Evaluating the Condition-Based Approach to Solve Consensus

Several approaches have been proposed to circumvent the impossibility to solve consensus in asynchronous distributed systems prone to process crash failures. Among them, randomization, unreliable failure detectors, and leader oracles have been particularly investigated. Recently a new approach (called “condition-based”) has been proposed. Let an input vector be a vector whose i-th entry contains the value proposed by process pi. The conditionbased approach consists in stating conditions on input vectors that make consensus solvable despite up to f process crashes. Several conditions have been proposed. (As an example, one of them requires that the greatest value in an input vector appears more than f times.) This paper presents an evaluation of the condition-based approach to solve consensus. It shows that this approach is particularly attractive and very efficient when the probability of process crashes is low (a common fact in practice). In these cases, the probability for the condition-based protocol to terminate is practically equal to 1.