论文部分内容阅读
Benchmarks play a crucial role in database performance evaluation,and have been effectively promoting the development of database management systems.With critical transaction processing requirements of new applications,we see an explosion of innovative database technologies for dealing with highly intensive transaction workloads (OLTP) with the obvious characteristics of sharp dynamics,terrific skewness,high contention,or high concurrency (abbr.DSC2),which can not be well described or evaluated by current standard benchmarks.In this paper,based on the representative SecKill applications,we define a pacakge of workloads simulating intensive transactional processing re quirements.And we create a general and flexible benchmark framework PeakBench for evaluating intensive OLTP workloads on databases.We are the first work to have full control on simulating DSC2,especially for the fine granularity control for contention generation.With a comprehensive set of experiments conducted on popular open sourced DBMSs compared with the other representative OLTP benchmarks,we completely demonstrate the usefulness of PeakBench.