스케일링

# Kubernetes HPA (Horizontal Pod Autoscaler)
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
  - type: Resource
    resource:
      name: memory
      target:
        type: Utilization
        averageUtilization: 80
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300   # 축소 전 5분 대기
      policies:
      - type: Percent
        value: 10
        periodSeconds: 60               # 분당 10%씩 축소
    scaleUp:
      stabilizationWindowSeconds: 0     # 즉시 확장
      policies:
      - type: Percent
        value: 100
        periodSeconds: 15               # 15초마다 100%까지 확장
---
# AWS Auto Scaling (Terraform)
resource "aws_autoscaling_group" "web" {
  name                = "web-asg"
  min_size            = 2
  max_size            = 20
  desired_capacity    = 4
  vpc_zone_identifier = var.subnet_ids

  launch_template {
    id      = aws_launch_template.web.id
    version = "$Latest"
  }

  target_group_arns = [aws_lb_target_group.web.arn]

  tag {
    key                 = "Name"
    value               = "web-instance"
    propagate_at_launch = true
  }
}

resource "aws_autoscaling_policy" "scale_up" {
  name                   = "scale-up"
  scaling_adjustment     = 2
  adjustment_type        = "ChangeInCapacity"
  cooldown               = 300
  autoscaling_group_name = aws_autoscaling_group.web.name
}