[AWS] EKS Autoscaling - 5주차 - Cluster Autoscaler

실습 전 미리 확인해보기 

aws ec2 describe-instances  --filters Name=tag:Name,Values=$CLUSTER_NAME-ng1-Node --query "Reservations[*].Instances[*].Tags[*]" --output yaml | yh

export ASG_NAME=$(aws autoscaling describe-auto-scaling-groups --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='myeks']].AutoScalingGroupName" --output text)
aws autoscaling update-auto-scaling-group --auto-scaling-group-name ${ASG_NAME} --min-size 3 --desired-capacity 3 --max-size 6

 

 

배포

curl -s -O https://raw.githubusercontent.com/kubernetes/autoscaler/master/cluster-autoscaler/cloudprovider/aws/examples/cluster-autoscaler-autodiscover.yaml
sed -i "s/<YOUR CLUSTER NAME>/$CLUSTER_NAME/g" cluster-autoscaler-autodiscover.yaml
kubectl apply -f cluster-autoscaler-autodiscover.yaml

# 확인
kubectl get pod -n kube-system | grep cluster-autoscaler
kubectl describe deployments.apps -n kube-system cluster-autoscaler

# (옵션) cluster-autoscaler 파드가 동작하는 워커 노드가 퇴출(evict) 되지 않게 설정
kubectl -n kube-system annotate deployment.apps/cluster-autoscaler cluster-autoscaler.kubernetes.io/safe-to-evict="false"

 

모니터링 시작

# 모니터링 
kubectl get nodes -w
while true; do kubectl get node; echo "------------------------------" ; date ; sleep 1; done
while true; do aws ec2 describe-instances --query "Reservations[*].Instances[*].{PrivateIPAdd:PrivateIpAddress,InstanceName:Tags[?Key=='Name']|[0].Value,Status:State.Name}" --filters Name=instance-state-name,Values=running --output text ; echo "------------------------------"; date; sleep 1; done

# Deploy a Sample App
# We will deploy an sample nginx application as a ReplicaSet of 1 Pod
cat <<EoF> nginx.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-to-scaleout
spec:
  replicas: 1
  selector:
    matchLabels:
      app: nginx
  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 nginx.yaml
kubectl get deployment/nginx-to-scaleout

# Scale our ReplicaSet
# Let’s scale out the replicaset to 15
kubectl scale --replicas=15 deployment/nginx-to-scaleout && date

# 확인
kubectl get pods -l app=nginx -o wide --watch
kubectl -n kube-system logs -f deployment/cluster-autoscaler

# 노드 자동 증가 확인
kubectl get nodes
aws autoscaling describe-auto-scaling-groups \
    --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='myeks']].[AutoScalingGroupName, MinSize, MaxSize,DesiredCapacity]" \
    --output table

# 디플로이먼트 삭제
kubectl delete -f nginx.yaml && date

# 노드 갯수 축소 : 기본은 10분 후 scale down 됨, 물론 아래 flag 로 시간 수정 가능 >> 그러니 디플로이먼트 삭제 후 10분 기다리고 나서 보자!
# By default, cluster autoscaler will wait 10 minutes between scale down operations, 
# you can adjust this using the --scale-down-delay-after-add, --scale-down-delay-after-delete, 
# and --scale-down-delay-after-failure flag. 
# E.g. --scale-down-delay-after-add=5m to decrease the scale down delay to 5 minutes after a node has been added.

# 터미널1
watch -d kubectl get node

 

리소스 삭제

curl -s -O https://raw.githubusercontent.com/kubernetes/autoscaler/master/cluster-autoscaler/cloudprovider/aws/examples/cluster-autoscaler-autodiscover.yaml
sed -i "s/<YOUR CLUSTER NAME>/$CLUSTER_NAME/g" cluster-autoscaler-autodiscover.yaml
kubectl apply -f cluster-autoscaler-autodiscover.yaml

# 확인
kubectl get pod -n kube-system | grep cluster-autoscaler
kubectl describe deployments.apps -n kube-system cluster-autoscaler

# (옵션) cluster-autoscaler 파드가 동작하는 워커 노드가 퇴출(evict) 되지 않게 설정
kubectl -n kube-system annotate deployment.apps/cluster-autoscaler cluster-autoscaler.kubernetes.io/safe-to-evict="false"