Abstract
Backfill is a technique in which lower priority jobs requiring fewer resources are initiated before one or more currently waiting higher priority jobs requiring as yet unavailable resources. Processors are frequently the resource involved and the purpose of backfilling is to increase system utilization and reduce average wait time. Generally, a scheduler backfills when the user-specified run times indicate that executing the lower priority jobs will not delay the anticipated initiation of the higher priority jobs. This paper explores the possibility of using a relaxed backfill strategy in which the lower priority jobs are initiated as long as they do not delay the highest priority job too much. A simulator was developed to model this approach; it uses a parameter ω to control the length of the acceptable delay as a factor times the wait time of the highest priority job. Experiments were performed for a range of ω values with both user-estimated run times and actual run times using workload data from two parallel systems, a Cray T3E and an SGI Origin 3800. For these workloads, overall average job wait time typically decreases as ω increases and use of user-estimated run times is superior to use of actual run times. More experiments must be performed to determine the generality of these results.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aida, K., Kasahara, H., Narita, S.: Job scheduling scheme for pure space sharing among rigid jobs. In Feitelson, D.G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 1459 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (1998) 98–121 89
Gibbons, R.: A historical application profiler for use by parallel schedulers. In Feitelson, D. G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 1291 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (1997) 58–77 89
Parsons, E.W., Sevcik, K.C.: Implementing multiprocessor scheduling disciplines. In Feitelson, D. G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 1291 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (1997) 166–192 89
Finkel, R.: An Operating System Vade Mecum. Prentice-Hall, Englewood Cliffs, New Jersey (1988) 89
Talby, D., Feitelson, D. G.: Supporting priorities and improving utilization of the IBMS P2 scheduler using slack-based backfilling. In: 13th Intl. Parallel Processing Symp. (1999) 513–517 89, 90
Feitelson, D.G.: A survey of scheduling in multiprogrammed parallel systems. Research Report RC 19790 (87657), IBMT. J. Watson Research Center (1994) 89
Intel Corp.: iPSC/860 Multi-User Accounting, Control, and Scheduling Utilities Manual. (1992) Order Number 312261-002. 89
Das Sharma, D., Pradhan, D. K.: Job scheduling in mesh multicomputers. In: Intl. Conf. Parallel Processing. Volume II. (1994) 1–18 89
Jackson, D., Snell, Q., Clement, M.: Core algorithms of the Maui scheduler. In Feitelson, D. G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 2221 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (2001) 87–102 89
Zhang, Y., Franke, H., Moreira, J. E., Sivasubramanian, A.: An integrated approach to parallel scheduling using gang-scheduling, backfill, and migration. In Feitelson, D. G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 2221 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (2001) 133–158 89
Lifka, D. A.: The ANL/IBMSP scheduling system. In Feitelson, D.G., Rudolph, L., eds.: Job Scheduling Strategies for Parallel Processing. Volume 949 of Lecture Notes in Computer Science., Berlin Heidelberg New York, Springer-Verlag (1995) 295–303 89
Cormen, T.H., Leiserson, C. E., Rivest, R. L.: Introduction to Algorithms. MIT Press, Cambridge, Massachusetts (1990) 90
Moret, B. M.E., Shapiro, H.D.: Algorithms from P to NP. Benjamin/Cummings, Redwood City, California (1991) 90
Zotkin, D., Keleher, P. J.: Job-length estimation and performance in backfilling schedulers. In: 8th High Performance Distributed Computing Conf., IEEE (1999) 90, 96
Zotkin, D., Keleher, P. J., Perkovic, D.: Attacking the bottlenecks of backfilling schedulers. Cluster Computing 3 (2000) 245–254 90, 96
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ward, W.A., Mahood, C.L., West, J.E. (2002). Scheduling Jobs on Parallel Systems Using a Relaxed Backfill Strategy. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds) Job Scheduling Strategies for Parallel Processing. JSSPP 2002. Lecture Notes in Computer Science, vol 2537. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36180-4_6
Download citation
DOI: https://doi.org/10.1007/3-540-36180-4_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00172-0
Online ISBN: 978-3-540-36180-0
eBook Packages: Springer Book Archive