Abstract
We present demand-based coscheduling, a new approach to scheduling parallel computations on multiprogrammed multiprocessors. In demand-based coscheduling, rather than making the pessimistic assumption that all the processes constituting a parallel job must be simultaneously scheduled in order to achieve good performance, we use information about which processes are communicating in order to coschedule only these; the result is more opportunities for coscheduling and fewer preemptions than in more traditional coscheduling schemes. We introduce two particular types of demand-based coscheduling. The first is dynamic coscheduling, which was conceived for use on message-passing architectures. We present an analytical model and a simulation of dynamic coscheduling that show that the algorithm can achieve good performance under pessimistic assumptions. The second is predictive coscheduling, for which we present an algorithm that detects communication by using virtual memory system information on a bus-based shared-memory multiprocessor.
Support for Patrick Sobalvarro's work was provided in part under a Draper Fellowship from the Charles Stark Draper Laboratory, Inc. This work was supported in part by the Advanced Research Projects Agency under Contract N00014-91-J-1698, by grants from IBM and AT&T, and by an equipment grant from DEC.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Chaiken, D., Kubiatowicz, J., and Agarwal, A. “LimitLESS Directories: A Scalable Coherence Scheme,” in Fourth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS IV), April 1991, pp. 224–234.
Chandra, R., et al. “Scheduling and Page Migration for Multiprocessor Compute Servers,” in Sixth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS VI), San Jose, California, October, 1994, pp. 12–24.
Crovella, M., et al. “Multiprogramming on Multiprocessors,” in Third IEEE Symposium on Parallel and Distributed Processing, 1991, pp. 590–597.
Feitelson, D. G., and Rudolph, L. “Coscheduling Based on Run-Time Identification of Activity Working Sets,” in International Journal of Parallel Programming, Vol. 23, No. 2, pp. 135–160, April, 1995.
Feitelson, D. G., and Rudolph, L. “Distributed Hierarchical Control for Parallel Processing,” in IEEE Computer, Vol. 25, No. 3, pp. 65–77, May, 1990.
Feitelson, D. G., and Rudolph, L. “Gang Scheduling Performance Benefits for Fine-Grain Synchronization,” in Journal of Parallel and Distributed Computing, Vol. 16, No. 4, pp. 306–318, December, 1992.
Gupta, A., Tucker, A., and Urushibara, S. “The Impact of Operating System Scheduling Policies and Synchronization Methods on the Performance of Parallel Applications,” in Proceedings of SIGMETRICS Conference on Measurement and Modeling of Computer Systems, May, 1991, pp. 120–132.
Helmbold, D. P., and McDowell, C. E. “Modeling Speedup(n) Greater than n,” in IEEE Transactions on Parallel and Distributed Systems, Vol. 1, No. 2, April 1990, pp. 250–256.
Kuskin, J. et al. “The Stanford FLASH Multiprocessor,” in Proceedings of the 21st Annual Symposium on Computer Architecture, Chicago, Illinois, April, 1994.
Ousterhout, John K. “Scheduling Techniques for Concurrent Systems,” in Third International Conference on Distributed Computing Systems, October, 1982, pp. 22–30.
Reinhardt, S. K., Larus, J. R., and Wood, D. A. “Tempest and Typhoon: Userlevel Shared Memory,” in Proceedings of the 21st Annual Symposium on Computer Architecture, Chicago, Illinois, April, 1994.
Sobalvarro, P. G. “Adaptive Gang-Scheduling for Distributed-Memory Multiprocessors,” in Proceedings of the 1994 MIT Student Workshop on Scalable Computing, MIT Laboratory for Computer Science Technical Report No. 622, July, 1994.
Tucker, A. Efficient Scheduling on Multiprogrammed Shared-Memory Multiprocessors. Stanford University Department of Computer Science Technical Report CSL-TR-94-601, November, 1993.
Tucker, A. and Gupta, A. “Process Control and Scheduling Issues for Multiprogrammed Shared-Memory Multiprocessors,” in Proceedings of the 12th ACM Symposium on Operating Systems Principles, 1989, pp. 159–186.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sobalvarro, P.G., Weihl, W.E. (1995). Demand-based coscheduling of parallel jobs on multiprogrammed multiprocessors. In: Feitelson, D.G., Rudolph, L. (eds) Job Scheduling Strategies for Parallel Processing. JSSPP 1995. Lecture Notes in Computer Science, vol 949. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60153-8_25
Download citation
DOI: https://doi.org/10.1007/3-540-60153-8_25
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60153-1
Online ISBN: 978-3-540-49459-1
eBook Packages: Springer Book Archive