Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
HDFS >> mail # user >> Re: MapReduce shuffle algorithm


Copy link to this message
-
Re: MapReduce shuffle algorithm
An introduction to the subject can be found in the best known reference :

Hadoop: The Definitive Guide, 3rd Edition
 Storage and Analysis at Internet Scale
By Tom White <http://shop.oreilly.com/product/0636920021773.do#tab_04>
Publisher: O'Reilly Media / Yahoo Press
Released: May 2012

Chapter 6 How MapReduce Works -> Shuffle and Sort -> around page 208
http://shop.oreilly.com/product/0636920021773.do

After reading this, you should have a good understanding of the
architecture and know that indeed there is no "shuffle phase replication
factor" (cf your question on another thread). For the technical details,
the code is probably the next step.

Regards

Bertrand

On Tue, May 21, 2013 at 6:58 PM, John Lilley <[EMAIL PROTECTED]>wrote:

>  I am very interested in a deep understanding of the MapReduce “Shuffle”
> phase algorithm and implementation.  Are there whitepapers I could read for
> an explanation?  Or another mailing list for this question?  Obviously
> there is the code ;-)****
>
> john****
>
> ** **
>