CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis

TL;DR

This paper introduces CMMD, a novel cross-metric multi-dimensional root cause analysis method that leverages graph neural networks and genetic algorithms to improve accuracy in identifying causes of KPI anomalies in large-scale online services.

Contribution

The paper presents a new RCA approach that models complex metric relationships with GNNs and localizes root causes using genetic algorithms, addressing limitations of previous methods.

Findings

CMMD outperforms baseline methods in synthetic and real datasets.

CMMD effectively models complex metric relationships.

CMMD is deployed as an online service in Microsoft Azure.

Abstract

In large-scale online services, crucial metrics, a.k.a., key performance indicators (KPIs), are monitored periodically to check their running statuses. Generally, KPIs are aggregated along multiple dimensions and derived by complex calculations among fundamental metrics from the raw data. Once abnormal KPI values are observed, root cause analysis (RCA) can be applied to identify the reasons for anomalies, so that we can troubleshoot quickly. Recently, several automatic RCA techniques were proposed to localize the related dimensions (or a combination of dimensions) to explain the anomalies. However, their analyses are limited to the data on the abnormal metric and ignore the data of other metrics which may be also related to the anomalies, leading to imprecise or even incorrect root causes. To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected. Experiments on synthetic datasets, public datasets and online production environment demonstrate the superiority of our proposed CMMD method compared with baselines. Currently, CMMD is running as an online service in Microsoft Azure.