A Time Based Analysis of Data Processing on Hadoop Cluster

摘要

Data when it becomes in that much amount that it cannot be managed by the traditional database management system then it is Big data. It is difficult to manage this much amount of the data. Hadoop is a technological answer to the Big Data. Data storage and retrieval of information from the data is done by the Hadoop Distributed File System and the Map Reduce Programming model. MapReduce provides effective bench marks for retrieving the information from the Big Data. In this paper we present our experimental work done on the Hadoop Cluster. We have analyzed the time required by the cluster for processing the data with increasing number of nodes into the cluster. We started with a single node and then increase the node by one each time. We have analyzed three types of time. The real time, user time, system time is analyzed.