Umeå University's logo

The introduction of microservices and functions using serverless deployment styles for cloud-native applications will trigger a shift in the orchestration paradigm towards an intent-driven model. In this model we shift from imperatively declaring an object’s state to the declaration of a set of desired intents. Intent-driven orchestration (IDO) enables the management of applications through their service level objectives (SLOs) while minimizing service owner and administrator overhead. By enabling service owners to express the desired target key performance indicator (KPI) objectives for their service components instead of declaratively defining the required state and resources, we enable ease of use and abstraction from underlying platforms. By adding a planning component to a Kubernetes-based orchestration stack, the feasibility of translating service objectives into actionable decisions is demonstrated. As this new architecture component introduces more autonomy in the control plane, a means to evaluate the results of planning is defined.