Highly parallel map reduce process and efficient job scheduling methodologies of big data systems

Abstract

This paper studies about various job scheduling methodologies used in big data systems. Map reduce is a highly efficient distributed job processing strategy for big data systems. Job scheduling is a critical task of any big data system as the volume of jobs need to be processed is tremendous. This study will go over the map reduce process in detail. It also reviews various job scheduling methodologies and tries to perform an efficient comparison among these methodologies.