but, how can it split the data, if there are dependencies in job ? unless
we write parallel program, Does hadoop do any thing faster than usual
processor?


On Sat, Mar 31, 2012 at 10:32 AM, Karthikeyan V.B <[email protected]>wrote:

> Hi,
>
> The NameNode splits the job into several tasks and submits to the
> different DataNode(i.e nodes) , the split size varies from 64KB to 128MB.
> The NameNode assigns the data split to a datanod.
>
> Namenode actually has a table to store the mappings of data node and block
> stored in it.
>
> it is possible to query the namenode and get data from it.
>
> Regards,
> Karthikeyan
>
>  --
> You received this message because you are subscribed to the Google Groups
> "Algorithm Geeks" group.
> To post to this group, send email to [email protected].
> To unsubscribe from this group, send email to
> [email protected].
> For more options, visit this group at
> http://groups.google.com/group/algogeeks?hl=en.
>



-- 

**Regards
*
* <[email protected]>

Bharat B | M.Tech II  | C.S.E | IITM
*
*
*Ph: +91 8056127652*

-- 
You received this message because you are subscribed to the Google Groups 
"Algorithm Geeks" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/algogeeks?hl=en.

Reply via email to