Abstract
We consider a distributed server system model and ask which policy should be used for assigning tasks to hosts. In our model each host processes tasks in First-Come-First-Serve order and the task’s service demand is known in advance. We consider four task assignment policies commonly proposed for such distributed server systems: Round-Robin, Random, Size-Based, in which all tasks within a give size range are assigned to a particular host, and Dynamic-Least-Work-Remaining, in which a task is assigned to the host with the least outstanding work. Our goal is to understand the inuence of task size variability on the decision of which task assignment policy is best. We find that no one of the above task assignment policies is best and that the answer depends critically on the variability in the task size distribution. In particular we find that when the task sizes are not highly variable, the Dynamic policy is preferable. However when task sizes show the degree of variability more characteristic of empirically measured computer workloads, the Size-Based policy is the best choice. We use the resulting observations to argue in favor of a specific size-based policy, SITA-E, that can out-perform the Dynamic policy by almost 2 orders of magnitude and can outperform other task assignment policies by many orders of magnitude, under a realistic task size distribution.
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.
Supported by the NSF Postdoctoral Fellowship in the Mathematical Sciences.
Supported in part by NSF Grants CCR-9501822 and CCR-9706685.
Supported by a grant from CAPES, Brazil.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M. E. Crovella and A. Bestavros. Self-similarity in World Wide Web traffic: Evidence and possible causes. IEEE/ACM Transactions on Networking, 5(6):835–846, December 1997.
M. E. Crovella and L. Lipsky. Long-lasting transient conditions in simulations with heavy-tailed workloads. In 1997 Winter Simulation Conference, 1997.
M. E. Crovella, M. S. Taqqu, and A. Bestavros. Heavy-tailed probability distributions in the world wide web. In A Practical Guide To Heavy Tails, pages 1–23. Chapman & Hall, New York, 1998.
M. Harchol-Balter, M. E. Crovella, and C. D. Murta. On choosing a task assignment policy for a distributed server system. Technical Report MIT-LCS-TR-757, MIT Laboratory for Computer Science, 1998.
M. Harchol-Balter and A. Downey. Exploiting process lifetime distributions for dynamic load balancing. ACM Transactions on Computer Systems, 15(3), 1997.
S. Hotovy, D. Schneider, and T. O’Donnell. Analysis of the early workload on the Cornell Theory Center IBM SP2. Technical Report 96TR234, CTC, Jan. 1996.
G. Irlam. Unix file size survey. http://www.base.com/gordoni/ufs93.html, 1994.
W. E. Leland and T. J. Ott. Load-balancing heuristics and process behavior. In Proceedings of Performance and ACM Sigmetrics, pages 54–69, 1986.
R. D. Nelson and T. K. Philips. An approximation for the mean response time for shortest queue routing with general interarrival and service times. Performance Evaluation, 17:123–139, 1998.
V. Paxson and S. Floyd. Wide-area traffic: The failure of Poisson modeling. IEEE/ACM Transactions on Networking, pages 226–244, June 1995.
D. L. Peterson and D. B. Adams. Fractal patterns in DASD I/O traffic. In CMG Proceedings, December 1996.
R. W. Weber. On the optimal assignment of customers to parallel servers. Journal of Applied Probability, 15:406–413, 1978.
Ward Whitt. Deciding which queue to join: Some counterexamples. Operations Research, 34(1):226–244, January 1986.
W. Winston. Optimality of the shortest line discipline. Journal of Applied Probability, 14:181–189, 1977.
R. W. Wolff. Stochastic Modeling and the Theory of Queues. Prentice Hall, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Harchol-Balter, M., Crovella, M.E., Murta, C.D. (1998). On Choosing a Task Assignment Policy for a Distributed Server System. In: Puigjaner, R., Savino, N.N., Serra, B. (eds) Computer Performance Evaluation. TOOLS 1998. Lecture Notes in Computer Science, vol 1469. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-68061-6_19
Download citation
DOI: https://doi.org/10.1007/3-540-68061-6_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64949-6
Online ISBN: 978-3-540-68061-1
eBook Packages: Springer Book Archive