Correctness of a distributed transaction system

Abstract

A distributed transaction system manages information that is dispersed over a number of storage devices. This paper deals with an experimental transaction system designed to satisfy real-time constraints through distributed control of the executions of transactions. Of interest is the correctness of the algorithm for distributed control. Demonstrating the correctness involves showing that the algorithm guarantees the consistency of distributed data, and equally importantly, that every transaction will eventually terminate. Proof of consistency is based on the notion of serializability of transactions while proof of termination is based on the conflict resolution and failure recovery strategies employed by the transaction system.