Server virtualization has created some growing problems and disorder, such as unresponsive virtualized system, crashed virtualized server, misconfigured virtual hosting platforms, performance tuning and erratic performance metrics with some benchmark tools. This research analyzed the performance of Oracle VM server virtualization software against that of bare-metal server environment. It also examined scalability offered by Oracle VM and its operation for supporting high volume transactions. Two open suite benchmark tools Swingbench and LMbench were used to measure performance. The Swingbench was also used to measure scalability. 30 and 50 active users were used for the performance evaluation. We discovered from our Swingbench results that Oracle database performance in a single Oracle VM resulted in 4% and 8% overhead for 30 and 50 active users respectively. Performance metrics of 75% and 87% were obtained with 30 and 50 active users correspondingly in dual Oracle VM server; an indication of performance scalability improvement with two virtual machines. Our results also revealed Oracle VM server achieved significant percentages in latency and bandwidth that cannot be neglected, despite some adrift results obtained from LMbench measurement.
[1]
Roel Wieringa,et al.
Security Implications of Virtualization: A Literature Study
,
2009,
2009 International Conference on Computational Science and Engineering.
[2]
Tal Garfinkel,et al.
Virtual machine monitors: current technology and future trends
,
2005,
Computer.
[3]
Qinghua Gao,et al.
Performance Measuring and Comparing of Virtual Machine Monitors
,
2008,
2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing.
[4]
Jie Ma,et al.
Solo: A Lightweight Virtual Machine
,
2009,
2009 IEEE International Symposium on Parallel and Distributed Processing with Applications.
[5]
Muli Ben-Yehuda,et al.
Quantitative Comparison of Xen and KVM
,
2008
.