Sky Cone

One of the main features of Knative is automatic scaling of replicas for an application to closely match incoming demand, including scaling applications to zero if no traffic is being received. However, this does not meet our requirements. The main reason we use Knative is that we could eliminate the cold start time that Lambda function previously introduces.

Disable the aforementioned feature and do not allow replicas scale to zero.
$ kubectl edit configmap config-autoscaler -n knative-serving

apiVersion: v1
kind: ConfigMap
data:
  enable-scale-to-zero: "false"
...