An Adaptive Fast Paxos for Making Quick Everlasting Decisions

We present a protocol designed to solve several consecutive consensus instances in an asynchronous distributed system prone to crash failures and message omissions. The protocol follows the Paxos approach and integrates two different optimizations to reduce the latency of learning a decision value. This protocol is adaptive as it tries to obtain the best performance gain depending on the current context. Moreover, it guarantees the persistence of all decision values. Our experimentation results focus on the impact of collisions.