Priority Based Transaction Scheduling Model and Concurrency Control in Grid Database

Abstract

Transaction scheduling models and control issues are two important problems in a distributed environment. A lot of research has been focused on the problems recently, and many models and measures (such as replication) have been proposed. However, some of them didn't fit for grid environment, as grid architecture is a new and distinguished from conventional distributed computing by its heterogeneous, dynamic and autonomous properties. So, Transaction scheduling models and concurrency control protocols should be revisited and reassessed for this new and evolving architecture. In this paper, we propose a three-level transaction scheduling model for grid database, which not only shows the autonomy of grid, but also lightens the pressure of communication and grid scheduler. We consider submitted and communication time of a transaction, user's priority and the number of DB sites accessed by the transaction as a priority of the transaction, and give scheduling algorithms for concurrency transaction based on priorities, which not only supports correctness of the data, but also improves the effectiveness of the system. The example and experiment show that the proposed scheduling algorithms could improve the performance of the grid database system.