docker run -d \
  --name=grafana \
  -p 3000:3000 \
  -v grafana_data:/var/lib/grafana \
  -e "GF_SECURITY_ADMIN_USER=admin" \
  -e "GF_SECURITY_ADMIN_PASSWORD=admin" \
  grafana/grafana:10.4.0

services:
  grafana:
    image: grafana/grafana:10.4.0
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin123
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=https://grafana.example.com
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro

# grafana/provisioning/datasources/prometheus.yml
apiVersion: 1

datasources:
  - name: Prometheus
    type: prometheus
    access: proxy
    url: http://prometheus:9090
    isDefault: true
    editable: true
    jsonData:
      httpMethod: POST
      timeInterval: '15s'
      queryTimeout: '60s'

  - name: Prometheus-Thanos
    type: prometheus
    access: proxy
    url: http://thanos-query:9090
    editable: true
    jsonData:
      httpMethod: POST

# grafana/provisioning/dashboards/dashboards.yml
apiVersion: 1

providers:
  - name: 'Custom'
    orgId: 1
    folder: 'Custom'
    type: file
    disableDeletion: false
    editable: true
    allowUiUpdates: true
    options:
      path: /etc/grafana/provisioning/dashboards/json
      foldersFromFilesStructure: true

// grafana/provisioning/dashboards/json/node-exporter.json
{
  "dashboard": {
    "id": null,
    "uid": "node-exporter",
    "title": "Node Exporter",
    "tags": ["node", "linux"],
    "timezone": "browser",
    "refresh": "30s",
    "panels": [
      {
        "id": 1,
        "title": "CPU Usage",
        "type": "timeseries",
        "datasource": "Prometheus",
        "targets": [
          {
            "expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
            "legendFormat": "{{ instance }}"
          }
        ],
        "fieldConfig": {
          "defaults": {
            "unit": "percent",
            "min": 0,
            "max": 100,
            "thresholds": {
              "steps": [
                { "value": null, "color": "green" },
                { "value": 80, "color": "yellow" },
                { "value": 90, "color": "red" }
              ]
            }
          }
        }
      }
    ],
    "time": {
      "from": "now-1h",
      "to": "now"
    }
  }
}

# 通过 Grafana API 导入
curl -X POST http://admin:admin@localhost:3000/api/dashboards/import \
  -H "Content-Type: application/json" \
  -d '{
    "dashboard": {"id": 1860},
    "overwrite": true,
    "inputs": [{"name": "DS_PROMETHEUS", "type": "datasource", "pluginId": "prometheus", "value": "Prometheus"}]
  }'

# 获取所有 job 名称
label_values(up, job)

# 获取特定 job 的实例
label_values(up{job="$job"}, instance)

# 获取所有集群名称
label_values(up, cluster)

# 获取所有状态码
label_values(http_requests_total, status)

# 获取所有命名空间
label_values(kube_pod_info, namespace)

# 在查询中使用变量
rate(http_requests_total{job="$job"}[5m])

# 多选变量
rate(http_requests_total{job=~"$job"}[5m])

# 使用 $interval 变量
rate(http_requests_total[$interval])

# 通过 Provisioning 配置告警规则
# grafana/provisioning/alerting/rules.yml
apiVersion: 1

groups:
  - orgId: 1
    name: Infrastructure
    folder: Alerts
    interval: 1m
    rules:
      - uid: cpu-high
        title: High CPU Usage
        condition: C
        data:
          - refId: A
            datasourceUid: prometheus
            model:
              expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
              intervalMs: 60000
          - refId: B
            datasourceUid: __expr__
            model:
              type: reduce
              expression: A
              reducer: last
          - refId: C
            datasourceUid: __expr__
            model:
              type: threshold
              expression: B
              conditions:
                - evaluator:
                    type: gt
                    params: [80]
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "CPU usage is above 80%"

# grafana/provisioning/alerting/contact_points.yml
apiVersion: 1

contactPoints:
  - orgId: 1
    name: slack-alerts
    receivers:
      - uid: slack-1
        type: slack
        settings:
          url: https://hooks.slack.com/services/xxx/yyy/zzz
          recipient: "#alerts"
          title: '{{ template "default.title" . }}'
          text: '{{ template "default.message" . }}'

  - orgId: 1
    name: email-alerts
    receivers:
      - uid: email-1
        type: email
        settings:
          addresses: team@example.com