An impudent approach for prudential Hadoop cluster

The amount of data that has to be handled in daily life is increasing exponentially. In this scenario, the need for big data manipulation in a distributed environment arises and the significance of Hadoop comes forth. Along with the setup of a clustered environment for Hadoop framework, appropriate mechanisms for resource management, monitoring and package management should be integrated. This paper introduces a novel approach for accomplishing these objectives in a low cost cluster environment. In the current effort, Hadoop is implemented over Rocks cluster which ensures a simple, rapid cluster deployment and management thereby easing the cluster administration. Moreover Rocks is incorporated with resource management tools Torque and Condor, monitoring tool like Ganglia and Bio package management toolkit thus providing a foundation for the attainment of the objectives.