Model-Driven Orchestration for Cloud Resources
Hayet Brabra, Achraf Mtibaa, Walid Gaaloul, Boualem Benatallah, Faı̈ez Gargouri · 2019
Several DevOps tools have emerged to orchestrate cloud resources. However, inherent heterogeneity and complex implementation within these tools make it hard for DevOps users to design required resource-related artifacts. Currently, the defacto standard for cloud resource modeling and orchestration is TOSCA. Nonetheless, TOSCA is usually bound to TOSCA-compliant orchestration tools. Moreover, the actual integration between TOSCA and DevOps tools is still performed using costly coding and in ad-hoc manner. To resolve this, we believe that mapping and translation mechanisms between TOSCA and DevOps tools should be provided. In this paper, we propose a new model-driven approach for cloud resource orchestration. Our approach (i) adopts TOSCA to design resource-related artifacts regardless of a specific DevOps tool; (ii) enables a new model-driven translation technique that serves to translate the designed artifacts using TOSCA into DevOps specific artifacts and (iii) provides Connectors that intend to establish the bridge between DevOps-specific artifacts and the DevOps tools. Our approach provides a powerful enhancement to DevOps productivity and reusability by assisting toward a seamless integration between TOSCA and DevOps tools.