[Deploy] : deploy eks logs and debug

.github/workflows/deploy.yml

@@ -19,11 +19,12 @@ jobs:
         aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
         aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
         aws-region: ap-northeast-2
-        
-    - name: Get current IAM user
+
+    - name: Verify AWS Configuration
       run: |
+        echo "🔍 AWS 설정 확인..."
         aws sts get-caller-identity
-        echo "위 결과의 'Arn' 값을 EKS 액세스 항목에 입력하세요"
+        aws eks describe-cluster --name nestjs-cluster --region ap-northeast-2 --query 'cluster.status'
 
     - name: Install eksctl
       run: |
@@ -39,43 +40,57 @@ jobs:
         sudo install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl
         kubectl version --client
 
+    - name: Update kubeconfig and verify connection
+      run: |
+        echo "🔧 EKS kubeconfig 설정..."
+        aws eks update-kubeconfig --region ap-northeast-2 --name nestjs-cluster
+
+        echo "🔍 클러스터 연결 테스트..."
+        kubectl cluster-info
+        kubectl get nodes -o wide
+
+        echo "🔍 현재 context 확인..."
+        kubectl config current-context
+
     - name: Login to Amazon ECR
       id: login-ecr
       uses: aws-actions/amazon-ecr-login@v1
 
+    - name: Verify ECR Repository
+      run: |
+        echo "🔍 ECR 리포지토리 확인..."
+        aws ecr describe-repositories --repository-names nestjs-app --region ap-northeast-2 || {
+          echo "❌ ECR 리포지토리가 존재하지 않습니다. 생성합니다..."
+          aws ecr create-repository --repository-name nestjs-app --region ap-northeast-2
+        }
+
     - name: Build, tag, and push image to Amazon ECR
       env:
         ECR_REGISTRY: ${{ steps.login-ecr.outputs.registry }}
         ECR_REPOSITORY: nestjs-app
         IMAGE_TAG: ${{ github.sha }}
       run: |
+        echo "🏗️ Docker 이미지 빌드 및 푸시..."
         docker build -t $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG .
         docker push $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG
         docker tag $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG $ECR_REGISTRY/$ECR_REPOSITORY:latest
         docker push $ECR_REGISTRY/$ECR_REPOSITORY:latest
-
-    - name: Update kubeconfig
-      run: |
-        # EKS 클러스터 kubeconfig 설정
-        aws eks update-kubeconfig --region ap-northeast-2 --name nestjs-cluster
 
-        # 연결 테스트
-        kubectl cluster-info
-        kubectl get nodes
+        echo "✅ 이미지 푸시 완료: $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG"
 
     - name: Install AWS Load Balancer Controller (if not exists)
       run: |
-        # Check if AWS Load Balancer Controller exists
+        echo "🔍 AWS Load Balancer Controller 확인..."
         if ! kubectl get deployment -n kube-system aws-load-balancer-controller > /dev/null 2>&1; then
-          echo "Installing AWS Load Balancer Controller..."
+          echo "📦 AWS Load Balancer Controller 설치 중..."
 
           # Download IAM policy
           curl -O https://raw.githubusercontent.com/kubernetes-sigs/aws-load-balancer-controller/v2.7.2/docs/install/iam_policy.json
 
           # Create IAM policy (ignore if exists)
           aws iam create-policy \
             --policy-name AWSLoadBalancerControllerIAMPolicy \
-            --policy-document file://iam_policy.json || true
+            --policy-document file://iam_policy.json || echo "IAM 정책이 이미 존재합니다"
 
           # Create service account with eksctl
           eksctl create iamserviceaccount \
@@ -85,15 +100,15 @@ jobs:
             --role-name AmazonEKSLoadBalancerControllerRole \
             --attach-policy-arn=arn:aws:iam::863518449560:policy/AWSLoadBalancerControllerIAMPolicy \
             --approve \
-            --region=ap-northeast-2 || true
+            --region=ap-northeast-2 || echo "서비스 계정이 이미 존재합니다"
 
           # Install cert-manager
           kubectl apply \
             --validate=false \
             -f https://github.com/jetstack/cert-manager/releases/download/v1.13.0/cert-manager.yaml
 
           # Wait for cert-manager
-          echo "Waiting for cert-manager to be ready..."
+          echo "⏳ cert-manager 준비 대기 중..."
           kubectl wait --for=condition=ready pod -l app.kubernetes.io/instance=cert-manager -n cert-manager --timeout=300s
 
           # Download and apply AWS Load Balancer Controller
@@ -102,10 +117,10 @@ jobs:
           kubectl apply -f v2_7_2_full.yaml
 
           # Wait for controller to be ready
-          echo "Waiting for AWS Load Balancer Controller to be ready..."
+          echo "⏳ AWS Load Balancer Controller 준비 대기 중..."
           kubectl wait --for=condition=ready pod -l app.kubernetes.io/name=aws-load-balancer-controller -n kube-system --timeout=300s
         else
-          echo "AWS Load Balancer Controller already exists"
+          echo "✅ AWS Load Balancer Controller가 이미 설치되어 있습니다"
         fi
 
     - name: Deploy to EKS
@@ -114,29 +129,130 @@ jobs:
         ECR_REPOSITORY: nestjs-app
         IMAGE_TAG: ${{ github.sha }}
       run: |
+        echo "🚀 EKS 배포 시작..."
+
         # Create namespace
+        echo "📁 네임스페이스 생성..."
         kubectl apply -f k8s/namespace.yaml
 
         # Create or update secrets
+        echo "🔐 시크릿 생성/업데이트..."
         kubectl create secret generic app-secrets \
           --from-literal=database-url="${{ secrets.DATABASE_URL }}" \
           --from-literal=redis-url="${{ secrets.REDIS_URL }}" \
           --namespace=nestjs-app \
           --dry-run=client -o yaml | kubectl apply -f -
 
         # Update deployment image
+        echo "🔄 배포 이미지 업데이트..."
         sed -i "s|863518449560.dkr.ecr.ap-northeast-2.amazonaws.com/nestjs-app:latest|$ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG|g" k8s/deployment.yaml
 
         # Deploy application
+        echo "📦 애플리케이션 배포..."
         kubectl apply -f k8s/deployment.yaml
         kubectl apply -f k8s/service.yaml
         kubectl apply -f k8s/hpa.yaml
         kubectl apply -f k8s/ingress.yaml
 
-        # Check deployment status
-        kubectl rollout status deployment/nestjs-app -n nestjs-app
+        echo "✅ 리소스 배포 완료"
+
+    - name: Monitor Deployment Progress
+      run: |
+        echo "🔍 배포 진행 상황 모니터링..."
+
+        # Start rollout status check in background
+        kubectl rollout status deployment/nestjs-app -n nestjs-app --timeout=600s &
+        ROLLOUT_PID=$!
+
+        # Monitor pods and logs in real-time
+        echo "📊 실시간 모니터링 시작..."
+        for i in {1..30}; do
+          echo "--- 체크 #$i ($(date '+%H:%M:%S')) ---"
+
+          echo "Pod 상태:"
+          kubectl get pods -n nestjs-app -l app=nestjs-app -o wide
+
+          echo "ReplicaSet 상태:"
+          kubectl get rs -n nestjs-app -l app=nestjs-app -o wide
+
+          echo "최근 이벤트:"
+          kubectl get events -n nestjs-app --field-selector involvedObject.kind=Pod --sort-by='.lastTimestamp' | tail -3
+
+          # Get logs from any running pods
+          PODS=$(kubectl get pods -n nestjs-app -l app=nestjs-app -o jsonpath='{.items[*].metadata.name}')
+          if [ ! -z "$PODS" ]; then
+            echo "현재 Pod 로그:"
+            for pod in $PODS; do
+              echo "--- $pod 로그 ---"
+              kubectl logs $pod -n nestjs-app --tail=5 --since=30s 2>/dev/null || echo "로그 없음"
+            done
+          fi
+
+          # Check if rollout is still running
+          if ! kill -0 $ROLLOUT_PID 2>/dev/null; then
+            echo "✅ 롤아웃 완료!"
+            break
+          fi
+
+          echo "⏳ 20초 후 다시 확인..."
+          sleep 20
+        done
+
+        # Wait for rollout to complete
+        wait $ROLLOUT_PID
+
+    - name: Debug Deployment Issues
+      if: failure()
+      run: |
+        echo "🔍 ===== 배포 실패 디버깅 ====="
+
+        echo "📊 Deployment 상세 정보:"
+        kubectl describe deployment nestjs-app -n nestjs-app
+
+        echo ""
+        echo "📊 ReplicaSet 상태:"
+        kubectl describe rs -n nestjs-app -l app=nestjs-app
+
+        echo ""
+        echo "🚨 실패한 Pod 상세 정보:"
+        kubectl get pods -n nestjs-app -l app=nestjs-app -o wide
+
+        # 각 Pod의 상세 정보와 로그 출력
+        PODS=$(kubectl get pods -n nestjs-app -l app=nestjs-app -o jsonpath='{.items[*].metadata.name}')
+        for pod in $PODS; do
+          echo ""
+          echo "--- Pod: $pod 상세 정보 ---"
+          kubectl describe pod $pod -n nestjs-app
+
+          echo ""
+          echo "--- Pod: $pod 현재 로그 ---"
+          kubectl logs $pod -n nestjs-app --tail=50 || echo "현재 로그 없음"
+
+          echo ""
+          echo "--- Pod: $pod 이전 로그 ---"
+          kubectl logs $pod -n nestjs-app --previous --tail=50 || echo "이전 로그 없음"
+        done
+
+        echo ""
+        echo "🔍 최근 이벤트 (상세):"
+        kubectl get events -n nestjs-app --sort-by='.lastTimestamp' | tail -20
+
+        echo ""
+        echo "🔍 클러스터 리소스 상태:"
+        kubectl top nodes || echo "메트릭 서버 사용 불가"
+        kubectl describe nodes | grep -A 10 "Allocated resources" || echo "노드 리소스 정보 없음"
+
+        echo ""
+        echo "🔍 네임스페이스 리소스:"
+        kubectl get all -n nestjs-app
+
+        echo ""
+        echo "🔍 Secret 및 ConfigMap 상태:"
+        kubectl get secrets -n nestjs-app
+        kubectl get configmaps -n nestjs-app
 
     - name: Post-Deployment Verification
+      if: success()
       run: |
         echo "🚀 ===== 배포 완료 확인 ====="