Workflow System Performance Improving and Analyzing by Using Memory Cache

Workflow techniques may be broadly used in business processing and scientific computing and thus focused research interest over the last decade. The performance of workflow applications mainly depend upon task scheduling strategies in workflow engine. In this paper, a novel active workflow instance memory cache (WfIC) architecture is proposed, which is used for improving workflow system performance. By caching active workflow instances in main memory, instance database IO operations are pruned during task scheduling and processing. Additionally, theory analysis shows that WfIC can effectively improve the performance of workflow systems. Also, theory analysis gives an instruction on how to configure the instance cache and the lower/upper limit of the instance executing time.