Ginflow: A Decentralised Adaptive Workflow Execution Manager

Workflow-based computing has become a dominant paradigm to design and execute scientific applications. After the initial breakthrough of now standard workflow management systems, several approaches have recently proposed to decentralise the coordination of the execution. In particular, shared space-based coordination has been shown to provide appropriate building blocks for such a decentralised execution. Uncertainty is also still a major concern in scientific workflows. The ability to adapt the workflow, change its shape and switch for alternate scenarios on-the-fly is still missing in workflow management systems. In this paper, based on a shared space approach, we firstly devise a programmatic way to specify such adaptive workflows. We use a reactive, rule-based programming model to modify the workflow description by changing its associated direct acyclic graph on-the-fly without needing to stop and restart the execution from the beginning. Secondly, we present the GinFlow middleware, a resilient decentralised workflow execution manager implementing these concepts. Through a set of deployments of adaptive workflows of different characteristics, we discuss the GinFlow performance and resilience and show the limited overhead of the adaptiveness mechanism, making it a promising decentralised adaptive workflow execution manager.