Filtering and Scalability in the ECO Distributed Event Model

Event-based communication is useful in many application domains, ranging from small centralised applications to large distributed systems. Many different event models have been developed to address the requirements of different application domains. One such model is the ECO (events, constraints, objects) model, which was designed to support distributed virtual world applications. Like many other event models, ECO has event-filtering capabilities that are meant to improve scalability by decreasing the network traffic in a distributed implementation. Our recent work in event-based systems has included building a fully-distributed version of the ECO model, including event-filtering capabilities. This paper describes the results of our evaluation of filters as a means of achieving increased scalability in the ECO model. The evaluation is empirical, and real data gathered from an actual event-based system is used. The findings show that: (i) filters are highly valuable in making distributed implementations of the model scale, (ii) multicasting contributes to the scalability and, perhaps most significantly, (iii) multicast groups can be dynamically generated from filters using local (per-node) knowledge rather than global knowledge of the distributed application