모니터링·알람

helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm install prometheus prometheus-community/kube-prometheus-stack \
  -n monitoring --create-namespace \
  --values prometheus-values.yaml

prometheus:
  prometheusSpec:
    retention: 30d
    retentionSize: "50GB"

    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: gp3
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 100Gi

    serviceMonitorSelectorNilUsesHelmValues: false
    podMonitorSelectorNilUsesHelmValues: false
    ruleSelectorNilUsesHelmValues: false

    additionalScrapeConfigs:
      - job_name: ec2-spot-instance
        ec2_sd_configs:
          - region: ap-northeast-2

    remoteWrite:
      - url: https://aps-workspaces.ap-northeast-2.amazonaws.com/workspaces/ws-xxx/api/v1/remote_write
        sigv4:
          region: ap-northeast-2

grafana:
  adminPassword: ""
  ingress:
    enabled: true
    ingressClassName: alb
    annotations:
      alb.ingress.kubernetes.io/scheme: internet-facing
      alb.ingress.kubernetes.io/listen-ports: '[{"HTTPS":443}]'
      alb.ingress.kubernetes.io/certificate-arn: arn:aws:acm:...
    hosts:
      - grafana.myshop.example.com
  persistence:
    enabled: true
    storageClassName: gp3
    size: 10Gi

alertmanager:
  alertmanagerSpec:
    storage:
      volumeClaimTemplate:
        spec:
          storageClassName: gp3
          resources:
            requests:
              storage: 10Gi
  config:
    route:
      receiver: default
    receivers:
      - name: default

kubectl get pods -n monitoring
kubectl get servicemonitors -A
kubectl get prometheusrules -A

NAME                                                      READY   STATUS    RESTARTS
prometheus-grafana-xxx                                    3/3     Running   0
prometheus-kube-prometheus-operator-xxx                   1/1     Running   0
prometheus-kube-state-metrics-xxx                         1/1     Running   0
prometheus-prometheus-kube-prometheus-prometheus-0        2/2     Running   0
prometheus-prometheus-node-exporter-xxx                   1/1     Running   0
alertmanager-prometheus-kube-prometheus-alertmanager-0    2/2     Running   0

from fastapi import FastAPI
from prometheus_fastapi_instrumentator import Instrumentator

app = FastAPI()
Instrumentator().instrument(app).expose(app)

from prometheus_client import Counter, Histogram

orders_created = Counter(
    "myshop_orders_created_total",
    "Total orders created",
    ["status"]
)

checkout_duration = Histogram(
    "myshop_checkout_duration_seconds",
    "Checkout flow duration"
)

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: {{ include "myshop-api.fullname" . }}
  namespace: {{ .Release.Namespace }}
  labels:
    app.kubernetes.io/name: myshop-api
spec:
  selector:
    matchLabels:
      app.kubernetes.io/name: myshop-api
  endpoints:
    - port: http
      interval: 30s
      path: /metrics

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: {{ include "myshop-api.fullname" . }}
  namespace: {{ .Release.Namespace }}
  labels:
    release: prometheus
spec:
  groups:
    - name: myshop-api.golden-signals
      interval: 30s
      rules:
        # Errors — 5xx 비율
        - alert: MyshopApiHighErrorRate
          expr: |
            sum(rate(http_requests_total{app="myshop-api",status=~"5.."}[5m]))
              / sum(rate(http_requests_total{app="myshop-api"}[5m])) > 0.05
          for: 5m
          labels:
            severity: critical
            team: backend
          annotations:
            summary: "myshop-api 5xx rate > 5% ({{ "{{ $value | humanizePercentage }}" }})"
            description: "5xx 비율이 5% 넘은 상태가 5분 이상 유지됨."
            runbook_url: "https://runbooks.myshop.example.com/myshop-api-5xx"

        # Latency — P95
        - alert: MyshopApiHighLatencyP95
          expr: |
            histogram_quantile(0.95,
              sum by (le) (rate(http_request_duration_seconds_bucket{app="myshop-api"}[5m]))
            ) > 1.0
          for: 10m
          labels:
            severity: warning
            team: backend
          annotations:
            summary: "myshop-api P95 latency > 1s ({{ "{{ $value | printf \"%.2f\" }}" }}s)"

        # Traffic — 트래픽 급감 (downstream 장애 신호)
        - alert: MyshopApiTrafficDrop
          expr: |
            sum(rate(http_requests_total{app="myshop-api"}[5m]))
              < 0.3 * sum(rate(http_requests_total{app="myshop-api"}[5m] offset 1h))
          for: 10m
          labels:
            severity: warning
            team: backend
          annotations:
            summary: "myshop-api traffic 급감 (지난 1시간 대비 30% 미만)"

        # Saturation — Pod 메모리 사용률
        - alert: MyshopApiPodMemoryHigh
          expr: |
            sum by (pod) (
              container_memory_working_set_bytes{namespace="myshop",pod=~"myshop-api-.*"}
            ) / sum by (pod) (
              kube_pod_container_resource_limits{namespace="myshop",pod=~"myshop-api-.*",resource="memory"}
            ) > 0.85
          for: 10m
          labels:
            severity: warning
            team: backend
          annotations:
            summary: "myshop-api Pod memory > 85% of limit"

route:
  receiver: default
  group_by: ['alertname', 'team', 'namespace']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 4h

  routes:
    - matchers:
        - severity = "critical"
      receiver: pagerduty-backend
      continue: true
      routes:
        - matchers:
            - severity = "critical"
            - team = "backend"
          receiver: pagerduty-backend
        - matchers:
            - severity = "critical"
            - team = "platform"
          receiver: pagerduty-platform

    - matchers:
        - severity = "warning"
      receiver: slack-warnings
      group_wait: 1m
      repeat_interval: 12h

receivers:
  - name: default
    slack_configs:
      - api_url: ${SLACK_WEBHOOK}
        channel: '#alerts'

  - name: slack-warnings
    slack_configs:
      - api_url: ${SLACK_WEBHOOK}
        channel: '#alerts-warning'
        title: '{{ "{{ .GroupLabels.alertname }}" }}'

  - name: pagerduty-backend
    pagerduty_configs:
      - service_key: ${PAGERDUTY_BACKEND_KEY}

  - name: pagerduty-platform
    pagerduty_configs:
      - service_key: ${PAGERDUTY_PLATFORM_KEY}

inhibit_rules:
  - source_matchers: [severity = "critical"]
    target_matchers: [severity = "warning"]
    equal: [alertname, namespace]

helm repo add grafana https://grafana.github.io/helm-charts
helm install loki grafana/loki-stack \
  -n monitoring \
  --set promtail.enabled=true \
  --set loki.persistence.enabled=true \
  --set loki.persistence.storageClassName=gp3 \
  --set loki.persistence.size=100Gi

helm repo add aws-observability https://aws-observability.github.io/helm-charts
helm install amazon-cloudwatch-observability \
  aws-observability/amazon-cloudwatch-observability \
  -n amazon-cloudwatch --create-namespace \
  --set clusterName=myshop-prod \
  --set region=ap-northeast-2

컨테이너 로그
   |
   |-> Loki (in-cluster, 단기 검색)
   `-> CloudWatch Logs (S3 export, 장기 보관)

Row 1: Latency P50 / P95 / P99
Row 2: Request rate (도메인별, status 별)
Row 3: Error rate (4xx / 5xx)
Row 4: Pod CPU / 메모리 사용률
Row 5: HPA 현재 replicas
Row 6: PgBouncer 활성 연결 / 대기 큐
Row 7: 비즈니스 메트릭 (orders/min, checkout success rate)
Row 8: 상위 ERROR 로그 (Loki)
Row 9: 최근 배포 (annotations)

1. PagerDuty 에서 알람 본문 확인 (alertname, team, severity)
2. annotation 의 runbook_url 클릭
3. Runbook 의 "1차 점검" 섹션 따라가기 — 관련 Grafana 대시보드 / 로그 쿼리 / kubectl 명령 제시
4. 1차 대응 (스케일 업, 재시작, 트래픽 차단 등)
5. Slack 사고 채널에 상태 공유

kubectl exec -n monitoring prometheus-prometheus-kube-prometheus-prometheus-0 -c prometheus -- \
  promtool tsdb analyze /prometheus/wal | head -50

kubectl exec -n monitoring alertmanager-prometheus-kube-prometheus-alertmanager-0 -c alertmanager -- \
  amtool alert query --alertmanager.url=http://localhost:9093

kubectl exec -n monitoring loki-0 -- df -h /data