Chainscope accepted at PACMNet (CoNEXT) 2026.

Our paper titled “ChainScope: Balancing Accuracy and Overhead in Non-intrusive Distributed Tracing of Microservices “ will be presented at Conext 2026

Congrats to the team, especially Ruipeng, and Gabriele.

Abstract: Distributed tracing is essential for monitoring and debugging services deployed on top of microservice architectures. However, existing solutions face a fundamental trade-off between non-intrusiveness, language/protocol independence, overhead, and accuracy. We present ChainScope, a distributed tracing system that uses eBPF to establish a universal tracing system in the kernel that enables trace-level sampling in non-intrusive tracing frameworks to control overhead. ChainScope operates independently of application languages and protocols, and introduces kernel-level context propagation for high-accuracy and efficient trace reconstruction across diverse service processing models. Evaluation results show that ChainScope achieves better accuracy-overhead trade-offs than existing non-intrusive tracing approaches with up to 2.2× better accuracy, and 1.6× higher end-to-end service throughput in complex scenarios such as asynchronous processing and RPC (Remote Procedure Call) protocols. Furthermore, we demonstrate that ChainScope accurately identifies the root cause of long-tail latency in a realistic use case.