Virtual Machine Density Calculator

Work out virtual machine density instantly with clear inputs, formula shown and shareable results.

About Virtual Machine Density Calculator

VM density is the lower of the CPU and memory limits. CPU can be overcommitted — 4:1 vCPU to physical core is common for general workloads — but memory cannot be safely overcommitted without swapping, so it is usually the binding constraint. Reserving about 6 percent of RAM for the hypervisor is also necessary and frequently forgotten.

Formula

VM density

CPU limit = floor(cores x overcommit / vCPUs per VM); memory limit = floor((host RAM - hypervisor overhead) / VM RAM); density = min of the two

Worked example

With the default values below, Virtual Machine Density Calculator returns VMs per host of 30. Change any input above and every figure here is recalculated in your browser.

Inputs used

Physical cores per hostminimum 1: 64
Host memoryminimum 1 GB: 512 GB
vCPUs per VMminimum 1: 4
Memory per VMminimum 0.1 GB: 16 GB

Results

VMs per host: 30
Limit from vCPU allocation at 4:1 overcommit: 64
Limit from memory: 30
Binding constraint: Memory

Step by step

1Values used
2VM density
3VMs per host= 30
4Limit from vCPU allocation at 4:1 overcommit= 64
5Limit from memory= 30
6Binding constraint= Memory

Assumptions and limits

The result is derived only from the 4 inputs listed above. Anything not among them is not part of the calculation.
In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
Figures are rounded for display to whole numbers, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Why is memory the usual constraint?

Because CPU cycles can be time-shared while memory pages cannot be shared without either ballooning or swapping, both of which degrade performance sharply.

What vCPU overcommit is safe?

Two to four times for general server workloads, one-to-one for latency-sensitive or licensed-by-core applications. Monitor CPU ready time or steal to validate.