Capacity planning for elastic cloud infrastructure platforms like OpenStack is critical for successful deployments. The proper sizing of compute resources within OpenStack allows for easier scheduling, optimal efficiency in hardware utilization, and consistency of resource allocation.
Google Compute Engine and Amazon Web Services offer deterministic compute resources designed to meet both cloud provider business requirements and cloud consumer service-level requirements. In this session, we’ll explore these public provider approaches, extend them to OpenStack, and provide sizing data and tools to help with your deployment.
In this session, you’ll learn about:
- Approaches for providing consistent compute service levels in OpenStack.
- Building instance families for your workloads.
- Sizing compute node for OpenStack.