DynaCausal: Dynamic Causality-Aware Root Cause Analysis for Distributed Microservices

TL;DR

DynaCausal is a novel framework that improves root cause analysis in dynamic microservice systems by modeling time-varying dependencies, reducing noise interference, and enhancing causal attribution for more accurate diagnoses.

Contribution

It introduces a dynamic causality-aware approach that unifies multi-modal signals, employs contrastive learning, and optimizes causal ranking to address limitations of existing RCA methods.

Findings

Achieves an average AC@1 of 0.63, outperforming state-of-the-art methods.

Effectively captures dynamic service dependencies and fault propagation.

Provides accurate and interpretable root cause diagnoses in complex environments.

Abstract

Cloud-native microservices enable rapid iteration and scalable deployment but also create complex, fast-evolving dependencies that challenge reliable diagnosis. Existing root cause analysis (RCA) approaches, even with multi-modal fusion of logs, traces, and metrics, remain limited in capturing dynamic behaviors and shifting service relationships. Three critical challenges persist: (i) inadequate modeling of cascading fault propagation, (ii) vulnerability to noise interference and concept drift in normal service behavior, and (iii) over-reliance on service deviation intensity that obscures true root causes. To address these challenges, we propose DynaCausal, a dynamic causality-aware framework for RCA in distributed microservice systems. DynaCausal unifies multi-modal dynamic signals to capture time-varying spatio-temporal dependencies through interaction-aware representation learning. It further introduces a dynamic contrastive mechanism to disentangle true fault indicators from contextual noise and adopts a causal-prioritized pairwise ranking objective to explicitly optimize causal attribution. Comprehensive evaluations on public benchmarks demonstrate that DynaCausal consistently surpasses state-of-the-art methods, attaining an average AC@1 of 0.63 with absolute gains from 0.25 to 0.46, and delivering both accurate and interpretable diagnoses in highly dynamic microservice environments.