Uptime

# Prometheus + Grafana로 Uptime 모니터링

# prometheus-rules.yaml - SLO/SLI 정의
groups:
  - name: slo-rules
    rules:
      # 성공 요청 비율 (SLI)
      - record: http_request_success_rate:5m
        expr: |
          sum(rate(http_requests_total{status!~"5.."}[5m]))
          /
          sum(rate(http_requests_total[5m]))

      # 99.9% SLO 위반 여부
      - alert: HighErrorRate
        expr: http_request_success_rate:5m < 0.999
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "서비스 가용성 SLO 위반"
          description: "현재 성공률: {{ $value | humanizePercentage }}"

      # Error Budget 소진율
      - record: error_budget_remaining:30d
        expr: |
          1 - (
            (1 - avg_over_time(http_request_success_rate:5m[30d]))
            /
            (1 - 0.999)  # 99.9% SLO
          )

---
# Kubernetes Liveness/Readiness Probe 설정
apiVersion: apps/v1
kind: Deployment
metadata:
  name: api-server
spec:
  replicas: 3  # 고가용성을 위한 복제본
  template:
    spec:
      containers:
      - name: api
        image: myapp/api:v1.0.0
        ports:
        - containerPort: 8080
        # Liveness: 컨테이너가 살아있는지 확인
        livenessProbe:
          httpGet:
            path: /healthz
            port: 8080
          initialDelaySeconds: 10
          periodSeconds: 10
          failureThreshold: 3
        # Readiness: 트래픽을 받을 준비가 되었는지 확인
        readinessProbe:
          httpGet:
            path: /ready
            port: 8080
          initialDelaySeconds: 5
          periodSeconds: 5
          failureThreshold: 2
        resources:
          requests:
            cpu: 100m
            memory: 128Mi
          limits:
            cpu: 500m
            memory: 512Mi

---
# PodDisruptionBudget - 업그레이드 중 가용성 보장
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: api-pdb
spec:
  minAvailable: 2  # 최소 2개 Pod 유지
  selector:
    matchLabels:
      app: api-server

---
# 상태 페이지 API 예제 (Node.js)
# GET /status 응답 예시
{
  "status": "operational",
  "uptime": "99.98%",
  "uptime_30d": "99.95%",
  "components": {
    "api": { "status": "operational", "latency_p99": "45ms" },
    "database": { "status": "operational", "latency_p99": "12ms" },
    "cache": { "status": "degraded", "message": "Redis failover in progress" }
  },
  "incidents": [
    {
      "id": "inc-2024-001",
      "title": "API 응답 지연",
      "status": "resolved",
      "duration_minutes": 15,
      "resolved_at": "2024-01-15T10:30:00Z"
    }
  ]
}