Step 13: Implementing Auto Scaling
Step 13.1: Configure Horizontal Pod AutoScaler (HPA) - Deploy the Metrics Server
$ helm install stable/metrics-server \
--name metrics-server \
--version 2.0.4 \
--namespace metrics
$ kubectl get apiservice v1beta1.metrics.k8s.io -o yaml
Step 13.2: Scale an Application with Horizontal Pod AutoScaler (HPA)
kubectl run php-apache --image=k8s.gcr.io/hpa-example --requests=cpu=200m --expose --port=80
$ kubectl autoscale deployment php-apache --cpu-percent=50 --min=1 --max=10
$ kubectl get hpa
- Generate load to trigger scaling
$ kubectl run -i --tty load-generator --image=busybox /bin/sh
$ while true; do wget -q -O - http://php-apache; done
$ kubectl get hpa -w
Step 13.3: Configure Cluster AutoScaler (CA)
- Configure the Cluster Autoscaler (CA)
$ mkdir ~/environment/cluster-autoscaler
$ cd ~/environment/cluster-autoscaler
$ vi ~/environment/cluster-autoscaler/cluster_autoscaler.yml
- Change , AWS_REGION and minimum nodes (2) and maximum nodes (8)
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-addon: cluster-autoscaler.addons.k8s.io
k8s-app: cluster-autoscaler
name: cluster-autoscaler
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
name: cluster-autoscaler
labels:
k8s-addon: cluster-autoscaler.addons.k8s.io
k8s-app: cluster-autoscaler
rules:
- apiGroups: [""]
resources: ["events","endpoints"]
verbs: ["create", "patch"]
- apiGroups: [""]
resources: ["pods/eviction"]
verbs: ["create"]
- apiGroups: [""]
resources: ["pods/status"]
verbs: ["update"]
- apiGroups: [""]
resources: ["endpoints"]
resourceNames: ["cluster-autoscaler"]
verbs: ["get","update"]
- apiGroups: [""]
resources: ["nodes"]
verbs: ["watch","list","get","update"]
- apiGroups: [""]
resources: ["pods","services","replicationcontrollers","persistentvolumeclaims","persistentvolumes"]
verbs: ["watch","list","get"]
- apiGroups: ["extensions"]
resources: ["replicasets","daemonsets"]
verbs: ["watch","list","get"]
- apiGroups: ["policy"]
resources: ["poddisruptionbudgets"]
verbs: ["watch","list"]
- apiGroups: ["apps"]
resources: ["statefulsets"]
verbs: ["watch","list","get"]
- apiGroups: ["storage.k8s.io"]
resources: ["storageclasses"]
verbs: ["watch","list","get"]
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: Role
metadata:
name: cluster-autoscaler
namespace: kube-system
labels:
k8s-addon: cluster-autoscaler.addons.k8s.io
k8s-app: cluster-autoscaler
rules:
- apiGroups: [""]
resources: ["configmaps"]
verbs: ["create"]
- apiGroups: [""]
resources: ["configmaps"]
resourceNames: ["cluster-autoscaler-status"]
verbs: ["delete","get","update"]
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
name: cluster-autoscaler
labels:
k8s-addon: cluster-autoscaler.addons.k8s.io
k8s-app: cluster-autoscaler
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: cluster-autoscaler
subjects:
- kind: ServiceAccount
name: cluster-autoscaler
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: RoleBinding
metadata:
name: cluster-autoscaler
namespace: kube-system
labels:
k8s-addon: cluster-autoscaler.addons.k8s.io
k8s-app: cluster-autoscaler
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: cluster-autoscaler
subjects:
- kind: ServiceAccount
name: cluster-autoscaler
namespace: kube-system
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: cluster-autoscaler
namespace: kube-system
labels:
app: cluster-autoscaler
spec:
replicas: 1
selector:
matchLabels:
app: cluster-autoscaler
template:
metadata:
labels:
app: cluster-autoscaler
spec:
serviceAccountName: cluster-autoscaler
containers:
- image: k8s.gcr.io/cluster-autoscaler:v1.2.2
name: cluster-autoscaler
resources:
limits:
cpu: 100m
memory: 300Mi
requests:
cpu: 100m
memory: 300Mi
command:
- ./cluster-autoscaler
- --v=4
- --stderrthreshold=info
- --cloud-provider=aws
- --skip-nodes-with-local-storage=false
- --nodes=2:8:<AUTOSCALING GROUP NAME>
env:
- name: AWS_REGION
value: us-east-1
volumeMounts:
- name: ssl-certs
mountPath: /etc/ssl/certs/ca-certificates.crt
readOnly: true
imagePullPolicy: "Always"
volumes:
- name: ssl-certs
hostPath:
path: "/etc/ssl/certs/ca-bundle.crt"
$ test -n "$ROLE_NAME" && echo ROLE_NAME is "$ROLE_NAME" || echo ROLE_NAME is not set
$ mkdir ~/environment/asg_policy
cat <<EoF > ~/environment/asg_policy/k8s-asg-policy.json
{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": [
"autoscaling:DescribeAutoScalingGroups",
"autoscaling:DescribeAutoScalingInstances",
"autoscaling:SetDesiredCapacity",
"autoscaling:TerminateInstanceInAutoScalingGroup"
],
"Resource": "*"
}
]
}
EoF
$ aws iam put-role-policy --role-name $ROLE_NAME --policy-name ASG-Policy-For-Worker --policy-document file://~/environment/asg_policy/k8s-asg-policy.json
$ aws iam get-role-policy --role-name $ROLE_NAME --policy-name ASG-Policy-For-Worker
- Deploy the Cluster Autoscaler
$ kubectl apply -f ~/environment/cluster-autoscaler/cluster_autoscaler.yml
$ kubectl logs -f deployment/cluster-autoscaler -n kube-system
Step 13.4: Scale a Cluster with Cluster Auto Scaler
cat <<EoF> ~/environment/cluster-autoscaler/nginx.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: nginx-to-scaleout
spec:
replicas: 1
template:
metadata:
labels:
service: nginx
app: nginx
spec:
containers:
- image: nginx
name: nginx-to-scaleout
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 500m
memory: 512Mi
EoF
kubectl apply -f ~/environment/cluster-autoscaler/nginx.yaml
kubectl get deployment/nginx-to-scaleout
- Scale our ReplicaSet to 10
$ kubectl scale --replicas=10 deployment/nginx-to-scaleout
$ kubectl get pods -o wide --watch
$ kubectl logs -f deployment/cluster-autoscaler -n kube-system
$ kubectl delete -f ~/environment/cluster-autoscaler/cluster_autoscaler.yml
$ kubectl delete -f ~/environment/cluster-autoscaler/nginx.yaml
$ kubectl delete hpa,svc php-apache
$ kubectl delete deployment php-apache load-generator
$ rm -rf ~/environment/cluster-autoscaler