Power-aware performance management of virtualized enterprise servers via robust adaptive control

详细信息    查看全文

• 作者：Xiaoyu Shi (1)
  Christopher A. Briere (2)
  Seddik M. Djouadi (2)
  Yefu Wang (2)
  Yong Feng (3)
  
  1. School of Computer Science & Engineering ; University of Electronic Science and Technology of China ; Chengdu ; 611731 ; Sichuan ; China
  2. Department of Electrical Engineering and Computer Science ; University of Tennessee ; Knoxville ; TN ; 37996 ; USA
  3. Chongqing Institute of Green and Intelligent Technology ; Chinese Academy of Science ; Chongqing ; 400714 ; China
  
• 关键词：Virtualization ; Power efficiency ; Performance management ; Robust control ; Server
• 刊名：Cluster Computing
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：18
• 期：1
• 页码：419-433
• 全文大小：1,398 KB
• 参考文献：1. Sugerman, J., Venkitachalam, G., Lim, B.H.: Virtualizing I/O devices on VMware workstations hosted virtual machine monitor. In: Proceedings of USENIX Annual Technical Conference, General Track, pp. 1鈥?4 (2002)
  2. Barham, P., Dragovic, B., Fraser, K., Hand, S., Harris, T., Ho, A., Neugebauer, R., Pratt I., Warfield, A.: Xen and the art of virtualization. In: Proceedings of the 19th ACM Symposium on Operating Systems Principles (SOSP鈥?3), Lake George, New York, 19鈥?2 October 2003, pp. 164鈥?77 (2003)
  3. http://www.microsoft.com/windowsserversystem/virtualserver
  4. Zhuravlev, S, Blagodurov, S, Fedorova, A (2010) Addressing shared resource contention in multicore processors via scheduling. ACM SIGARCH Comput. Arch. News 38: pp. 129-142 CrossRef
  5. Koh, Y., Knauerthase, R., Brett, P., Bowman, M., Wen, Z., Pu, C.: An analysis of performance interference effects in virtual environments, In Proceedings of IEEE International Symposium on Performance Analysis of Systems Software (ISPASS), pp. 200鈥?09 (2007)
  6. United States Environmental Protection Agency.: Report to congress on server and data center energy efficiency (2007)
  7. Huebscher, MC, McCann, JA (2008) A survey of autonomic computing: degrees, models, and applications. ACM Comput. Surv. (CSUR) 40: pp. 7 CrossRef
  8. Gmach, D., Rolia, J., Cherkasova, L.: Resource and virtualization costs up in the cloud: models and design choices. In Proceedings of 2011 IEEE/IFIP 41st International Conference on Dependable Systems & Networks (DSN), pp. 395鈥?02 (2011)
  9. Lu, C, Lu, Y, Abdelzaher, TF, Stankovic, JA, Son, SH (2006) Feedback control architecture and design methodology for service delay guarantees in web servers. IEEE Trans. Parallel Distrib. Syst. 17: pp. 1014-1027 CrossRef
  10. Kumar, PR (1983) Optimal adaptive control of linear-quadratic-Gaussian systems. SIAM J. Control Optim. 21: pp. 163-178 CrossRef
  11. Sueur, L.E., Heiser, G.: Dynamic voltage and frequency scaling: the laws of diminishing returns. In: Proceedings of the 2010 international conference on Power aware computing and systems (USENIX), pp. 1鈥? (2010)
  12. Wang, Y, Wang, X, Chen, M, Zhu, X (2011) PARTIC: power-aware response time control for virtualized web servers. IEEE Trans. Parallel Distrib. Syst. (TPDS) 22: pp. 323-336 CrossRef
  13. Ljung, L (1999) System identification: theory for the user. Prentice Hall, New Jersey
  14. http://wiki.xen.org/wiki/Credit_Scheduler
  15. Niedzwiecki, M (2000) Identification of time-varying processes. Wiley, New York
  16. Campi, MC (1996) The problem of pole-zero cancellation in transfer function identification and application to adaptive stabilization. Automatica 32: pp. 849-857 CrossRef
  17. Prandini, M, Campi, MC (2000) Adaptive LQG control of input鈥搊utput systems: a cost-biased approach. SIAM J. Control Optim. 39: pp. 1499-1519 CrossRef
  18. Becker, J, Arthur, PK, Wei, C (1985) Adaptive control with the stochastic approximation algorithm: geometry and convergence. IEEE Trans. Autom. Control 30: pp. 330-338 CrossRef
  19. Prandini, M.: Adaptive linear quardratic gaussian control: optimality analysis and robust controller design. Doctoral dissertation, Ph.D. thesis, University of Brescia (1998)
  20. Vidyasagar, M (2001) Randomized algorithm for robust ontroller synthesis using statistical learning theory. Automatica 37: pp. 1515-1528 CrossRef
  21. Green, M, Limebeer, DJ (2012) Linear robust control. dover, Mineola
  22. Kusic, D, Kephart, JO, Hanson, JE, Kandasamy, N, Jiang, G (2009) Power and performance management of virtualized computing environments via lookahead control. Clust. Comput. 12: pp. 1-15 CrossRef
  23. Wang, X, Wang, Y (2011) Coordinating power control and performance management for virtualized enterprise servers. IEEE Trans. Parallel Distrib. Syst. (TPDS) 22: pp. 245-259 CrossRef
  24. Padala, P., Hou, K., Shin. K.G., Zhu, X., Uysal, M., Wang, Z., Singhal, S., Merchant, A.: Automated control of multiple virtulized resources. In: Proceedings of the 4th ACM European Conference on Computer Systems, pp. 13鈥?6 (2009)
  25. Gong, J., Cheng, Z.: VPnP:Automated coordination of power and performance in virtualized datacenters. In Proceedings of the 18th IEEE International Workshop on Quality of Service (IWQoS), pp. 1鈥? (2010)
  26. Lama, P., Zhou, X.: PERFUME: power and performance guarantee with fuzzy mimo control in virtualized servers. In: Proceedings of the 19th IEEE International Workshop on Quality of Service (IWQoS), pp. 1鈥? (2011)
  27. Arlitt, M, Jin, T (2000) A workload characterization study of the 1998 world cup web site. IEEE Netw. 14: pp. 30-37 CrossRef
  28. Karamanolis, C., Karlsson, M., Zhu, X.: Designing controllable computer systems. In: Proceedings of the 10th Conference on Hot Topics in Operating Systems (HotOS鈥?5), p. 9 (2005)
  29. Lu, C, Wang, X, Koutsoukos, X (2005) Feedback utilization control in distributed real-time systems with end-to-end tasks. IEEE Trans. Parallel Distrib. Syst. (TPDS) 16: pp. 550-561 CrossRef
  30. Abdelzaher, TF, Shin, KG, Bhatti, N (2002) Performance guarantees for web server end-systems: a control-theoretical approach. IEEE Trans. Parallel Distribut. Syst. (TPDS) 13: pp. 80-96 CrossRef
  31. Gandhi, A, Mor, HB, Das, R, Lefurgy, C (2009) Optimal power allocation in server farms. ACM SIGMETRICS Perform. Eval. Rev. 37: pp. 157-168
  32. Wang, X., Chen, M.: Cluster-level feedback power control for performance optimization. In: Proceedings of 14th IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 101鈥?10 (2008)
  33. Jung, G., Hiltunen, M.A., Joshi, K.R., Schlichting, R.D., Pu, C.: Mistral: dynamically managing power, performance, and adaptation cost in cloud infrastructures. In: Proceedings of the 30th International Conference on Distributed Computing Systems (ICDCS), pp. 62鈥?3 (2010)
  34. Padala, P, Shin, KG, Zhu, X, Uysal, M, Wang, Z, Singhal, S, Merchant, A, Salem, K (2007) Adaptive control of virtualized resources in utility computing environments. ACM SIGOPS Oper. Syst. Rev. 41: pp. 289-302 CrossRef
  35. Nathuji, R, Schwan, K (2007) VirtualPower: coordinated power management in virtualized enterprise systems. ACM SIGOPS Oper. Syst. Rev. 41: pp. 265-278 CrossRef
  36. Lim, M.Y., Rawson, F., Bletsch, T., Freeh, V.W.: Padd: power aware domain distribution. In: Proceedings of 29th IEEE International Conference on Distributed Computing Systems (ICDCS), pp. 239鈥?47 (2009)
  37. Verma, A., Puneet, A., Anindya, N.: pMapper: power and migration cost aware application placement in virtualized systems. In: Middleware 2008, pp. 243鈥?64. Springer, Berlin(2008)
  38. http://www.wattsupmeters.com
  
• 刊物类别：Computer Science
• 刊物主题：Processor Architectures
  Operating Systems
  Computer Communication Networks
  
• 出版者：Springer Netherlands
• ISSN：1573-7543

文摘

Virtualization technology provides a promising approach for efficiently managing the power and performance of enterprise servers. Previous studies on using control theory in a virtualized environment have mostly emphasized deterministic control policies or relied on models that were trained offline for specific workloads. In this paper, we demonstrate that these solutions may suffer from deficiencies when workload variations cause uncertain alterations in the system models. We propose a robust control architecture based on a robust adaptive control theory that simultaneously guarantees power and meets performance specifications with flexible tradeoffs even in the face of highly dynamic, bursty workloads. In order to overcome the shortcomings of existing control approaches and to free systems from the ill effects of inaccurate system models, an adaptive Linear Quadratic Gaussian algorithm with stochastic method is adopted and integrated into our control design. Experiments on our testbed server with a variety of workload patterns demonstrate both that our control method outperforms existing control solutions under dynamical workloads in terms of control accuracy and power savings, and that it is robust against workloads that occur in short, intense bursts.