You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@hbase.apache.org by Bing Jiang <ji...@gmail.com> on 2013/04/17 05:47:04 UTC

how to evaluate the up-limit number of Regions?

hi,all
I want to know whether it it a criterio or bible to measure the capicity of
hbase cluster.
>From my views, it depends on:
1. hdfs volumn
2. system memory setting
3. Network IO, etc
However, with the increase of number of table and region, how to evaluate
the ability of service is not enough, and we should make a supplement of
physical resource?

Any idea will be welcome.
Regards.
-- 
Bing Jiang
weibo: http://weibo.com/jiangbinglover
BLOG: http://www.binospce.com
National Research Center for Intelligent Computing Systems
Institute of Computing technology
Graduate University of Chinese Academy of Science

Re: how to evaluate the up-limit number of Regions?

Posted by Ted Yu <yu...@gmail.com>.
I am not sure I understand your question completely.

Were you asking the upper bound of number of regions, given certain
hardware resources ? Can you outline your expectation for throughput /
latency ?

I guess answers you may get would vary, depending on type of application,
etc.

On Tue, Apr 16, 2013 at 8:47 PM, Bing Jiang <ji...@gmail.com>wrote:

> hi,all
> I want to know whether it it a criterio or bible to measure the capicity of
> hbase cluster.
> From my views, it depends on:
> 1. hdfs volumn
> 2. system memory setting
> 3. Network IO, etc
> However, with the increase of number of table and region, how to evaluate
> the ability of service is not enough, and we should make a supplement of
> physical resource?
>
> Any idea will be welcome.
> Regards.
> --
> Bing Jiang
> weibo: http://weibo.com/jiangbinglover
> BLOG: http://www.binospce.com
> National Research Center for Intelligent Computing Systems
> Institute of Computing technology
> Graduate University of Chinese Academy of Science
>