Skip to content

OverCommit ratio

Francesc Guasch edited this page Oct 21, 2019 · 2 revisions

This is some thought from the Telegram group

What OpenStack does

for example : OpenStack allows you to overcommit CPU and RAM on compute nodes. This allows you to increase the number of instances running on your cloud at the cost of reducing the performance of the instances. The Compute service uses the following ratios by default:

CPU allocation ratio: 16:1

RAM allocation ratio: 1.5:1

The default CPU allocation ratio of 16:1 means that the scheduler allocates up to 16 virtual cores per physical core. For example, if a physical node has 12 cores, the scheduler sees 192 available virtual cores. With typical flavor definitions of 4 virtual cores per instance, this ratio would provide 48 instances on a physical node.

RAM allocation is 1.5 : 1 . That means with 10 free GB of RAM you could run virtual machines up to 15 GB.

This value must be fixed in a configuration file so that it can be modified.

Calculation Example

https://kb.vmware.com/s/article/2002181 CPU summation value / ( * 1000)) * 100 = CPU ready %

The values ​​of% best practices are to be taken by vCPU.

<2.5% No worries to be made!

2.5% -5% Minimal restraint, to be monitored during peaks.

5% -10% Contention to take into account, investigate to improve quickly.

10% Big contention, to solve urgently!

Clone this wiki locally