EKS マネージドノードグループの Warm Pool を検証 — poolState 別スケールアウト時間と reuseOnScaleIn の実態

REGION=ap-northeast-1
CLUSTER=eks-sandbox
 
aws eks create-addon --cluster-name $CLUSTER --addon-name vpc-cni --region $REGION
aws eks create-addon --cluster-name $CLUSTER --addon-name kube-proxy --region $REGION
aws eks create-addon --cluster-name $CLUSTER --addon-name coredns --region $REGION

cat > node-trust-policy.json << 'EOF'
{
  "Version": "2012-10-17",
  "Statement": [{
    "Effect": "Allow",
    "Principal": { "Service": "ec2.amazonaws.com" },
    "Action": "sts:AssumeRole"
  }]
}
EOF
 
aws iam create-role \
  --role-name eks-warmpool-verify-node-role \
  --assume-role-policy-document file://node-trust-policy.json
 
aws iam attach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy
aws iam attach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy
aws iam attach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly

# アカウント ID を取得
ACCOUNT_ID=$(aws sts get-caller-identity --query 'Account' --output text)
NODE_ROLE="arn:aws:iam::${ACCOUNT_ID}:role/eks-warmpool-verify-node-role"
 
# クラスターのプライベートサブネットを取得
SUBNETS=$(aws eks describe-cluster --name $CLUSTER --region $REGION \
  --query 'cluster.resourcesVpcConfig.subnetIds' --output text)

 
# 1. コールドスタート（ウォームプールなし）
aws eks create-nodegroup \
  --cluster-name $CLUSTER --nodegroup-name ng-cold-start \
  --node-role $NODE_ROLE --subnets $SUBNETS \
  --instance-types t3.medium \
  --scaling-config minSize=2,maxSize=5,desiredSize=2 \
  --region $REGION
 
# 2. Stopped ウォームプール
aws eks create-nodegroup \
  --cluster-name $CLUSTER --nodegroup-name ng-warm-stopped \
  --node-role $NODE_ROLE --subnets $SUBNETS \
  --instance-types t3.medium \
  --scaling-config minSize=2,maxSize=5,desiredSize=2 \
  --warm-pool-config enabled=true,maxGroupPreparedCapacity=4,minSize=1,poolState=Stopped,reuseOnScaleIn=true \
  --region $REGION
 
# 3. Running ウォームプール
aws eks create-nodegroup \
  --cluster-name $CLUSTER --nodegroup-name ng-warm-running \
  --node-role $NODE_ROLE --subnets $SUBNETS \
  --instance-types t3.medium \
  --scaling-config minSize=2,maxSize=5,desiredSize=2 \
  --warm-pool-config enabled=true,maxGroupPreparedCapacity=4,minSize=1,poolState=Running,reuseOnScaleIn=false \
  --region $REGION

# ASG 名を取得
ASG=$(aws eks describe-nodegroup --cluster-name $CLUSTER --nodegroup-name ng-warm-stopped \
  --region $REGION --query 'nodegroup.resources.autoScalingGroups[0].name' --output text)
 
# ウォームプールのインスタンス状態を確認
aws autoscaling describe-warm-pool --auto-scaling-group-name $ASG --region $REGION \
  --query 'Instances[].{InstanceId:InstanceId,State:LifecycleState}' --output table

-------------------------------------------
|            DescribeWarmPool             |
+----------------------+------------------+
|      InstanceId      |      State       |
+----------------------+------------------+
|  i-0a546e64a73986140 |  Warmed:Stopped  |
|  i-0c0c0f4ad0652338a |  Warmed:Stopped  |
+----------------------+------------------+

NODEGROUP="ng-cold-start"  # ng-warm-stopped / ng-warm-running に置き換え
START_TIME=$(date +%s)
 
while true; do
  READY=$(kubectl get nodes --selector="eks.amazonaws.com/nodegroup=$NODEGROUP" \
    --no-headers 2>/dev/null | grep " Ready " | wc -l)
  TOTAL=$(kubectl get nodes --selector="eks.amazonaws.com/nodegroup=$NODEGROUP" \
    --no-headers 2>/dev/null | wc -l)
  ELAPSED=$(( $(date +%s) - START_TIME ))
  echo "$(date +%T) [${ELAPSED}s] Nodes: $TOTAL total, $READY ready"
  [ "$READY" -ge 3 ] && echo "=== New node Ready! ===" && break
  sleep 5
done

# 既存ノードを埋める Pod × 2 + Pending になる Pod × 1
kubectl apply -f - << 'EOF'
apiVersion: v1
kind: Pod
metadata:
  name: filler-pod-1
spec:
  nodeSelector:
    eks.amazonaws.com/nodegroup: ng-warm-stopped
  containers:
    - name: nginx
      image: nginx:alpine
      resources:
        requests:
          cpu: "1500m"
          memory: "2Gi"
---
apiVersion: v1
kind: Pod
metadata:
  name: filler-pod-2
spec:
  nodeSelector:
    eks.amazonaws.com/nodegroup: ng-warm-stopped
  containers:
    - name: nginx
      image: nginx:alpine
      resources:
        requests:
          cpu: "1500m"
          memory: "2Gi"
---
apiVersion: v1
kind: Pod
metadata:
  name: pending-pod
spec:
  nodeSelector:
    eks.amazonaws.com/nodegroup: ng-warm-stopped
  containers:
    - name: nginx
      image: nginx:alpine
      resources:
        requests:
          cpu: "1500m"
          memory: "2Gi"
EOF

REGION=ap-northeast-1
CLUSTER=eks-sandbox
 
# Pod 削除
kubectl delete pod filler-pod-1 filler-pod-2 pending-pod
 
# ノードグループ削除
for NG in ng-cold-start ng-warm-stopped ng-warm-running; do
  aws eks delete-nodegroup --cluster-name $CLUSTER --nodegroup-name $NG --region $REGION
done
 
# ノードグループ削除完了を待つ
for NG in ng-cold-start ng-warm-stopped ng-warm-running; do
  aws eks wait nodegroup-deleted --cluster-name $CLUSTER --nodegroup-name $NG --region $REGION
done
 
# アドオン削除（Auto Mode クラスターで追加した場合）
aws eks delete-addon --cluster-name $CLUSTER --addon-name vpc-cni --region $REGION
aws eks delete-addon --cluster-name $CLUSTER --addon-name kube-proxy --region $REGION
aws eks delete-addon --cluster-name $CLUSTER --addon-name coredns --region $REGION
 
# IAM ロール削除
aws iam detach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy
aws iam detach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy
aws iam detach-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-arn arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly
aws iam delete-role-policy --role-name eks-warmpool-verify-node-role \
  --policy-name ClusterAutoscalerPolicy 2>/dev/null  # 追加した場合のみ
aws iam delete-role --role-name eks-warmpool-verify-node-role