What is Shuffling in MapReduce?

Shuffling in MapReduce

As the Reducer receives the Mapper output which is also called as Intermediate Data as its input, it has to make sure that the Reducer receives the data sorted on its Key. For this purpose all the Unique keys are pulled together and sorted and sent to the Reducer. This phase is called Shuffling in MapReduce.

Happy Hadooping  :-) 

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.