The fabric architecture of the data center used by the FS technical team uses a hierarchical structure design, which can add or remove network nodes as needed to achieve rapid expansion and contraction. At the same time, this architecture also uses programmable network devices and API interfaces, which can better meet customer's different network needs and challenges, and also facilitate customer's subsequent network expansion.

FS uses EBGP/ECMP technology between the Spine-leaf layers to achieve network redundancy and M-LAG technology at the Leaf layer to achieve network redundancy. In this way, the reliability of the network can be improved, the continuity of business can be guaranteed, and the stability and reliability of the data center network operation can be greatly improved.

FS uses a 4U chassis design to build a data center network for customers. This chassis supports 2 subcards, 100G and 400G ports to meet customer's high bandwidth needs, and uses PFC/ECN and other network flow control technologies to achieve lower latency. This can improve the performance and responsiveness of applications for customer in areas such as financial transactions, thus creating greater value.