Abstract
The minimisation of the total cost of ownership is hard to be faced by the owners of large scale computing systems, without affecting negatively the quality of service for the users. Modern datacenters, often included in distributed environments, appear to be “elastic”, i.e., they are able to shrink or enlarge the number of local physical or virtual resources, also by recruiting them from private/public clouds. This increases the degree of dynamicity, making the infrastructure management more and more complex. Here, we report some advances in the realisation of an adaptive scheduling controller (ASC) which, by interacting with the datacenter resource manager, allows an effective and an efficient usage of resources. In particular, we focus on the mathematical formalisation of the ASC’s kernel that allows to dynamically configure, in a suitable way, the datacenter resources manager. The described formalisation is based on a probabilistic approach that, starting from both a hystorical resources usage and on the actual users request of the datacenter resources, identifies a suitable probability distribution for queue time with the aim to perform a short term forecasting. The case study is the SCoPE datacenter at the University of Naples Federico II.
Similar content being viewed by others
References
Aguilar, J., Gelenbe, E.: Task assignment and transaction clustering heuristics for distributed systems. Inf. Sci. 97, 1–2 (1997)
Barone, G., Boccia, V., Bottalico, D., Campagna, R., Carracciuolo, L., Laccetti, G.: An approach to model resources rationalisation in hybrid clouds through users activity characterisation. In: Proceedings of Future Computing 2015—The Seventh International Conference on Future Computational Technologies and Applications, Proceedings of FUTURE COMPUTING, International Conference on Future Computational Technologies and Applications, pp. 48–53 (2015). http://www.thinkmind.org/download.php?articleid=future_computing_2015_3_10_30022
Barone, G., Boccia, V., Bottalico, D., Carracciuolo, L., Doria, A., Laccetti, G.: Modelling the behaviour of an adaptive scheduling controller. In: 2012 Sixth International Conference on Complex, Intelligent and Software Intensive Systems (CISIS), pp. 438–442 (2012). doi:10.1109/CISIS.2012.26
Caruso, P., Laccetti, G., Lapegna, M.: A performance contract system in a grid enabling, component based programming environment. In: Advances in Grid Computing—EGC 2005, European Grid Conference, Amsterdam, The Netherlands, February 14–16, 2005, Revised Selected Papers, pp. 982–992 (2005). doi:10.1007/11508380_100
Casavant, T., Kuhl, J.: A taxonomy of scheduling in general-purpose distributed computing systems. IEEE Trans. Softw. Eng. 14(2), 141–154 (1988). doi:10.1109/32.4634
Federated cloud: Building a grid of clouds. https://www.egi.eu/. Accessed 31 July 2016
Foster, I.: What’s faster a supercomputer or EC2? (2009). http://ianfoster.typepad.com/blog/2009/08/whats-fastera-supercomputer-or-ec2.html. Accessed 31 July 2016
Gkoutioudi, K., Karatza, H.D.: Task cluster scheduling in a grid system. Simul. Model. Pract. Theory 18(9), 1242–1252 (2010)
Italian Grid Infrastructure: http://www.italiangrid.it/. Accessed 31 July 2016
James Allen Fill, M.M.: Stochastic monotonicity and realizable monotonicity. Ann. Probab. 29(2), 938–978 (2001)
Laccetti, G., Lapegna, M., Mele, V., Romano, D., Murli, A.: A double adaptive algorithm for multidimensional integration on multicore based HPC systems. Int. J. Parallel Program. 40(4), 397–409 (2012). doi:10.1007/s10766-011-0191-4
Merola, L.: on behalf of S.Co.P.E. Project: The S.Co.P.E. Project. In: Proceedings of the Final Workshop of the Grid Projects of the Italian National Operational Programme 2000–2006 Call 1575, Edited by Consorzio COMETA, pp. 18–35 (2008)
Murli, A., Boccia, V., Carracciuolo, L., D’Amore, L., Laccetti, G., Lapegna, M.: Monitoring and migration of a PETSc-based parallel application for medical imaging in a grid computing PSE. IFIP Int. Fed. Inf. Process. 239, 421–432 (2007). doi:10.1007/978-0-387-73659-4_25
Nadarajah, S.: The waiting time distribution. Comput. Ind. Eng. 53(4), 693–699 (2007). doi:10.1016/j.cie.2007.06.004
Nazir, A., Srensen, S.A.: Cost-benefit analysis of high performance computing infrastructures. In: SOCA, pp. 1–8. IEEE (2010)
Papazachos, Z.C., Karatza, H.D.: The impact of task service time variability on gang scheduling performance in a two-cluster system. Simul. Model. Pract. Theory 17, 1276–1289 (2009)
Potts, C.N., Strusevich, V.A.: Fifty years of scheduling: a survey of milestones. JORS (2009). doi:10.1057/jors.2009.2
Powers, S.: A study of the impact of scheduling parameters in heterogeneous computing environments. In: Proceedings of the 2014 Winter Simulation Conference. WSC ’14, pp. 933–942. IEEE Press, Piscataway (2014)
Serazzi, G., Calzarossa, M.: Adaptive optimization of a system’s load. IEEE Trans. Softw. Eng. 10(6), 837–845 (1984)
STAT 415 Intro Mathematical Statistics online course. https://onlinecourses.science.psu.edu/stat414/node/3. Accessed 31 July 2016
Sun, H., Cao, Y., Hsu, W.J.: Fair and efficient online adaptive scheduling for multiple sets of parallel applications. In: ICPADS, pp. 64–71. IEEE (2011)
Sztrik, J.: Queueing theory and its applications: a personal view. In: Proceedings of the Third Symposium on Information and Communication Technology, SoICT ’12, pp. 1–1. ACM, New York (2012). doi:10.1145/2350716.2350717
Wilk, M.B., Gnanadesikan, R.: Probability plotting methods for the analysis of data. Biometrika 55(1), 1–17 (1968). doi:10.1093/biomet/55.1.1
Acknowledgments
This work is part of the activities of a multidisciplinary group (GTT), responsible for the SCoPE infrastructure management. It has been realised thanks to the use of the SCoPE computing infrastructure at the University of Naples, also in the framework of PON ”Rete di Calcolo per SuperB e le altre applicazioni” (ReCaS) project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Barone, G.B., Boccia, V., Bottalico, D. et al. An Approach to Forecast Queue Time in Adaptive Scheduling: How to Mediate System Efficiency and Users Satisfaction. Int J Parallel Prog 45, 1164–1193 (2017). https://doi.org/10.1007/s10766-016-0457-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10766-016-0457-y