Creating virtual machines with virtual GPUs

Limitations

Virtual machines with attached vGPUs cannot be suspended and live migrated.
The default QLX driver for the VNC console and the NVIDIA GPU driver are incompatible
After installing the NVIDIA GPU driver inside a virtual machine with an attached vGPU, the VNC console stops working. You can use RDP for a remote connection. Alternatively, for templates that already have the NVIDIA GPU driver installed, you can set the hw_use_vgpu_display property, to disable the integrated QLX driver. For example:
```
# openstack --insecure image set --property hw_use_vgpu_display 007db63f-9b41-4918-b572-2c5eef4c8f4b
```

Prerequisites

The compute cluster is reconfigured for vGPU support, as described in Enabling PCI passthrough and vGPU support.
To authorize further OpenStack commands, the OpenStack command-line client must be configured, as outlined in Connecting to OpenStack command-line interface.

To create a virtual machine with any vGPU enabled on a node

Create a flavor with the resources property specifying the number of vGPUs to use. For example, to create the vgpu-flavor flavor with 2 vCPUs and 4 GiB of RAM, run:
```
# openstack --insecure flavor create --ram 4096 --vcpus 2 --property resources:VGPU=1 --public vgpu-flavor
```
Create a virtual machine specifying the vgpu-flavor flavor. For example, to create the vgpu-vm from the vol2 volume, run:
```
# openstack --insecure server create --volume vol2 --flavor vgpu-flavor vgpu-vm
```

The created virtual machine will have a virtual GPU of a randomly chosen vGPU type that is enabled on the host.

To create a virtual machine with a vGPU of a particular type

Create a flavor with the resources and trait properties specifying the number of vGPUs and the vGPU type to use. For example, to create the vgpu228-flavor flavor with 2 vCPUs, 4 GiB of RAM, and the nvidia-228 vGPU type, run:
```
# openstack --insecure flavor create --ram 4096 --vcpus 2 --property resources:VGPU=1 \
--property trait:CUSTOM_NVIDIA_228=required --public vgpu228-flavor
```
Create a virtual machine specifying the vgpu228-flavor flavor. For example, to create the vgpu-vm from the vol2 volume, run:
```
# openstack --insecure server create --volume vol2 --flavor vgpu228-flavor vgpu-vm
```

The created virtual machine will have a virtual GPU of the nvidia-228 vGPU type.