Experience Report State-Replication-Based Matching System

Traditional financial trading systems were developed in database-based standalone model years ago. Given that there exist some evident drawbacks like high latency and low availability in such architecture, it is imperative to design a new model which can meet the requirements of time-sensitive financial transactions. Therefore, in this paper we design and implement a state-replication based matching system which includes the critical technical points like order sequencing and asynchronous data persistence. The performance experiment indicates that this new model can dramatically increase the throughput by three times and the latency only accounts for nearly 10% compared with the conventional architecture. High availability and robustness can be guaranteed as well.