msiСовременная наука и инновацииModern Science and Innovations2307-910XNorth-Caucasus Federal University10.37493/2307-910X.2021.4.1msi-468Research ArticleТЕХНИЧЕСКИЕ НАУКИ. ИНФОРМАТИКА, ВЫЧИСЛИТЕЛЬНАЯ ТЕХНИКА И УПРАВЛЕНИЕTECHNICAL SCIENCES. INFORMATION, COMPUTING AND MANAGEMENTМАТЕМАТИЧЕСКАЯ МОДЕЛЬ РАСПРЕДЕЛЕНИЯ РЕСУРСОВ ВЫЧИСЛИТЕЛЬНОГО КЛАСТЕРА ОБЛАЧНЫХ ЦЕНТРОВ ОБРАБОТКИ ДАННЫХMATHEMATICAL MODEL OF RESOURCE DISTRIBUTION OF THE COMPUTING CLUSTER OF CLOUD DATA CENTERSМочаловВ. П.MochalovV. P.n.b.20062@yandex.ruЛинецГ. И.LinetsG. I.kbytw@mail.ruБратченкоН. Ю.BratchenkoN. Y.n.b.20062@yandex.ruПалкановИ. С.PalkanovI. S.n.b.20062@yandex.ruСеверо-Кавказский федеральный университетРоссияNorth-Caucasus Federal UniversityRussian Federation202104082022041022Copyright © Мочалов В.П., Линец Г.И., Братченко Н.Ю., Палканов И.С., 20222022Мочалов В.П., Линец Г.И., Братченко Н.Ю., Палканов И.С.Mochalov V.P., Linets G.I., Bratchenko N.Y., Palkanov I.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://msi.elpub.ru/jour/article/view/468

Предметом исследования являются системы распределения и балансировки нагрузки вычислительных кластеров облачных центров обработки данных (ЦОД), содержащие множество серверов, систем хранения данных, систему ввода-вывода связанных между собой коммуникационной сетью. В основе решения задачи эффективного распределения ресурсов ЦОД рассмотрен подход, в основе которого лежат эвристический жадный алгоритм с процедурой ограниченного перебора и ограничения на ресурсы его аппаратно-программного комплекса. Отмечена важность перебора, по определению максимально возможного число серверов и виртуальных машин, для которых назначается распределение. Глубина такого перебора обеспечивает необходимый баланс между качеством сервиса и временем распределения. Поэтому решение задачи распределения и балансировки нагрузки рассмотрено в виде следующих этапов: оптимального распределения программных приложений по виртуальным машинам, распределения виртуальных машин по серверам кластера ЦОД, построения схемы алгоритма балансировки нагрузки и определение основных показателей качества обработки запросов путем аналитического и имитационного моделирования. В процессе исследования проведено математическое описание системы, учитывающее состояния серверов кластера в каждый из моментов поступления заявок на обслуживание в установившемся режиме.

The subject of the study is the distribution and load balancing systems of computing clusters of cloud data centers (data centers) containing a variety of servers, data storage systems, I/O system interconnected by a communication network. The solution of the problem of efficient allocation of data center resources is based on an approach based on a heuristic greedy algorithm with a limited search procedure and restrictions on the resources of its hardware and software complex. The importance of sorting is noted, by determining the maximum possible number of servers and virtual machines for which distribution is assigned. The depth of such a search provides the necessary balance between the quality of service and the distribution time. Therefore, the solution of the problem of distribution and load balancing is considered in the form of the following stages: optimal distribution of software applications across virtual machines, distribution of virtual machines across the servers of a data center cluster, and the construction of an algo scheme.

вычислительные кластерывиртуальные машиныфизические серверымодель распределения ресурсовэвристические алгоритмымодельный экспериментcomputing clustersvirtual machinesphysical serversresource allocation modelheuristic algorithmsmodel experimentReferencesGnedenko B.V., Kovalenko I.N. (2007).Introduction to queuing theory / B.V. Gnedenko, I.N. Kovalenko. - М.: LCI Publisher, 2007. - 400 p.Gnedenko B.V., Kovalenko I.N. (2007).Introduction to queuing theory / B.V. Gnedenko, I.N. Kovalenko. - М.: LCI Publisher, 2007. - 400 p.Aliev T.I. (2009). Fundamentals of modeling of discrete systems. / T.I.Aliev. - St. Petersburg: ITMO, 2009. - 363 p.Aliev T.I. (2009). Fundamentals of modeling of discrete systems. / T.I.Aliev. - St. Petersburg: ITMO, 2009. - 363 p.Kleinrock L. (1979). Queueing Theory / L. Kleinrock. - М.: Mashinostroenie, 1979. - 432 p.Kleinrock L. (1979). Queueing Theory / L. Kleinrock. - М.: Mashinostroenie, 1979. - 432 p.Kuzin L.T. (1979). Fundamentals of Cybernetics. In 2 v. V.2. Fundamentals of cybernetic models / L.T. Kuzin. - М.: Energia, 1979. - 584 p.Kuzin L.T. (1979). Fundamentals of Cybernetics. In 2 v. V.2. Fundamentals of cybernetic models / L.T. Kuzin. - М.: Energia, 1979. - 584 p.Mochalov V.P., Bratchenko N.Yu., Yakovlev S.V., Gosteva D.V. (2018). "Distributed management system for infocommunication networks based on TM Forum Framework", CEUR Workshop Proceedings, 2254, pp. 81-93.Mochalov V.P., Bratchenko N.Yu., Yakovlev S.V., Gosteva D.V. (2018). "Distributed management system for infocommunication networks based on TM Forum Framework", CEUR Workshop Proceedings, 2254, pp. 81-93.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2018). "Analytical model of object r e-quest broker based on Corba standard", Journal of Physics: Conference Series, 1015 (2). doi: 10.1088/1742-6596/1015/2/022012.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2018). "Analytical model of object r e-quest broker based on Corba standard", Journal of Physics: Conference Series, 1015 (2). doi: 10.1088/1742-6596/1015/2/022012.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2018). "Analytical model of integr a-tion system for program components of distributed object applications", Internatio nal Russian Automation Conference, RusAutoCon 2018, № 8501806. doi: 10.1109/ RUSAUTOCON.2018.8501806.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2018). "Analytical model of integr a-tion system for program components of distributed object applications", Internatio nal Russian Automation Conference, RusAutoCon 2018, № 8501806. doi: 10.1109/ RUSAUTOCON.2018.8501806.Mochalov V., Bratchenko N., Linets G., Yakovlev S. (2019). "Distributed management systems for infocommunication networks: A model based on tm forum fr ameworx", Computers 2019, 8(2). doi: 10.3390/computers8020045.Mochalov V., Bratchenko N., Linets G., Yakovlev S. (2019). "Distributed management systems for infocommunication networks: A model based on tm forum fr ameworx", Computers 2019, 8(2). doi: 10.3390/computers8020045.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2019). "Process-Oriented Management System for Infocommunication Networks and Services Based on TM Forum Frameworx", Proceedings - 2019 International Russian Automation Conference, RusAutoCon 2019, № 8867619. doi: 10.1109/RUSAUTOCON.2019.8867619.Mochalov V.P., Bratchenko N.Y., Yakovlev S.V. (2019). "Process-Oriented Management System for Infocommunication Networks and Services Based on TM Forum Frameworx", Proceedings - 2019 International Russian Automation Conference, RusAutoCon 2019, № 8867619. doi: 10.1109/RUSAUTOCON.2019.8867619.Mochalov V.P., Linets G.I., Bratchenko N.Y., Govorova S.V. (2020). "An analytical model of a corporate software-controlled network switch", Scalable Computing, 21 (2), pp. 337346.Mochalov V.P., Linets G.I., Bratchenko N.Y., Govorova S.V. (2020). "An analytical model of a corporate software-controlled network switch", Scalable Computing, 21 (2), pp. 337346.Balashov N., Baranov A., Korenkov V. (2016). Optimization of over-provisioned clouds, Physics of Particles and Nuclei Letters, Vol. 13, No. 5, pp. 609-612.Balashov N., Baranov A., Korenkov V. (2016). Optimization of over-provisioned clouds, Physics of Particles and Nuclei Letters, Vol. 13, No. 5, pp. 609-612.McNab A., Stagni F., and Luzzi C. (2015). LHCb experience with running jobs in virtual machines, J. Phys.: Conf. Ser., Vol. 664.McNab A., Stagni F., and Luzzi C. (2015). LHCb experience with running jobs in virtual machines, J. Phys.: Conf. Ser., Vol. 664.Computing Center of the Institute of High Energy Physics (IHEP-CC) (2016). "VCondor - virtual computing resource pool manager based on HTCondor". Retrieved from https://github.com/hep-gnu/VCondor.Computing Center of the Institute of High Energy Physics (IHEP-CC) (2016). "VCondor - virtual computing resource pool manager based on HTCondor". Retrieved from https://github.com/hep-gnu/VCondor.McNab A., Love P., and MacMahon E. (2015). Managing virtual machines with Vac and Vcycle, J. Phys.: Conf. Ser., Vol. 664.McNab A., Love P., and MacMahon E. (2015). Managing virtual machines with Vac and Vcycle, J. Phys.: Conf. Ser., Vol. 664.Feller E., Rilling L., and Morin C. Snooze (2012). A scalable and autonomic virtual machine management framework for private Clouds, Proceedings of the 12th IEEE/ACMInternational Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 482-489.Feller E., Rilling L., and Morin C. Snooze (2012). A scalable and autonomic virtual machine management framework for private Clouds, Proceedings of the 12th IEEE/ACMInternational Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 482-489.Beloglazov, R. Buyya (2015). OpenStack Neat: A Framework for Dynamic and Energy-Efficient Consolidation of Virtual Machines in OpenStack Clouds, Concurrency and Computation: Practice and Experience (CCPE), Vol. 27, No. 5, pp. 1310-1333.Beloglazov, R. Buyya (2015). OpenStack Neat: A Framework for Dynamic and Energy-Efficient Consolidation of Virtual Machines in OpenStack Clouds, Concurrency and Computation: Practice and Experience (CCPE), Vol. 27, No. 5, pp. 1310-1333.Anne-C'ecile Orgerie, Laurent Lef ever (2009). When Clouds become Green: the Green Open Cloud Architecture, International Conference on Parallel Computing (ParCo), pp. 228-237.Anne-C'ecile Orgerie, Laurent Lef ever (2009). When Clouds become Green: the Green Open Cloud Architecture, International Conference on Parallel Computing (ParCo), pp. 228-237.Ward J.S., Barker A. (2014). Observing the clouds: a survey and taxonomy of cloud monitoring, Journal of Cloud Computing: Advances, Systems and Applications, Vol. 3.Ward J.S., Barker A. (2014). Observing the clouds: a survey and taxonomy of cloud monitoring, Journal of Cloud Computing: Advances, Systems and Applications, Vol. 3.Ward J.S., Barker A. (2015). Cloud cover: monitoring large-scale clouds with Varanus, Journal of Cloud Computing: Advances, Systems and Applications, Vol. 4.Ward J.S., Barker A. (2015). Cloud cover: monitoring large-scale clouds with Varanus, Journal of Cloud Computing: Advances, Systems and Applications, Vol. 4.Open Grid Forum (2016). "Open Cloud Computing Interface". Retrieved from http://occiwg.org/.Open Grid Forum (2016). "Open Cloud Computing Interface". Retrieved from http://occiwg.org/.

The authors declare that there are no conflicts of interest present.