ARCHIVES

Abstract: In this project we have discussed the challenges and opportunities for efficient parallel data processing environment and the first data processing framework to exploit the dynamic resources provision offered today’s peer-to-peer system. We have described basic architecture and presented a performance comparison to the well-establish data processing framework Hadoop. The performance evaluation gives a first impression on how the ability to assign specific virtual machine types to specific task of the processing job, as well as the Possibility to automatically allocate/deallocate virtual machines in the course of the job execution, can help to improve overall resource and the time utilization and consequentially reduce the processing cost. Over current profiling approach builds a valuable basis for this however, at the moment the system still requires a reasonable amount of user annotation. In general, we think over work represent an important contribution to the growing field of cloud computing services and point out exiting new opportunities in the field of parallel data processing.