Reduction of Subtask Dispersion in Fork-Join Systems
Fork-join and split-merge queueing systems are well-known abstractions of parallel systems in which each incoming task splits into subtasks that are processed by a set of parallel servers. A task exits the system when all of its subtasks have completed service. Two key metrics of interest in such systems are task response time and subtask dispersion. This paper presents a technique applicable to a class of fork-join systems with heterogeneous exponentially distributed service times that is able to reduce subtask dispersion with only a marginal increase in task response time. Achieving this is challenging since the unsynchronised operation of fork-join systems naturally militates against low subtask dispersion. Our approach builds on our earlier research examining subtask dispersion and response time in split-merge systems, and involves the frequent application and updating of delays to the subtasks at the head of the parallel service queues. Numerical results show the ability to reduce dispersion in fork-join systems to levels comparable with or below that observed in all varieties of split-merge systems while retaining the response time and throughput benefits of a fork-join system.
KeywordsFork-Join System Subtask Dispersion Task Response Time
Unable to display preview. Download preview PDF.
- 3.Bolch, G., et al.: Queueing Networks and Markov Chains. J. Wiley & Sons, Inc. (2006)Google Scholar
- 6.David, H.A.: Order Statistics. Wiley Series in Probability and Mathematical Statistics. John Wiley (1980)Google Scholar
- 7.David, H.A., Nagaraja, H.N.: Order Statistics, 3rd edn. Wiley Series in Probability and Mathematical Statistics. John Wiley (2003)Google Scholar
- 12.Jeffay, K., Stanat, D.F., Martel, C.U.: On non-preemptive scheduling of periodic and sporadic tasks. In: Proc. 12th Real-Time Systems Symposium, pp. 129–139 (1991)Google Scholar
- 13.Kameda, H., Li, J., Kim, C., Zhang, Y.: A comparison of static and dynamic load balancing. In: Optimal Load Balancing in Distributed Computer Systems. Telecommunication Networks and Computer Systems, pp. 225–240. Springer (1997)Google Scholar
- 15.Knottenbelt, W.J., Tsimashenka, I.: Reducing subtask dispersion in parallel systems. In: Trends in Parallel, Distributed, Grid and Cloud Computing for Engineering, ch. 9, pp. 203–227. Saxe-Coburg Publications (April 2013)Google Scholar
- 17.Lebrecht, A., Knottenbelt, W.J.: Response Time Approximations in Fork-Join Queues. In: 23rd Annual UK Performance Engineering Workshop, UKPEW 2007 (July 2007)Google Scholar
- 24.Tsimashenka, I., Knottenbelt, W.J.: Reduction of Variability in Split-Merge Systems. In: Imperial College Computing Student Workshop (ICCSW 2011), pp. 101–107 (2011)Google Scholar
- 30.Zhao, H., Xia, C.H., Liu, Z., Towsley, D.: A unified modeling framework for distributed resource allocation of general fork and join processing networks. In: Proc. ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2010), pp. 299–310. ACM, New York (2010)Google Scholar