AIOps根因定位（二）：微服务架构的异常检测与根因定位

1 背景

本文主要从基于日志、基于trace和基于监控指标这三个方面，初步罗列了微服务架构的异常检测和根因定位的相关论文。

2 基于日志的异常检测与根因定位

2.1 异常检测

Anomaly Detection Using Program Control Flow Graph Mining From Execution Logs.

An Approach for Anomaly Diagnosis Based on Hybrid Graph Model with Logs for Distributed Services.

LogSed: Anomaly Diagnosis through Mining Time-Weighted Control Flow Graph in Logs.

2.2 根因定位

Localization of Operational Faults in Cloud Applications by Mining Causal Dependencies in Logs using Golden Signals.

3 基于trace的异常检测与根因定位

3.1 异常检测

3.1.1 无监督检测

Unsupervised Detection of Microservice Trace Anomalies through Service-Level Deep Bayesian Networks.

Anomaly Detection from System Tracing Data Using Multi-modal Deep Learning.

An Anomaly Detection Algorithm for Microservice Architecture Based on Robust Principal Component Analysis.

3.1.2 有监督检测

Anomaly Detection and Classification using Distributed Tracing and Deep Learning.

Seer: Leveraging Big Data to Navigate the Complexity of Performance Debugging in Cloud Microservices.

Self-SupervisedAnomalyDetectionfrom Distributed Traces.

Latent Error Prediction and Fault Localization for Microservice Applications by Learning from System Trace Logs.

3.1.3 trace比对

Workflow-Aware Automatic Fault Diagnosis for Microservice-Based Applications With Statistics.

Detecting anomalies in microservices with execution trace comparison.

A Framework of Virtual War Room and Matrix Sketch-Based Streaming Anomaly Detection for Microservice Systems.

3.2 根因定位

3.2.1 基于可视化的分析

Graph-Based Trace Analysis for Microservice Architecture Understanding and Problem Diagnosis.

Fault Analysis and Debugging of Microservice Systems: Industrial Survey, Benchmark System, and Empirical Study.

3.2.2 直接分析（Direct Analysis）

Toward Fine-Grained, Unsupervised, Scalable Performance Diagnosis for Production Cloud Computing Systems.

Unsupervised Detection of Microservice Trace Anomalies through Service-Level Deep Bayesian Networks.

3.2.3 基于拓扑图的分析

MicroHECL: High-Efficient Root Cause Localization in Large-Scale Microservice Systems.

Root Cause Detection in a Service-Oriented Architecture.

4 基于监控指标的异常检测

4.1 异常检测

4.1.1 无监督检测

Detecting Anomalous Behavior of Black-Box Services Modeled with Distance-Based Online Clustering.

Localizing Faults in Cloud Systems.

DLA: Detecting and Localizing Anomalies in Containerized Microservice Architectures Using Markov Models.

Performance Diagnosis in Cloud Microservices using Deep Learning.

MicroRCA: Root Cause Localization of Performance Issues in Microservices.

4.1.2 有监督检测

Predicting failures in multi-tier distributed systems.

Anomaly Detection and Diagnosis for Container-Based Microservices with Performance Monitoring.

4.1.3 SLO Check（Service Level Objective）

CauseInfer: Automated End-to-End Performance Diagnosis with Hierarchical Causality Graph in Cloud Environment.

CauseInfer: Automatic and distributed performance diagnosis with hierarchical causality graph in large distributed systems.

On Anomaly Detection and Root Cause Analysis of Microservice Systems.

Microscope: Pinpoint Performance Issues with Causal Graphs in Micro-service Environments.

4.2 根因分析

4.2.1 直接分析（Direct Analysis）

-Diagnosis: Unsupervised and Real-Time Diagnosis of Small-Window Long-Tail Latency in Large-Scale Microservice Platforms.

Root-Cause Metric Location for Microservice Systems via Log Anomaly Detection.

PAL: Propagation-Aware Anomaly Localization for Cloud Hosted Distributed Applications.

FChain: Toward Black-Box Online Fault Localization for Cloud Systems.

4.2.2 基于拓扑图的分析

Graph-based root cause analysis for service-oriented and microservice architectures.

Sieve: Actionable Insights from Monitored Metrics in Distributed Systems.

Performance Diagnosis in Cloud Microservices using Deep Learning.

MicroRCA: Root Cause Localization of Performance Issues in Microservices.

DLA: Detecting and Localizing Anomalies in Containerized Microservice Architectures Using Markov Models.

4.2.3 基于因果图的分析

CauseInfer: Automated End-to-End Performance Diagnosis with Hierarchical Causality Graph in Cloud Environment.

CauseInfer: Automatic and distributed performance diagnosis with hierarchical causality graph in large distributed systems.

On Anomaly Detection and Root Cause Analysis of Microservice Systems.

Microscope: Pinpoint Performance Issues with Causal Graphs in Micro-service Environments.

FacGraph: Frequent Anomaly Correlation Graph Mining for Root Cause Diagnose in Micro-Service Architecture.

MS-Rank: Multi-Metric and Self-Adaptive Root Cause Diagnosis for Microservice Applications.

Self-Adaptive Root Cause Diagnosis for Large-Scale Microservice Architecture.

AutoMAP: Diagnose Your Microservice-Based Web Applications Automatically.

CloudRanger: Root Cause Identification for Cloud Native Systems.

Localizing Failure Root Causes in a Microservice through Causality Inference.

Localizing Faults in Cloud Systems.