The example config/samples/sfnettest/client-server.yaml requires customization to your environment. The manifest uses two separately deployed resources which are recommended as part of a full Onload Operator deployment:
- A Multus network
- Connects the pods to hardware that supports acceleration.
- An Onload profile
- Sets environment variables for the pod which are then consumed by user-space Onload running in the container(s).
Review the defaults and apply:
- Node names
-
compute-0andcompute-1 - Network
-
ipvlan-bond0(Multus) - Namespace
-
default - Onload accelerated
-
amd.com/onloadresource - Onload profile
-
onload-latency-profile
kubectl apply --validate=true -f client-server.yaml
kubectl describe pods -l app.kubernetes.io/part-of=sfnettest