Abstract
We study the conditional sojourn time distributions of processor sharing (PS), foreground background processor sharing (FBPS) and shortest remaining processing time first (SRPT) scheduling disciplines on an event where the job size of a customer arriving in stationarity is smaller than exactly k≥0 out of the preceding m≥k arrivals. Then, conditioning on the preceding event, the sojourn time distribution of this newly arriving customer behaves asymptotically the same as if the customer were served in isolation with a server of rate (1−ρ)/(k+1) for PS/FBPS, and (1−ρ) for SRPT, respectively, where ρ is the traffic intensity. Hence, the introduced notion of conditional limits allows us to distinguish the asymptotic performance of the studied schedulers by showing that SRPT exhibits considerably better asymptotic behavior for relatively smaller jobs than PS/FBPS.
Inspired by the preceding results, we propose an approximation to the SRPT discipline based on a novel adaptive job grouping mechanism that uses relative size comparison of a newly arriving job to the preceding m arrivals. Specifically, if the newly arriving job is smaller than k and larger than m−k of the previous m jobs, it is routed into class k. Then, the classes of smaller jobs are served with higher priorities using the static priority scheduling. The good performance of this mechanism, even for a small number of classes m+1, is demonstrated using the asymptotic queueing analysis under the heavy-tailed job requirements. We also discuss refinements of the comparison grouping mechanism that improve the accuracy of job classification at the expense of a small additional complexity.
Similar content being viewed by others
References
Anantharam, V. (1999). Scheduling strategies and long-range dependence. Queueing Systems: Theory and Applications, 33(1–3), 73–89.
Asmussen, S., Schmidli, H., & Schmidt, V. (1999). Tail probabilities for non-standard risk and queueing processes with subexponential jumps. Advances in Applied Probability, 31(2), 422–447.
Baccelli, F., & Bremaud, P. (1994). Elements of queueing theory: Palm-Martingale calculus and stochastic recurrence. Berlin: Springer.
Bansal, N., & Gamarnik, D. (2006). Handling load with less stress. Queueing systems: Theory and Applications, 54(1), 45–54.
Bansal, N., & Harchol-Balter, M. (2001). Analysis of SRPT scheduling: investigating unfairness. In Proceedings of ACM SIGMETRICS & Performance’01 (pp. 279–290). Cambridge, MA.
Borst, S., Boxma, O., & Jelenković, P. (2003a). Reduced-load equivalence and induced burstiness in GPS queues with long-tailed traffic flows. Queueing Systems: Theory and Applications, 43(4), 273–306.
Borst, S. C., Boxma, O. J., Núñez-Queija, R., & Zwart, A. P. (2003b). The impact of the service discipline on delay asymptotics. Performance Evaluation, 54(2), 175–206.
Caprita, B., Nieh, J., & Stein, C. (2006). Grouped distributed queues: distributed queue, proportional share multiprocessor scheduling. In PODC’06: Proceedings of the twenty-fifth annual ACM symposium on principles of distributed computing (pp. 72–81), New York, NY, USA.
Harchol-Balter, M., Schroeder, B., Bansal, N., & Agrawal, M. (2003). Size-based scheduling to improve Web performance. ACM Transactions on Computer Systems (TOCS), 21(2), 207–233.
Jelenković, P. R., & Lazar, A. A. (1998). Subexponential asymptotics of a Markov-modulated random walk with queueing applications. Journal of Applied Probability, 35(2), 325–347.
Jelenković, P. R., & Momčilović, P. (2002). Resource sharing with subexponential distributions. In Proceedings of IEEE INFOCOM’02 (Vol. 3, pp. 1316–1325). New York, NY, USA.
Jelenković, P. R., & Momčilović, P. (2003a). Asymptotic loss probability in a finite buffer fluid queue with heterogeneous heavy-tailed on-off processes. Annals of Applied Probability, 13(2), 576–603.
Jelenković, P. R., & Momčilović, P. (2003b). Large deviation analysis of subexponential waiting times in a processor-sharing queue. Mathematics of Operations Research, 28(3), 587–608.
Jelenković, P. R., Kang, X., & Tan, J. (2007). Adaptive and scalable comparison scheduling. In Proceedings of ACM SIGMETRICS’07 (Vol. 35, No. 1, pp. 215–226). San Diego, CA, USA.
Kleinrock, L. (1976). Queueing systems volume II: computer applications. New York: Wiley-Interscience.
Loynes, R. M. (1962). The stability of a queue with non-independent inter-arrival and service times. Mathematical Proceedings of the Cambridge Philosophical Society, 58, 497–520.
Núñez-Queija, R. (2000). Processor-sharing models for integrated-services networks. PhD thesis, Eindhoven University of Technology, the Netherlands.
Nuyens, M., & Zwart, B. (2006). A large-deviations analysis of the GI/GI/1 SRPT queue. Queueing Systems: Theory and Applications, 54(2), 85–97.
Nuyens, M., Wierman, A., & Zwart, B. (2008). Preventing large sojourn times using SMART scheduling. Operations Research, 56(1), 88–101.
Pakes, A. (1975). On the tails of waiting-time distributions. Journal of Applied Probability, 12(3), 555–564.
Palmowski, Z., & Rolski, T. (2006). On the exact asymptotics of the busy period in GI/G/1 queues. Advances in Applied Probability, 38, 792–803.
Park, K., & Willinger, W. (Eds.). (2000). Self-similar network traffic and performance evaluation. New York: Wiley.
Rai, I. A., Urvoy-Keller, G., Vernon, M. K., & Biersack, E. W. (2004). Performance analysis of LAS-based scheduling disciplines in a packet switched network. In SIGMETRICS/Performance ’04 (pp. 106–117). New York, NY, USA.
Rai, I. A., Biersack, E. W., & Urvoy-Keller, G. (2005). Size-based scheduling to improve the performance of short TCP flows. IEEE Network, 19(1), 12–17.
Ramanan, K., & Stolyar, A. L. (2001). Largest weighted delay first scheduling: Large deviations and optimality. Annals of Applied Probability, 11(1), 1–48.
Rawat, M., & Kshemkalyani, A. (2003). SWIFT: Scheduling in web servers for fast response time. In Proceedings of the second IEEE international symposium on network computing and applications (p. 15). Los Alamitos, CA, USA.
Schrage, L. E. (1968). A proof of the optimality of the shortest remaining processing time discipline. Operations Research, 16(3), 687–690.
Schrage, L. E., & Miller, L. W. (1966). The queue M/G/1 with the shortest remaining processing time discipline. Operations Research, 14(4), 670–684.
Squillante, M. S., Yao, D. D., & Zhang, L. (1999). Web traffic modeling and Web server performance analysis. ACM SIGMETRICS Performance Evaluation Review, 27(3), 24–27.
Wierman, A., & Harchol-Balter, M. (2003). Classifying scheduling policies with respect to unfairness in an M/GI/1. In Proceedings of ACM SIGMETRICS’03 (pp. 238–249). San Diego, CA, USA.
Wolff, R. W. (1989). Stochastic modeling and theory of queues. New York: Prentice Hall.
Zwart, A. P., & Boxma, O. J. (2000). Sojourn time asymptotics in the M/G/1 processor sharing queue. Queueing Systems, 35(1–4), 141–166.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work is supported by NSF Grant 0615126.
Rights and permissions
About this article
Cite this article
Jelenković, P.R., Kang, X. & Tan, J. Heavy-tailed limits for medium size jobs and comparison scheduling. Ann Oper Res 170, 133–159 (2009). https://doi.org/10.1007/s10479-008-0432-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10479-008-0432-0