Middleware Systems Research Group, University of Toronto, 2014.
Refining a topology of a distributed messaging middleware (DMM) is an important management technique to provide a better service to the end-users. Nevertheless, determining the appropriate steps to transform a DMM from one topology to another, in a way that minimizes service disruptions, has received little attention. This is a critical problem since service disruptions can be particularly harmful and costly for DMMs hosting mission-critical services. In this paper, we introduce the incremental topology transformation (ITT) problem. To address it, we draw parallels to automated plan automated planning techniques for solving the ITT problem. While state-of-the-art domain-independent planning techniques were effective for solving small problem instances, we found that they did not scale to the level necessary to solve large ITT problem instances. To address this shortcoming, we developed a suite of planners that use novel domain-specific heuristics to guide the search for a solution. We empirically evaluated our planners on a wide range of topologies. Our results illustrate that automated planning offers a viable solution to a diversity of ITT problems. We envision that our approach could eventually provide a compelling addition to the arsenal of techniques currently employed by the administrators of DMM to support its runtime refinement with minimal disruption to services.