Brian J. Watson
ABSTRACT
Virtualization technologies enable organizations to dynamically flex their IT resources based on workload fluctuations and changing business needs. However, only through a formal understanding of the relationship between application performance and virtualized resource allocation can over-provisioning or over-loading of physical IT resources be avoided. In this paper, we examine the probabilistic relationships between virtualized CPU allocation, CPU contention, and application response time, to enable autonomic controllers to satisfy service level objectives (SLOs) while more effectively utilizing IT resources. We show that with only minimal knowledge of application and system behaviors, our methodology can model the probability distribution of response time with a mean absolute error of less than 6% when compared with the measured response time distribution. We then demonstrate the usefulness of a probabilistic approach with case studies. We apply basic laws of probability to our model to investigate whether and how CPU allocation and contention affect application response time, correcting for their effects on CPU utilization. We find mean absolute differences of 8-10% between the modeled response time distributions of certain allocation states, and a similar difference when we add CPU contention. This methodology is general, and should also be applicable to non-CPU virtualized resources and other performance modeling problems.
- R. Koenker, "Quantile Regression", Cambridge University Press, 2005.Google Scholar
- RUBiS: Rice University Bidding System. http://www.cs.rice.edu/CS/Systems/DynaServer/rubisGoogle Scholar
- B. Urgaonkar, G. Pacifici, P. Shenoy, M. Spreitzer, and A. Tantawi, "An Analytical Model for Multi-tier Internet Services and its Applications". In Proc. of ACM SIGMETRICS, June 2005. Google ScholarDigital Library
- E. Lazowska, J. Zahorjan, G. Graham, and K. Sevcik, "Quantitative System Performance: Computer System Analysis Using Queueing Network Models". Prentice-Hall, Inc., 1984. Google ScholarDigital Library
- C. Stewart, T. Kelly, and A. Zhang, "Exploiting Nonstationarity for Performance Prediction". In Proc. of EuroSys 2007. Google ScholarDigital Library
- Q. Zhang, L. Cherkasova, and E. Smirni. "A Regression-Based Analytic Model for Dynamic Resource Provisioning of Multi-Tier Applications". In Proc. of the 4th Int. Conf. on Autonomic Computing and Communications (ICAC), 2007. Google ScholarDigital Library
- V. Gupta, M. Harchol-Balter, A. Scheller Wolf, and U. Yechiali. "Fundamental Characteristics of Queues with Fluctuating Load". In Proc. of SIGMETRICS 2006, 2006. Google ScholarDigital Library
- Y. Chen, S. Iyer, A. Sahai, and D. Milojicic, "A Systematic and Practical Approach to Generating Policies from Service Level Objectives". In Proc. of the 11th IFIP/IEEE Int. Symposium on Integrated Network Management, June 2009. Google ScholarDigital Library
- Z. Wang, Y. Chen, D. Gmach, S. Singhal, B. Watson, W. Rivera, X. Zhu, and C. Hyser, "AppRAISE: Application-level Performance Management in Virtualized Server Environment". IEEE Transactions on Networking and Service Management, Vol. 6, No. 4, pp. 240--254, 2009. Google ScholarDigital Library
- C. Stewart and K. Shen, "Performance modeling and system management for multi-component online services". In Proc. of USENIX NSDI, 2005. Google ScholarDigital Library
- E. Ipek, S. McKee, B. Supinski, M. Schultz, and R. Caruana, "Efficiently exploring architectural design spaces via predictive modeling". In ASPLOS, 2006. Google ScholarDigital Library
- P. Bodik, C. Sutton, A. Fox, D. Patterson, and M. Jordan, "Response-Time Modeling for Resource Allocation and Energy-Informed SLAs". In Workshop on Statistical Learning Techniques for Solving Systems Problems (MLSys), Whistler, Canada, 2007.Google Scholar
- I. Cohen, S. Zhang, M. Goldszmidt, J. Symons, T. Kelly, and A. Fox, "Capturing, indexing, clustering and retrieving system history", 20th ACM Symposium on Operating Systems Principles (SOSP), 2005. Google ScholarDigital Library
- V. Kumar, K. Schwann, S. Iyer, Y. Chen, and A. Sahai, "A State Space Approach to SLA based Management". In Proc. of the IEEE/IFIP NOMS, 2008.Google ScholarCross Ref
- U. Bhatt, "Sixty Years of Queueing Theory", Management Science, Vol. 15, No. 6, pp. B280--B294, 1969.Google ScholarDigital Library
- R. Howard, "The Practicality Gap", Management Science, Vol. 14, No. 7, pp. 503--507, 1968.Google ScholarDigital Library
- A. Lee, "Applied Queueing Theory", Macmillan, 1966.Google Scholar
- G. DeCandia, D. Hastorun, M. Jampani, G. Kakulapati, A. Lakshman, A. Pilchin, S. Sivasubramanian, P. Vosshall, and W. Vogels, "Dynamo: Amazon's Highly Available Key-value Store", SOSP, Stevenson, WA, 2007. Google ScholarDigital Library
- T. Price, "A Note on the Effect of the Central Processor Service Time Distribution on Processor Utilization in Multiprogrammed Computer Systems", J. ACM, Vol. 23, No. 2, pp. 342--346, 1976. Google ScholarDigital Library
- E. Lazowska, "The Use of Percentiles in Modeling CPU Service Time Distributions", Computer Performance, North Holland Publishing Company, 1977.Google Scholar
- U. Lublin and D. Feitelson, "The workload on parallel supercomputers: modeling the characteristics of rigid jobs", Journal of Parallel and Distributed Computing, 2003. Google ScholarDigital Library
- D. Eager, D. Sorin, and M. Vernon, "AMVA Techniques for High Service Time Variability", ACM SIGMETRICS, Santa Clara, CA, 2000. Google ScholarDigital Library
- I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," J. Machine Learning Research 3, 1157--1182, 2003. Google ScholarDigital Library
- Xen. http://bits.xensource.com/Xen/docs/user.pdfGoogle Scholar
- D. Gaver, "Probability Models for Multiprogramming Computer Systems", J. ACM, Vol. 14, No. 3, pp. 423--438, 1967. Google ScholarDigital Library
- S. Boyd and L. Vandenberghe, "Convex Optimization", Cambridge University Press, 2004. Google ScholarDigital Library
Index Terms
- Probabilistic performance modeling of virtualized resource allocation
Recommendations
Autonomic Resource Allocation in Virtualized Data Centers
ISPA '12: Proceedings of the 2012 IEEE 10th International Symposium on Parallel and Distributed Processing with ApplicationsVirtualization has been widely adopted in data centers for improving efficiency and flexibility. Multiple applications are co-hosted in virtualized data centers. In order to meet the Service Level Agreements (SLA), how to allocate resources for multiple ...
Revenue Driven Resource Allocation for Virtualized Data Centers
ICAC '15: Proceedings of the 2015 IEEE International Conference on Autonomic ComputingThe increasing VM density in cloud hosting services makes careful management of physical resources such as CPU, memory, and I/O bandwidth within individual virtualized servers a priority. To maximize cost-efficiency, resource management needs to be ...
Resource Allocation in Contending Virtualized Environments through VM Performance Modeling and Feedback
CHINAGRID '11: Proceedings of the 2011 Sixth Annual ChinaGrid ConferenceWith active deployment of virtualization in large scale data centers and cloud computing environments, allocation and scheduling of virtual and physical resources raise more challenges and may have negative impacts on system performance due to: (1) the ...
Comments