MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Shuai, Chen, Pengfei, Tian, Bozhe, Tan, Gou, Xu, Maohong, Qu, Youjun, Zhao, Yahui, Shang, Yiduo, Tan, Chongkang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912937363374080
author Liang, Shuai
Chen, Pengfei
Tian, Bozhe
Tan, Gou
Xu, Maohong
Qu, Youjun
Zhao, Yahui
Shang, Yiduo
Tan, Chongkang
author_facet Liang, Shuai
Chen, Pengfei
Tian, Bozhe
Tan, Gou
Xu, Maohong
Qu, Youjun
Zhao, Yahui
Shang, Yiduo
Tan, Chongkang
contents The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA). While causality-based RCA methods have shown significant progress in recent years, their practical adoption is fundamentally limited by three intertwined challenges: poor scalability against system complexity, brittle generalization across different system topologies, and inadequate integration of domain knowledge. These limitations create a vicious cycle, hindering the development of robust and efficient RCA solutions. This paper introduces MetaRCA, a generalizable RCA framework for cloud-native systems. MetaRCA first constructs a Meta Causal Graph (MCG) offline, a reusable knowledge base defined at the metadata level. To build the MCG, we propose an evidence-driven algorithm that systematically fuses knowledge from Large Language Models (LLMs), historical fault reports, and observability data. When a fault occurs, MetaRCA performs a lightweight online inference by dynamically instantiating the MCG into a localized graph based on the current context, and then leverages real-time data to weight and prune causal links for precise root cause localization. Evaluated on 252 public and 59 production failures, MetaRCA demonstrates state-of-the-art performance. It surpasses the strongest baseline by 29 percentage points in service-level and 48 percentage points in metric-level accuracy. This performance advantage widens as system complexity increases, with its overhead scaling near-linearly. Crucially, MetaRCA shows robust cross-system generalization, maintaining over 80% accuracy across diverse systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02032
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge
Liang, Shuai
Chen, Pengfei
Tian, Bozhe
Tan, Gou
Xu, Maohong
Qu, Youjun
Zhao, Yahui
Shang, Yiduo
Tan, Chongkang
Software Engineering
The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA). While causality-based RCA methods have shown significant progress in recent years, their practical adoption is fundamentally limited by three intertwined challenges: poor scalability against system complexity, brittle generalization across different system topologies, and inadequate integration of domain knowledge. These limitations create a vicious cycle, hindering the development of robust and efficient RCA solutions. This paper introduces MetaRCA, a generalizable RCA framework for cloud-native systems. MetaRCA first constructs a Meta Causal Graph (MCG) offline, a reusable knowledge base defined at the metadata level. To build the MCG, we propose an evidence-driven algorithm that systematically fuses knowledge from Large Language Models (LLMs), historical fault reports, and observability data. When a fault occurs, MetaRCA performs a lightweight online inference by dynamically instantiating the MCG into a localized graph based on the current context, and then leverages real-time data to weight and prune causal links for precise root cause localization. Evaluated on 252 public and 59 production failures, MetaRCA demonstrates state-of-the-art performance. It surpasses the strongest baseline by 29 percentage points in service-level and 48 percentage points in metric-level accuracy. This performance advantage widens as system complexity increases, with its overhead scaling near-linearly. Crucially, MetaRCA shows robust cross-system generalization, maintaining over 80% accuracy across diverse systems.
title MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge
topic Software Engineering
url https://arxiv.org/abs/2603.02032