Dynamic resources management of virtual appliances on a computational cluster



виртуальные инструменты, вычислительные кластеры, управление ресурсами, методы оптимизации, вычислительный сервис, веб-сервис


The virtual machine (VM) technology offers an increased flexibility in resource provisioning. The load for applications typically varies over time, justifying a need for the dynamic resource allocation/relinquish mdash; exactly what the VM technology allows. We have devised an approach for the automated dynamic resource management of applications running on a computational cluster. A job of the framework is to maintain a certain service level of an application within tolerable limits. To accomplish this, the framework is able to dynamically vary resources available to the application. To facilitate the performance optimization, an application performance profile can be created using stress-testing tools. We have created a software toolkit that allows running single and multiple VM applications. Sample services (including both computing oriented and web oriented) have been tested and performance-resource dependences studied. We present an ongoing work on dynamic resource allocation, involving optimal control and optimization methods. The paper was prepared on the basis of the authors’ report at the International Conference on Parallel Computing Technologies (PaVT-2008; http://agora.guru.ru/pavt2008).

Author Biographies

A.A. Moskovsky

A.Yu. Pervin

B.J. Walker

Hewlett-Packard Laboratories
6280 America Center Dr., San Jose, California, 95002, United States


  1. Xen hypervisor (http://www.xen.org/).
  2. Keahey K., Foster I., Freeman F., Zhang X., Galron D. Virtual workspaces in the grid // Proc. of the 11th Euro-Par Conf. Lisbon, 2005 (http://workspace.globus.org/papers/VW_EuroPar05.pdf). .
  3. Yousef L., Wolski R., Gorda B., Krintz C. Paravirtualization for HPC systems // Proc. Workshop on Xen in HPC Cluster and Grid Computing Environments. Sorrento, 2006, pp. 474-486
    doi 10.1007/11942634_49
  4. Novaes R.C., Roisenberg P., Sheer R., Northfleet C., Jornado J.H., Cirne W. Non-dedicated distributed environment: a solution for safe and continuous exploitation of idle cycles // Proc. Workshop on Adaptive Grid Middleware. New Orleans, 2003.
  5. Абрамов С., Московский А., Первин А., Коряка Ф. Развертывание испытательного полигона для Grid-приложений в Переславле-Залесском // Распределенные вычисления и грид-технологии в науке и образовании. Дубна, 2006.
  6. Andersen R., Vinter B. Harvesting idle Windows CPU cycles for grid computing // Int. Conf. on Grid Computing and Application. Las-Vegas, 2006. pp. 121-126.
  7. Moore J., Irwin D., Grit L., Sprenkle S., Chase J. Managing mixed-use cluster with Cluster-on-Demand. Durham: Duke University Press, 2002.
  8. Sotomayor B. A resource management model for VM based virtual workspaces. Chicago: University of Chicago, 2007.
  9. Kallahalla M., Uysal M., Swaminathan R., Lowell D.E., Wray M., Christian T., Edwards N., Dalton C.I., Gittler F. SoftUDC: a software-based data center for utility computing. Los Alamitos: IEEE Computer Society Press, 2004.
  10. Fu Y., Chase J., Chun B., Schwab S., Vahdat A. SHARP: An architecture for secure resource peering // ACM SIGOPS Operating Systems Review. 37, N 5. 133-148.
  11. Lai K., Rasmusson L., Adar E., Sorkin S., Zhang L., Huberman B. Tycoon: an implementation of a distributed market-based resource allocation system. Palo Alto: HP Labs, 2004.
  12. Moroni S., Jofre A., Figueroa N., Sahai A., Chen Y., Iyer S. A game-theoretic framework for Optimal SLA/Contract creation. Palo Alto: HP Labs, 2007.
  13. Bennani M., Menasce D. Resource allocation for autonomic data centers using analytic performance models // Proc. of the Second Int. Conf. on Autonomic Computing. Washington: IEEE Computer Society Press, 2005. pp. 229-240.
  14. Menasce D., Bennani M. Autonomic virtualized environment // Int. Conf. on Autonomic and Autonomous Systems. Washington: IEEE Computer Society Press, 2006.
  15. MapServer (http://mapserver.gis.umn.edu/).
  16. Воеводин Вл., Филамофитский M. Суперкомпьютер на выходные // Открытые системы. 2003. № 5. 43-48.
  17. Thain D., Livny M. Distributed computing in practice: The Condor Experience. Concurrency and Computation // Practice and Experience. 2004. 17, N 2-4. 323-356.
  18. Абрамов С., Адамович А., Инюхин А., Московский А., Роганов В., Шевчук Ю., Шевчук E. Т-система с открытой архитектурой // Суперкомпьютерные системы и приложения. Минск: ОИПИ НАН Беларуси, 2004. 18-22.
  19. Httperf homepage (http://www.hpl.hp.com/research/linux/httperf/).
  20. Chen Y., Iyer S., Liu X., Milojicic D., Sahai A. SLA decomposition: translating service level objectives to system level threshold. Palo Alto: HP Labs, 2007.
  21. Dean J., Ghemawat S. MapReduce: simplifed data processing on large clusters // Proc. of the 6th Symposium on Operating System Design and Implementation. San Francisco, 2004



How to Cite

Московский А.А., Первин А.Ю., Walker B.J. Dynamic Resources Management of Virtual Appliances on a Computational Cluster // Numerical Methods and Programming (Vychislitel’nye Metody i Programmirovanie). 2008. 9. 32-40



Section 2. Programming