Software fault injection and its application in distributed systems

The authors describe a software fault injector (SFI) developed to facilitate the validation of dependability mechanisms on an experimental distributed real-time system called HARTS. SFI introduces a number of extensions to previous work done on fault injection tools. In particular, it allows combinations of fault types to be injected in the nodes of a distributed system. It also allows control of all timing parameters of the injection at each node. A description is given of the features and implementation of SFI. As a demonstration of the utility of SFI, the results of some sample experiments are presented.