The problem of fair bandwidth sharing among adaptive (TCP) and non-adaptive(i.e. CBR-UDP) flows at an Internet gateway is considered. An algorithm thatdrops packet preventively, in an attempt to actively penalize the non-adaptivetraffic that attempts to "steal" buffer space, and therefore bandwidth from theadaptive traffic flows, is presented. The algorithm maintains minimal flow stateinformation and is therefore scalable. The performance of the algorithm iscompared with other gateway algorithms, and it is shown that, in the presence of non-adaptive traffic, it achieves a more balanced bandwidth allocation among thedifferent flows. The behavior of a flow subjected to the given algorithm has also been analyzed in detail.