Distributed Self-Organizing Event Space Partitioning for Content-Based Publish/Subscribe Systems

Choosing the best platform for distributed publish/subscribe communications usually implies a careful choice of the desired event selection model; content-based systems allow fine grained interest selection through expressive subscriptions usually at the cost of limited scalability; topic-based systems offer high-performance and scalable event dissemination at the cost of reduced expressiveness for the subscribers that must then locally filter uninteresting events. In this paper we present a novel solution for implementing a content-based event selection model on top of an existing topic-based system; our solution is based on the idea of dynamically partition the event space and mapping subscribers interests on the resulting discrete intervals represented by topics; the partitioning is automatically built and continuously adapted at runtime in a distributed way with the goal of maintaining predefined minimum target performance despite possible changes in the subscriber interests. The effectiveness of our solution is shown through an extensive set of experiments.