mention I am using C* 2.2.4
On Jan 15, 2016 3:53 PM, "Kai Wang" <depend@gmail.com> wrote:

> Hi,
>
> I am trying to figure out the bottleneck of compaction on my node. The
> node is CentOS 7 and has SSDs installed. The table is configured to use
> LCS. Here is my compaction related configs in cassandra.yaml:
>
> compaction_throughput_mb_per_sec: 160
> concurrent_compactors: 4
>
> I insert about 10G of data and start observing compaction.
>
> *nodetool compaction* shows most of time there is one compaction.
> Sometimes there are 3-4 (I suppose this is controlled by
> concurrent_compactors). During the compaction, I see one CPU core is 100%.
> At that point, disk IO is about 20-25 M/s write which is much lower than
> the disk is capable of. Even when there are 4 compactions running, I see
> CPU go to +400% but disk IO is still at 20-25M/s write. I use *nodetool
> setcompactionthroughput 0* to disable the compaction throttle but don't
> see any difference.
>
> Does this mean compaction is CPU bound? If so 20M/s is kinda low. Is there
> anyway to improve the throughput?
>
> Thanks.
>

--001a114a9bbe339fc90529662cf5
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<p dir=3D"ltr">I forget to mention I am using C* 2.2.4</p>
<div class=3D"gmail_quote">On Jan 15, 2016 3:53 PM, &quot;Kai Wang&quot; &l=
t;<a href=3D"mailto:depend@gmail.com">depend@gmail.com</a>&gt; wrote:<br ty=
pe=3D"attribution"><blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 =
.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir=3D"ltr"><div><di=
v><div>Hi,<br><br></div>I am trying to figure out the bottleneck of compact=
ion on my node. The node is CentOS 7 and has SSDs installed. The table is c=
onfigured to use LCS. Here is my compaction related configs in cassandra.ya=
ml:<br><br>compaction_throughput_mb_per_sec: 160<br>concurrent_compactors: =
4<br><br>I insert about 10G of data and start observing compaction.<br><br>=
</div><b>nodetool compaction</b> shows most of time there is one compaction=
. Sometimes there are 3-4 (I suppose this is controlled by concurrent_compa=
ctors). During the compaction, I see one CPU core is 100%. At that point, d=
isk IO is about 20-25 M/s write which is much lower than the disk is capabl=
e of. Even when there are 4 compactions running, I see CPU go to +400% but =
disk IO is still at 20-25M/s write. I use <b>nodetool setcompactionthroughp=
ut 0</b> to disable the compaction throttle but don&#39;t see any differenc=
e.<br><br></div><div>Does this mean compaction is CPU bound? If so 20M/s is=
 kinda low. Is there anyway to improve the throughput?<br><br></div><div>Th=
anks.<br></div></div>
</blockquote></div>

--001a114a9bbe339fc90529662cf5--