The decentralized control scheme for routing in current IP networks has been questioned, and a centralized control scheme has been proposed. In this paper, we compare the convergence process in a centralized control scheme with decentralized link-state routing protocols. We first identify the components of the convergence time. Thereafter, we study how to achieve fast routing convergence in networks with centralized control. In particular, we analyze how to distribute forwarding information efficiently. Finally, we perform simulation studies on convergence time for both real and synthetic network topologies, and study the impact of control element location, link weights, and number of failures on the convergence time. The results show that the centralized control scheme can provide faster routing convergence than link-state routing protocols.