Analysis of the Performance of Hadoop Applications on Eucalyptus Cloud

Abstract

In cloud computing, enterprises and individual consumers can have access to storage, computing and bandwidth resources through network terminal, and do not need to install applications. Cloud computing can be divided into three categories: Software as a Service (SaaS) and Platform as a Service (PaaS) and Infrastructure as a Service (IaaS). Eucalyptus is the most widely deployed IaaS cloud service software platform in the world. It builds a cloud service layer as IaaS by using the existing infrastructure. In this article, we built the Eucalyptus cloud platform on the server, and the deployment of software Dev C++ on the Eucalyptus platform. Consumers can have remote access to the software through the Internet without installing the software in the local. Over the last few years, Big Data analysis has attracted huge attention from enterprises and research institutions. Hadoop is considered as one of the most important tools in computing development in order to tackle the Big Data. It is very convenient for Eucalyptus to create and deploy the VM instances which is provided the distributed environment on demand, where the Hadoop applications are going to be executed. So we implement Hadoop platform on Eucalyptus cloud infrastructure, and evaluate the Hadoop applications running on Eucalyptus cloud under different stressing conditions.