Enable the Huge Pages support

Enable the Huge Pages support

This section exaplains how to configure the support for the Huge Pages feature in your MCP depoyment.

To enable Huge Pages:

  1. Log in to the host machine.

  2. To verify that CPU supports Huge Pages, analyze the system response of the following command:

    cat /proc/cpuinfo
    

    In the system output, search for the parameters:

    • PSE - support of 2MB hugepages

    • PDPE1GB - support of 1GB hugepages

  3. Include the class in cluster.<name>.openstack.compute:

    - system.nova.compute.nfv.hugepages
    
  4. Set the parameters in cluster.<name>.openstack.init on all compute nodes:

    compute_hugepages_size: 1G # or 2M
    compute_hugepages_count: 40
    compute_hugepages_mount: /mnt/hugepages_1G # or /mnt/hugepages_2M
    
  5. Select from the following options:

    • If you are performing the initial deployment your environment, proceed with the further environment configurations.

    • If you are making changes to an existing environment, re-run the salt configuration on the Salt Master node:

      salt "cmp*" state.sls linux,nova
      
  6. Reboot the affected servers.

  7. If you need to set different values for each compute node, define them in cluster.<name>.infra.config for each node.

    Example:

    openstack_compute_node02:
      name: ${_param:openstack_compute_node02_hostname}
      domain: ${_param:cluster_domain}
      classes:
      - cluster.${_param:cluster_name}.openstack.compute
      params:
        salt_master_host: ${_param:reclass_config_master}
        linux_system_codename: xenial
        compute_hugepages_size: 1G # or 2M
        compute_hugepages_count: 40
        compute_hugepages_mount: /mnt/hugepages_1G # or /mnt/hugepages_2M