William Joel Watson

A flexible ServerNet-based fault-tolerant architecture

The paper introduces a new fault-tolerant architecture that combines the best attributes of the software fault-tolerant Tandem NonStop systems with the hardware fault-tolerant integrity systems. This architecture is based on the ServerNet System Area Network (SAN). ServerNet, formerly called TNet, is a packetized byte-serial multistage network that supports both I/O and interprocessor traffic in fault-tolerant systems. Dual-ported CPUs and VO controllers connect to independent subnetworks in a variety of different network topologies. Systems can expand either through shared or distributed memory multiprocessing. A separate maintenance system controls system initialization, online configuration changes, and error reporting. The architectures flexibility makes it suitable for a wide range of environments with varying requirements for performance, fault tolerance, and software compatibility.<<ETX>>

Performance modeling of ServerNet topologies

This paper describes a performance analysis of ServerNet SAN, a new system area network architecture developed by Tandem Computers. The paper focuses on three main topics: a brief description of the ServerNet SAN architecture and the simulation tool, the basis for modeling assumptions, and the initial results of the performance and scalability analysis. The ServerNet SAN is a new core technology for server architectures that focuses on moving data. The analysis uses simulation to obtain performance characteristics such as delivery time, throughput, and hot spot identification. The goal of the analysis is to provide a realistic measure of current system performance, while optimizing features such as network topology and traffic patterns to provide future improvement.

Maximum delivery time and hot spots in ServerNet/sup TM/ topologies

This paper centers 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. ServerNet/sup TM/, 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. 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. Link usage statistics were recorded by the simulator for the purpose of performing a detailed investigation of congestion effects and hot spots. 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.

Flow Control in ServerNet ® Clusters

This paper investigates the performance implications of several end-to-end flow control protocols in clusters based on the ServerNet® system-area network. The Static Window (SW) and Packet Pair (PP) flow control protocols are studied. Based on them, the Simplified Packet Pair (SPP) and the Alternating Static Window (ASW) protocols are defined. Previously, it has been proven that PP is stable for store-and-forward networks based on Rate Allocation Servers. The applicability of PP to wormhole-routing networks is studied. Simulation results for the performance characteristics are obtained and evaluated. It is shown that if high throughput is desired, ASW is the best method for controlling the average latency. On the other hand, if low throughput is acceptable, SPP can be applied to maintain low latencies.

Flow Control in ServerNetR Clusters

This paper investigates the performance implications of several end-to-end flow-control schemes based on the ServerNetR systemarea network. The static window (SW), packet pair (PP), and the simplified packet pair (SPP) flow control schemes are studied. Additionally, the alternating static window (ASW) flow control is defined and evaluated. Previously, it has been proven that the packet-pair scheme is stable for store-and-forward networks based on Rate Allocation Servers. The applicability of a PP flow control to wormhole-routing networks is studied and evaluated through simulation. It is shown that if high throughput is desired, ASW is the best method for controlling the average latency. On the other hand, if low throughput is acceptable, SPP can be applied to maintain low latencies.

Maximum delivery time and hot spots in ServerNet TM topologies

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. ServerNet TM , 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.