ABSTRACT
This paper describes results of an empirical study to evaluate the effect of communications delays on the performance of the Time Warp mechanism in order to assess the effectiveness of Time Warp in distributed computing environments. An implementation of Time Warp on a collection of networked workstations is used in this study. Performance using synchronous and asynchronous message passing primitives are compared, and it is observed that Time Warp experiences much more rolled back computation when using the synchronous primitives for certain applications. Message passing is decomposed into a computation component at the sender and receiver processors, and a transmission delay component that represents the amount of time the message remains “in transit” within the network. The effect of each of these components on Time Warp performance is studied. It is observed that communications latency in distributed computing environments can significantly degrade the efficiency of Time Warp for applications containing large numbers of simulator objects with small event granularity (by increasing the amount of rolled back computation), particularly applications using “self-driving” simulator objects. However, for applications containing large grained events, communication delay appears to have little effect on rollback behavior in Time Warp.
- 1.J. Briner, Jr. Fast parallel simulation of digital systems. In Advances in Parallel and Distributed Simulation, volume 23, pages 71-77. SCS Simulation Series, January 1991.Google Scholar
- 2.R. Brown. Calendar queues: A fast O(1) priority queue implementation for the simulation event set problem. Communications of the ACM, 31(10):1220--1227, Oct. 1988. Google ScholarDigital Library
- 3.C.D. Carothers, R. M. Fujimoto, Y-B. Lin, and P. England. Distributed simulation of large-scale pes networks. In Proceedings of the 1994 MASCOTS Conference, January 1994. Google ScholarDigital Library
- 4.D. C. Cox. Personal Communications - A View~int. IEEE Communications Magazine, 128(11), 1990.Google ScholarDigital Library
- 5.R. M. Fujimoto. Time Warp on a shared memory multiprocessor. Transactions of the Society for Computer Simulation, 6(3):211-239, July 1989. Google ScholarDigital Library
- 6.R.M. Fujimoto. Performance of Time Warp under synthetic workloads. In Proceedings of the SCS Multiconference on Distributed Simulation, volume 22, pages 23-28. SCS Simulation Series, January 1990.Google Scholar
- 7.R.M. Fujimoto. Parallel and distributed discrete event simulation: Algorithms and applications. In 1993 Winter Simulation Conference Proceedings, December 1993. Google ScholarDigital Library
- 8.R.M. Fujimoto and D. M. Nicol. State of the art in parallel simulation. In 1992 Winter Simulation Conference Proceedings, pages 122-127, December 1992. Google ScholarDigital Library
- 9.Brian K. Grant and Anthony Skjellum. The pvm systems: An indepth analysis and documenting study consise edition. Unpublished work, Aug 1992.Google Scholar
- 10.A. Gupta, I. F. Akyildiz, and R. M. Fujimoto. Performance analysis of Time Warp with multiple homogenousprocessorso IEEE Transactions on Software Engineering, 17 (10): 1013-1027, October 1991. Google ScholarDigital Library
- 11.D. R. Jefferson. Virtual time. ACM Transactions on Programruing Languages and Systems, 7(3):404--425, July 1985. Google ScholarDigital Library
- 12.B. Lubaehevsky, A. Weiss, and A. Shwartz. An analysis of rollback-based simulation. ACM Transactions on Modeling and Computer Simulation, 1(2):154-192, April 1991. Google ScholarDigital Library
- 13.N. Manjikian and W. M. Loucks. High performance parallel logic simulation on a network of workstations. In 7tn Workshop on Parallel and Distributed Simulation, volume 23, pages 76- 84. SCS Simulation Series, May 1993. Google ScholarDigital Library
- 14.M. Presley, M. Ebling, F. Wieland, and D. R. Jefferson. Benchmarking the Time Warp Operating System with a computer network simulation. In Proceedings of the SCS Multiconferentre on Distributed Simulation, volume 21, pages 8-13. SCS Simulation Series, March 1989.Google Scholar
- 15.C. Sporrer and H. Bauer. Corolla partitioning for distributed logic simulation of vlsi-circuits. In 7 Workshop on Parallel and Distributed Simulation, volume 23, pages 85-92. SCS Simulation Series, May 1993. Google ScholarDigital Library
- 16.J. S. Steinman. Breathing time warp. In 7tn Workshop on Parallel and Distributed Simulation, volume 23, pages 109- 118. SCS Simulation Series, May 1993. Google ScholarDigital Library
- 17.F. Wieland, L. Hawley, A. Feinberg, M. DiLorento, L. Blume, P. Reiher, B. Beckman, P. Hontalas, S. Bellenot, and D. R. Jefferson. Distributed combat simulation and Time Warp: The model and its performance. In Proceedings of the SCS Multiconference onDistributed Simulation, volume 21, pages 14--20. SCS Simulation Series, March 1989.Google Scholar
Index Terms
- Effect of communication overheads on Time Warp performance: an experimental study
Recommendations
Effect of communication overheads on Time Warp performance: an experimental study
This paper describes results of an empirical study to evaluate the effect of communications delays on the performance of the Time Warp mechanism in order to assess the effectiveness of Time Warp in distributed computing environments. An implementation ...
Performance of a riskfree Time Warp operating system
Optimistic methods of synchronizing parallel discrete event simulations can be risky by sending (positive) messages (events) before they have been committed. Risky methods often use anti-messages (negative messages) to cancel incorrectly sent positive ...
Performance of a riskfree Time Warp operating system
PADS '93: Proceedings of the seventh workshop on Parallel and distributed simulationOptimistic methods of synchronizing parallel discrete event simulations can be risky by sending (positive) messages (events) before they have been committed. Risky methods often use anti-messages (negative messages) to cancel incorrectly sent positive ...
Comments