An Orchestration Framework for a Global Multi-Cloud

Abstract

Orchestration management in a global multi-cloud environment encounters many challenges, such as the centralized management of global cloud computing and application resources, more diverse cloud platforms and APIs, differentiated service catalogs. Network latency and instability between cloud platforms in various countries and accessibility between data centers of different security levels also makes orchestration not easy to manage. Orchestration tools, such as Ansible[1], has high requirements for many server ports and network quality. In a complex network environment, SaltStack[2] or Puppet[3], cannot deal with the multi-cloud management of large-scale computing and storage resource nodes. Apache Ambari[4], for applications that run on different cloud computing service providers, it lacks effective management capabilities. Therefore, it is difficult for common orchestration management tools to overcome these problems. In this paper, we propose a global multi-cloud orchestration framework (MCOF), which converts the orchestration instructions initiated from the MCOF master into a standardized orchestration definition model that is distributed to the MCOF workers inside each data center through the message queue. Then the MCOF workers perform the orchestration activities suitable for the corresponding cloud service provider behind the data center firewall to adapt to the complex cloud platform operating environment, and achieve standardization, efficiency, quality, reliability, and traceable orchestration management.