• 기본 클러스터 배포

# YAML 파일 다운로드
curl -O https://s3.ap-northeast-2.amazonaws.com/cloudformation.cloudneta.net/K8S/eks-oneclick3.yaml

# CloudFormation 스택 배포
aws cloudformation deploy --template-file eks-oneclick4.yaml --stack-name myeks --parameter-overrides KeyName=nasirk17 SgIngressSshCidr=$(curl -s ipinfo.io/ip)/32  MyIamUserAccessKeyID=(개인 액세스키) MyIamUserSecretAccessKey=(개인 시크릿키) ClusterBaseName=myeks --region ap-northeast-2

# CloudFormation 스택 배포 완료 후 작업용 EC2 IP 출력
aws cloudformation describe-stacks --stack-name myeks --query 'Stacks[*].Outputs[0].OutputValue' --output text

# 작업용 EC2 SSH 접속
ssh -i ~/.ssh/nasirk17.pem ec2-user@$(aws cloudformation describe-stacks --stack-name myeks --query 'Stacks[*].Outputs[0].OutputValue' --output text)

• 기본 설정 및 필요 도구 구성(ExternalDNS, kube-ops-view, LB cntlr)

# default 네임스페이스 적용
kubectl ns default

# (옵션) context 이름 변경
NICK=<각자 자신의 닉네임>
NICK=nasir
kubectl ctx
kubectl config rename-context admin@myeks.ap-northeast-2.eksctl.io $NICK@myeks

# ExternalDNS
MyDomain=<자신의 도메인>
echo "export MyDomain=<자신의 도메인>" >> /etc/profile
MyDomain=devxmonitor.click
echo "export MyDomain=devxmonitor.click" >> /etc/profile
MyDnzHostedZoneId=$(aws route53 list-hosted-zones-by-name --dns-name "${MyDomain}." --query "HostedZones[0].Id" --output text)
echo $MyDomain, $MyDnzHostedZoneId
curl -s -O https://raw.githubusercontent.com/gasida/PKOS/main/aews/externaldns.yaml
MyDomain=$MyDomain MyDnzHostedZoneId=$MyDnzHostedZoneId envsubst < externaldns.yaml | kubectl apply -f -

# kube-ops-view
helm repo add geek-cookbook https://geek-cookbook.github.io/charts/
helm install kube-ops-view geek-cookbook/kube-ops-view --version 1.2.2 --set env.TZ="Asia/Seoul" --namespace kube-system
kubectl patch svc -n kube-system kube-ops-view -p '{"spec":{"type":"LoadBalancer"}}'
kubectl annotate service kube-ops-view -n kube-system "external-dns.alpha.kubernetes.io/hostname=kubeopsview.$MyDomain"
echo -e "Kube Ops View URL = http://kubeopsview.$MyDomain:8080/#scale=1.5"

# AWS LB Controller
helm repo add eks https://aws.github.io/eks-charts
helm repo update
helm install aws-load-balancer-controller eks/aws-load-balancer-controller -n kube-system --set clusterName=$CLUSTER_NAME \
  --set serviceAccount.create=false --set serviceAccount.name=aws-load-balancer-controller

# 노드 보안그룹 ID 확인
NGSGID=$(aws ec2 describe-security-groups --filters Name=group-name,Values='*ng1*' --query "SecurityGroups[*].[GroupId]" --output text)
aws ec2 authorize-security-group-ingress --group-id $NGSGID --protocol '-1' --cidr 192.168.1.100/32

• Metrics, 프로메테우스, 그라파나 구성

# 사용 리전의 인증서 ARN 확인
CERT_ARN=`aws acm list-certificates --query 'CertificateSummaryList[].CertificateArn[]' --output text`
echo $CERT_ARN

# repo 추가
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts

# 파라미터 파일 생성
cat <<EOT > monitor-values.yaml
prometheus:
  prometheusSpec:
    podMonitorSelectorNilUsesHelmValues: false
    serviceMonitorSelectorNilUsesHelmValues: false
    retention: 5d
    retentionSize: "10GiB"

  verticalPodAutoscaler:
    enabled: true

  ingress:
    enabled: true
    ingressClassName: alb
    hosts: 
      - prometheus.$MyDomain
    paths: 
      - /*
    annotations:
      alb.ingress.kubernetes.io/scheme: internet-facing
      alb.ingress.kubernetes.io/target-type: ip
      alb.ingress.kubernetes.io/listen-ports: '[{"HTTPS":443}, {"HTTP":80}]'
      alb.ingress.kubernetes.io/certificate-arn: $CERT_ARN
      alb.ingress.kubernetes.io/success-codes: 200-399
      alb.ingress.kubernetes.io/load-balancer-name: myeks-ingress-alb
      alb.ingress.kubernetes.io/group.name: study
      alb.ingress.kubernetes.io/ssl-redirect: '443'

grafana:
  defaultDashboardsTimezone: Asia/Seoul
  adminPassword: prom-operator

  ingress:
    enabled: true
    ingressClassName: alb
    hosts: 
      - grafana.$MyDomain
    paths: 
      - /*
    annotations:
      alb.ingress.kubernetes.io/scheme: internet-facing
      alb.ingress.kubernetes.io/target-type: ip
      alb.ingress.kubernetes.io/listen-ports: '[{"HTTPS":443}, {"HTTP":80}]'
      alb.ingress.kubernetes.io/certificate-arn: $CERT_ARN
      alb.ingress.kubernetes.io/success-codes: 200-399
      alb.ingress.kubernetes.io/load-balancer-name: myeks-ingress-alb
      alb.ingress.kubernetes.io/group.name: study
      alb.ingress.kubernetes.io/ssl-redirect: '443'

defaultRules:
  create: false
kubeControllerManager:
  enabled: false
kubeEtcd:
  enabled: false
kubeScheduler:
  enabled: false
alertmanager:
  enabled: false
EOT

# 배포
kubectl create ns monitoring
helm install kube-prometheus-stack prometheus-community/kube-prometheus-stack --version 45.27.2 \
--set prometheus.prometheusSpec.scrapeInterval='15s' --set prometheus.prometheusSpec.evaluationInterval='15s' \
-f monitor-values.yaml --namespace monitoring

# Metrics-server 배포
kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml

• 노드 할당 가능 용량과 요청 request 리소스 표시, 실제 파드 리소스 사용량 X

# go 설치
yum install -y go

# EKS Node Viewer 설치 : 현재 ec2 spec에서는 설치에 다소 시간이 소요됨 = 2분 이상
go install github.com/awslabs/eks-node-viewer/cmd/eks-node-viewer@latest

# bin 확인 및 사용 
tree ~/go/bin
cd ~/go/bin
./eks-node-viewer
3 nodes (875m/5790m) 15.1% cpu ██████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ $0.156/hour | $113.880/month
20 pods (0 pending 20 running 20 bound)

ip-192-168-3-41.ap-northeast-2.compute.internal cpu ████████░░░░░░░░░░░░░░░░░░░░░░░░░░░  22% (7 pods) t3.medium/$0.0520 On-Demand
ip-192-168-1-112.ap-northeast-2.compute.internal  cpu ████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  12% (6 pods) t3.medium/$0.0520 On-Demand
ip-192-168-2-245.ap-northeast-2.compute.internal cpu ████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  12% (7 pods) t3.medium/$0.0520 On-Demand
Press any key to quit

명령 샘플
# Standard usage
./eks-node-viewer

# Display both CPU and Memory Usage
./eks-node-viewer --resources cpu,memory

# Karenter nodes only
./eks-node-viewer --node-selector "karpenter.sh/provisioner-name"

# Display extra labels, i.e. AZ
./eks-node-viewer --extra-labels topology.kubernetes.io/zone

# Specify a particular AWS profile and region
AWS_PROFILE=myprofile AWS_REGION=us-west-2

기본 옵션
# select only Karpenter managed nodes
node-selector=karpenter.sh/provisioner-name

# display both CPU and memory
resources=cpu,memory

• php-apache.yaml

# Run and expose php-apache server
curl -s -O https://raw.githubusercontent.com/kubernetes/website/main/content/en/examples/application/php-apache.yaml
cat php-apache.yaml | yh
kubectl apply -f php-apache.yaml

# 확인
kubectl exec -it deploy/php-apache -- cat /var/www/html/index.php
...

# 모니터링 : 터미널2개 사용
watch -d 'kubectl get hpa,pod;echo;kubectl top pod;echo;kubectl top node'
kubectl exec -it deploy/php-apache -- top

# 접속
PODIP=$(kubectl get pod -l run=php-apache -o jsonpath={.items[0].status.podIP})
curl -s $PODIP; echo

• 증가 시 기본 대기 시간(30초), 감소 시 기본 대기 시간(5분) → 조정 가능

# Create the HorizontalPodAutoscaler : requests.cpu=200m - 알고리즘
# Since each pod requests 200 milli-cores by kubectl run, this means an average CPU usage of 100 milli-cores.
kubectl autoscale deployment php-apache --cpu-percent=50 --min=1 --max=10
kubectl describe hpa
...
Metrics:                                               ( current / target )
  resource cpu on pods  (as a percentage of request):  0% (1m) / 50%
Min replicas:                                          1
Max replicas:                                          10
Deployment pods:                                       1 current / 1 desired
...

# HPA 설정 확인
kubectl krew install neat
kubectl get hpa php-apache -o yaml
kubectl get hpa php-apache -o yaml | kubectl neat | yh
spec: 
  minReplicas: 1               # [4] 또는 최소 1개까지 줄어들 수도 있습니다
  maxReplicas: 10              # [3] 포드를 최대 5개까지 늘립니다
  scaleTargetRef: 
    apiVersion: apps/v1
    kind: Deployment
    name: php-apache           # [1] php-apache 의 자원 사용량에서
  metrics: 
  - type: Resource
    resource: 
      name: cpu
      target: 
        type: Utilization
        averageUtilization: 50  # [2] CPU 활용률이 50% 이상인 경우

# 반복 접속 1 (파드1 IP로 접속) >> 증가 확인 후 중지
while true;do curl -s $PODIP; sleep 0.5; done

# 반복 접속 2 (서비스명 도메인으로 접속)
# Run this in a separate terminal
# so that the load generation continues and you can carry on with the rest of the steps
kubectl run -i --tty load-generator --rm --image=busybox:1.28 --restart=Never -- /bin/sh -c "while sleep 0.01; do wget -q -O- http://php-apache; done"

• 사전 준비

# 코드 다운로드
git clone https://github.com/kubernetes/autoscaler.git
cd ~/autoscaler/vertical-pod-autoscaler/
tree hack

# openssl 버전 확인
openssl version
OpenSSL 1.0.2k-fips  26 Jan 2017

# openssl 1.1.1 이상 버전 확인
yum install openssl11 -y
openssl11 version
OpenSSL 1.1.1g FIPS  21 Apr 2020

# 스크립트파일내에 openssl11 수정
sed -i 's/openssl/openssl11/g' ~/autoscaler/vertical-pod-autoscaler/pkg/admission-controller/gencerts.sh

# Deploy the Vertical Pod Autoscaler to your cluster with the following command.
watch -d kubectl get pod -n kube-system
cat hack/vpa-up.sh
./hack/vpa-up.sh
kubectl get crd | grep autoscaling

• pod가 실행되면 약 2~3분 뒤에 pod resource.reqeust가 VPA에 의해 수정

# 모니터링
watch -d kubectl top pod

# 공식 예제 배포
cd ~/autoscaler/vertical-pod-autoscaler/
cat examples/hamster.yaml | yh
kubectl apply -f examples/hamster.yaml && kubectl get vpa -w

# 파드 리소스 Requestes 확인
kubectl describe pod | grep Requests: -A2
    Requests:
      cpu:        100m
      memory:     50Mi
--
    Requests:
      cpu:        587m
      memory:     262144k
--
    Requests:
      cpu:        587m
      memory:     262144k

# VPA에 의해 기존 파드 삭제되고 신규 파드가 생성됨
kubectl get events --sort-by=".metadata.creationTimestamp" | grep VPA
2m16s       Normal    EvictedByVPA             pod/hamster-5bccbb88c6-s6jkp         Pod was evicted by VPA Updater to apply resource recommendation.
76s         Normal    EvictedByVPA             pod/hamster-5bccbb88c6-jc6gq         Pod was evicted by VPA Updater to apply resource recommendation.

• 태그 값 확인

# EKS 노드에 이미 아래 tag가 들어가 있음
# k8s.io/cluster-autoscaler/enabled : true
# k8s.io/cluster-autoscaler/myeks : owned
aws ec2 describe-instances  --filters Name=tag:Name,Values=$CLUSTER_NAME-ng1-Node --query "Reservations[*].Instances[*].Tags[*]" --output yaml | yh
...
- Key: k8s.io/cluster-autoscaler/myeks
      Value: owned
- Key: k8s.io/cluster-autoscaler/enabled
      Value: 'true'
...

• CA 배포

# 현재 autoscaling(ASG) 정보 확인
# aws autoscaling describe-auto-scaling-groups --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='클러스터이름']].[AutoScalingGroupName, MinSize, MaxSize,DesiredCapacity]" --output table

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

-----------------------------------------------------------------
|                   DescribeAutoScalingGroups                   |
+------------------------------------------------+----+----+----+
|  eks-ng1-4ec42f64-2813-ec34-7280-4cef8f8169f3  |  3 |  3 |  3 |
+------------------------------------------------+----+----+----+

# MaxSize 6개로 수정
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

# 확인
aws autoscaling describe-auto-scaling-groups --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='myeks']].[AutoScalingGroupName, MinSize, MaxSize,DesiredCapacity]" --output table
-----------------------------------------------------------------
|                   DescribeAutoScalingGroups                   |
+------------------------------------------------+----+----+----+
|  eks-ng1-4ec42f64-2813-ec34-7280-4cef8f8169f3  |  3 |  6 |  3 |
+------------------------------------------------+----+----+----+

# 배포 : Deploy the Cluster Autoscaler (CA)
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"

• Scale a cluster w/ca

# 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

./eks-node-viewer
42 pods (0 pending 42 running 42 bound)
ip-192-168-3-41.ap-northeast-2.compute.internal  cpu █████████████████████████████░░░░
ip-192-168-1-112.ap-northeast-2.compute.internal cpu █████████████████████████████████
ip-192-168-2-245.ap-northeast-2.compute.internal cpu █████████████████████████████████
ip-192-168-3-167.ap-northeast-2.compute.internal cpu █████████████████████████████░░░░
ip-192-168-1-220.ap-northeast-2.compute.internal cpu █████████████████████████████░░░░

# 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

• KEDA 설치

# KEDA 설치
cat <<EOT > keda-values.yaml
metricsServer:
  useHostNetwork: true

prometheus:
  metricServer:
    enabled: true
    port: 9022
    portName: metrics
    path: /metrics
    serviceMonitor:
      # Enables ServiceMonitor creation for the Prometheus Operator
      enabled: true
    podMonitor:
      # Enables PodMonitor creation for the Prometheus Operator
      enabled: true
  operator:
    enabled: true
    port: 8080
    serviceMonitor:
      # Enables ServiceMonitor creation for the Prometheus Operator
      enabled: true
    podMonitor:
      # Enables PodMonitor creation for the Prometheus Operator
      enabled: true

  webhooks:
    enabled: true
    port: 8080
    serviceMonitor:
      # Enables ServiceMonitor creation for the Prometheus webhooks
      enabled: true
EOT

kubectl create namespace keda
helm repo add kedacore https://kedacore.github.io/charts
helm install keda kedacore/keda --version 2.10.2 --namespace keda -f keda-values.yaml

# KEDA 설치 확인
kubectl get-all -n keda
kubectl get all -n keda
kubectl get crd | grep keda

• 특정 시간(매 0/15/30/45분부터 5분간 php-apache 파드 생성)

# keda 네임스페이스에 디플로이먼트 생성
kubectl apply -f php-apache.yaml -n keda
kubectl get pod -n keda

# ScaledObject 정책 생성 : cron
cat <<EOT > keda-cron.yaml
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: php-apache-cron-scaled
spec:
  minReplicaCount: 0
  maxReplicaCount: 2
  pollingInterval: 30
  cooldownPeriod: 300
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: php-apache
  triggers:
  - type: cron
    metadata:
      timezone: Asia/Seoul
      start: 00,15,30,45 * * * *
      end: 05,20,35,50 * * * *
      desiredReplicas: "1"
EOT
kubectl apply -f keda-cron.yaml -n keda

# 그라파나 대시보드 추가
# 모니터링
watch -d 'kubectl get ScaledObject,hpa,pod -n keda'
kubectl get ScaledObject -w

# 확인
kubectl get ScaledObject,hpa,pod -n keda
kubectl get hpa -o jsonpath={.items[0].spec} -n keda | jq
...
"metrics": [
    {
      "external": {
        "metric": {
          "name": "s0-cron-Asia-Seoul-00,15,30,45xxxx-05,20,35,50xxxx",
          "selector": {
            "matchLabels": {
              "scaledobject.keda.sh/name": "php-apache-cron-scaled"
            }
          }
        },
        "target": {
          "averageValue": "1",
          "type": "AverageValue"
        }
      },
      "type": "External"
    }

• ㅇㅇ

# helm repository 추가
helm repo add cluster-proportional-autoscaler https://kubernetes-sigs.github.io/cluster-proportional-autoscaler

# CPA규칙을 설정하고 helm차트를 릴리즈 필요
helm upgrade --install cluster-proportional-autoscaler cluster-proportional-autoscaler/cluster-proportional-autoscaler

# Release "cluster-proportional-autoscaler" does not exist. Installing it now.
Error: execution error at (cluster-proportional-autoscaler/templates/deployment.yaml:3:3): options.target must be one of deployment, replicationcontroller, or replicaset

# nginx 디플로이먼트 배포
cat <<EOT > cpa-nginx.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - name: nginx
        image: nginx:latest
        resources:
          limits:
            cpu: "100m"
            memory: "64Mi"
          requests:
            cpu: "100m"
            memory: "64Mi"
        ports:
        - containerPort: 80
EOT
kubectl apply -f cpa-nginx.yaml

# CPA 규칙 설정
cat <<EOF > cpa-values.yaml
config:
  ladder:
    nodesToReplicas:
      - [1, 1]
      - [2, 2]
      - [3, 3]
      - [4, 3]
      - [5, 5]
options:
  namespace: default
  target: "deployment/nginx-deployment"
EOF

# helm 업그레이드
helm upgrade --install cluster-proportional-autoscaler -f cpa-values.yaml cluster-proportional-autoscaler/cluster-proportional-autoscaler

• 노드 증가 및 축소

# 노드 5개로 증가
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 5 --desired-capacity 5 --max-size 5
aws autoscaling describe-auto-scaling-groups --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='myeks']].[AutoScalingGroupName, MinSize, MaxSize,DesiredCapacity]" --output table

# 노드 4개로 축소
aws autoscaling update-auto-scaling-group --auto-scaling-group-name ${ASG_NAME} --min-size 4 --desired-capacity 4 --max-size 4
aws autoscaling describe-auto-scaling-groups --query "AutoScalingGroups[? Tags[? (Key=='eks:cluster-name') && Value=='myeks']].[AutoScalingGroupName, MinSize, MaxSize,DesiredCapacity]" --output table

• 기존 클러스터 제거 후 신규 실습환경 배포

# YAML 파일 다운로드
curl -O https://s3.ap-northeast-2.amazonaws.com/cloudformation.cloudneta.net/K8S/karpenter-preconfig.yaml

# CloudFormation 스택 배포
예시) aws cloudformation deploy --template-file karpenter-preconfig.yaml --stack-name myeks2 --parameter-overrides KeyName=nasirk17 SgIngressSshCidr=$(curl -s ipinfo.io/ip)/32  MyIamUserAccessKeyID=AKIA5... MyIamUserSecretAccessKey='CVNa2...' ClusterBaseName=myeks2 --region ap-northeast-2

# CloudFormation 스택 배포 완료 후 작업용 EC2 IP 출력
aws cloudformation describe-stacks --stack-name myeks2 --query 'Stacks[*].Outputs[0].OutputValue' --output text

# 작업용 EC2 SSH 접속
ssh -i ~/.ssh/nasirk17.pem ec2-user@$(aws cloudformation describe-stacks --stack-name myeks2 --query 'Stacks[*].Outputs[0].OutputValue' --output text)

• 배포 확인 및 추가도구 구성 (eks-node-viewer)

# IP 주소 확인 : 172.30.0.0/16 VPC 대역에서 172.30.1.0/24 대역을 사용 중
ip -br -c addr

# EKS Node Viewer 설치 : 현재 ec2 spec에서는 설치에 다소 시간이 소요됨 = 2분 이상
go install github.com/awslabs/eks-node-viewer/cmd/eks-node-viewer@latest

# [터미널1] bin 확인 및 사용
tree ~/go/bin
cd ~/go/bin
./eks-node-viewer -h
./eks-node-viewer  # EKS 배포 완료 후 실행

# eks-node-viewer 좀더 편하게 사용하기 위해 이동
sudo mv ./eks-node-viewer /usr/local/bin/eks-node-viewer

# k9s도 아래처럼 간편히 설치해서 사용가능합니다.
wget https://github.com/derailed/k9s/releases/download/v0.27.3/k9s_Linux_amd64.tar.gz
tar -zxvf k9s_Linux_amd64.tar.gz 
sudo mv ./k9s /usr/local/bin/k9s

• eks 클러스터 배포

# 환경변수 정보 확인
export | egrep 'ACCOUNT|AWS_|CLUSTER' | egrep -v 'SECRET|KEY'

# 환경변수 설정
export KARPENTER_VERSION=v0.27.5
export TEMPOUT=$(mktemp)
echo $KARPENTER_VERSION $CLUSTER_NAME $AWS_DEFAULT_REGION $AWS_ACCOUNT_ID $TEMPOUT

# CloudFormation 스택으로 IAM Policy, Role, EC2 Instance Profile 생성 : 3분 정도 소요
curl -fsSL https://karpenter.sh/"${KARPENTER_VERSION}"/getting-started/getting-started-with-karpenter/cloudformation.yaml  > $TEMPOUT \
&& aws cloudformation deploy \
  --stack-name "Karpenter-${CLUSTER_NAME}" \
  --template-file "${TEMPOUT}" \
  --capabilities CAPABILITY_NAMED_IAM \
  --parameter-overrides "ClusterName=${CLUSTER_NAME}"

# 클러스터 생성 : myeks2 EKS 클러스터 생성 19분 정도 소요
eksctl create cluster -f - <<EOF
---
apiVersion: eksctl.io/v1alpha5
kind: ClusterConfig
metadata:
  name: ${CLUSTER_NAME}
  region: ${AWS_DEFAULT_REGION}
  version: "1.24"
  tags:
    karpenter.sh/discovery: ${CLUSTER_NAME}

iam:
  withOIDC: true
  serviceAccounts:
  - metadata:
      name: karpenter
      namespace: karpenter
    roleName: ${CLUSTER_NAME}-karpenter
    attachPolicyARNs:
    - arn:aws:iam::${AWS_ACCOUNT_ID}:policy/KarpenterControllerPolicy-${CLUSTER_NAME}
    roleOnly: true

iamIdentityMappings:
- arn: "arn:aws:iam::${AWS_ACCOUNT_ID}:role/KarpenterNodeRole-${CLUSTER_NAME}"
  username: system:node:{{EC2PrivateDNSName}}
  groups:
  - system:bootstrappers
  - system:nodes

managedNodeGroups:
- instanceType: m5.large
  amiFamily: AmazonLinux2
  name: ${CLUSTER_NAME}-ng
  desiredCapacity: 2
  minSize: 1
  maxSize: 10
  iam:
    withAddonPolicies:
      externalDNS: true

## Optionally run on fargate
# fargateProfiles:
# - name: karpenter
#  selectors:
#  - namespace: karpenter
EOF

# eks 배포 확인
eksctl get cluster
eksctl get nodegroup --cluster $CLUSTER_NAME
eksctl get iamidentitymapping --cluster $CLUSTER_NAME
eksctl get iamserviceaccount --cluster $CLUSTER_NAME
eksctl get addon --cluster $CLUSTER_NAME

# [터미널1] eks-node-viewer
cd ~/go/bin && ./eks-node-viewer

# k8s 확인
kubectl cluster-info
kubectl get node --label-columns=node.kubernetes.io/instance-type,eks.amazonaws.com/capacityType,topology.kubernetes.io/zone
kubectl get pod -n kube-system -owide
kubectl describe cm -n kube-system aws-auth
...
mapRoles:
----
- groups:
  - system:bootstrappers
  - system:nodes
  rolearn: arn:aws:iam::911283464785:role/KarpenterNodeRole-myeks2
  username: system:node:{{EC2PrivateDNSName}}
- groups:
  - system:bootstrappers
  - system:nodes
  rolearn: arn:aws:iam::911283464785:role/eksctl-myeks2-nodegroup-myeks2-ng-NodeInstanceRole-1KDXF4FLKKX1B
  username: system:node:{{EC2PrivateDNSName}}
...

# 카펜터 설치를 위한 환경 변수 설정 및 확인
export CLUSTER_ENDPOINT="$(aws eks describe-cluster --name ${CLUSTER_NAME} --query "cluster.endpoint" --output text)"
export KARPENTER_IAM_ROLE_ARN="arn:aws:iam::${AWS_ACCOUNT_ID}:role/${CLUSTER_NAME}-karpenter"
echo $CLUSTER_ENDPOINT $KARPENTER_IAM_ROLE_ARN

# EC2 Spot Fleet 사용을 위한 service-linked-role 생성 확인 : 만들어있는것을 확인하는 거라 아래 에러 출력이 정상!
# If the role has already been successfully created, you will see:
# An error occurred (InvalidInput) when calling the CreateServiceLinkedRole operation: Service role name AWSServiceRoleForEC2Spot has been taken in this account, please try a different suffix.
aws iam create-service-linked-role --aws-service-name spot.amazonaws.com || true

# docker logout : Logout of docker to perform an unauthenticated pull against the public ECR
docker logout public.ecr.aws

# karpenter 설치
helm upgrade --install karpenter oci://public.ecr.aws/karpenter/karpenter --version ${KARPENTER_VERSION} --namespace karpenter --create-namespace \
  --set serviceAccount.annotations."eks\.amazonaws\.com/role-arn"=${KARPENTER_IAM_ROLE_ARN} \
  --set settings.aws.clusterName=${CLUSTER_NAME} \
  --set settings.aws.defaultInstanceProfile=KarpenterNodeInstanceProfile-${CLUSTER_NAME} \
  --set settings.aws.interruptionQueueName=${CLUSTER_NAME} \
  --set controller.resources.requests.cpu=1 \
  --set controller.resources.requests.memory=1Gi \
  --set controller.resources.limits.cpu=1 \
  --set controller.resources.limits.memory=1Gi \
  --wait

# 확인
kubectl get-all -n karpenter
kubectl get all -n karpenter
kubectl get cm -n karpenter karpenter-global-settings -o jsonpath={.data} | jq
kubectl get crd | grep karpenter

• 클러스터 추가도구 배포 (ExternalDNS, kube-ops-view)
• 는 초기 구성 참조하여 재배포
  

• Provisioner 생성
• eksctl은 ASG를 사용해 노드그룹을 구성하였던것처럼, 카펜터는 프로비저너를 사용해 노드그룹을 구성
  • spot 인스턴스 사용 설정
  • 30초 이상 노드가 비어있으면 노드 제거
  • karpenter.sh/discovery 태그가 달린 서브넷/보안그룹 사용

# Create Provisioner
cat <<EOF | kubectl apply -f -
apiVersion: karpenter.sh/v1alpha5
kind: Provisioner
metadata:
  name: default
spec:
  requirements:
    - key: karpenter.sh/capacity-type
      operator: In
      values: ["spot"]
  limits:
    resources:
      cpu: 1000
  providerRef:
    name: default
  ttlSecondsAfterEmpty: 30
---
apiVersion: karpenter.k8s.aws/v1alpha1
kind: AWSNodeTemplate
metadata:
  name: default
spec:
  subnetSelector:
    karpenter.sh/discovery: ${CLUSTER_NAME}
  securityGroupSelector:
    karpenter.sh/discovery: ${CLUSTER_NAME}
EOF

# 확인
kubectl get awsnodetemplates,provisioners

• deploy 배포 후 수량 조절 > 노드 배포속도 확인

# pause 파드 1개에 CPU 1개 최소 보장 할당
cat <<EOF | kubectl apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: inflate
spec:
  replicas: 0
  selector:
    matchLabels:
      app: inflate
  template:
    metadata:
      labels:
        app: inflate
    spec:
      terminationGracePeriodSeconds: 0
      containers:
        - name: inflate
          image: public.ecr.aws/eks-distro/kubernetes/pause:3.7
          resources:
            requests:
              cpu: 1
EOF
kubectl scale deployment inflate --replicas 5
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller

# 스팟 인스턴스 확인!
aws ec2 describe-spot-instance-requests --filters "Name=state,Values=active" --output table
kubectl get node -l karpenter.sh/capacity-type=spot -o jsonpath='{.items[0].metadata.labels}' | jq
kubectl get node --label-columns=eks.amazonaws.com/capacityType,karpenter.sh/capacity-type,node.kubernetes.io/instance-type

NAME                                                STATUS   ROLES    AGE     VERSION                CAPACITYTYPE   CAPACITY-TYPE   INSTANCE-TYPE
ip-192-168-19-252.ap-northeast-2.compute.internal   Ready    <none>   17m     v1.24.13-eks-0a21954   ON_DEMAND                      m5.large
ip-192-168-40-43.ap-northeast-2.compute.internal    Ready    <none>   2m25s   v1.24.13-eks-0a21954                  spot            c4.2xlarge
ip-192-168-85-220.ap-northeast-2.compute.internal   Ready    <none>   17m     v1.24.13-eks-0a21954   ON_DEMAND                      m5.large

• Scale down deployment : ttlSecondsAfterEmpty 30초

# Now, delete the deployment. After 30 seconds (ttlSecondsAfterEmpty), Karpenter should terminate the now empty nodes.
kubectl delete deployment inflate
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller

• Consolidation: 강화, 합병, 합동
• 효율적으로 사용되고 있지 않는 리소스를 병합하여 워커노드 최적화

# 기존 provisioner 삭제 후 신규 provisioner 생성
kubectl delete provisioners default
cat <<EOF | kubectl apply -f -
apiVersion: karpenter.sh/v1alpha5
kind: Provisioner
metadata:
  name: default
spec:
  consolidation:
    enabled: true
  labels:
    type: karpenter
  limits:
    resources:
      cpu: 1000
      memory: 1000Gi
  providerRef:
    name: default
  requirements:
    - key: karpenter.sh/capacity-type
      operator: In
      values:
        - on-demand
    - key: node.kubernetes.io/instance-type
      operator: In
      values:
        - c5.large
        - m5.large
        - m5.xlarge
EOF

# dummy 파드 배포
cat <<EOF | kubectl apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: inflate
spec:
  replicas: 0
  selector:
    matchLabels:
      app: inflate
  template:
    metadata:
      labels:
        app: inflate
    spec:
      terminationGracePeriodSeconds: 0
      containers:
        - name: inflate
          image: public.ecr.aws/eks-distro/kubernetes/pause:3.7
          resources:
            requests:
              cpu: 1
EOF
kubectl scale deployment inflate --replicas 12
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller

# 인스턴스 확인
# This changes the total memory request for this deployment to around 12Gi, 
# which when adjusted to account for the roughly 600Mi reserved for the kubelet on each node means that this will fit on 2 instances of type m5.large:
kubectl get node -l type=karpenter
kubectl get node --label-columns=eks.amazonaws.com/capacityType,karpenter.sh/capacity-type
kubectl get node --label-columns=node.kubernetes.io/instance-type,topology.kubernetes.io/zone

# Next, scale the number of replicas back down to 5:
kubectl scale deployment inflate --replicas 5

# The output will show Karpenter identifying specific nodes to cordon, drain and then terminate:
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller

...
~ INFO    controller.deprovisioning deprovisioning via consolidation replace, terminating 1 machines ~
~ INFO    controller.termination    cordoned node ~
~ INFO    controller.termination    deleted node ~
...

# Next, scale the number of replicas back down to 1
kubectl scale deployment inflate --replicas 1
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller

...
~
...

# 인스턴스 확인
kubectl get node -l type=karpenter
kubectl get node --label-columns=eks.amazonaws.com/capacityType,karpenter.sh/capacity-type
kubectl get node --label-columns=node.kubernetes.io/instance-type,topology.kubernetes.io/zone

# 삭제
kubectl delete deployment inflate