Understanding Scalability Issues for a Distributed Simulation Environment Using Intelligent Coordinated Entities

Distributed applications are no longer an exception to software architecture design. Scalability is a strong motivation of many organizations to implement a distributed application. This paper presents a scalability case study using a distributed highway simulation environment. We report on improving an application’s scalability using different measures related to the simulation architecture. Specifically, we study thread reorganization and network communication reorganization issues and their effect on scalability. We use performance and efficiency as the main tests for application scalability considerations. We use CPU overheads (measured in terms of CPU utilization), collision detection, thread sleep cycle, and network efficiency as the measures for testing performance and efficiency. We adopt a scheme with successive modifications, so that we can learn from each individual effort to improve scalability and judge collectively improvements.

[1]  Gordon Lyon.  Comparing Two Distinct Approaches to Scalability Testing , 1996 .

[2]  Srini Ramaswamy,et al.  A Three-Tier Communication and Control Structure for the Distributed Simulation of an Automated Highway System , 2002 .

[3]  Pere Vilà,et al.  SCALABILITY STUDY AND DISTRIBUTED SIMULATIONS OF AN ATM NETWORK MANAGEMENT SYSTEM BASED ON INTELLIGENT AGENTS , 2000 .

[4]  Willy Zwaenepoel,et al.  Performance and scalability of EJB applications , 2002, OOPSLA '02.

[5]  Tian He,et al.  MAC Layer Abstraction for Simulation Scalability Improvements , 2001 .

[6]  Ian Foster,et al.  Designing and building parallel programs , 1994 .

[7]  David M. Nicol.  Scalability, locality, partitioning and synchronization PDES , 1998, Workshop on Parallel and Distributed Simulation.

[8]  Peter Druschel,et al.  Design and scalability of NLS, a scalable naming and location service , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

[9]  Connie U. Smith,et al.  Performance and Scalability of Distributed Software Architectures: An SPE Approach , 2000, Scalable Comput. Pract. Exp..

[10]  Dan Shen,et al.  Performance and Scalability of a Large-Scale N-gram Based Information Retrieval System , 2000, J. Digit. Inf..

[11]  Sandeep K. Singhal,et al.  Using projection aggregations to support scalability in distributed simulation , 1996, Proceedings of 16th International Conference on Distributed Computing Systems.

[12]  Wei Hu,et al.  Scalability in the XFS File System , 1996, USENIX Annual Technical Conference.