Job Batch Generation and Scheduling in Distributed Computing Environment

Authors

  • Victor V. Toporkov National Research University “MPEI”
  • Dmitry M. Yemelyanov National Research University “MPEI”
  • Petr A. Potekhin National Research University “MPEI”

DOI:

https://doi.org/10.14529/cmse150204

Keywords:

distributed computing, scheduling, slot, cyclic scheduling scheme, job batch, job generation

Abstract

The paper considers approaches to ranked jobs system generation in the model of cyclic scheduling in the virtual organizations of distributed computing environments. Two different methodologies of job selection for scheduling are proposed and compared: the first one is based on the solution of knapsack problem, the second one utilizes a heuristic "compatibility" indicator of jobs and computing domains. Experimental results that allow estimating of the proposed solutions efficiency are presented, the solutions are compared to random job selection.

Author Biography

Victor V. Toporkov, National Research University “MPEI”

заведующий кафедрой Вычислительной техники НИУ "МЭИ"

References

Foster I. The Anatomy of the Grid: Enabling Scalable Virtual Organizations / I. Foster, C. Kesselman, S. Tuecke // International J. Supercomputer Applications. — 2001. — Vol. 15, No. 3. — P. 200–220.

Garg S.K. Scheduling Parallel Applications on Utility Grids: Time and Cost Trade-off Management / S.K. Garg, R. Buyya, H.J. Siegel // 32nd Australasian Computer Science Conference, Wellington, New Zealand, Proceedings. — 2009. — Vol. 91. — P. 151–159.

Buyya R. Economic Models for Resource Management and Scheduling in Grid Compu-ting / R. Buyya, D. Abramson, J. Giddy // J. Concurrency and Computation. — 2002. — Vol. 14, No. 5. — P. 1507–1542.

Топорков В.В. Экономическая модель планирования и справедливого разделения ресурсов в распределенных вычислениях / В.В. Топорков, Д.М. Емельянов // Программирование. — 2014. — № 1. — С. 54–65.

Мультиагентный подход к управлению распределенными вычислениями в кластерной GRID-системе / В.Г. Богданова, И.В. Бычков, А.С. Корсуков // Известия РАН. ТиСУ. — 2014. — № 5. — С. 95-105.

Mutz A. Eliciting Honest Value Information in a Batch-queue Environment / A. Mutz, R. Wolski, J. Brevik // 2007 8th IEEE/ACM International Conference on Grid Computing. — 2007. — P. 291–297.

Adaptive Computing on the Grid Using AppLeS / F. Berman, R. Wolski, H. Casanova et al. // IEEE Trans. On Parallel and Distributed Systems. — 2003. — Vol. 14, No. 4. — P. 369-382.

Scheduling in Bag-of-task Grids: The PAUÁ Case / W. Cirne, F. Brasileiro, L. Costa et al. // 16th Symposium on Computer Architecture and High Performance Computing. — 2004. — P. 124–131.

Эволюция системы метакомпьютинга X-Com / Вл.В. Воеводин, Ю.А. Жолудев, С.И. Соболев, К.С. Стефанов // Вестник Нижегородского университета им. Н.И. Лобачевского. — 2009. — № 4. — С. 157–164.

Scheduling in the Grid Application Development Software Project / H. Dail, O. Sievert, F. Berman et al. // Grid resource management. State of the Art and Future Trends. / Eds J. Nabrzyski, J.M. Schopf, J. Weglarz. — Kluwer Acad. Publ., 2003. — P. 73–98.

Multi-criteria Grid Resource Management Using Performance Prediction Techniques / K. Kurowski, A. Oleksiak, J. Nabrzyski et al. // Integrated Research in GRID Computing. / Eds. S. Gorlatch, M. Danelutto. — Springer, 2007. — P. 215–225.

Moab HPC Suite Enterprise Edition. URL:

http://www.adaptivecomputing.com/products/hpc-products/moab-hpc-suite-enterprise-edition (дата обращения: 08.02.2014).

Workload Management with LoadLeveler. / S. Kannan, M. Roberts, P. Mayes et al. — IBM, First ed., 2001. — 210 p.

Tsafrir D. Backfilling Using System-generated Predictions Rather than User Runtime Estimates / D. Tsafrir, Y. Etsion, D. Feitelson // IEEE Transactions on Parallel and Distributed Systems. — 2007. — Vol. 18, No. 6. — P. 789–803.

Preference-Based Fair Resource Sharing and Scheduling Optimization in Grid VOs / V. Toporkov, A. Toporkova, A. Tselishchev et al. // Procedia Computer Science. — 2014. — Vol. 29. — P. 831–843.

Reducing Energy Costs for IBM Blue Gene/P via Power-Aware Job Scheduling / Z. Zhou, Z. Lan, W. Tang, N. Desai // Seventeenth Workshop on Job Scheduling Strate-gies for Parallel Processing. — May 2013. — P. 96–115.

Slot Selection Algorithms in Distributed Computing / V. Toporkov, A. Toporkova, A. Tselishchev, D. Yemelyanov // Journal of Supercomputing. — 2014. — Vol. 69, No. 1. — P. 53–60.

Soner S. Integer Programming Based Heterogeneous CPU-GPU Cluster Scheduler for SLURM Resource Manager / S. Soner, C. Özturan // Fourteenth IEEE International Conference on High Performance Computing and Communication & Ninth IEEE Inter-national Conference on Embedded Software and Systems. — June 2012. — P. 418–424.

Методы и эвристики планирования в распределенных вычислениях с неотчуждае-мыми ресурсами / В.В. Топорков, А.В. Бобченков, Д.М. Емельянов, А.С. Целищев // Вестник ЮУрГУ, серия «Вычислительная математика и информатика». — 2014. — Т. 3., № 2. — С. 43–62.

Published

2015-03-17

Issue

Section

Informatics, Computers and Control