This Article 
 Bibliographic References 
 Add to: 
The Stochastic Rendezvous Network Model for Performance of Synchronous Client-Server-like Distributed Software
January 1995 (vol. 44 no. 1)
pp. 20-34

Abstract—Distributed or parallel software with synchronous communication via rendezvous is found in client-server systems and in proposed Open Distributed Systems, in implementation environments such as Ada, V, Remote Procedure Call systems, in Transputer systems, and in specification techniques such as CSP, CCS and LOTOS. The delays induced by rendezvous can cause serious performance problems, which are not easy to estimate using conventional models which focus on hardware contention, or on a restricted view of the parallelism which ignores implementation constraints. Stochastic Rendezvous Networks are queueing networks of a new type which have been proposed as a modelling framework for these systems. They incorporate the two key phenomena of included service and a second phase of service. This paper extends the model to also incorporate different services or entries associated with each task. Approximations to arrival-instant probabilities are employed with a Mean-Value Analysis framework, to give approximate performance estimates. The method has been applied to moderately large industrial software systems.

Index Terms—Client-server, performance, remote procedure call, software performance, distributed software, rendezvous networks, multiple entries.

[1] D. Bowen,“Open distributed processing,”Comput. Netw. and ISDN Syst., vol. 23, pp. 195–201, 1991.
[2] C.A.R. Hoare, Communicating Sequential Processes, Prentice Hall, Englewood Cliffs, N.J., 1985.
[3] C.M. Woodside, “Throughput Calculation for Basic Stochastic Rendezvous Networks,” Performance Evaluation, vol. 9, pp. 143-160, 1989.
[4] C. M. Woodside and G. M. Yee,“Traffic relationships in networks of tasks,”inProc. IEEE Infocom '89, Apr. 1989, pp. 1040–1049.
[5] C. M. Woodside, J. E. Neilson, J. W. Miernik, D. C. Petriu, and R. Constantin,“Performance of concurrent rendezvous systems with complex pipeline structures,”inProc. 4th Int. Conf. Modelling Tech. and Tools for Comput. Perform. Eval., Sept. 1988, pp. 361–378.
[6] C. M. Woodside, E. Neron, E. D. S. Ho, and B. Mondoux,“An `active-server' model for the performance of parallel programs written using rendezvous,”J. Syst. and Software, vol. 6, pp. 125–132, 1986.
[7] G. Ciardo and K. S. Trivedi,“Solution of large GSPN models,”inProc. First Int. Conf. Numerical Solution of Markov Chains, North Carolina State Univ., Raleigh, NC, Jan. 1990, pp. 603–626.
[8] D. C. Petriu and C. M. Woodside,“Approximate MVA from Markov model of software client/server systems,”inThird IEEE Symp. Parallel Distrib. Processing, Dallas, TX, Dec. 1991, pp. 322–329.
[9] Reference Manual for the Ada Programming Language ANSI-MIL-STD 1815. U.S. Dep. of Defense, Jan. 1983.
[10] D. R. Cheriton,“The V kernel: A software base for distributed systems,”IEEE Software, vol. 1, no. 2, pp. 19–42, Apr. 1984.
[11] E.D. Lazowska, J. Zahorjan, G.S. Graham, and K.C. Sevcik, Quantitative System Performance, Prentice Hall, pp 64-66, 1984.
[12] L. Flatto and S. Hahn,“Two parallel queues created by arrivals with two demands,”SIAM Appl. Math., vol. 44, no. 5, pp. 1041–1053, Oct. 1984.
[13] P. Goyer, P. Momtahan, and B. Selic,“A synchronization service for locally distributed applications,”inDistributed Processing. Amsterdam: Elsevier Science Publishers B. V., North-Holland, 1988.
[14] P. Heidelberger and K. S. Trivedi,“Analytic queueing models for programs with internal concurrency,”IEEE Trans. Comput., vol. C-32, no. 1, pp. 73–82, Jan. 1983.
[15] J. A. Rolia,“Performance estimates for systems with software servers: The lazy boss method,”inProc. VIII SCCC Int. Conf. Comput. Sci., July 1988.
[16] J. A. Rolia“Predicting the performance of software systems,”Ph.D thesis, Univ. of Toronto, Jan. 1992.
[17] J.L. Peterson, Petri Net Theory and the Modeling of Systems.Englewood Cliffs, N.J.: Prentice Hall, 1981.
[18] J. W. Miernik, C. M. Woodside, J. E. Neilson, and D. C. Petriu,“Performance of stochastic rendezvous networks with priority tasks,”InProc. Int. Seminar on Perform. Distrib. Parallel Syst., Dec. 1988, pp. 501–515.
[19] J. W. Miernik, C. M. Woodside, J. E. Neilson, and D. C. Petriu,“Throughput of stochastic rendezvous networks with caller-specific service and processor contention,”inProc. IEEE Infocom '88, Mar. 1988, pp. 1040–1049.
[20] M. A. Holliday and M. K. Vernon,“A generalized timed Petri net model for performance analysis,”IEEE Trans. Software Eng., vol. SE-13, pp. 1297–1310, Dec. 1987.
[21] M.Ajmone Marsan,G. Balbo,, and G. Conte,“A class of generalized stochastic Petri nets for the performance evaluation of multiprocessor systems,” ACM Trans. Computer Systems, pp. 93-122, vol. 2, no. 2, May 1984.
[22] M. J. Fontenot,“Software congestion, mobile servers, and the hyperbolic model,”IEEE Trans. Software Eng., vol. 15, pp. 947–962, 1989.
[23] S. Majumdar, C. M. Woodside, J. E. Neilson, and D. C. Petriu,“Performance bounds for concurrent software with rendezvous,”Perform, Eval., vol. 13, pp. 207–236, 1991.
[24] R. Milner, A Calculus of Communicating Systems. Berlin: Springer Verlag, vol. 92, 1980.
[25] O. S. I.,“LOTOS: A formal description technique based on temporal ordering of observational behavior,”Int. Organization for Standardization, Inform. Processing Systems, Open Syst. Interconnect., vol. ISO8807, 1988.
[26] D. C. Petriu,“Approximate mean value analysis of client-server systems with multi-class requests,”inProc. of ACM Sigmetrics Conf. on Measurement and Modeling of Computer Systems, Nashville, TN, May 1994, pp. 77–86.
[27] R. M. Bryant, A. E. Krzesinski, M. S. Lakshmi and K. M. Chandy,“The MVA priority approximation,”ACM Trans. Comput. Syst., vol. 2, no. 4, pp. 335–359, Nov. 1984.
[28] M. Reiser,“A queueing analysis of computer communication networks with window flow control,”IEEE Trans. Commun., vol. COM-27, pp. 1199–1209, Aug. 1979.
[29] S. C. Agrawal and J. P. Buzen,“The aggregate server method for analyzing serialization delays in computer systems,”ACM Trans. Comput. Syst., vol. 1, no. 2, pp. 116–143, May 1983.
[30] S.S. Lavenberg, Computer Performance Modeling Handbook. Academic Press, 1983.
[31] S. S. Lavenberg and M. Reiser,“Stationary state probabilities at arrival instants for closed queueing networks with multiple types of customers,”J. Appl. Probab., vol. 17, pp. 1048–1061, 1980.
[32] J. Zahorjan, E. D. Lazowska, and D. L. Eager,“Spinning versus blocking in parallel systems with uncertainty,”presented at theInt. Sem. Perform. of Distrib. Parallel Syst., Dec. 1988.
[33] E. de Souza e Silva and R. R. Muntz,“Approximate solutions for a class of non-product form queueing network models,”Perform. Eval., vol. 7, pp. 221–242, 1987.
[34] E. de Souza e Silva,S.S. Lavenberg,, and R.R. Muntz., “A perspective oniterative methods for the approximate analysis of closed queueingnetworks,” G. Iazeolla, P.J. Courtois, and A Hordijk, eds., Math. Computer Performance and Reliability.New York: Elsevier Science, 1984.

C. Murray Woodside, John E. Neilson, Dorina C. Petriu, and Shikharesh Majumdar, "The Stochastic Rendezvous Network Model for Performance of Synchronous Client-Server-like Distributed Software," IEEE Transactions on Computers, vol. 44, no. 1, pp. 20-34, Jan. 1995, doi:10.1109/12.368012
Usage of this product signifies your acceptance of the Terms of Use.