Implementing Hadoop Platform on Eucalyptus Cloud Infrastructure

Today, cloud computing is used as a model in most scientific, commercial, military, etc. In this model, the main body of the system is virtual servers, which currently provide services to customers around the world. Eucalyptus is an open source implementation of Cloud computing infrastructure that has a particular architecture. By using Eucalyptus, we can make public and private Clouds. Hadoop also is an open platform that is used for distributing data and jobs in large clusters. This platform can be used for processing and storing huge volumes of data and executing parallel jobs (e.g. analyzing system logs, weather data, and customer relationship behavior and so on.). In this article, we using integrating Hadoop platform on Eucalyptus infrastructure, facilitate and accelerate the deployment of a Hadoop cluster and moreover represent one of the uses of Eucalyptus system in serving services to the Cloud customers. It is worth mentioning that we have successfully implemented our method on the supercomputer of Amirkabir University and according to executed program on our cluster, efficiency has increased to about 80 percent in 32 cores compared to 4 cores clusters.