Mailing-List: contact user-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@hbase.apache.org
Received-SPF: pass (nike.apache.org: domain of jdcryans@gmail.com designates
 209.85.160.169 as permitted sender)
MIME-Version: 1.0
Sender: jdcryans@gmail.com
In-Reply-To: <84B5E4309B3B9F4ABFF7664C3CD7698302D0DCE7@kairo.scch.at>
References: <84B5E4309B3B9F4ABFF7664C3CD7698302D0DCE7@kairo.scch.at>
Date: Wed, 3 Aug 2011 15:26:01 -0700
Message-ID: 
 <CAGpTDNfza6m1rnZFD_V2a7MH814_+FrXOHK2j3YoBQiWpBWsbQ@mail.gmail.com>
Subject: Re: Monitoring HBase counters while running tests
From: Jean-Daniel Cryans <jdcryans@apache.org>
To: user@hbase.apache.org
Content-Type: text/plain; charset=ISO-8859-1

Hi Thomas,

No specific guide for monitoring performance but I strongly recommend
that you read the following sections of the book:

http://hbase.apache.org/book/performance.html
http://hbase.apache.org/book/trouble.html

And regarding general advices, lookout for swap and high iowait,
verify that you don't max out your network (but also make sure it runs
a decent speeds, same for the disks), if you do a lot of random reads
look for the efficiency of the block cache (it has a few metrics),
and... that's all I can think of right now.

Good luck,

J-D

On Wed, Aug 3, 2011 at 1:08 AM, Steinmaurer Thomas
<Thomas.Steinmaurer@scch.at> wrote:
> Hello,
>
>
>
> we are in process running our first load test on a Cloudera test cluster
> with 8 region servers. We also have Ganglia in use for monitoring. I
> wonder what counters one should watch out during the tests to identify
> possible bottlenecks, improvements etc ... Is there some kind of quick
> start guide into Hbase specific measures?
>
>
>
> Thanks!
>
>
>
> Thomas
>
>
>
>