Load Balancing Through Map Reducing Application Using CentOS System

Abstract

The main aim is to design an algorithm for Map-Reduce application, with a ballot count application, which explains how the big data can be handled by the individual Mappers and how data is split using map() function. The output of Mappers and is given to the Reducer and reduce () function is applied. The execution takes set of input key/value pairs, and gives a set of output key/value pairs. Map, accepts the input from the user, processes it and generates a set of intermediate key/value pairs. The Map Reduce library groups all the intermediate values of the same category and passes it to the Reduce function. The Reduce function takes the intermediate key and a set of values associated with the key. It groups together all the associated values and generates a smaller set of values. Finally, only zero or one output value is generated by the reducer. The iterate is responsible for accepting the intermediate key and its associated value.