Distributed Response Time Analysis of GSPN Models with MapReduce

Authors:
Oliver J. Haggarty;William J. Knottenbelt;Jeremy T. Bradley
Affiliations:
Department of Computing Imperial College London 180Queen's Gate, London SW7 2BZ, UK;Department of Computing Imperial College London 180Queen's Gate, London SW7 2BZ, UK;Department of Computing Imperial College London 180Queen's Gate, London SW7 2BZ, UK
Venue:
Simulation
Year:
2009

Citing 7
Cited 1

The Fourier-series method for inverting transforms of probability distributions

Queueing Systems: Theory and Applications - Numerical computations in queues
Passage time distributions in large Markov chains

SIGMETRICS '02 Proceedings of the 2002 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Response time densities in generalised stochastic petri net models

WOSP '02 Proceedings of the 3rd international workshop on Software and performance
The ipc/HYDRA Tool Chain for the Analysis of PEPA Models

QEST '04 Proceedings of the The Quantitative Evaluation of Systems, First International Conference
Uniformization and hypergraph partitioning for the distributed computation of response time densities in very large Markov models

Journal of Parallel and Distributed Computing
MapReduce: simplified data processing on large clusters

OSDI'04 Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation - Volume 6
MapReduce for Data Intensive Scientific Analyses

ESCIENCE '08 Proceedings of the 2008 Fourth IEEE International Conference on eScience

Simulation-based optimization of discrete event systems with alternative structural configurations using distributed computation and the Petri net paradigm

Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Generalized stochastic Petri nets (GSPNs) are widely used in the performance analysis of computer and communications systems. Response time densities and quantiles are often key outputs of such analysis. These can be extracted from a GSPN's underlying semi-Markov process using a method based on numerical Laplace transform inversion. This method typically requires the solution of thousands of systems of complex linear equations, each of rank n, where n is the number of states in the model. For large models substantial processing power is needed and the computation must therefore be distributed. In this paper we describe the implementation of a response time analysis module for the Platform Independent Petri net Editor (PIPE2) which interfaces with Hadoop, an open-source implementation of Google's MapReduce distributed programming environment, to provide distributed calculation of response time densities in GSPN models. The software is validated with results calculated analytically as well as simulated results for larger models. Excellent scalability is shown.