Split View: Kubernetes VPA + In-Place Pod Resize 실전 가이드 — 재시작 없는 리소스 자동 조정

# 1. Recommender: Analyzes resource usage and computes recommendations
# 2. Updater: Triggers Pod updates based on recommendations
# 3. Admission Controller: Applies recommendations to newly created Pods

# Add VPA Helm chart
helm repo add fairwinds-stable https://charts.fairwinds.com/stable
helm repo update

# Install VPA
helm install vpa fairwinds-stable/vpa \
  --namespace vpa-system \
  --create-namespace \
  --set recommender.enabled=true \
  --set updater.enabled=true \
  --set admissionController.enabled=true

# Verify installation
kubectl get pods -n vpa-system

git clone https://github.com/kubernetes/autoscaler.git
cd autoscaler/vertical-pod-autoscaler

# Install CRDs and components
./hack/vpa-up.sh

# Verify
kubectl get customresourcedefinitions | grep verticalpodautoscaler

# vpa-nginx.yaml
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: nginx-vpa
  namespace: default
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: nginx-deployment
  updatePolicy:
    updateMode: 'Auto' # Off, Initial, Recreate, Auto
  resourcePolicy:
    containerPolicies:
      - containerName: nginx
        minAllowed:
          cpu: '50m'
          memory: '64Mi'
        maxAllowed:
          cpu: '2'
          memory: '2Gi'
        controlledResources: ['cpu', 'memory']
        controlledValues: RequestsAndLimits

kubectl apply -f vpa-nginx.yaml

# Check VPA recommendations
kubectl get vpa nginx-vpa -o yaml

# Off: Only provides recommendations, no automatic updates (for monitoring)
updateMode: "Off"

# Initial: Applies recommendations only at Pod creation time
updateMode: "Initial"

# Recreate: Recreates Pods when recommendations change
updateMode: "Recreate"

# Auto: Automatically selects the optimal method (includes In-Place on 1.35+)
updateMode: "Auto"

# InPlaceOrRecreate: Prefers In-Place, falls back to recreate if not possible (1.35+ Beta)
updateMode: "InPlaceOrRecreate"

# Check cluster version
kubectl version --short

# Check feature gate status (default true on 1.35+)
kubectl get --raw /api/v1/nodes | jq '.items[0].status.features'

# deployment-with-resize.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: web-app
spec:
  replicas: 3
  selector:
    matchLabels:
      app: web-app
  template:
    metadata:
      labels:
        app: web-app
    spec:
      containers:
        - name: web
          image: nginx:1.27
          resources:
            requests:
              cpu: '100m'
              memory: '128Mi'
            limits:
              cpu: '500m'
              memory: '512Mi'
          resizePolicy:
            - resourceName: cpu
              restartPolicy: NotRequired # CPU adjusted without restart
            - resourceName: memory
              restartPolicy: NotRequired # Memory also adjusted without restart

kubectl apply -f deployment-with-resize.yaml

# vpa-inplace.yaml
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: web-app-vpa
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  updatePolicy:
    updateMode: 'InPlaceOrRecreate'
    minReplicas: 2 # Minimum replicas to maintain
  resourcePolicy:
    containerPolicies:
      - containerName: web
        minAllowed:
          cpu: '50m'
          memory: '64Mi'
        maxAllowed:
          cpu: '4'
          memory: '4Gi'
        controlledResources: ['cpu', 'memory']

kubectl apply -f vpa-inplace.yaml

# Verify In-Place resize events
kubectl get pods -w
# STATUS remains Running while resources change

# Check current resources of a Pod
kubectl get pod web-app-xxx -o jsonpath='{.spec.containers[0].resources}'

# Check allocated resources (actually assigned)
kubectl get pod web-app-xxx -o jsonpath='{.status.containerStatuses[0].allocatedResources}'

# Check resize status
kubectl get pod web-app-xxx -o jsonpath='{.status.resize}'
# "InProgress", "Proposed", "Deferred", "" (complete)

#!/bin/bash
# watch-vpa.sh - Real-time VPA recommendation monitoring

VPA_NAME=${1:-web-app-vpa}
NAMESPACE=${2:-default}

while true; do
  echo "=== $(date) ==="
  kubectl get vpa $VPA_NAME -n $NAMESPACE -o jsonpath='
  Target:
    CPU: {.status.recommendation.containerRecommendations[0].target.cpu}
    Memory: {.status.recommendation.containerRecommendations[0].target.memory}
  Lower Bound:
    CPU: {.status.recommendation.containerRecommendations[0].lowerBound.cpu}
    Memory: {.status.recommendation.containerRecommendations[0].lowerBound.memory}
  Upper Bound:
    CPU: {.status.recommendation.containerRecommendations[0].upperBound.cpu}
    Memory: {.status.recommendation.containerRecommendations[0].upperBound.memory}
  '
  echo ""
  sleep 30
done

# Key VPA-related metrics
# kube_verticalpodautoscaler_status_recommendation_target
# vpa_recommender_recommendation_latency
# vpa_updater_evictions_total

# Pod CPU recommendation vs actual usage
rate(container_cpu_usage_seconds_total[5m])
# vs
kube_verticalpodautoscaler_status_recommendation_target{resource="cpu"}

# Step 1: Observe recommendations in Off mode (1-2 weeks)
updateMode: "Off"

# Step 2: Apply only to new Pods with Initial mode
updateMode: "Initial"

# Step 3: Enable automatic adjustment with InPlaceOrRecreate
updateMode: "InPlaceOrRecreate"

apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: web-app-pdb
spec:
  minAvailable: 2
  selector:
    matchLabels:
      app: web-app
---
# VPA respects PDBs during Recreate fallback
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: web-app-vpa
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  updatePolicy:
    updateMode: 'InPlaceOrRecreate'
    minReplicas: 2
    evictionRequirements:
      - resources: ['cpu', 'memory']
        changeRequirement: TargetHigherThanRequests

# HPA: CPU-based horizontal scaling
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: web-app-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
---
# VPA: Vertical scaling for memory only (CPU managed by HPA)
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: web-app-vpa
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  updatePolicy:
    updateMode: 'InPlaceOrRecreate'
  resourcePolicy:
    containerPolicies:
      - containerName: web
        controlledResources: ['memory']
        minAllowed:
          memory: '128Mi'
        maxAllowed:
          memory: '4Gi'

# Install Goldilocks (VPA recommendation dashboard)
helm install goldilocks fairwinds-stable/goldilocks \
  --namespace goldilocks \
  --create-namespace

# Enable Goldilocks for a namespace
kubectl label namespace default goldilocks.fairwinds.com/enabled=true

# Access the dashboard
kubectl port-forward -n goldilocks svc/goldilocks-dashboard 8080:80

# 1. Check Kubernetes version
kubectl version --short
# 1.35+ required

# 2. Check the node's Container Runtime
kubectl get nodes -o jsonpath='{.items[*].status.nodeInfo.containerRuntimeVersion}'
# containerd 1.7+ or CRI-O 1.29+ required

# 3. Check the Pod's resizePolicy
kubectl get pod <pod-name> -o jsonpath='{.spec.containers[0].resizePolicy}'

# 4. Check resize status
kubectl get pod <pod-name> -o jsonpath='{.status.resize}'
# "Deferred" -> Insufficient resources on node
# "Infeasible" -> Node does not support resize

# 5. Check events
kubectl describe pod <pod-name> | grep -A5 "Events"

# Check VPA Recommender logs
kubectl logs -n vpa-system -l app=vpa-recommender --tail=50

# Verify metrics-server is working
kubectl top pods

# Check VPA status
kubectl describe vpa <vpa-name>

apiVersion: apps/v1
kind: Deployment
metadata:
  name: spring-boot-app
spec:
  replicas: 3
  selector:
    matchLabels:
      app: spring-boot
  template:
    metadata:
      labels:
        app: spring-boot
    spec:
      containers:
        - name: app
          image: myregistry/spring-boot-app:latest
          resources:
            requests:
              cpu: '500m'
              memory: '512Mi'
            limits:
              cpu: '2'
              memory: '2Gi'
          resizePolicy:
            - resourceName: cpu
              restartPolicy: NotRequired
            - resourceName: memory
              restartPolicy: RestartContainer # JVM needs heap reconfiguration
          env:
            - name: JAVA_OPTS
              value: '-XX:+UseContainerSupport -XX:MaxRAMPercentage=75.0'
---
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: spring-boot-vpa
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: spring-boot-app
  updatePolicy:
    updateMode: 'InPlaceOrRecreate'
  resourcePolicy:
    containerPolicies:
      - containerName: app
        minAllowed:
          cpu: '200m'
          memory: '256Mi'
        maxAllowed:
          cpu: '4'
          memory: '4Gi'