ABSTRACT
Horizontally scalable Internet services present an opportunity to use automatic resource allocation strategies for system management in the datacenter. In most of the previous work, a controller employs a performance model of the system to make decisions about the optimal allocation of resources. However, these models are usually trained offline or on a small-scale deployment and will not accurately capture the performance of the controlled application. To achieve accurate control of the web application, the models need to be trained directly on the production system and adapted to changes in workload and performance of the application. In this paper we propose to train the performance model using an exploration policy that quickly collects data from different performance regimes of the application. The goal of our approach for managing the exploration process is to strike a balance between not violating the performance SLAs and the need to collect sufficient data to train an accurate performance model, which requires pushing the system close to its capacity. We show that by using our exploration policy, we can train a performance model of a Web 2.0 application in less than an hour and then immediately use the model in a resource allocation controller.
- J. Allspaw. The Art of Capacity Planning: Scaling Web Resources. O'Reilly Media, Inc., 2008. Google ScholarDigital Library
- S. Babu, N. Borisov, S. Duan, H. Herodotou, and V. Thummala. Automated experiment-driven management of (database) systems. In HotOS, 2009. Google ScholarDigital Library
- M. N. Bennani and D. A. Menasce. Resource allocation for autonomic data centers using analytic performance models. In ICAC, 2005. Google ScholarDigital Library
- P. Bodík, G. Friedman, L. Biewald, H. Levine, G. Candea, K. Patel, G. Tolle, J. Hui, A. Fox, M. I. Jordan, and D. Patterson. Combining visualization and statistical analysis to improve operator confidence and efficiency for failure detection and localization. In ICAC, 2005.Google ScholarDigital Library
- J. Chase, D. C. Anderson, P. N. Thakar, A. M. Vahdat, and R. P. Doyle. Managing energy and server resources in hosting centers. In Symposium on Operating Systems Principles (SOSP), 2001. Google ScholarDigital Library
- D. Kusic, J. O. Kephart, J. E. Hanson, N. Kandasamy, and G. Jiang. Power and performance management of virtualized computing environments via lookahead control. In ICAC'08: Proceedings of the 2008 International Conference on Autonomic Computing, pages 3--12, Washington, DC, USA, 2008. IEEE Computer Society. Google ScholarDigital Library
- X. Liu, J. Heo, L. Sha, and X. Zhu. Adaptive control of multi-tiered web applications using queueing predictor. Network Operations and Management Symposium, 2006. NOMS 2006. 10th IEEE/IFIP, pages 106--114, April 2006.Google Scholar
- P. Shivam, S. Babu, and J. Chase. Active sampling for accelerated learning of performance models. In SysML, 2006.Google Scholar
- P. Shivam, V. Marupadi, J. Chase, T. Subramaniam, and S. Babu. Cutting corners: Workbench automation for server benchmarking. In USENIX, 2008. Google ScholarDigital Library
- W. Sobel, S. Subramanyam, A. Sucharitakul, J. Nguyen, H. Wong, S. Patil, A. Fox, and D. Patterson. Cloudstone: Multi-platform, multi-language benchmark and measurement tools for web 2.0, 2008.Google Scholar
- C. Stewart and K. Shen. Performance modeling and system management for multi-component online services. In NSDI, 2005. Google ScholarDigital Library
- R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning). The MIT Press, March 1998. Google ScholarDigital Library
- G. Tesauro, N. Jong, R. Das, and M. Bennani. A hybrid reinforcement learning aproach to autonomic resource allocation. In International Conference on Autonomic Computing (ICAC), 2006. Google ScholarDigital Library
- B. Urgaonkar, P. Shenoy, A. Chandra, and P. Goyal. Dynamic provisioning of multi-tier internet applications. In ICAC, 2005. Google ScholarDigital Library
- P. Vosshall. Amazon, Personal communication.Google Scholar
- L. Wasserman. All of Nonparametric Statistics (Springer Texts in Statistics). Springer-Verlag New York, Inc., Secaucus, NJ, USA, 2006. Google ScholarDigital Library
Index Terms
- Automatic exploration of datacenter performance regimes
Recommendations
Automatic performance space exploration of web applications using genetic algorithms
SAC '16: Proceedings of the 31st Annual ACM Symposium on Applied ComputingWe describe a tool-supported performance exploration approach in which we use genetic algorithms to find a potential user behavioural pattern that maximizes the resource utilization of the system under test. This work is built upon our previous work in ...
Framework for Exploration of Performance Space
NIME 2015: Proceedings of the international conference on New Interfaces for Musical ExpressionThis paper presents a framework for the analysis and exploration of performance space. It enables the user to visualize performances in relation to other performances of the same piece based on a set of features extracted from audio. A performance space ...
Comments