Elsevier

Computer Networks

Volume 31, Issue 18, 17 August 1999, Pages 1891-1910
Computer Networks

Maximum delivery time and hot spots in ServerNetTM topologies

https://doi.org/10.1016/S1389-1286(98)00024-3Get rights and content
Under a Creative Commons license
open archive

Abstract

This paper will center on analysis of the performance characteristics of ServerNet topologies, concentrating on the prediction, through simulation and statistical analysis, of the maximum two-way delivery time, the identification of congested links (hot spots) and tree saturation.

ServerNetTM, developed by Tandem Computers Inc., is a wormhole-routed, packet-switched, point-to-point network, with special attention paid to reducing latency and to assuring reliability. ServerNet uses multiple high-speed, low-cost routers to rapidly switch data directly between data sources and destinations.

The maximum two-way delivery time is necessary for determining the values of timeout counters, which are relevant to the fault-tolerant aspect of the system, and the QoS guarantees.

Hot spots may cause the occurrence of tree saturation in the network i.e., where an individual tree will become congested (tree saturation) while all other trees are mostly idle, which leads to significant performance degradation.

Our study is based on data generated by a simulation tool. Statistical analysis and inference methods were used to process the samples generated by the simulator and to obtain estimates for the maximum two-way packet delivery time. These methods were also used to determine the number of the samples that were required to produce estimates of the desired accuracy. Both the degree of confidence and the percentage of packets are determined by the number of samples generated by the simulator. This allows us to control the quality and accuracy of the estimate to suit our needs.

Link usage statistics were recorded by the simulator for the purpose of performing a detailed investigation of congestion effects and hot spots. The study of the static and dynamic link usage statistics revealed that the extreme values of the two-way maximum delivery time were caused by links operating under heavy traffic loads and that under certain traffic patterns a tree saturation effect occurs.

Keywords

Networks
Performance
Simulation
Maximum delivery time
Hot spot
Tree saturation

Cited by (0)

Dimiter R. Avresky is an associate professor in the Department of Electrical Engineering at Boston University, Boston, MA, USA. His research interests focus on hardware & software fault-tolerant systems, network computing, parallel computers, performance evaluation, testing and fault-injection. He has published more than 80 papers in that area. He is a head of Network Computing Research Lab. He is an editor and co-author of “Hardware and Software Fault-Tolerance in Parallel Computing Systems”, 1992, “Fault-Tolerant Parallel and Distributed Systems”, 1995, IEEE Computer Society, USA and “Fault-Tolerant Parallel and Distributed Systems”, Kluwer Academic Publishers, USA. He is a Member of IEEE and The New York Academy of Sciences.

Vladimir Shurbanov received the M.S. degree in Computer Systems from the Higher Institute of Mechanical and Electrical Engineering, Sofia, Bulgaria. He is currently pursuing a Ph.D. degree at the Department of Electrical and Computer Engineering at Boston University, Boston, MA, USA. His research interests include simulation, performance evaluation, and analysis and optimization of interconnection networks.

Robert Horst is a Technical Director in Compaq Tandem Labs. He led the ServerNet architecture team, and has contributed to the architecture and design of several generations of fault tolerant systems. He received the B.S. degree in Electrical Engineering from Bradley University in 1975, the M.S.E.E. from University of Illinois in 1976 and a Ph.D. in Computer Science from the University of Illinois in 1991. He holds 35 patents in computer architecture, fault tolerant computing, and high performance networks.

William J. Watson works in Austin, Texas for the Tandem Division of Compaq Computer Corporation. He received a B.S.E.E. from Rice University in 1983, and worked from ROLM Corporation and KMW Systems Corporation before joining Tandem Computers, Inc. in 1989. He has worked on the ServerNet protocols, system architecture, and ASIC design in the Parallel Systems Group since 1991. He may be reached at “[email protected]”.

Luke T. Young received the B.S. and M.S. degrees from Louisiana State University and the Ph.D. degree from the University of Illinois, Urbana-Champaign, in 1982, 1983, and 1993, respectively, all in electrical engineering. He worked on software-implemented fault injection techniques and recovery mechanisms at Tandem Computers from 1992 to 1998. Recently, he joined the BCS unit of Bell Laboratories at Lucent Technologies, where he is involved in forward-looking work pertaining to enterprise communications servers. Dr. Young was the keynote speaker at the ACM's SIGUCCS-16 and has served on the program committees of several IEEE workshops related to fault tolerance. His technical interests include fault-tolerant computing, computer architecture, and software reliability engineering.