Fail*: towards a versatile fault-injection experiment framework

Abstract

Many years of research on dependable, fault-tolerant software systems yielded many tool implementations for vulnerability analysis and experimental validation of resilience measures. We identify two disjoint classes of fault-injection (FI) experiment tools in the field, and argue that both are plagued by inherent deficiencies, such as insufficient target state access, little or no means to switch to another target system, and non-reusable experiment code. In this article, we present a novel design approach for a FI infrastructure that aims at combining the strengths of both classes. Our FAIL* experiment framework provides carefully-chosen abstractions simplifying both the implementation of different simulator/hardware target backends and the reuse of experiment code, while retaining the ability for deep target-state access for specialized FI experiments. An exemplary report on first experiences with a prototype implementation based on existing X86 and ARM simulators demonstrates the tool's versatility.