Concurrency control of bulk access transactions on shared nothing parallel database machines

Abstract

New concurrency control schemes are proposed for bulk access transactions (BATs) on shared-nothing database machines. A BAT is a transaction accessing a large bulk of data, such as a transaction updating a whole file. BATs are used for batch jobs in database services, and many BATs should be finished in a short time. Thus it is necessary to execute BATs concurrently on a database machine. When scheduling BATs, the performance is degraded by very high contention of both data and resources. Therefore, the strategy for scheduling BATs is to reduce the contention as much as possible. A weighted transaction precedence graph (WTPG) and two schedulers using it are proposed. A WTPG is used to estimate the degree of contention in a serializable schedule. Using a WTPG, the proposed schedulers reduced the contention by optimization. In the simulation, both schedulers achieve from 1.2 to 1.8 times higher throughput than atomic static lock and two-phase lock. >