Advanced configuration for OpenStack compute nodes

Note

Consider this section as part of Deploy an OpenStack cluster.

The section describes how to perform advanced configuration for the OpenStack compute nodes. Such configuration can be required in some specific use cases, such as DPDK, SR-IOV, or huge pages features usage.

• Configuration recommendations for compute node types
• Configure the CPU model
• Enable huge pages for OpenStack
• Configure CPU isolation for an instance
• Configure custom CPU topologies
• Configure PCI passthrough for guests
• Configure initial resource oversubscription
• Limit HW resources for hyperconverged OpenStack compute nodes
• Configure GPU virtualization
  • Obtain drivers
  • Install drivers
  • Manage virtual GPU types
  • Partition to Multi-Instance GPUs
  • Find mdev class of virtual GPU type
  • Configure the Compute service
    • Time-sliced vGPU
    • Multi-Instance GPU (MIG)
  • Verify resource providers
  • Create required resources