ABSTRACT
I input data is divided into chunks, eachchunk is processed independently of the others, possibly in parallel, and the results are combined at the end. The Map Reduce style, commonly known as MapReduce, comprises two key abstractions: (1) a map function takes chunks of data, as well as a function, as arguments, and applies that function to each chunk independently, producing a collection of results; (2) a reduce function takes a collection of results as well as a function, as arguments, and applies that function to the collection of results in order to extract some global knowledge out of that collection.
