ESTIMATING BOTTLENECKS OF VERY LARGE MODELS

Queueing theory has been extensively used since 70’s to carry out performance evaluations of complex computer systems. However, handling the complexity of modern computer networks with thousands of servers and millions of customers is still a challenge. Indeed, although the identification of product-form queueing networks has promoted the development of computationally tractable exact solution techniques, the dimensionality of “very large” models makes it difficult to meet the requirements of either exact and approximate algorithms. In this paper we focus on the bottleneck analysis as a technique that may provide answers to many capacity planning questions (e.g., “which is the maximum number of transactions per second the computer system is able to process?” or “which is the minimum response time that can be achieved per transaction?”) for “very large” computer installations with a limited complexity. The problem to be solved with this technique is the identification of the set of resources that may saturate among the thousands of components. We show some results concerning the application of the theory of convex polyhedra to bottleneck analysis that can sensibly reduce the complexity of the analysis. The connections between this technique and the behavior of closed and open models are also investigated.

[1]  Harry G. Perros,et al.  Some Equivalencies Between Closed Queueing Networks with Blocking , 1989, Perform. Evaluation.

[2]  John Zahorjan,et al.  Accuracy, Speed, and Convergence of Approximate Mean Value Analysis , 1988, Perform. Evaluation.

[3]  John Zahorjan,et al.  Balanced job bound analysis of queueing networks , 1982, CACM.

[4]  Derek L. Eager,et al.  Bound hierarchies for multiple-class queuing networks , 1986, JACM.

[5]  Derek L. Eager,et al.  The AMVA Priority Approximation , 1988, Perform. Evaluation.

[6]  Teemu Kerola.  The Composite Bound Method for Computing Throughput Bounds in Multiple Class Environments , 1986, Perform. Evaluation.

[7]  Satish K. Tripathi,et al.  Single-class bounds of multi-class queuing networks , 1992, JACM.

[8]  Charles H. Sauer,et al.  The Tree MVA Algorithm , 1985, Perform. Evaluation.

[9]  Giuseppe Serazzi,et al.  Asymptotic Analysis of Multiclass Closed Queueing Networks: Multiple Bottlenecks , 1997, Perform. Evaluation.

[10]  Luis G. Vargas.  Review: Marcel F. Neuts, Matrix-geometric solutions in stochastic models, an algorithmic approach , 1983 .

[11]  K. Mani Chandy,et al.  The MVA priority approximation , 1984, TOCS.

[12]  Peter G. Harrison,et al.  On the asymptotic behaviour of closed multiclass queueing networks , 2002, Perform. Evaluation.

[13]  F. R. Moore,et al.  Computational model of a closed queuing network with exponential servers , 1972 .

[14]  James R. Jackson,et al.  Jobshop-Like Queueing Systems , 2004, Manag. Sci..

[15]  Eugene Wong,et al.  The solution of separable queueing network models using mean value analysis , 1981, SIGMETRICS '81.

[16]  Ian F. Akyildiz,et al.  Exact Product Form Solution for Queueing Networks with Blocking , 1987, IEEE Transactions on Computers.

[17]  K. G. Ramakrishnan,et al.  A class of closed Markovian queuing networks: integral representations, asymptotic expansions, and generalizations , 1981, The Bell System Technical Journal.

[18]  K. Mani Chandy,et al.  Linearizer: a heuristic algorithm for queueing network models of computing systems , 1982, CACM.

[19]  Jiri Kriz,et al.  Throughput bounds for closed queueing networks , 1984, Perform. Evaluation.

[20]  K. Mani Chandy,et al.  Open, Closed, and Mixed Networks of Queues with Different Classes of Customers , 1975, JACM.

[21]  Stephen S. Lavenberg,et al.  Mean-Value Analysis of Closed Multichain Queuing Networks , 1980, JACM.

[22]  W. J. Gordon,et al.  Closed Queuing Systems with Exponential Servers , 1967, Oper. Res..

[23]  Steven C. Bruell,et al.  A tree-structured mean value analysis algorithm , 1986, TOCS.

[24]  K. G. Ramakrishnan,et al.  Panacea: An Integrated Set of Tools for Performance Analysis , 1989 .

[25]  Jonathan R Goodman,et al.  The non-ergodic Jackson network , 1984 .

[26]  Simonetta Balsamo,et al.  Product Form Queueing Networks , 2000, Performance Evaluation.

[27]  Jeffrey P. Buzen,et al.  Computational algorithms for closed queueing networks with exponential servers , 1973, Commun. ACM.

[28]  Hisashi Kobayashi,et al.  A Computational Algorithm for Queue Distributions via the Pólya Theory of Enumeration , 1979, International Symposium on Computer Modeling, Measurement and Evaluation.

[29]  Stephen S. Lavenberg,et al.  Calculating joint queue-length distributions in product-form queuing networks , 1988, JACM.

[30]  Hisashi Kobayashi,et al.  Queuing Networks with Multiple Closed Chains: Theory and Computational Algorithms , 1975, IBM J. Res. Dev..

[31]  Stephen S. Lavenberg,et al.  Stationary state probabilities at arrival instants for closed queueing networks with multiple types of customers , 1980, Journal of Applied Probability.

[32]  Nicolas D. Georganas,et al.  RECAL—a new efficient algorithm for the exact analysis of multiple-chain closed queuing networks , 1986, JACM.

[33]  Stephen S. Lavenberg,et al.  Mean Value Analysis by Chain of Product Form Queueing Networks , 1989, IEEE Trans. Computers.

[34]  Peter J. Denning,et al.  The Operational Analysis of Queueing Network Models , 1978, CSUR.

[35]  We-Min Chow.  Approximations for large scale closed queueing networks , 1983, Perform. Evaluation.

[36]  Isi Mitrani,et al.  The Distribution of Queuing Network States at Input and Output Instants , 1979, JACM.

[37]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[38]  Giuseppe Serazzi,et al.  A Survey of Bottleneck Analysis in Closed Networks of Queues , 1993, Performance/SIGMETRICS Tutorials.

[39]  David Avis,et al.  How good are convex hull algorithms? , 1995, SCG '95.

[40]  Yonathan Bard,et al.  Some Extensions to Multiclass Queueing Network Analysis , 1979, Performance.

[41]  Franco P. Preparata,et al.  Computational Geometry , 1985, Texts and Monographs in Computer Science.

[42]  Luke Y.-C. Lien,et al.  A tree convolution algorithm for the solution of queueing networks , 1983, CACM.

[43]  Giuseppe Serazzi,et al.  A Unifying Framework for the Approximate Solution of Closed Multiclass Queuing Networks , 2002, IEEE Trans. Computers.

[44]  Giuseppe Serazzi,et al.  Asymptotic Analysis of Multiclass Closed Queueing Networks: Common Bottleneck , 1996, Perform. Evaluation.

[45]  Marcel F. Neuts,et al.  Matrix-geometric solutions in stochastic models - an algorithmic approach , 1982 .