Microservices Performance Testing with Causality-enhanced Large Language Models

Efficient performance testing of microservices is essential for engineers to ensure that deviations of performance/resource usage metrics from expectations are promptly identified within their rapid release cycle. To this aim, engineers would need to explore the space of possible workload configurations and focus only on the critical ones, e.g., low-load configurations that unexpectedly cause performance issues. This requires a great effort, and can be infeasible in short release cycles.We present CALLMIT, a framework using Large Language Models (LLM) enhanced by causal reasoning to automatically generate critical workloads for microservices performance testing. Engineers query CALLMIT to generate workload configurations expected to expose deviations from performance requirements, so as to actually run only tests that trigger critical configurations. We present the experimental evaluation on three subjects, with comparison to a conventional Retrieval-Augmented Generation technique. The results show that causal models improve the correct identification by LLM of performance-critical workload configurations.