Grafana — Dashboards et visualisation

# docker-compose.yml
services:
  grafana:
    image: grafana/grafana:10.4.2
    ports: ["3000:3000"]
    environment:
      GF_SECURITY_ADMIN_USER: admin
      GF_SECURITY_ADMIN_PASSWORD: "${GRAFANA_PASSWORD}"
      GF_USERS_ALLOW_SIGN_UP: "false"
      GF_SERVER_ROOT_URL: "http://localhost:3000"
      GF_SMTP_ENABLED: "true"
      GF_SMTP_HOST: "smtp.example.com:587"
      GF_SMTP_FROM_ADDRESS: "grafana@example.com"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
      - ./grafana/dashboards:/var/lib/grafana/dashboards
  loki:
    image: grafana/loki:3.0.0
    ports: ["3100:3100"]
    volumes:
      - ./grafana/loki-config.yml:/etc/loki/local-config.yaml
      - loki_data:/loki
    command: -config.file=/etc/loki/local-config.yaml
  promtail:
    image: grafana/promtail:3.0.0
    volumes:
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - ./grafana/promtail-config.yml:/etc/promtail/config.yml
    command: -config.file=/etc/promtail/config.yml
volumes:
  grafana_data:
  loki_data:

docker compose up -d grafana loki promtail
# Interface : http://localhost:3000  (admin / voir .env)

# grafana/provisioning/datasources/datasources.yml
apiVersion: 1
datasources:
  - name: Prometheus
    type: prometheus
    access: proxy
    url: http://prometheus:9090
    isDefault: true
    jsonData:
      timeInterval: "15s"
  - name: Loki
    type: loki
    access: proxy
    url: http://loki:3100
    jsonData:
      maxLines: 1000
  - name: Elasticsearch
    type: elasticsearch
    access: proxy
    url: http://elasticsearch:9200
    basicAuth: true
    basicAuthUser: elastic
    secureJsonData:
      basicAuthPassword: "${ELASTIC_PASSWORD}"
    jsonData:
      index: "logstash-*"
      timeField: "@timestamp"
      esVersion: "8.0.0"

# grafana/provisioning/dashboards/dashboards.yml
apiVersion: 1
providers:
  - name: default
    folder: Infra
    type: file
    options:
      path: /var/lib/grafana/dashboards
      foldersFromFilesStructure: true

# grafana/loki-config.yml
auth_enabled: false
server:
  http_listen_port: 3100
ingester:
  lifecycler:
    ring:
      kvstore:
        store: inmemory
      replication_factor: 1
schema_config:
  configs:
    - from: 2024-01-01
      store: boltdb-shipper
      object_store: filesystem
      schema: v11
      index:
        prefix: index_
        period: 24h
storage_config:
  boltdb_shipper:
    active_index_directory: /loki/index
    cache_location: /loki/index_cache
  filesystem:
    directory: /loki/chunks
limits_config:
  retention_period: 30d
  ingestion_rate_mb: 16
  max_query_series: 5000

# grafana/promtail-config.yml
server:
  http_listen_port: 9080
positions:
  filename: /tmp/positions.yaml
clients:
  - url: http://loki:3100/loki/api/v1/push
scrape_configs:
  - job_name: system
    static_configs:
      - targets: [localhost]
        labels:
          job: syslog
          __path__: /var/log/syslog
  - job_name: auth
    static_configs:
      - targets: [localhost]
        labels:
          job: auth
          __path__: /var/log/auth.log
  - job_name: docker
    docker_sd_configs:
      - host: unix:///var/run/docker.sock
        refresh_interval: 5s
    relabel_configs:
      - source_labels: [__meta_docker_container_name]
        target_label: container
      - source_labels: [__meta_docker_container_log_stream]
        target_label: stream

# Gauge CPU (%)
100 - (avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
# Time series — trafic réseau
rate(node_network_receive_bytes_total{device!="lo"}[5m]) * 8 / 1024 / 1024
# Stat — uptime serveur
(node_time_seconds - node_boot_time_seconds) / 3600 / 24
# Bar gauge — espace disque par volume
(node_filesystem_size_bytes - node_filesystem_avail_bytes) / node_filesystem_size_bytes * 100
# Table — containers actifs avec RAM
container_memory_usage_bytes{name!=""} / 1024 / 1024

# Tous les logs d'erreur SSH
{job="auth"} |= "Failed password"
# Logs par container
{container="nginx"} |= "error"
# Parser les logs Nginx (pattern)
{job="nginx"} | pattern `<ip> - - [<date>] "<method> <uri> <proto>" <status> <size>`
  | status >= 500
# Compter les erreurs 5xx par minute
sum(rate({job="nginx"} | pattern `<_> <status> <_>` | status >= 500 [1m]))
# Filtrer par niveau de log
{container="app"} | json | level="error"

# Via API — créer un contact point Slack
curl -X POST http//adminpasswordlocalhost3000/api/v1/provisioning/contact-points 
  -H "Content-Type: application/json" 
  -d 
    "name" "slack-ops"
    "type" "slack"
    "settings" 
      "url" "<SLACK_WEBHOOK_URL>"
      "channel" "#alerts"
    
  
# Créer une règle d alerte via API
curl -X POST http//adminpasswordlocalhost3000/api/v1/provisioning/alert-rules 
  -H "Content-Type: application/json" 
  -d 
    "title" "CPU High"
    "condition" "C"
    "data" 
      
        "refId" "A"
        "datasourceUid" "__expr__"
        "model" 
          "expr" "100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100) > 85"
        
      
    
    "for" "5m"
    "labels"  "severity" "warning" 
    "annotations"  "summary" "CPU élevé" 
    "folderUID" "infra"
    "ruleGroup" "infra-alerts"
  

# Vérifier la santé de Grafana
curl -s http//localhost3000/api/health | jq
# Lister les datasources
curl -s http//adminpasswordlocalhost3000/api/datasources | jq '.[].name'
# Exporter un dashboard (récupérer l'UID depuis l'URL)
curl -s http//adminpasswordlocalhost3000/api/dashboards/uid/<UID> | jq '.dashboard' > dashboardjson
# Importer un dashboard
curl -X POST http//adminpasswordlocalhost3000/api/dashboards/import 
  -H "Content-Type: application/json" 
  -d '{"dashboard": <JSON>, "overwrite": true, "folderId": 0}'
# Vérifier Loki
curl -s http//localhost3100/ready
curl -s "http://localhost:3100/loki/api/v1/query?query={job=\"auth\"}&limit=5" | jq
# Vérifier Promtail
curl -s http//localhost9080/metrics | grep promtail_sent_entries

# Importer depuis Grafana.com via API
curl -X POST http//adminpasswordlocalhost3000/api/dashboards/import 
  -H "Content-Type: application/json" 
  -d '{"inputs":[{"name":"DS_PROMETHEUS","type":"datasource","pluginId":"prometheus","value":"Prometheus"}],"folderId":0,"overwrite":true,"path":"https://grafana.com/api/dashboards/1860/revisions/latest/download"}'