Abstract
Allocating submeshes to jobs in mesh-connected multicomputers in an FCFS fashion leads to poor system performance because a large job at the head of the waiting queue can prevent the allocation of free submeshes to other smaller waiting jobs. However, serving jobs aggressively out-of-order can lead to excessive waiting delays for large jobs located at the head of the waiting queue. In this paper, we show that the ability of the job scheduling algorithm to bypass the head of the waiting queue should increase with the load, and we propose a scheduling scheme that can bypass the waiting queue head in a load-dependent adaptive fashion. Also, giving priority to large jobs because they are more difficult to accommodate is investigated. The performance of the proposed scheme has been compared to that of FCFS, aggressive out-of-order scheduling, and other previous job scheduling schemes. Extensive simulation results based on synthetic workloads and real workload traces indicate that our scheduling strategy is a good strategy when both average and maximum job waiting delays are considered. In particular, it is substantially superior to FCFS in terms of mean turnaround times, and to aggressive out-of-order scheduling in terms of maximum waiting delays.
Similar content being viewed by others
References
Ababneh I (2001) Job scheduling and contiguous processor allocation for three-dimensional mesh multicomputers. AMSE Adv Model Analysis 6(4):43–58
Ababneh I (2008) Availability-based noncontiguous processor allocation policies for 2D mesh-connected multicomputers. J Syst Softw 81(7):1081–1092
Ababneh I (2009) On submesh allocation for 2D mesh multicomputers using the free-list approach: global placement schemes. Perform Eval 66(2):105–120
Aridor Y, Domany T, Goldshmidt O, Moreira JE, Shmueli E (2005) Resource allocation and utilization in the BlueGene/L supercomputer. IBM J Res Dev 49(2/3):425–436
Athas WC, Seitz CL (1988) Multicomputers: message-passing concurrent computers. IEEE Comput 21(8):9–24
Bani-Mohammad S, Ould-Khaoua M, Ababneh I (2007) A new processor allocation strategy with a high degree of contiguity in mesh-connected multicomputers. J Simul Model Pract Theory (SIMPRA) 15(4):465–480
Bani-Mohammad S, Ould-Khaoua M, Ababneh I, Mackenzie L (2009) Comparative evaluation of contiguous allocation strategies on 3D mesh multicomputers. J Syst Softw 82(2):307–318
Bhattacharya S, Tsai W-T (1994) Lookahead processor allocation in mesh-connected massively parallel multicomputer. In: Proc. int’l parallel processing symposium, pp 868–875
Blumrich M, Chen D, Coteus P, Gara A, Giampapa M, Heidelberger P, Singh S, Steinmacher-Burow B, Takken T, Vranas P (2003) Design and analysis of the BlueGene/L torus interconnection network. IBM Research Report RC23025, IBM Research Division, Thomas J. Watson Research Center, Dec. 3, 2003
Bunde DP, Leung VJ, Mache J (2004) Communication patterns and allocation strategies. Sandia Technical Report SAND2003-4522, Jan. 2004
Cray (2004) Cray XT3 datasheet
Chang C-Y, Mohapatra P (1998) Performance improvement of allocation schemes for mesh-connected computers. J Parallel Distributed Comput 52(1):40–68
Chiu G-M, Chen S-K (1999) An efficient submesh allocation scheme for two-dimensional meshes with little overhead. IEEE Trans Parallel Distributed Syst 10(5):471–486
Choo H, Yoo S-M, Yoon H (2000) Processor scheduling and allocation for 3D torus multicomputer systems. IEEE Trans Parallel Distributed Syst 11(5):475–484
Das Sharma D, Pradhan DK (1996) Submesh allocation in mesh multicomputers using busy-list: a best-fit approach with complete recognition capability. J Parallel Distributed Comput 36(2):106–118
Das Sharma D, Pradhan DK (1998) Job scheduling in multicomputers. IEEE Trans Parallel Distributed Syst 9(1):57–70
Intel Corp (1991) Paragon XP/S product overview
Kim G, Yoon H (1998) On submesh allocation for mesh multicomputers: a best-fit allocation and a virtual submesh allocation for faulty meshes. IEEE Trans Parallel Distributed Syst 9(2):175–185
Lo V, Windisch KJ, Liu W, Nitzberg B (1997) Noncontiguous processor allocation algorithms for mesh-connected multicomputers. IEEE Trans Parallel Distributed Syst 8(7):712–725
ProcSimity v4.3 user’s manual (1996) University of Oregon. ftp://ftp.cs.uoregon.edu/pub/lo/procsim_man.ps.gz
Parallel Workloads Archive (2008). http://www.cs.huji.ac.il/labs/parallel/workload/
Mu’alem AW, Feitelson DG (2001) Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans Parallel Distributed Syst 12(6):529–543
Yoo S-M, Youn HY, Shirazi B (1997) An efficient task allocation scheme for 2D mesh architectures. IEEE Trans Parallel Distributed Syst 8(9):934–942
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ababneh, I., Bani-Mohammad, S. & Ould-Khaoua, M. An adaptive job scheduling scheme for mesh-connected multicomputers. J Supercomput 53, 5–25 (2010). https://doi.org/10.1007/s11227-009-0333-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-009-0333-2