Abstract
This paper deals with a shared server environment where the server is divided into a number of resource partitions and used to host multiple applications at the same time. In a case study where the HP-UX Process Resource Manager is taken as the server partitioning technology, we investigate the technical challenges in performing automated sizing of a resource partition using a feedback control approach, where the CPU entitlement for the partition is dynamically tuned to regulate output metrics such as the CPU utilization or SLO-based application performance metric. We identify the nonlinear and bimodal properties of the models across different operating regions, and discuss their implications for the design of the control loops. To deal with these challenges, we then propose two adaptive controllers for tracking the target utilization and target response time respectively. We evaluate the performance of the closed-loop systems while varying certain operating conditions. We demonstrate that better performance and robustness can be achieved with these controllers compared with other controllers or our prior solution.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
HP Process Resource Manager, http://h30081.www3.hp.com/products/prm/index.html
IBM Application Workload Manager, http://www.ibm.com/servers/eserver/xseries/systems_management/director_4/awm.html
SUN Solaris Resource Manager, http://www.sun.com/software/resourcemgr/index.html
Liu, X., Zhu, X., Singhal, S., Arlitt, M.: Adaptive entitlement control of resource partitions on shared servers. In: 9th International Symposium on Integrated Network Management (May 2005)
Banga, G., Druschel, P., Mogul, J.C.: Resource Containers: A new facility for resource management in server systems. In: 3rd USENIX Symposium on Operating Systems Design and Implementation (February 1999)
Jones, M.B., Rosu, D., Rosu, M.-C.: CPU reservations and time constraints: Efficient, predictable scheduling of independent activities. In: 16th ACM Symposium on Operating Systems Principles (1997)
Rajkumar, R., Juvva, K., Molano, A., Oikawa, S.: Resource Kernels: A resource-centric approach to real-time and multimedia systems. In: ACM Conference on Multimedia Computing and Networking (1998)
Goyal, P., Guo, X., Vin, H.: A hierarchical CPU scheduler for multimedia operating systems. In: 2nd USENIX Symposium on Operating System Design and Implementation (October 1996)
Waldspurger, C., Weihl, W.: Lottery Scheduling: Flexible proportional-share resource management. In: 1st USENIX Symposium on Operating System Design and Implementation (1994)
Steere, D.C., et al.: A feedback-driven proportion allocator for real-rate scheduling. In: 3rd USENIX Symposium on Operating System Design and Implementation (1999)
HP-UX Workload Manager, http://h30081.www3.hp.com/products/wlm/index.html
IBM Enterprise Workload Manager, http://www.ibm.com/developerworks/autonomic/ewlm/
Hellerstein, J.L., Diao, Y., Parekh, S., Tilbury, D.: Feedback Control of Computing Systems. Wiley-Interscience, Hoboken (2004)
Abdelzaher, T.F., Lu, Y., Zhang, R., Henriksson, D.: Practical application of control theory to Web services. American Control Conference (June 2004) (invited paper)
Karlsson, M., Karamanolis, C., Zhu, X.: Triage: Performance isolation and differentiation for storage systems. In: 12th IEEE International Workshop on Quality of Service (2004)
Lu, C., Abdelzaher, T.F., Stankovic, J., Son, S.: A feedback control approach for guaranteeing relative delays in Web servers. In: IEEE Real-Time Technology and Applications Symposium (2001)
Abdelzaher, T.F., Shin, K.G., Bhatti, N.: Performance guarantees for Web server end-systems: A control-theoretical approach. IEEE Transactions on Parallel and Distributed Systems 13 (2002)
Almeida, J., Dabu, M., Manikutty, A., Cao, P.: Providing differentiated levels of service in Web content hosting. In: SIGMETRICS Workshop on Internet Server Performance (June 1998)
Eggert, L., Heidemann, J.: Application-Level differentiated services for Web servers. World Wide Web Journal 3(1), 133–142 (1999)
Kanodia, V., Knightly, E.: Multi-Class latency-bounded Web services. In: 8th IEEE International Workshop on Quality of Service (June 2000)
Bhoj, P., Ramanathan, S., Singhal, S.: Web2K: Bringing QoS to Web servers. HP Labs Technical Report, HPL-2000-61 (May 2000)
Lu, Y., Lu, C., Abdelzaher, T., Tao, G.: An adaptive control framework for QoS guarantees and its application to differentiated caching services. In: IEEE International Workshop on Quality of Service (May 2002)
Diao, Y., Gandhi, N., Hellerstein, J.L., Parekh, S., Tilbury, D.M.: MIMO control of an Apache Web server: Modeling and controller design. In: American Control Conference (2002)
Ljung, L.: System Identification: Theory for the User, 2nd edn. Prentice Hall, Englewood Cliffs (1999)
Matlab System Identification Toolbox, http://www.mathworks.com/products/sysid/
Wang, Z., Zhu, X., Singhal, S.: Utilization and SLO-Based Control for Dynamic Sizing of Resource Partitions. HP Labs Technical Report, HPL-2005-126 (July 2005)
Apache Web server, http://www.apache.org/
Astrom, K., Hagglund, T.: PID Controllers: Theory, Design, and Tuning, 2nd edn. Instrument Society of America (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 IFIP International Federation for Information Processing
About this paper
Cite this paper
Wang, Z., Zhu, X., Singhal, S. (2005). Utilization and SLO-Based Control for Dynamic Sizing of Resource Partitions. In: Schönwälder, J., Serrat, J. (eds) Ambient Networks. DSOM 2005. Lecture Notes in Computer Science, vol 3775. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11568285_12
Download citation
DOI: https://doi.org/10.1007/11568285_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29388-0
Online ISBN: 978-3-540-32244-3
eBook Packages: Computer ScienceComputer Science (R0)