AMVA techniques for high service time variability

Motivated by experience gained during the validation of a recent Approximate Mean Value Analysis (AMVA) model of modern shared memory architectures, this paper re-examines the “standard” AMVA approximation for non-exponential FCFS queues. We find that this approximation is often inaccurate for FCFS queues with high service time variability. For such queues, we propose and evaluate: (1) AMVA estimates of the mean residual service time at an arrival instant that are much more accurate than the standard AMVA estimate, (2) a new AMVA technique that provides a much more accurate estimate of mean center residence time than the standard AMVA estimate, and (3) a new AMVA technique for computing the mean residence time at a “downstream” queue which has a more bursty arrival process than is assumed in the standard AMVA equations. Together, these new techniques increase the range of applications to which AMVA may be fruitfully applied, so that for example, the memory system architecture of shared memory systems with complex modern processors can be analyzed with these computationally efficient methods.

[1]  Mary K. Vernon,et al.  Managing server load in global memory systems , 1997, SIGMETRICS '97.

[2]  Josep Torrellas,et al.  Analysis of Critical Architectural and Program Parameters in a Hierarchical Shared Memory Multiprocessor , 1990, SIGMETRICS.

[3]  Mary K. Vernon,et al.  Comparison of hardware and software cache coherence schemes , 1991, ISCA '91.

[4]  Jean-Loup Baer,et al.  A performance evaluation of cluster architectures , 1997, SIGMETRICS '97.

[5]  Jean-Loup Baer,et al.  A Performance Evaluation of Cluster-Based Architectures , 1997, SIGMETRICS.

[6]  Leonard Kleinrock,et al.  Theory, Volume 1, Queueing Systems , 1975 .

[7]  Ward Whitt,et al.  The Influence of Service-Time Variability in a Closed Network of Queues , 1986, Perform. Evaluation.

[8]  Mary K. Vernon,et al.  LoPC: modeling contention in parallel algorithms , 1997, PPOPP '97.

[9]  Jignesh M. Patel,et al.  Accurate Modeling of the Hybrid Hash Join Algorithm , 1994, SIGMETRICS.

[10]  Edward D. Lazowska,et al.  Quantitative system performance - computer system analysis using queueing network models , 1983, Int. CMG Conference.

[11]  M. Reiser,et al.  A Queueing Network Analysis of Computer Communication Networks with Window Flow Control , 1979, IEEE Trans. Commun..

[12]  Mary K. Vernon,et al.  Performance Analysis of Hierarchical Cache-Consistent Multiprocessors , 1989, Perform. Evaluation.

[13]  Yonathan Bard.  A simple approach to system modeling , 1981, Perform. Evaluation.

[14]  M. Thomas.  Queueing Systems. Volume 1: Theory (Leonard Kleinrock) , 1976 .

[15]  Edward D. Lazowska,et al.  A decomposition approach to modelling high service time variability , 1983, Perform. Evaluation.

[16]  Yelena Yesha,et al.  An analytic model of hierarchical mass storage systems with network-attached storage devices , 1996, SIGMETRICS '96.

[17]  Peter G. Harrison,et al.  An Analytical Model of the Standard Coherent Interface "SCI" , 1995, ICPP.

[18]  Mary K. Vernon,et al.  Performance Analysis of Mesh Interconnection Networks with Deterministic Routing , 1994, IEEE Trans. Parallel Distributed Syst..

[19]  Mary K. Vernon,et al.  An accurate and efficient performance analysis technique for multiprocessor snooping cache-consistency protocols , 1988, ISCA '88.

[20]  Yonathan Bard,et al.  A model of shared dasd and multipathing , 1980 .

[21]  D. Cox.  A use of complex probabilities in the theory of stochastic processes , 1955, Mathematical Proceedings of the Cambridge Philosophical Society.

[22]  T.-F. Tsuei,et al.  A Multiprocessor Bus Design Model Validated by System Measurement , 1992, IEEE Trans. Parallel Distributed Syst..

[23]  Anant Agarwal,et al.  Evaluating the performance of software cache coherence , 1989, ASPLOS III.

[24]  M.-C. Chiang,et al.  Evaluating Design Choices for Shared Bus Multiprocessors in a Throughput-Oriented Environment , 1992, IEEE Trans. Computers.

[25]  Mary K. Vernon,et al.  Measurements and prediction of contention in multiprocessor operating systems with scientific application workloads , 1988, ICS '88.

[26]  Mary K. Vernon,et al.  A mean-value performance analysis of a new multiprocessor architecture , 1988, SIGMETRICS 1988.