Optimized Cloud Resource Management and Scheduling

12

Toward Running Scientific Workflows in the Cloud

Cloud computing is gaining tremendous momentum in both academia and industry. The application of cloud computing, however, has mostly focused on web and business applications thus far, whereas workflow applications, especially data-intensive scientific workflows on the cloud, are still largely unexplored. In this chapter, we present the Swift scientific workflow management system (SWFMS) as a service in the cloud. We present our experience migrating the Swift SWFMS into the cloud, which supports workflow specification and submission, on-demand virtual cluster provisioning, high-throughput task scheduling and execution, and efficient and scalable cloud resource management. We discuss two integration ...