FastFix: a control theoretic view of self-healing for automatic corrective software maintenance

One of the main objectives of self-adaptive systems is to reduce maintenance costs through automatic adaptation. Self-healing is a self-adapting property that helps systems return to a normal state after a fault or vulnerability exploit has been detected. The problem is intuitively appealing as a way to automate the different type of maintenance processes (corrective, adaptive and perfective) and forms an interesting area of research that has inspired many initiatives. As a result, several surveys on self-healing have been published to describe the state of the art in this field. According to those surveys, the major trend towards finding a solution of the self-healing problem relies on redundancy that may concern both architecture and code resources. These approaches are therefore better suited to address adaptive and perfective maintenance. As part of the EU FP7 FastFix project [1], we focus on self-healing for corrective maintenance. We propose a framework for automating corrective maintenance that is based on software control principles. Our approach automates the engineering of self-healing systems as it does not require the system to be designed in a specific way. Instead it can be applied to legacy systems and automatically equip them with observation and control points. Moreover, the proposed approach relies on a sound control theory developed for Discrete Event Systems. Finally, this paper contributes to the field by introducing challenges to the effective application of this approach to relevant industrial systems. Some of these challenges are currently being tackled within FastFix.