Adaptive Content-based Routing using Subscription Subgrouping in Structured Overlays

TL;DR

This paper presents a clustering-based dynamic routing method for publish/subscribe systems over cyclic overlays, improving scalability and reducing message overhead by exploiting structured topology and subscription subgrouping.

Contribution

It introduces a novel clustering approach with bit-vector techniques for inter-cluster routing and optimized advertisement forwarding in cyclic overlays, enhancing scalability and fault tolerance.

Findings

Fewer inter-broker messages compared to existing methods

Enhanced scalability demonstrated through experiments

Effective handling of network failures and congestion

Abstract

Cyclic or general overlays may provide multiple paths between publishers and subscribers. However, an advertisement tree and a matching subscription activates only one path for notifications routing in publish/subscribe systems. This poses serious challenges in handling network conditions like congestion, and link or broker failures. Further, content-based dynamic routing of notifications requires instantaneous updates in routing paths, which is not a scalable option. This paper introduces a clustering approach with a bit-vector technique for inter-cluster dynamic routing of notifications in a structured cyclic topology that provides multiple paths between publishers and interested subscribers. The advertisement forwarding process exploits the structured nature of the overlay topology to generate advertisement trees of length 1 without generating duplicate messages in the advertisement forwarding process. Issued subscriptions are divided into multiple disjoint subgropus, where each subscription is broadcast to a cluster, which is a limited part of the structured cyclic overlay network. We implemented novel static and intra-cluster dynamic routing algorithms in the proposed overlay topology for our advertisement-based publish/subscribe system, called OctopiA. We also performed a pragmatic comparison of our two algorithms with the state-of-the-art. Experiments on a cluster testbed show that our approach generates fewer inter-broker messages, and is scalable.