Abstract
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 at the complexity of the workloads and presents algorithms for computing the bounds of performance metrics for distributed systems under asymptotic and nonasymptotic conditions, that is, with saturated and nonsaturated resources. The techniques used are hybrid in nature, making use of performance evaluation and linear and nonlinear programming models. The workloads are characterized by the workload intensity, which represents the total number of users in the system, and by the workload mixes, which depict the number of users in each class of service. The results presented in this article can be applied to distributed transactional systems. Such systems serve a large number of users with many classes of services and can thus be considered as representative of a large class of autonomic computing systems.
- Apera. 2006. Application performance evaluation and resource allocator. http://www.alpha works.ibm.com/tech/apera.Google Scholar
- Tomcat, Application Server. 2006. http://tomcat.apache.org/.Google Scholar
- Balbo, G. And Serazzi, G. 1997. Asymptotic analysis of multiclass closed queuing networks: Multiple bottlenecks. Perform. Eval. J. 30, 115--152. Google ScholarDigital Library
- Bazaraa, M. S., Sherali, H. D., and Shetty, C. M. 1993. Nonlinear Programming. John Wiley.Google Scholar
- Chvatal, V. 1983. Linear Programming. W. H. Freeman and Company.Google Scholar
- Chen, J., Amza, C., and Soundararajan, G. 2006. Autonomic provisioning for backend databases in dynamic content Web servers. In Proceedings of the IEEE International Conference on Autonomic Computing. Dublin, Ireland, 221--231. Google ScholarDigital Library
- Eager, D. L. and Sevcik, K. C. 1983. Performance bound hierarchies for queuing networks. ACM Trans. Comput. Syst. 1, 2, 99--115. Google ScholarDigital Library
- Hellerstein, J., Diao, Y., Parech, S., and Tilbury, D. 2004. Feedback Control of Computing Systems. Wiley. Google ScholarDigital Library
- Kephart, J. O. and Chess, D. M. 2003. The vision of automatic computing. IEEE Comput. 36, 1, 41--52. Google ScholarDigital Library
- Lazowska, E. D., Zahorjan, J., Graham J., and Sevcik, K. 1984. Quantitative System Performance, Computer Systems Analysis Using Queuing Network Models. Prentice-Hall. Google ScholarDigital Library
- Litoiu, M., Rolia, J., and Serazzi, G. 2000. Designing process replication and activation, a quantitative approach. IEEE Trans. Softw. Eng. 26, 12, 1168--1178. Google ScholarDigital Library
- Litoiu, M., Zheng, T., and Woodside, M. 2005. Hierarchical model-based autonomic control of software systems. In Proceedings of the Workshop on Design and Evolution of Autonomic Application Software (DEAS'05). St. Louis, MO. Google ScholarDigital Library
- Lu, Y., Abdelzaher, T., Lu, C., Sha, L., and Liu, X. 2003. Feedback control with queueing-theoretic prediction for relative delay guarantees in Web servers. Real-Time and Embedded Technology and Applications Symposium. Toronto, Canada. Google ScholarDigital Library
- Menasce, D. A. and Bennani M. 2003. On the use of performance models to design self-managing computer systems. In Proceedings of the Computer Measurement Group Conference. Dallas. TX.Google Scholar
- Mcmullen, P. 1970. The maximum number of faces in a convex polytope. Matematika 17, 179--184.Google ScholarCross Ref
- Munz, R. R. and Wong, J. 1974. Asymptotic properties of closed queuing networks. In Proceedings of the 8th Annual Princeton Conference on Information Sciences and Systems. Princeton University.Google Scholar
- Reiser, M. and Lavenberg, S. S. 1980. Mean value analysis of closed multichain queuing networks. J. ACM 27, 2, 313--322. Google ScholarDigital Library
- JMX, Java Management Extension. 2006. http://java.sun.com/products/JavaManagement/.Google Scholar
- J2EE, Java 2 Platform, Enterprise Edition. 2006. http://java.sun.com/j2ee/.Google Scholar
- Zahorjan, J., Sevcik, K. C., Eager, D. L., and Galler, B. 1982. Balanced job bound analysis of queuing networks. Commu. ACM 25, 2, 134--141. Google ScholarDigital Library
- Zheng, T., Yang, J., Woodside, M., Litoiu, M., and Iszlai, G. 2005. Tracking time-varying parameters in software systems with extended Kalman filters. In Proceedings of CASCON '05. Toronto, Canada. Google ScholarDigital Library
- Woodside, M., Zheng, T., and Litoiu, M. 2005. The use of optimal filters to track parameters of performance models. In Proceedings of the 2nd International Conference on Quantitative Evaluation of Systems (QEST05). Torino, Italy. Google ScholarDigital Library
- Woodside, M., Litoiu, M., and Zheng, T. 2006. Service system resource management based on a tracked layered performance model. In Proceedings of IEEE International Conference on Autonomic Computing. Dublin, Ireland, 175--187. Google ScholarDigital Library
Index Terms
- A performance analysis method for autonomic computing systems
Recommendations
QoS-Aware Autonomic Resource Management in Cloud Computing: A Systematic Review
As computing infrastructure expands, resource management in a large, heterogeneous, and distributed environment becomes a challenging task. In a cloud environment, with uncertainty and dispersion of resources, one encounters problems of allocation of ...
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 ...
Comments