Litmus: Evaluating the Resilience of Blockchain-Enabled Software Systems for Supply Chains via Architecture Modeling and Chaos Injection

Resilience is vital to blockchain-enabled software systems for supply chains (ChainFusion) and enables them to automatically adapt and continue providing their service when adverse situations occur. Since the notion of resilience in ChainFusion encompasses both the characteristics of a blockchain-enabled software system and the features of supply chains, complex trade-offs often exist among its resilience metrics. Furthermore, while blockchain technology provides novel mechanisms for enhancing resilience, it also inevitably introduces new resilience-related challenges. Therefore, when evaluating the resilience, it is crucial to evaluate the impact of blockchain technology on its resilience. In this paper, we propose Litmus, a method for evaluating the resilience of Chain-Fusion via architecture modeling and chaos injection. Litmus first models the system architecture using activity diagrams and extracts the minimal paths of the business process. Litmus then evaluates the resilience and outputs resilience issues by continuously injecting chaos into the system and monitoring variations in system state resilience curve. We assess the quality of Litmus by comparison with related work and through ablation experiments. We conduct case studies on a shipbuilding supply chain to evaluate the effectiveness of Litmus. Litmus identifies three previously unknown potential resilience issues. Furthermore, the studies indicate that blockchain behaviors, resilience mapping relationships, disturbance propagation paths, and disturbance types and intensities all impact the resilience of ChainFusion.