ABSTRACT
Virtualization is a key technology for data centres to implement infrastructure as a service as well as to achieve server consolidation and application colocation. Over the years performance of virtual machine (VM) monitors have improved [8]. Thus, new services are being migrated to these environments. Latency sensitive applications however, are not considered fit for Virtual environments due to high virtualization overhead and potential interference from other VMs. In this paper, we performed measurement-based analysis of the performance impact on VOD server in presence of I/O bound workloads in co-located virtual machines. The focus of our study is on the QOS (quality of service) received by clients; metrics of delay, jitter, packet loss are examined. As expected, the performance of VOD server in a VM suffers severe degradation in presence of heavy disk-I/O bound and outbound network UDP co-located workloads.
- S. Appel and I. Petrov. Performance Evaluation of Multi Machine Virtual Environments. In 2010 SPEC Benchmark Workshop, pages 1--13, Paderborn, Germany, Oct. 2010.Google Scholar
- S. K. Barker and P. Shenoy. Empirical Evaluation of Latency-Sensitive Application Performance in the Cloud. In MMSYS 2010, pages 35--46, Phoenix, AZ, February 2010. Google ScholarDigital Library
- S. Chinni and R. Hiremane. Virtual Machine Device Queues. Intel Corp White Paper, 2007.Google Scholar
- W. Huang, J. Liu, B. Abali, and D. Panda. A Case for High Performance Computing with Virtual Machines. In International Conference on Supercomputing, pages 125--134, Queensland, Australia, June 2006. Google ScholarDigital Library
- A. Iosup, S. Ostermann, N. Yigitbasi, R. Prodan, T. Fahringer, and D. Epema. Performance Analysis of Cloud Computing Services for Many-tasks Scientific Computing. IEEE Transactions on Parallel and Distributed Systems, 22(6):931--945, June 2011. Google ScholarDigital Library
- A. Kivity, Y. Kamay, D. Laor, U. Lublin, and A. Liguori. KVM: The linux Virtual Machine Monitor. In Linux Symposium, pages 225--230, Ottawa, ON, Canada, June 2007.Google Scholar
- J. Liu. Evaluating Standard-based Self-virtualizing Devices: A Performance Study on 10 GbE NICs with SR-IOV Support. In IEEE International Parallel and Distributed Processing Symposium, pages 1--12, Atlanta, GA, April 2010.Google Scholar
- R. McDougall and J. Anderson. Virtualization Performance: Perspectives And Challenges Ahead. SIGOPS Oper. Syst. Rev, 44(4):40--56, 2010. Google ScholarDigital Library
- V. Nae, A. Iosup, R. Prodan, and T. Fahringer. The Impact of Virtualization on the Pperformance of Massively Multiplayer Online Games. In NetGames, pages 1--6, Paris, France, November 2009. Google ScholarDigital Library
- P. Padala, X. Zhu, Z. Wang, S. Singhal, and K. Shin. Performance Evaluation of Virtualization Technologies for Server Consolidation. Technical Report HPL-2007-59, HP Labs, 2007.Google Scholar
- R. Russell. Virtio: Towards a De-facto Standard for Virtual I/O Devices. SIGOPS Oper. Syst. Rev, 42(5):95--103, 2008. Google ScholarDigital Library
- H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson. RTP: A Transport Protocol for Real-Time Applications. RFC 3550 (Standard), July 2003. Updated by RFCs 5506, 5761, 6051, 6222. Google ScholarDigital Library
- F. Boronat Segu;ı, G. Cebollada, J. Carlos, and J. Lloret Mauri. An RTP/RTCP based approach for multimedia group and inter-stream synchronization. Multimedia Tools Appl., 40(2):285--319, Nov. 2008. Google ScholarDigital Library
- J. Shafer. I/O Virtualization Bottlenecks in Cloud Computing Today. In USENIX WIOV Workshop, pages 1--7, Pittsburgh, PA, March 2010. Google ScholarDigital Library
- B. Tarnai and M. Telekom. Requirements and Traffic Dimensioning for System Concepts and Architecture. Technical report, OASE/ACCORDANCE, 2010.Google Scholar
- G.I. Wang and T. S. Ng. The Impact of Virtualization on Network Performance of Amazon EC2 Data Center. In IEEE INFOCOM, pages 1163--1171, San Diego, CA, March 2010. Google ScholarDigital Library
Index Terms
- Performance evaluation of video-on-demand in virtualized environments: the client perspective
Recommendations
IO Core Manager for Virtual Environments
SYSTOR '16: Proceedings of the 9th ACM International on Systems and Storage ConferencePara-virtualization is the leading approach in IO device virtualization. It allows the hypervisor to interpose on and inspect a virtual machine's I/O traffic at run-time. Examples of such interfaces are KVM's virtio [6] and VMWare's VMXNET [7]. Current ...
A Virtual CPU Scheduling Model for I/O Performance in Paravirtualized Environments
RACS '17: Proceedings of the International Conference on Research in Adaptive and Convergent SystemsParavirtualization manages virtual machines and virtual resources efficiently by the communication between the virtualization layer and modified guest OSes. In a paravirtual environment, the I/O response of a virtual machine is hard to approach that of ...
Evaluating and optimizing I/O virtualization in kernel-based virtual machine (KVM)
NPC'10: Proceedings of the 2010 IFIP international conference on Network and parallel computingI/O virtualization performance is an important problem in KVM. In this paper, we evaluate KVM I/O performance and propose several optimizations for improvement. First, we reduce VM Exits by merging successive I/O instructions and decreasing the ...
Comments