A workflow engine with multi-level parallelism support

This paper presents the SWFL workflow engine, a general workflow framework that meets the needs of business processes as well as scientific computing processes with fine multi-level parallelism supports. The workflow description language, SWFL, follows a graph-oriented model to specify workflow processes composed of services. The workflow engine provides an efficient enactment environment for SWFL flow model composed of services. It provides multi-level parallelism supports: a server-level parallelism support using flexible server-level schedule algorithms, a flow-level parallelism support by partitioning a workflow into sub-flows and running the sub-flows in multiple job processing servers in parallel, and a message-passing parallelism support by using the MPFL, an extension language to SWFL and its associated tools. The architecture of the workflow engine and some other related implementation issues are also presented in the paper.