Hi,
What are the best practices and recommendations for over-committing the frequency of processors (GHz) in a cloud environment? In other words, what should be the mapping ratio of vCPUs to GHz? How many GHz should one vCPU be considered equivalent to while allocating compute to Virtual Machines?
It's still the same formula: 4 x (frequency of physical core)
Your question doesn't make a lot of sense. One vCPU is equal to whatever the frequency of the physical CPU of the host on which the VM is running, regardless of how many cores there are. If you have a physical CPU running at 2.0 GHz, then one vCPU assigned to a VM will be up to 2.0 GHz. Two vCPUs will be two cores or sockets, depending on how you configure it inside the guest, and will entitle you up to 4.0 GHz.
Hi daphnissov,
Thank you for your response. Let me try to explain better with a scenario. I have a 24 core physical server with a total of 59.93GHz. I want to allocate 4 cores for a VM; but vCloud Director does not have an option to allocate cores directly. It requires us to input GHz instead. So that's where I need help to understand what I can do in this situation. How many GHz would be required for the required 4 core VM?
It's still the same formula: 4 x (frequency of physical core)