Scheduling batch transactions on shared-nothing parallel database machines: effects of concurrency and parallelism

Concurrency-control scheduling of batch transactions on shared-nothing (or loosely-coupled) multiprocessor database machines is discussed. Various schedulers are tested for these batch transactions to examine how well they perform when both intertransaction parallelism and intratransaction parallelism are limited. New schedulers designed for batch transaction processing are outlined which use a new tool called a weighted transaction-precedence graph (WTPG). Simulation results show that two new schedulers (globally and locally optimized WTPG schedulers) are the best performers under various workloads.<
>