Why do we see a discrepancy between VSphere and perfmon when reporting on cpu?

[danielbb]

For a certain Windows Server 2016 Standard, VSphere reports around 50% cpu utilization while perfmon reports around 30% cpu utilization. Why is it? an SA here told me that perfmon goes straight against the OS while VSphere looks at the VM not OS. Not sure...

[danielbb]

This might explain it - A Tale of Two Metrics: Windows CPU or vCenter VM CPU

It says the following, which might be true about the perfmon stats -

-- Because it doesn't know it's virtualized.

-- There are times when the Guest OS (windows perfmon, etc) will show lower CPU usage than VMware reports. The guest doesn't know anything about the CPU used to virtualize the hardware resources it is requesting. ESXi does, and accurately attributes that load.