The authors presents a problem that arises in the design of protocols for ring networks. It is shown that some existing and proposed protocols can reach a livelocked state as a result of a single transmission error. Livelock-free modifications of the protocols are described. The protocols covered fall into two classes: those in which error recovery utilizes a unique monitor station, and those in which all stations in the ring follow the same algorithm (decentralized protocols). It is shown that although the simplest protocol in each class is susceptible to livelocks, there are some nonobvious differences between the two classes. The problem is outlined and the assumptions made are also presented. Protocols with a monitor station are studied along with decentralized protocols. An example is given of a livelock. Informal arguments are used to show that the modifications proposed are livelock-free.>