A Survey on Optimal Data Storage of Cache Manager for Big Data Using Map Reduce Framework

MapReduce is an open-source framework used for implement big-data sets. The very famous word big-data that points to the wide-ranging diffused applications that works on unmatched huge data sets. While processing on this big-data in-between abundant knowledge that being neglected after getting process finished. In this paper we analyze various techniques emerged for simplified data processing on large data sets (big-data) and along with new and very effective technique that sensible of data cache model (framework). In this model process collects its in-between data to the cache manager. This new proposed cache model reduces the execution time of the task as it checks in cache, which could keep and store up execution.