HPM takes advanced of the P and C states of the host's processors and leverages them for power savings, while (hopefully) not impacting performance—unless your real goal is to save on energy consumption. Here's a breakdown of the options.
P-states can be used to save power when the workloads running on the system do not require full CPU capacity. C-states can help save energy only when CPUs have significant idle time. — VMware vSphere 5.5 Host Power Management
- High Performance: This power policy maximizes performance, using no power management features. It keeps CPUs in the highest P-state at all times. It uses only the top two C-states (running and halted), not any of the deep states (for example, C3 and C6). High performance is the default power policy for ESXi releases prior to 5.0.
- Balanced: This power policy is designed to reduce host power consumption while having little or no impact on performance. This is the default power policy since version 5.0. ESXi has used P-states in the Balanced power policy since 5.0. Beginning in ESXi 5.5, we now also use deep C-states (greater than C1) in the Balanced power policy. Formerly, when a CPU was idle, it would always enter C1. Now ESXi chooses a suitable deep C-state depending on its estimate of when the CPU will next need to wake up.
- Low Power: This power policy is designed to save substantially more power than the Balanced policy by making the P-state and C-state selection algorithms more aggressive, at the risk of reduced performance.
- Custom: This power policy starts out the same as Balanced, but it allows individual parameters to be modified.
No matter what you choose, though, make sure you are consistent and use vSphere Host Profiles to maintain enterprise-wide and cluster compliance.