2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (2010)
Sept. 23, 2010 to Sept. 26, 2010
Workflow management systems allow the development of complex applications at a higher level, by orchestrating functional components without handling the implementation details. Although a wide range of workflow engines are developed in enterprise environments, the open source engines available for scientific applications lack some functionalities or are too difficult to use for non-specialists. Moreover, the key middleware services in grids, like meta-schedulers, employ complex resource matching logic, but lack control flow orchestration capabilities. On the other hand, workflow engines suitably control process logic but are unaware of execution requirements of tasks. In this paper we present PEGAF, a workflow management platform for distributed systems targeted at scientific applications. Our platform provides features like an intuitive way to describe workflows and flexible fault tolerance support, while integrating both workflow orchestration and meta-scheduling. We validate our integrated platform within several test scenarios, outlining a significant performance increaseflow orchestration solutions.
workflow management, distributed systems, grids, scheduling, fault tolerance
V. Cristea, C. Dobre, F. Pop and A. Costan, "A Worklow Management Platform for Scientific Applications in Grid Environments," 2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing(SYNASC), Timisoara, Romania, 2010, pp. 261-268.