Abstract
Dynamic capacity provisioning is a useful technique for handling the multi-time-scale variations seen in Internet workloads. In this article, we propose a novel dynamic provisioning technique for multi-tier Internet applications that employs (1) a flexible queuing model to determine how much of the resources to allocate to each tier of the application, and (2) a combination of predictive and reactive methods that determine when to provision these resources, both at large and small time scales. We propose a novel data center architecture based on virtual machine monitors to reduce provisioning overheads. Our experiments on a forty-machine Xen/Linux-based hosting platform demonstrate the responsiveness of our technique in handling dynamic workloads. In one scenario where a flash crowd caused the workload of a three-tier application to double, our technique was able to double the application capacity within five minutes, thus maintaining response-time targets. Our technique also reduced the overhead of switching servers across applications from several minutes to less than a second, while meeting the performance targets of residual sessions.
- Abdelzaher, T. and Bhatti, N. 1999. Web content adaptation to improve server overload behavior. In Proceedings of the World Wide Web Conference (WWW8). Tornoto. Google ScholarDigital Library
- Abdelzaher, T., Shin, K. G., and Bhatti, N. 2002. Performance guarantees for Web server end-systems: A control-theoretical approach. IEEE Trans. Para. Distrib. Syst. 13, 1 (Jan.). Google ScholarDigital Library
- AMAZON. 2000. The Holiday Shopping Season, So Far. http://www.fool.com/news/2000/wmt001127.htm.Google Scholar
- Appleby, K., Fakhouri, S., Fong, L., Goldzmidt, M. K. G., Krishnakumar, S., Pazel, D., Pershing, J., and Rochwerger, B. 2001. Oceano---SLA-based management of a computing utility. In Proceedings of the IFIP/IEEE Symposium on Integrated Network Management.Google Scholar
- Arlitt, M. and Jin, T. 1999. Workload characterization of the 1998 World Cup Web site. Tech. Rep. HPL-1999-35R1, HP Labs.Google Scholar
- Aron, M., Druschel, P., and Zwaenepoel, W. 2000. Cluster reserves: A mechanism for resource management in cluster-based network servers. In Proceedings of the ACM SIGMETRICS Conference. Santa Clara, CA. Google ScholarDigital Library
- Barham, P., Dragovic, B., Fraser, K., Hand, S., Harris, T., Ho, A., Neugebuer, R., Pratt, I., and Warfield, A. 2003. Xen and the art of virtulization. In Proceedings of the Nineteenth Symposium on Operating Systems Principles (SOSP). Google ScholarDigital Library
- Benani, M. and Menasce, D. 2005. Resource allocation for autonomic data centers using analytic performance models. In Proceedings of the IEEE International Conference on Autonomic Computing, Seattle (ICAC-05). WA. Google ScholarDigital Library
- Chandra, A., Gong, W., and Shenoy, P. 2003. Dynamic resource allocation for shared data centers using online measurements. In Proceedings of the Eleventh International Workshop on Quality of Service (IWQoS 2003). Monterey, CA. Google ScholarDigital Library
- Chase, J. and Doyle, R. 2001. Balance of power: Energy management for server clusters. In Proceedings of the Eighth Workshop on Hot Topics in Operating Systems (HotOS-VIII). Elmau, Germany. Google ScholarDigital Library
- Chase, J., Grit, L., Irwin, D., Moore, J., and Sprenkle, S. 2003. Dynamic virtual clusters in a grid site manager. In Twelfth International Symposium on High Performance Distributed Computing (HPDC-12). Google ScholarDigital Library
- Cherkasova, L. and Phaal, P. 1999. Session-based admission control: A mechanism for improving performance of commercial Web sites. In Proceedings of the Seventh International Workshop on Quality of Service, IEEE/IFIP Event. London.Google Scholar
- Cohen, I., Chase, J., Goldszmidt, M., Kelly, T., and Symons, J. 2004. Correlating instrumentation data to system states: A building block for automated diagnosis and control. In Proceedings of the Sixth USENIX Symposium in Operating Systems Design and Implementation (OSDI 2004). San Francisco, CA. Google ScholarDigital Library
- Doyle, R., Chase, J., Asad, O., Jin, W., and Vahdat, A. 2003. Model-based resource provisioning in a Web service utility. In Proceedings of the Fourth USITS. Google ScholarDigital Library
- DYNASERVER. 2005. Dynaserver project. http://compsci.rice.edu/CS/Systems/DynaServer/.Google Scholar
- Elnikety, S., Nahum, E., Tracey, J., and Zwaenepoel, W. 2004. A method for transparent admission control and request scheduling in e-commerce Web sites. In Proceedings of the Thirteenth International Conference on the World Wide Web. New York, NY. 276--286. Google ScholarDigital Library
- Fox, A., Gribble, S., Chawathe, Y., Brewer, E., and Gauthier, P. 1997. Cluster-based scalable network services. In Proceedings of the Sixteenth Symposium on Operating Systems Principles (SOSP'97). Google ScholarDigital Library
- Franks, R. G. 1999. Performance analysis of distributed server systems. Ph.D. Dissertation, Carleton University. Google ScholarDigital Library
- Goldberg, R. 1974. Survey of virtual machine research. IEEE Comput. 34--45.Google Scholar
- Hellerstein, J., Zhang, F., and Shahabuddin, P. 1999. An approach to predictive detection for service management. In Proceedings of the IEEE International Conference on Systems and Network Management.Google Scholar
- Iyer, R., Tewari, V., and Kant, K. 2000. Overload control mechanisms for Web servers. In Workshop on Performance and QoS of Next Generation Networks.Google Scholar
- Jamjoom, H., Reumann, J., and Shin, K. 2000. QGuard: Protecting Internet servers from overload. Tech. rep., CSE-TR-427-00, Department of Computer Science, University of Michigan.Google Scholar
- Kamra, A., Misra, V., and Nahum, E. 2004. Yaksha: A controller for managing the performance of 3-tiered Websites. In Proceedings of the Twelfth IWQoS.Google Scholar
- Kanodia, V. and Knightly, E. 2000. Multi-class latency-bounded Web servers. In Proceedings of International Workshop on Quality of Service (IWQoS'00).Google Scholar
- Kleinrock, L. 1976. Queueing Systems, Volume 2: Computer Applications. John Wiley and Sons, Inc.Google Scholar
- Kounev, S. and Buchmann, A. 2003. Performance modeling and evaluation of large-scale J2EE applications. In Proceedings of the Computer Measurement Group's 2003 International Conference (CMG 2003). Dallas, TX.Google Scholar
- Knightly, E. and Shroff, N. 1999. Admission control for statistical QoS: Theory and practice. In IEEE Netw. 13, 2, 20--29. Google ScholarDigital Library
- KTCPVS. 2005. Kernel TCP Virtual Server. http://www.linuxvirtualserver.org/software/ktcpvs/ktcpvs.html.Google Scholar
- Levy, R., Nagarajarao, J., Pacifici, G., Spreitzer, M., Tantawi, A., and Youssef, A. 2003. Performance management for cluster based Web services. In IFIP/IEEE Eighth International Symposium on Integrated Network Management. vol. 246, 247--261.Google Scholar
- Li, S. and Jamin, S. 2000. A Measurement-based admission-controlled Web server. In Proceedings of the Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM 2000). Tel Aviv, Israel.Google Scholar
- Liu, T.-K., Kumaran, S., and Luo, Z. 2001. Layered queueing models for enterprise Java Beans applications. Tech. rep., IBM. (June).Google Scholar
- Menasce, D. 2003. Web server software architectures. In IEEE Internet Comput. vol. 7. Google ScholarDigital Library
- ORACLE9I. 2005. Oracle9i. http://www.oracle.com/technology/products/oracle9i.Google Scholar
- Pai, V., Aron, M., Banga, G., Svendsen, M., Druschel, P., Zwanepoel, W., and Nahum, E. 1998. Locality-aware request distribution in cluster-based network servers. In Proceedings of the Eighth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS-VIII). San Jose, CA. Google ScholarDigital Library
- Ranjan, S., Rolia, J., Fu, H., and Knightly, E. 2002. QoS-driven server migration for Internet data centers. In Proceedings of the Tenth International Workshop on Quality of Service. Miami, FL.Google Scholar
- Rolia, J. and Sevcik, K. 1995. The method of layers. IEEE Trans. Softw. Eng. 21, 8, 689--700. Google ScholarDigital Library
- Rolia, J., Zhu, X., Arlitt, M., and Andrzejak, A. 2002. Statistical service assurances for applications in utility grid environments. Tech. rep. HPL-2002-155, HP Labs.Google Scholar
- Saito, Y., Bershad, B., and Levy, H. 1999. Manageability, availability and performance in Porcupine: A highly scalable, cluster-based mail service. In Proceedings of the Seventeenth Symposium on Operating Systems Principles (SOSP'99). Google ScholarDigital Library
- SAR. 2005. Sysstat Package. http://freshmeat.net/projects/sysstat.Google Scholar
- Schroeder, B. and Harchol-Balter, M. 2003. Web servers under overload: How scheduling can help. In Proceedings of the Eighteenth International Teletraffic Congress.Google Scholar
- Shen, K., Tang, H., Yang, T., and Chu, L. 2002. Integrated resource management for cluster-based Internet services. In Proceedings of the Fifth USENIX Symposium on Operating Systems Design and Implementation (OSDI). Boston, MA. Google ScholarDigital Library
- Slothouber, L. 1996. A model of Web server performance. In Proceedings of the Fifth International World Wide Web Conference.Google Scholar
- Urgaonkar, B., Pacifici, G., Shenoy, P., Spreitzer, M., and Tantawi, A. 2005. An analytical model for multi-tier Internet services and its applications. In Proceedings of the ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2005). Banff, Canada. Google ScholarDigital Library
- Urgaonkar, B. and Shenoy, P. 2004a. Cataclysm: Handling extreme overloads in Internet services. In Proceedings of the Twenty-Third Annual ACM SIGACT-SIGOPS Symposium on Principles of Distributed Computing (PODC 2004). St. John's, Newfoundland, Canada. Google ScholarDigital Library
- Urgaonkar, B. and Shenoy, P. 2004b. Sharc: Managing CPU and network bandwidth in shared clusters. In IEEE Trans. Para. Distrib. Syst. 15, 1, 2--17. Google ScholarDigital Library
- Urgaonkar, B., Shenoy, P., and Roscoe, T. 2002. Resource overbooking and application profiling in shared hosting platforms. In Proceedings of the Fifth USENIX Symposium on Operating Systems Design and Implementation (OSDI 2002). Boston, MA. Google ScholarDigital Library
- Verma, A. and Ghosal, S. 2003. On admission control for profit maximization of networked service providers. In Proceedings of the 12th International World Wide Web Conference (WWW2003). Budapest, Hungary. Google ScholarDigital Library
- Villela, D., Pradhan, P., and Rubenstein, D. 2004. Provisioning servers in the application tier for e-commerce systems. In Proceedings of the Twelfth IWQoS.Google Scholar
- Voigt, T., Tewari, R., Freimuth, D., and Mehra, A. 2001. Kernel mechanisms for service differrentiation in overloaded Web servers. In Proceedings of USENIX Annual Technical Conference. Google ScholarDigital Library
- Welsh, M. and Culler, D. 2003. Adaptive overload control for busy Internet servers. In Proceedings of the Fourth USENIX Conference on Internet Technologies and Systems (USITS'03). Google ScholarDigital Library
- Welsh, M., Culler, D., and Brewer, E. 2001. SEDA: An architecture for well-conditioned, scalable Internet services. In Proceedings of the 18th Symposium on Operating Systems Principles (SOSP'01). Google ScholarDigital Library
- Woodside, C. and Raghunath, G. 1995. General bypass architecture for high-performance distributed algorithms. In Proceedings of the Sixth IFIP Conference on Performance of Computer Networks. Istanbul, Turkey. Google ScholarDigital Library
- WSLA. http://www.research.ibm.com/wsla. Web service level agreements (wsla) project.Google Scholar
- Xu, J., Oufimtsev, A., Woodside, M., and Murphy, L. 2006. Performance modeling and prediction of enterprise JavaBeans with layered queuing network templates. SIGSOFT Softw. Eng. Notes 31, 2. Google ScholarDigital Library
Index Terms
- Agile dynamic provisioning of multi-tier Internet applications
Recommendations
Performance modeling and analysis of virtualized multi-tier applications under dynamic workloads
Virtual machine technology facilitates implementation of modern Internet services, especially multi-tier applications. Server virtualization aims to reduce the cost of service provisioning and improve fault tolerance, portability and security of ...
Sandpiper: Black-box and gray-box resource management for virtual machines
Virtualization can provide significant benefits in data centers by enabling dynamic virtual machine resizing and migration to eliminate hotspots. We present Sandpiper, a system that automates the task of monitoring and detecting hotspots, determining a ...
An analytical model for multi-tier internet services and its applications
SIGMETRICS '05: Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systemsSince many Internet applications employ a multi-tier architecture, in this paper, we focus on the problem of analytically modeling the behavior of such applications. We present a model based on a network of queues, where the queues represent different ...
Comments