Virtualized Hadoop Performance with VMware vSphere 5.1

Virtualized Hadoop Performance with VMware vSphere 5.1
Performance Study

About the Author
Jeff Buell is a Staff Engineer in the Performance Engineering group at VMware. His work focuses on the performance of various virtualized applications, most recently in the HPC and Big Data areas. His findings can be found in white papers, blog articles, and VMworld presentations.

Technical Paper
Publisher:VMware

Latest Revision:
Apr 18, 2013

Download:
http://www.vmware.com/files/pdf/techpaper/hadoop-vsphere51-32hosts.pdf

Description

A cluster of 32 high-performance hosts was used to run three demanding Hadoop applications. The performance of native and several VMware vSphere configurations was compared. The apples-to-apples case of a single virtual machine per host shows performance close to that of native. Improvements in elapsed time of up to 13% can be achieved by partitioning each host into two or four virtual machines, resulting in competitive or even better than native performance. The origins of the improvements are examined and recommendations for optimal hardware and software configuration are given.

Technical Resource | VMware | Performance | PDF | vSphere 5 | Performance Study