ABSTRACT
Internet Service Providers resist innovating in the network core, fearing that deploying a new protocol or service compromises the network operation and their profit, as a consequence. Therefore, a new Internet model, called Future Internet, which enables core innovation, must accommodate new protocols and services with the current scenario, isolating each protocol stack from others. Virtualization is the key technique that provides concurrent protocol stack capability to the Future Internet elements. In this paper, we evaluate the performance of three widespread virtualization tools, Xen, VMware, and OpenVZ, considering their use for router virtualization. We conduct experiments with benchmarking tools to measure the overhead introduced by virtualization in terms of memory, processor, network, and disk performance of virtual routers running on commodity hardware. We also evaluate the effects of the increasing number of virtual machines on Xen network virtualization mechanism. Our results show that Xen best fits virtual router requirements. Moreover, Xen fairly shares the network access among virtual routers, but needs further enhancement when multiple virtual machines simultaneously forward traffic.
- BGP Reports. http://bgp.potaroo.net/ipv4-stats/prefixes_adv_pool.txt, Jan. 2012.Google Scholar
- M. Casado, T. Koponen, R. Ramanathan, and S. Shenker. Virtualizing the network forwarding plane. PRESTO '10, pages 8:1--8:6, 2010. Google ScholarDigital Library
- S. Chen, M. Zhu, and L. Xiao. Implementation of virtual time system for the distributed virtual machine monitor. IEEE/ISECS International Colloquium on Computing, Communication, Control, and Management, August 2009.Google Scholar
- R. S. Couto, M. E. M. Campista, and L. H. M. K. Costa. XTC: a throughput control mechanism for Xen-based virtualized software routers. In IEEE Global Communications Conference (GLOBECOM'2011), Houston, Texas, USA, Dec. 2011.Google ScholarCross Ref
- N. Egi, A. Greenhalgh, M. Handley, M. Hoerdt, L. Mathy, and T. Schooley. Evaluating xen for router virtualization. In International Workshop on Performance Modeling and Evaluation (PMECT), August 2007.Google ScholarCross Ref
- N. Feamster, L. Gao, and J. Rexford. How to Lease the Internet in your Spare Time. SIGCOMM Comput. Commun. Rev., 37:61--64, Jan. 2007. Google ScholarDigital Library
- N. Fernandes, M. Moreira, I. Moraes, L. Ferraz, R. Couto, H. Carvalho, M. Campista, L. Costa, and O. Duarte. Virtual networks: isolation, performance, and trends. Annals of Telecommunications, 66:339--355, 2011.Google ScholarCross Ref
- D. Gupta, R. Gardner, and L. Cherkasova. Xenmon: Qos monitoring and performance profiling tool. HP Labs, Tech. Rep., 2005.Google Scholar
- K. Ibrahim, S. Hofmeyr, and C. Iancu. Characterizing the performance of parallel applications on multi-socket virtual machines. In Cluster, Cloud and Grid Computing (CCGrid), 2011 11th IEEE/ACM International Symposium on, pages 1--12. IEEE, 2011. Google ScholarDigital Library
- V. Makhija, B. Herndon, P. Smith, L. Roderick, E. Zamost, and J. Anderson. Vmmark: A scalable benchmark for virtualized systems. VMware Inc., CA, Tech. Rep. VMware-TR-2006-002, September, 2006.Google Scholar
- N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S., and J. Turner. OpenFlow: Enabling innovation in campus networks. ACM SIGCOMM Computer Communication Review, 38(2):69--74, Apr. 2008. Google ScholarDigital Library
- A. Menon, A. L. Cox, and W. Zwaenepoel. Optimizing network virtualization in Xen. In USENIX Annual Technical Conference, pages 15--28, May 2006. Google ScholarDigital Library
- G. Schaffrath, C. Werle, P. Papadimitriou, A. Feldmann, R. Bless, A. Greenhalgh, A. Wundsam, M. Kind, O. Maennel, and L. Mathy. Network Virtualization Architecture: Proposal and Initial Prototype. In Proceedings of the 1st ACM workshop on Virtualized infrastructure systems and architectures, VISA '09, pages 63--72, New York, NY, USA, 2009. ACM. Google ScholarDigital Library
- SWsoft Inc. OpenVZ User's Guide, 2005.Google Scholar
- VMWare Inc. VMware ESX Server 2 Architecture and Performance Implications, 2005.Google Scholar
- VMWare Inc. A Performance Comparison of Hypervisors, 2007.Google Scholar
- XenSource, Inc. A Performance Comparison of Commercial Hypervisors, 2007.Google Scholar
Index Terms
- Evaluating virtual router performance for a pluralist future internet
Recommendations
HPC Performance and Energy-Efficiency of Xen, KVM and VMware Hypervisors
SBAC-PAD '13: Proceedings of the 2013 25th International Symposium on Computer Architecture and High Performance ComputingWith a growing concern on the considerable energy consumed by HPC platforms and data centers, research efforts are targeting green approaches with higher energy efficiency. In particular, virtualization is emerging as the prominent approach to mutualize ...
GPU Passthrough Performance: A Comparison of KVM, Xen, VMWare ESXi, and LXC for CUDA and OpenCL Applications
CLOUD '14: Proceedings of the 2014 IEEE International Conference on Cloud ComputingAs more scientific workloads are moved into the cloud, the need for high performance accelerators increases. Accelerators such as GPUs offer improvements in both performance and power efficiency over traditional multi-core processors, however, their use ...
My VM is Lighter (and Safer) than your Container
SOSP '17: Proceedings of the 26th Symposium on Operating Systems PrinciplesContainers are in great demand because they are lightweight when compared to virtual machines. On the downside, containers offer weaker isolation than VMs, to the point where people run containers in virtual machines to achieve proper isolation. In this ...
Comments