Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data

About

Root cause analysis (RCA) for microservice systems has gained significant attention in recent years. However, there is still no standard benchmark that includes large-scale datasets and supports comprehensive evaluation environments. In this paper, we introduce RCAEval, an open-source benchmark that provides datasets and an evaluation environment for RCA in microservice systems. First, we introduce three comprehensive datasets comprising 735 failure cases collected from three microservice systems, covering various fault types observed in real-world failures. Second, we present a comprehensive evaluation framework that includes fifteen reproducible baselines covering a wide range of RCA approaches, with the ability to evaluate both coarse-grained and fine-grained RCA. We hope that this ready-to-use benchmark will enable researchers and practitioners to conduct extensive analysis and pave the way for robust new solutions for RCA of microservice systems.

Luan Pham, Hongyu Zhang, Huong Ha, Flora Salim, Xiuzhen Zhang• 2024

Related benchmarks

TaskDatasetResultRank
Root Cause AnalysisRE3TT Train Ticket with code-level faults
F1@10.00e+0
9
Root Cause AnalysisRCAEval Overall All nine datasets (RE1OB-RE3TT) 1.0
Top-1 Accuracy9
9
Root Cause AnalysisRE2TT (Train Ticket with multimodal data)
CPU Top-10.00e+0
9
Root Cause AnalysisRE3OB Online Boutique with code-level faults
F1 Top-1 Accuracy11
9
Root Cause AnalysisRE3SS Sock Shop with code-level faults
F1 Top-10.2
8
Root Cause AnalysisRE1SS (Sock Shop) unimodal data
CPU Top-120
8
Root Cause AnalysisRE1TT Train Ticket unimodal data
CPU Top-10.00e+0
8
Root Cause AnalysisRE2SS Sock Shop with multimodal data (test)
CPU Top-1 Accuracy20
8
Root Cause AnalysisRE1OB (Online Boutique) RCAEval benchmark unimodal data
CPU Top-1 Acc0.00e+0
8
Showing 9 of 9 rows

Other info

Follow for update