ABSTRACT
In this paper, we propose the use of surrogate models to avoid or limit violations of the service level agreements (protect SLAs) of enterprise applications executed within virtualized data centers (VDCs).
Modern enterprise services are delivered along with service level agreements (SLAs) that formalize the expected quality of service, and define penalties in case of violations. By deploying enterprise applications within VDCs, providers can dynamically change the execution configuration of the services to react to unplanned environmental conditions, like sudden changes in the workload mix and intensity, with the goal of avoiding SLA violations while reducing operational costs with respect to traditional over-provisioning solutions.
Surrogate models are successfully used in modern engineering to approximate systems' behavior, and thus support a wide scope of activities, especially design optimization. In this paper, we show that by reducing the problem of protecting SLAs in VDCs to an optimization problem, we can adapt surrogate models to this new framework and implement SLA protection controller components. In the paper, we present the main ideas, we illustrate how surrogate models can be used to protect SLAs, and we discuss preliminary results obtained on a case study deployed in an industrial virtualized infrastructure.
- D. Ardagna, C. Ghezzi, and R. Mirandola. Rethinking the use of models in software architecture. In Proc. of International Conference Series on the Quality of Software Architectures, pages 1--27, 2008. Google ScholarDigital Library
- Y. Brun, G. D. M. Serugendo, C. Gacek, H. Giese, H. M. Kienle, M. Litoiu, H. A. Müller, M. Pezzè, and M. Shaw. Engineering self-adaptive systems through feedback loops. In Software Engineering for Self-Adaptive Systems, pages 48--70, 2009. Google ScholarDigital Library
- S. Duan and S. Babu. Proactive identification of performance problems. In Proc. of ACM SIGMOD international conference on Management of data, pages 766--768, 2006. Google ScholarDigital Library
- R. B. Gramacy, H. K. H. Lee, and W. G. Macready. Parameter space exploration with gaussian process trees. In Proc. of the international conference on Machine learning, pages 353--360, 2004. Google ScholarDigital Library
- IBM. An Architectural Blueprint for Autonomic Computing. Technical report, IBM, 2003.Google Scholar
- R. Jin, X. Du, and W. Chen. The use of metamodeling techniques for optimization under uncertainty. Structural and Multidisciplinary Optimization, 25(2):99--116, 2003.Google ScholarCross Ref
- G. Jung, K. Joshi, M. Hiltunen, R. Schlichting, and C. Pu. Generating adaptation policies for multi-tier applications in consolidated server environments. In Proc. of International Conference on Autonomic Computing, pages 23--32, 2008. Google ScholarDigital Library
- J. O. Kephart and D. M. Chess. The vision of autonomic computing. IEEE Computer, 36(1):41--50, 2003. Google ScholarDigital Library
- P. Leitner, B. Wetzstein, F. Rosenberg, A. Michlmayr, S. Dustdar, and F. Leymann. Runtime prediction of service level agreement violations for composite services. In Proc. of the Workshop on Non-Functional Properties and SLA Management in Service-Oriented Computing, 2009. Google ScholarDigital Library
- G. Mariani, G. Palermo, C. Silvano, and V. Zaccaria. Meta-model assisted optimization for design space exploration of multi-processor systems-on-chip. In Proc. of Euromicro Conference on Digital System Design, pages 383--389, 2009. Google ScholarDigital Library
- D. C. Montgomery. Design and Analysis of Experiments. Wiley, 2006. Google ScholarDigital Library
- S. Parekh, N. Gandhi, J. Hellerstein, D. Tilbury, T. Jayram, and J. Bigus. Using control theory to achieve service level objectives in performance management. Real-Time Syst., 23(1/2):127--141, 2002. Google ScholarDigital Library
- The Reservoir Seed Team. Reservoir - An ICT infrastructure for reliable and effective delivery of services as utilities. Technical Report H-0262, IBM Research Division, 2008.Google Scholar
- B. Urgaonkar, G. Pacifici, P. Shenoy, M. Spreitzer, and A. Tantawi. Analytic modeling of multitier internet applications. ACM Transactions on the Web, 1(1):2--37, 2007. Google ScholarDigital Library
- W. van Beers and J. Kleijnen. Kriging interpolation in simulation: a survey. In Proc. of conference on Winter simulation, pages 113--121, 2004. Google ScholarDigital Library
- G. G. Wang and S. Shan. Review of metamodeling techniques in support of engineering design optimization. Mechanical Design, 129(4):370--380, 2007.Google ScholarCross Ref
- Y. Wang, M. J. Rutherford, A. Carzaniga, and A. L. Wolf. Automating experimentation on distributed testbeds. In Proc. of International Conference on Automated Software Engineering, pages 164--173, 2005. Google ScholarDigital Library
- M. Woodside, T. Zheng, and M. Litoiu. Service system resource management based on a tracked layered performance model. In Proc. of International Conference on Autonomic Computing, pages 175--184, 2006. Google ScholarDigital Library
- X. Zhu, M. Uysal, Z. Wang, S. Singhal, A. Merchant, P. Padala, and K. Shin. What does control theory bring to systems research? ACM SIGOPS Operating Systems Review, 43(1):62--69, 2009. Google ScholarDigital Library
Index Terms
- Protecting SLAs with surrogate models
Recommendations
Dynamic SLAs management in service oriented environments
The increasing adoption of service oriented architectures across different administrative domains, forces service providers to use effective mechanisms and strategies of resource management in order for them to be able to guarantee the quality levels ...
Monitoring Dependencies for SLAs: The MoDe4SLA Approach
SCC '08: Proceedings of the 2008 IEEE International Conference on Services Computing - Volume 1In service oriented computing different techniques for monitoring Service Level Agreements (SLAs) are available. Many of these monitoring approaches focus on bilateral agreements between partners. However, when monitoring composite services it is not ...
SLAs for cloud applications: agreement protocol and REST-based implementation
Users with critical data are still reluctant to move apps and data to commercial clouds, showing a substantial lack of trust in providers. Possible risks linked to availability, performance and security may be mitigated by the adoption of Service Level ...
Comments