A Research on KVM I/O Performance

Abstract:

With open source, stable performance, simple structure, integrated in Linux kernel, and good performance, KVM (Kernel-based Virtual Machine) gets wide attention from major IT vendors and academia circles. However, virtualization technology will introduce additional overhead, especially in the I/O virtualization. The current researches about KVM have been carried out mostly focused on the performance comparison and analysis between virtualization solutions. There is no systematic study of the KVM I/O performance. In this paper, the I/O architecture in KVM is firstly studied, and then the disk and network performance of fully virtualization KVM and Para-virtualization KVM with all the different configurations are systemically tested and analyzed. Both the KVM I/O performance and the influences of the different configuration options on the performance are figured out in this paper. These are quite important and useful for the users and designers.

• Periodical: Applied Mechanics and Materials (Volumes 385-386)
• Pages: 1790-1796
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.385-386.1790
• Online since: August 2013
• Authors: Lie Bin Yu
• Keywords: I/O Performance, KVM, Virtualization

References

[1] Goto Yasunori, Kernel-based virtual machine technology, Fujitsu Scientific and Technical Journal, Fujitsu Ltd, vol. 47, no. 3, pp.362-368, (2011).

[2] Bourguiba Manel, Haddadou Kamel, Pujolle Guy, Packet aggregation based network I/O virtualization for cloud computing, Computer Communications, vol. 35, no. 3, pp.309-319, (2012).

DOI: 10.1016/j.comcom.2011.10.002

[3] Zhang Bin-Bin, Wang Xiao-Lin, Yang Liang, Lai Rong-Feng1, Wang Zhen-Lin, Luo Ying-Wei, Li Xiao-Ming, Modifying Guest OS to optimize I/O virtualization in KVM, vol. 33, no. 12, pp.2312-2319, (2010).

DOI: 10.3724/sp.j.1016.2010.02312

[4] Liu Jiajun, Hao Qinfen, Research on optimizing KVM's network performance, Proceedings of 2011 International Conference on Internet Technology and Applications (iTAP), pp.1-4, (2011).

[5] Huang Guangjun, Wu Jian, Hu Zhengguo, Strategy and technology for management of memory in KVM, Jisuanji Gongcheng/Computer Engineering(in Chinese), vol. 29, no. 1, p.48, (2003).

[6] Chierici Andrea, Veraldi Riccardo1, A quantitative comparison between xen and kvm, Journal of Physics: Conference Series, Institute of Physics Publishing, vol. 219, no. 1 part4, pp.1-7, (2010).

DOI: 10.1088/1742-6596/219/4/042005

[7] Tafa Igli, Beqiri Ermal1, Paci Hakik, Kajo Elinda, Xhuvani Aleksandër, The evaluation of Transfer Time, CPU Consumption and Memory Utilization in XEN-PV, XEN-HVM, OpenVZ, KVM-FV and KVM-PV Hypervisors using FTP and HTTP approaches, Proceedings of 3rd IEEE International Conference on Intelligent Networking and Collaborative Systems, pp.502-507, (2011).

DOI: 10.1109/incos.2011.164

[8] Lucas Nussbaum, Fabienne Anhalt, Olivier Mornard, Jean-Patrick Gelas, Linux-based virtualization for HPC clusters, Proceedings of the Linux Symposium, pp.221-234, (2009).

[9] Che Jianhua, He Qinming, Gao Qinghua, Huang Dawei, Performance Measuring and Comparing of Virtual Machine Monitors, Proceedings of IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, pp.381-386, (2008).

DOI: 10.1109/euc.2008.127

[10] Nathan Regola, Jean-Christophe Ducom, Recommendations for Virtualization Technologies in High Performance Computing, Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, p.409–416, (2010).

DOI: 10.1109/cloudcom.2010.71

[11] Wang Xiaojing, Tong Wei, Zhao Wei, Liu Jingning, Evaluation on network load balancing in Xen, 2012 2nd International Conference on Consumer Electronics, Communications and Networks- Proceedings, pp.3235-3538, (2012).

DOI: 10.1109/cecnet.2012.6201781

[12] Li Xudong, Zhou Lei, Research on the performance of network virtualization based on Xen, Applied Mechanics and Materials, vol. 135-136, pp.834-839, (2012).

DOI: 10.4028/www.scientific.net/amm.135-136.834

[13] Xia Yubin, Yang Chun, Niu Yan, Cheng Xu, Credit-HC: An I/O-friendly CPU scheduler for xen, Chinese Journal of Electronics, vol. 19, no. 3, pp.409-413, (2010).

[14] Whiteaker Jon1, Schneider Fabian1, Teixeira Renata, Explaining packet delays under virtualization, Computer Communication Review, vol. 44, no. 1, pp.38-44, (2011).

DOI: 10.1145/1925861.1925867

[15] Nikolaev Ruslan, Back Godmar, Perfctr-xen: A framework for performance counter virtualization, ACM SIGPLAN Notices, vol. 46, no. 7, pp.15-25, (2011).

DOI: 10.1145/2007477.1952687

[16] Xue Hai-Feng, Qing Si-Han, Zhang Huan-Guo, Analysis on XEN virtualization machine, Xitong Fangzhen Xuebao / Journal of System Simulation(in Chinese), vol. 19, no. 23, pp.5556-5558+5569, (2007).

[17] Wang Kai, Hou Zifeng, A relaxed co-scheduling method of virtual CPUs on Xen virtual machines, Computer Research and Development, vol. 49, no. 1, pp.118-127, (2012).

[18] Hu Yanyan, Long Xiang, Zhang Jiong, I/O behavior characterizing and predicting of virtualization workloads, Journal of Computers, vol. 7, no. 7, pp.1712-1725, (2012).