Tractable flow analysis for anomaly detection in distributed programs

Abstract

Each process in a distributed program or design can be modelled as a process flow graph, where nodes represent program statements and directed edges represent control flows. This paper describes a flow analysis method to detect unreachable statements by examining the control flows and communication patterns in a collection of process flow graphs. The method can analyse programs with loops, non-deterministic structures and synchronous communication using an algorithm with a quadratic complexity in terms of program size. The method follows an approach described by Reif and Smolka [9] but delivers a more accurate result in assessing the reachability of statements. The higher accuracy is achieved using three techniques: statement dependency, history sets and statement re-reachability. The method is illustrated by a pump control application for a mining environment. A prototype has been implemented and its performance is presented.