hadoop-general mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Vijay <vijay2...@gmail.com>
Subject Re: Beginer
Date Fri, 01 May 2009 22:38:49 GMT
Simple way to explain is.....
Think abt it, if you have million things to do to complete a One JOB..... To
get that done you will divide it to 10 * 100 K things.... Send it 100K
server to do the job individually (Map Job)
Get the data back from it and run a reduce job which will combine all the
results and at the end you have the results of those million things....
Doing the same thing without any Loss of data or loss of processing time by
redundancy etc....

What you gain? It is like your car with 4 Cyl or 6 Cyl or even 8 Cyl in
it..... :)

the above is Just a simple over view or a 1min summary :) Well this is my
way of interpreting it.

Regards,
</VJ>




On Fri, May 1, 2009 at 1:40 PM, <gtsafas.bb@gmail.com> wrote:

> Hello everyone,
>
> I am new to hadoop. My company is looking into using it. I am trying to get
> an idea of it but some of the literature is beyond my comprehension. If
> someone would not mind giving me an easier explanation I would appreciate
> it.
>
> Thank you.
>
> Sent from my Verizon Wireless BlackBerry
>

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