Oh-RAM! One and a Half Round Atomic Memory

Abstract

Emulating atomic read/write shared objects in a message-passing system is a fundamental problem in distributed computing. Considering that network communication is the most expensive resource, efficiency is measured first of all in terms of the communication needed to implement read and write operations. It is well known that 2 communication round-trip phases involving in total 4 message exchanges are sufficient to implemented atomic operations. It is also known that under certain constraints on the number of readers with respect to the numbers of replica servers and failures it is possible to implement single-writer atomic objects such that each operation involves one round-trip phase. We present algorithms that allow operations to complete in 3 communication exchanges without imposing any constraints on the number of readers and writers. Specifically, we present an atomic memory implementation for the SWMR setting, where reads complete in 3 communication exchanges and writes complete in 2 exchanges. We pose the question of whether it is possible to implement MWMR memory where operations complete in at most 3 communication exchanges. We answer this question in the negative by showing that an atomic memory implementation is impossible if both read and write operations take 3 communication exchanges, even when assuming two writers, two readers, and a single replica server failure. Motivated by this impossibility result, we provide a MWMR atomic memory implementation where reads involve 3 and writes 4 communication exchanges. In light of our impossibility result these algorithms are optimal in terms of the number of communication exchanges. We rigorously reason about the correctness of the algorithms.