In our previous DaFab post, we introduced the overall multi-site orchestration vision. This entry focuses on a specific architectural building block: integrating Karmada with Argo Workflows to enable multi-cluster and multi-site workflow execution driven by rule-based placement. The key outcome is that workflow steps can be dispatched to different Kubernetes clusters (sites) based on explicit rules that reflect data locality and computing resource availability goals, without changing how users author workflows.

Bridging Cloud-Native Workflows and HPC for DaFab

One of the main goals of the DaFab project is to enable seamless, multisite scientific workflows—without the need to physically move data between sites. This is crucial in environments where data transfer is restricted by bandwidth, administrative domains, or security policies. One of the main DaFab’s goals is to orchestrate distributed workflows across multiple HPC and cloud sites, letting data stay in place while computation moves to where it’s needed.