You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@hbase.apache.org by Steinmaurer Thomas <Th...@scch.at> on 2011/08/03 10:08:44 UTC

Monitoring HBase counters while running tests

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

 


Re: Monitoring HBase counters while running tests

Posted by Jean-Daniel Cryans <jd...@apache.org>.
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
<Th...@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
>
>
>
>