Abstract
Various control algorithms are used in autonomic control to maintain Quality of Service (QoS) and Service Level Agreements (SLAs). Controllers are all based to some extent on models of the relationship between resources, QoS measures, and the workload imposed by the environment. This work discusses the range of algorithms with an emphasis on richer and more powerful models to describe non-linear performance relationships, and strong interactions among the system resources. A hierarchical framework is described which accommodates different scopes and timescales of control actions, and different control algorithms. The control algorithms and architectures can be considered in three stages: tuning, load balancing and provisioning. Different situations warrant different solutions, so this work shows how different control algorithms and architectures at the three stages can be combined to fit into different autonomic environments to meet QoS and SLAs across a large variety of workloads.
- Abdeen, M. and Woodside, C. M. Seeking Optimal Policies for Adaptive Distributed Computer Systems with Multiple Controls. Proc. Third International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT'02), Kanazawa, Japan, Sept. 2002.]]Google Scholar
- Abdelzaher, T., Shin, K. J and Bhatti, N., Performance Guarantees for Web Server End-Systems: A Control-Theoretical Approach. IEEE Transactions on Parallel and Distributed Systems, Vol. 13, No. 1, Jan 2002.]] Google ScholarDigital Library
- Åström, K. J. and Wittenmark B. Adaptive Control. 2nd edition. Addison-Wesley Publ Co, 1995.]]Google Scholar
- Diao, Y., Lui, X., Froehlich, S., Hellerstein, J. L., Parekh, S. and Sha, L. On-Line Response Time Optimization of An Apache Web Server. International Workshop on Quality of Service, 2003.]]Google ScholarDigital Library
- El-Sayed, H. E., Cameron, D. and Woodside, C. M. Automation Support for Software Performance Engineering. Proc Joint Int. Conf on Measurement and Modeling of Computer Systems (Sigmetrics 2001/Performance 2001), Cambridge, MA, June 16 -- 20, 2001, pp 301--311.]] Google ScholarDigital Library
- Franken, L. J. N. and Haverkort, B. R. Reconfiguring Distributed Systems using Markov-Decision Models. Proc. Trends in Distributed Systems (TreDS'96), Oct. 1996, pp. 219--228.]]Google Scholar
- Franks G., Majumdar, S., Neilson, J., Petriu, D., Rolia, J. and Woodside C. M. Performance Analysis of Distributed Server Systems. The Sixth International Conference on Software Quality (61CSQ), Ottawa, Ontario, 1996, pp. 15--26.]]Google Scholar
- Gandhi, N., Hellerstein, J. L., Parekh, S. and Tilbury, D. M. Managing the Performance of Lotus Notes: A Control Theoretic Approach. Proceedings of the Computer Measurement Group, 2001.]]Google Scholar
- Hellerstein, J., Diao, Y., Parech, S., Tilbury, D. Feedback Control of Computing Systems, John Wiley &Sons, Inc., 2004.]] Google ScholarDigital Library
- IBM Tivoli Intelligent Orchestrator, http://www-306.ibm.com/software/tivoli/products/intell-orch/, Jan 23, 2005.]]Google Scholar
- Litoiu, M. and Rolia, J. Object Allocation for Distributed Applications with Complex Workloads. Lecture Note in Computer Science 1786, Springer, 2000, pp 25--39.]] Google ScholarDigital Library
- Lu, Y., Abdelzaher, T., Lu, C., Sha, L. and Liu, X. Feedback Control with Queueing-Theoretic Prediction for Relative Delay Guarantees in Web Servers. Real-Time and Embedded Technology and Applications Symposium, Toronto, Canada, May 2003.]] Google ScholarDigital Library
- Menasce, D. A. and Bennani, M. On the Use of Performance Models to Design Self-Managing Computer Systems. Proc. 2003 Computer Measurement Group Conference, Dallas, TX, Dec. 7--12, 2003.]]Google Scholar
- Menasce, D. A. QoS-aware software components. IEEE Internet Computing, March/April 2004, Vol. 8, No. 2.]] Google ScholarDigital Library
- Neilson, J. E., Woodside, C. M., Petriu, D. C. and Majumdar, S. Software Bottlenecking in Client-Server Systems and Rendez-vous Networks. IEEE Trans. On Software Engineering. Vol. 21, No. 9, September 1995, pp. 776--782.]] Google ScholarDigital Library
- Rolia, J. A. and Sevcik, K. C. The Method of Layers. IEEE Trans. on Software Engineering. vol. 21, August 1995. no. 8, pp. 689--700.]] Google ScholarDigital Library
- Shin, K. G., Krishna, C. M. and Lee, Y-H. Optimal Dynamic Control of Resources in a Distributed System. IEEE Transactions on Software Engineering. Vol. 15, No. 10, October 1989.]] Google ScholarDigital Library
- Stojanovic, L., Schneider, J., Maedche, A., Libischer, S., Studer, R., Lumpp, T., Abecker, A., Breiter, G. and Dinger, J. The role of ontologies in autonomic computing systems. IBM Systems Journal, v. 43, n. 3, 2004.]] Google ScholarDigital Library
- Zheng, T. and Woodside, C. M. Heuristic Optimization of Scheduling and Allocation for Distributed Systems with Soft Deadlines. Lecture Notes in Computer Science, Springer-Verlag, vol. LNCS 2794, 2003, pp 169--181.]]Google Scholar
- Woodside, M. Tutorial Introduction to Layered Modeling of Software Performance, http://www.sce.carleton.ca/rads/lqn/lqn-documentation/, April 2005.]]Google Scholar
Index Terms
- Hierarchical model-based autonomic control of software systems
Recommendations
Hierarchical model-based autonomic control of software systems
DEAS '05: Proceedings of the 2005 workshop on Design and evolution of autonomic application softwareVarious control algorithms are used in autonomic control to maintain Quality of Service (QoS) and Service Level Agreements (SLAs). Controllers are all based to some extent on models of the relationship between resources, QoS measures, and the workload ...
Resource Provisioning Based Scheduling Framework for Execution of Heterogeneous and Clustered Workloads in Clouds: from Fundamental to Autonomic Offering
AbstractProvisioning of adequate resources to cloud workloads depends on the Quality of Service (QoS) requirements of these cloud workloads. Based on workload requirements (QoS) of cloud users, discovery and allocation of best workload-resource pair is an ...
A performance analysis method for autonomic computing systems
In an autonomic computing system, an autonomic manager makes tuning, load balancing, or provisioning decisions based on a predictive model of the system. This article investigates performance analysis techniques used by the autonomic manager. It looks ...
Comments