A new surrogate placement strategy, CCSP (capacity-constrained surrogate placement), is proposed to enhance the performance for content distribution networks (CDNs). CCSP aims to address surrogate placement in a manner that minimizes the communication cost while ensuring at the same time the maximization of system throughput. This work differs from the existing works on the resource allocation problem in communication networks, CCSP considers load distribution and processing capacity constraints on surrogates by modeling the underlying request-routing mechanism, thus guaranteeing a CDN to have minimum network resource consumption, maximum system throughput, and better load balancing among surrogates. An efficient greedy algorithm is developed for a simplified version of the CCSP problem in tree networks. The efficiency of the proposed algorithm is systematically analyzed through the experimental simulations.