Improved optimistic concurrency control and its use in distributed database systems

Abstract

The original optimistic concurrency control scheme (H.T. Kung, and J.T. Robinson, 1979) has weaknesses with respect to the validation technique, the treatment of long transactions, and the problem of starvation. Some alternatives for the validation-phase are considered that not only avoid these disadvantages but also improve the performance of the original approach. Most promising is a technique which supports read-transactions, thereby decreasing the number of backups substantially. An adaptation of a centralized optimistic concurrency control scheme to a distributed environment is presented. The proposed algorithm is deadlock-free and offers high parallelism.<>