Switch Scheduling and Network Design for Real-Time Systems

Abstract

The rapid need for high bandwidth and low latency communication in distributed real-time systems is driving system architects towards high-speed switches developed for high volume data transfer on the Internet. These switches employ complex scheduling algorithms for transferring data cells from the input line to the output line. From a real-time systems perspective, it is necessary to understand the behavior of these switching algorithms and obtain worst-case delay bounds for message transfer across these switches. Many researchers have derived average-case delay bounds for switching algorithms but mission-critical systems require guarantees for the worst-case. In this context, we derive upper bounds on cell delays across commonly available switches. Our bounds provide a starting point for research in this direction. Moreover, we use the delay bounds to construct low-cost networks of switches given a set of processors and their real-time communication requirements. Experiments with the heuristic algorithm that we propose for network design have produced encouraging results. Importantly, the algorithm is independent of the delay analysis technique and better techniques can be incorporated trivially. By addressing the network design problem, we hope to transform the system architecting process from a manual, ad-hoc operation to a simple and automated step that will result in better designs and cost savings.

Adapting a Main-Stream Internet Switch Architecture for Multihop Real-Time Industrial Networks

“…Some related work concerns the use of COTS switches for real-time systems using approximate bounds and designing networks of switches to meet end-to-end deadlines [27]. The work presented in this article complements such work; better switch architectures result in reduced message delays, which in turn reduces the cost of networks that can guarantee endto-end requirements.…”

“…The best known iSLIP delay bound is still "very pessimistic" [27]. For example, if in an N × N iSLIP switch, every input has periodic real-time traffic going to every output, the known single hop delay bound for packets from input…”

“…However, though iSLIP efficiently utilizes the switch hardware and is simple to implement, it does not guarantee real-time. In fact, real-time high-performance switch design is still an open problem [27].…”

A real-time multicast routing scheme for multi-hop switched fieldbuses

“…Though output queueing is simple and intuitive, its inborn "N speed-up" problem 1 [14] limits its real-world adoption. Input queueing, instead, becomes the de facto standard among switch vendors.…”

FlexTDMA for delay-stable communications in asynchronous industrial control networks

“…INTRODUCTION HERE is a need in industrial control networks, which are mission-oriented local networks, for frame forwarding techniques that offer a fixed delay to a subclass of traffic [7]. Industrial control networks have a portion of the exchanged bandwidth dedicated to support tight inter-process control and control loop communication.…”