hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Jack Sun <revlet...@gmail.com>
Subject Re: Scan from multiple client
Date Fri, 08 Apr 2011 06:10:43 GMT
Hi Stack:

The following is my test scenario.

I uses HBase version 0.20.6.
I tried starting 300 threads and each thread gets  100 records one by one
records from one table.
The table has 100,000 records and was split into two regionservers.

I read 100 records from same regionserver with different 100 record keys.
 1. getting data by some certain keys(continus) cost 700ms
 2. getting data by some certain keys(continus) cost 24000ms

The later result cost  30times time.

Could you tell me the possible reason? or how can investigate the reason?

Thanks.

Jack


On Thu, Apr 7, 2011 at 1:02 AM, Stack <stack@duboce.net> wrote:

> On Tue, Apr 5, 2011 at 10:49 PM, Jack Sun <revletter@gmail.com> wrote:
> > I tried to access HBaseDB from 3 WebServer(Tomcat) at the same time,
> >
> > I found that scan will takes more(10times) time comparing with the speed
> of
> > put.
> >
> >
> > When 1WebServer -> 1HBase DB , it takes about the same time on scan
> >
> > and put.
> >
> >
> > I wonder  in this case , hbase does something with  the multiple client
> IP
> > address
> >
>
> No.
>
> Tell us more about your hbase version and the numbers you are seeing.
>
> Sounds like 3 concurrent scans is taking longer than 3 concurrent
> puts?  This might help: http://hbase.apache.org/book/ch13s06.html
>
> St.Ack
>
>
> St.Ack
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message