Partition-Based Microservice Architecture for Civil Aviation Cloud Platforms

Abstract

Modern cloud-native microservice systems face significant challenges when deployed in ultra-large-scale, missioncritical environments such as civil aviation passenger service platforms. Existing SDK-based frameworks suffer from tight coupling and limited cross-language flexibility, while Service Mesh solutions introduce scalability bottlenecks due to globally synchronized service state and configuration overhead. This paper presents a partition-based microservice architecture that introduces a hierarchical control model separating local traffic interception from global routing intelligence. The system is built upon a decoupled Sidecar-Router design, where Sidecar Proxies handle lightweight request interception and partition-level forwarding, while Service Routers execute instance-level routing and traffic governance. By introducing partition-bounded service discovery and physical-IP-based cross-cluster communication, the proposed architecture eliminates global state synchronization of high-frequency service metadata and ensures constant resource overhead at the data plane. The system has been deployed in a large civil aviation PSS environment, supporting over 1,800 microservices and more than 6,000 instances, with a sustained production throughput of over 100,000 TPS and 60% business coverage via the traffic access platform. The results demonstrate that partitioned routing and decoupled control significantly improve scalability, fault isolation, and operational efficiency in large-scale distributed microservice systems.