On the accuracy of event distribution lists for publish/subscribe in dynamic distributed systems

The advent of very large scale distributed applications in the form of peer-to-peer systems, introduced new problems caused by their intrinsic dynamic behavior (i.e., nodes continuously joining and leaving the system). Such problems inhibit the usage of many techniques developed for quasi-static distributed systems. In this paper we analyze the behavior of a simple subscription-flooding based algorithm for publish/subscribe in a highly dynamic environment. Specifically we define the problem of keeping a list of processes matching a given event (Event Distribution List) complete and accurate. We propose a simple variant of the subscription flooding approach, introducing expiration of subscriptions and their periodic refresh, and show how it can maintain accurate and complete EDLs in a dynamic distributed system. © 2006 IEEE