Fast Access to Distributed Atomic Memory

We study efficient and robust implementations of an atomic read-write data structure over an asynchronous distributed message-passing system made of reader and writer processes, as well as a number of servers implementing the data structure. We determine the exact conditions under which every read and write involves one round of communication with the servers. These conditions relate the number of readers to the tolerated number of faulty servers and the nature of these failures. Key words. Atomic registers, Byzantine failures, Distributed algorithms, Fault-tolerance, Time-complexity, Shared-memory emulations.

• Type: Journal
• Year: 2010
• Where: SIAMCOMP
• Authors: Partha Dutta, Rachid Guerraoui, Ron R. Levy, Marko Vukolic
• Keywords: Atomic Read-write Data, Data Structure, Faulty Servers, SIAMCOMP 2010