Context:

this feature add a set of new config options which we intend to enable downstream by default.

https://docs.openstack.org/nova/latest/configuration/config.html#libvirt.cpu_power_management

the feature has two power saving strategies. either the unused cpus allocated to CPU pinning pCPUs can be turned off when not allocated to a VM this is the (cpu_state stargey which si the default)

https://docs.openstack.org/nova/latest/configuration/config.html#libvirt.cpu_power_management_strategy

the other stragy is to change the kernel CPU frequency scaling governor to use the high and low power governor specified in the config

https://docs.openstack.org/nova/latest/configuration/config.html#libvirt.cpu_power_governor_low

https://docs.openstack.org/nova/latest/configuration/config.html#libvirt.cpu_power_governor_high

we have upstream docs that can also be used as a source of reference fo the downstream docs

https://docs.openstack.org/nova/latest/admin/cpu-topologies.html#configuring-cpu-power-management-for-dedicated-cores

where we recommend how to select the power governor to uses

"""
This is the responsibility of the operator to ensure that the govenors defined by the configuration options are currently supported by the OS underlying kernel that runs the compute service.

As a side note, we recommend the schedutil governor as an alternative for the high-power state (if the kernel supports it) as the CPU frequency is dynamically set based on CPU task states. Other governors may be worth to be tested, including conservative and ondemand which are quite a bit more power consuming than schedutil but more efficient than performance. See Linux kernel docs for further explanations.
"""

if that strategy is desired.
in general, the cpu_state strategy should save more power and is what we would recommend.

As with all osp 18 features because of the new installer approach there will be no THT parameter or similar to set.

all configuration will be done via config override so the documentation will need to simply list the upstream segments to add and translate the recommendations and caveats into the topic-based doc style we use downstream.