We propose in this paper a new algorithm that, when called by existing token ring-based algorithms of parallel and distributed applications, easily renders the token tolerant to losses in presence of node crashes. At most k consecutive node crashes are tolerated in the ring. Our algorithm scales very well since a node monitors the liveness of at most k other nodes and neither a global election algorithm nor broadcast primitives are used to regenerate a new token. It is thus very effective in terms of latency cost. Finally, a study of the probability of having at most k consecutive node crashes in the presence of f failures and a discussion of how to extend our algorithm to other logical topologies are also presented.
