Monitoring

# prometheus.yml - Prometheus 설정
global:
  scrape_interval: 15s      # 메트릭 수집 주기
  evaluation_interval: 15s  # 알림 규칙 평가 주기

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['alertmanager:9093']

rule_files:
  - "alerts/*.yml"

scrape_configs:
  # Prometheus 자체 모니터링
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  # Kubernetes Pod 자동 발견
  - job_name: 'kubernetes-pods'
    kubernetes_sd_configs:
      - role: pod
    relabel_configs:
      # prometheus.io/scrape: "true" 어노테이션이 있는 Pod만
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      # 커스텀 경로 지원
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      # 포트 지정
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2

# alerts/api-alerts.yml - 알림 규칙
groups:
- name: api-alerts
  rules:
  # 높은 에러율 감지
  - alert: HighErrorRate
    expr: |
      sum(rate(http_requests_total{status=~"5.."}[5m])) by (service)
      /
      sum(rate(http_requests_total[5m])) by (service)
      > 0.05
    for: 5m
    labels:
      severity: critical
    annotations:
      summary: "High error rate on {{ $labels.service }}"
      description: "Error rate is {{ $value | humanizePercentage }}"

  # 느린 응답 시간
  - alert: HighLatency
    expr: |
      histogram_quantile(0.95,
        sum(rate(http_request_duration_seconds_bucket[5m])) by (le, service)
      ) > 1
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: "P95 latency above 1s on {{ $labels.service }}"

  # Pod 메모리 사용량
  - alert: PodHighMemory
    expr: |
      container_memory_working_set_bytes / container_spec_memory_limit_bytes > 0.9
    for: 15m
    labels:
      severity: warning