In this paper, we examine the problem of minimizing the variance of the download time in a particular Video on Demand System. This VOD system is based on a Grid Delivery Network which is a hybrid architecture based on P2P and Grid Computing concepts. In this system, videos are divided into blocks and replicated on hosts to decrease the average response time. The purpose of the paper is to study the impact of the block allocation scheme on the variance of the download time. We formulate this as an optimization problem, and show that this problem can be reduced to finding a Steiner System. We analyze different heuristics to solve it in practice, and validate through simulation that a random allocation is quasi-optimal.