Scopus; WoS

A new approach for buffering space in scheduling unknown service time jobs in a computational cluster with awareness of performance and energy consumption

Năm XB 2014 Tạp chí / Hội thảo Advances in Intelligent Systems and Computing Volume 282 DOI / Link https://doi.org/10.1007/978-3-319-06569-4_10 ↗

Tác giả

Tóm tắt

In this paper, we present a new approach concentrating on buffering schemes along with scheduling policies for distribution of compute-intensive jobs with unknown service times in a cluster of heterogeneous servers. We utilize two types of ADM Opteron processors of which parameters are measured according to SPEC's Benchmark and Green500 list. We investigate three cluster models according to buffering schemes (server-level queue, class-level queue, and cluster-level queue). The simulation results show that the buffering schemes significantly influence the performance capacity of clusters, regarding the waiting time and response time experienced by incoming jobs while they retain energy efficiency of system.

Tài liệu tham khảo

[1] El-Rewini, H., Lewis, T., Ali, H.: Task Scheduling in Parallel and distributed Systems. Prentice Hall, Englewood Cliffs (1994)

[2] Gkoutioudi, K.Z., Karatza, H.D.: Multi-Criteria Job Scheduling in Grid Using an Accelerated Genetic Algorithm. Journal of Grid Computing, 311–323 (March 2012)

[3] Yagoubi, B., Slimani, Y.: Dynamic load balancing strategy for grid computing. World Academy of Science, Engineering and Technology 19 (2006)

[4] Terzopoulos, G., Karatza, H.D.: Performance evaluation of a real-time grid system using power-saving capable processors. The Journal of Supercomputing, 1135–1153 (2012)

[5] Zikos, S., Karatza, H.D.: Communication cost effective scheduling policies of nonclairvoyant jobs with load balancing in a grid. Journal of Systems and Software, 2103–2116 (2009)

[6] Zikos, S.: Helen D. Karatza: A clairvoyant site allocation policy based on service demands of jobs in a computational grid. Simulation Modelling Practice and Theory, 1465–1478 (2011)

[7] Zikos, S., Karatza, H.D.: The impact of service demand variability on source allocation strategies in a grid system. ACM Trans. Model. Comput. Simul., 19:1–19:29 (November 2010)

[8] He, Y., Hsu, W., Leiserson, C.: Provably efficient online non-clairvoyant adaptive scheduling, pp. 1–10 (March 2007)

[9] Wang, T., Zhou, X.-S., Liu, Q.-R., Yang, Z.-Y., Wang, Y.-L.: An Adaptive Resource Scheduling Algorithm for Computational Grid, pp. 447–450 (December 2006)

[10] Opitz, A., König, H., Szamlewska, S.: What does grid computing cost? Journal of Supercomputing, 385–397 (2008)

[11] Kaur, P., Singh, H.: Adaptive dynamic load balancing in grid computing an approach. International Journal of Engineering Science and Advance Technology (IJESAT), 625–632 (June 2012)

[12] Chedid, W., Yu, C., Lee, B.: Power analysis and optimization techniques for energy efficient computer systems

[13] Zhuo, L., Liang, A., Xiao, L., Ruan, L.: Workload – aware Power Management of Cluster Systems, pp. 603–608 (August 2010)

[14] Chedid, W., Yu, C.: Survey on Power Management Techniques for Energy Efficient Computer Systems, http://academic.csuohio.edu/yuc/mcrl/survey-power.pdf (retrieved)

[15] Zikos, S., Karatza, H.D.: Performance and energy aware cluster-level scheduling of compute-intensive jobs with unknown service times. Simulation Modelling Practice and Theory, 239–250 (2011)

[16] AMD Opteron Processor-Based Server Benchmarks (2010), http://www.amd.com/us/products/server/benchmarks/Pages/benchmarks-filter.aspx

[17] SPEC’s Benchmarks and Published Results (2010), http://www.spec.org/benchmarks.html

[18] Feng, W., Cameron, K.: Power Measurement of High-End Clusters, The Green500 List, Version 0.1 (November 12, 2006)

← Quay lại danh sách bài báo