A Performance Analysis of OpenStack Cloud vs Real System on Hadoop Clusters

Abstract

This paper introduces the performance analysis of OpenStack Cloud with the commodity computers in the big data environments. It is necessary to analyze the performance of virtual system in cloud infrastructure with the commodity computers to identify effective and efficient system for processing big data. To determine performance measures, virtual systems were created in the Openstack cloud and Hadoop distributed framework was configured on all the virtual instances and commodity computers to form their respective clusters. For the experiment, image to pdf conversion and word count program are executed in the same configuration of OpenStack Cloud and Commodity computers. We found that personal computers hadoop cluster was as powerful and fault tolerant as the cloud hadoop cluster but not as scalable as the cloud cluster. This paper concludes that the data storage and analysis in hadoop cluster in cloud is more flexible and easily scalable than the real system cluster. This paper also concludes the cluster in commodities computers are faster than the cloud clusters.