Files
ENI-projet-piscine/monitoring/grafana/dashboards/donnees.json
T
Johan LEROY dc952d13aa feat(monitoring): supervise l'API, la base et l'hôte avec Prometheus et Grafana
L'API exposait /metrics, mais aucun collecteur ne le lisait : monitoring/ ne contenait que des
.gitkeep.

Sous le profil Compose `monitoring` : prometheus, alertmanager, grafana, postgres-exporter,
node-exporter et cadvisor. Tous ont un mem_limit, pour environ 700 Mo au total sur la VM de 8 Go,
et leurs interfaces n'écoutent que sur 127.0.0.1. Le profil est actif en prod via
COMPOSE_PROFILES, donc à chaque déploiement, et se lance à la demande ailleurs
(make monitoring-up).

- Neuf règles d'alerte (API, base, hôte, cibles). Chacune a un cas dans les tests joués par
  `promtool test rules`, en CI comme par make monitoring-check.
- Alertmanager route les alertes par courriel vers Mailpit ; un critical masque le warning de la
  même cible.
- Grafana est provisionné : sources Prometheus et TimescaleDB, et trois tableaux de bord (API,
  données et dérive du modèle, infrastructure).
- Le rôle PostgreSQL `supervision` est en lecture seule sur les seules tables métier
  (db/roles/supervision.sql), posé par make db-ensure-supervision et par stack-up quand le
  profil est actif.
- Le jeton de /metrics passe à Prometheus en secret Compose (APP_METRICS_TOKEN) ;
  provision-host.sh génère ce secret et les deux autres.

Backend :
- un APP_METRICS_TOKEN vide vaut absent ;
- les sondes de santé ne comptent plus dans les métriques ;
- seaux de latence fins autour de 500 ms ;
- un registre Prometheus par application, sans quoi toute application créée après la première
  (dans les tests) ne mesurait rien.

Réf : #26
2026-09-23 09:41:12 +02:00

529 lines
13 KiB
JSON

{
"uid": "enervision-donnees",
"title": "EnerVision · Données et modèle",
"description": "Fraîcheur des relevés, alertes métier et dérive du modèle, lus dans TimescaleDB par le rôle supervision.",
"tags": [
"enervision"
],
"timezone": "browser",
"editable": false,
"graphTooltip": 1,
"refresh": "1m",
"schemaVersion": 39,
"version": 1,
"time": {
"from": "now-7d",
"to": "now"
},
"templating": {
"list": []
},
"annotations": {
"list": []
},
"links": [],
"panels": [
{
"id": 1,
"type": "stat",
"title": "Sites suivis",
"gridPos": {
"x": 0,
"y": 0,
"w": 6,
"h": 4
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT count(*) AS \"Sites\" FROM site",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue",
"value": null
}
]
},
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "area",
"textMode": "auto"
}
},
{
"id": 2,
"type": "stat",
"title": "Relevés sur 24 h",
"gridPos": {
"x": 6,
"y": 0,
"w": 6,
"h": 4
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT count(*) AS \"Relevés\" FROM reading WHERE timestamp > now() - interval '24 hours'",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "green",
"value": 1
}
]
},
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "area",
"textMode": "auto"
},
"description": "Zéro : l'import de la Mock API ne tourne plus."
},
{
"id": 3,
"type": "stat",
"title": "Alertes sur 24 h",
"gridPos": {
"x": 12,
"y": 0,
"w": 6,
"h": 4
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT count(*) AS \"Alertes\" FROM alert WHERE timestamp > now() - interval '24 hours'",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "orange",
"value": 1
},
{
"color": "red",
"value": 10
}
]
},
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "area",
"textMode": "auto"
}
},
{
"id": 4,
"type": "stat",
"title": "Sites en dérive",
"gridPos": {
"x": 18,
"y": 0,
"w": 6,
"h": 4
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT count(*) AS \"Sites\" FROM (SELECT DISTINCT ON (site_id) status FROM drift_report WHERE site_id IS NOT NULL ORDER BY site_id, computed_at DESC) AS derniers WHERE status = 'derive'",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
},
"color": {
"mode": "thresholds"
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "area",
"textMode": "auto"
},
"description": "Dernier rapport de dérive de chaque site (ADR 0013)."
},
{
"id": 5,
"type": "table",
"title": "Fraîcheur des relevés par site",
"gridPos": {
"x": 0,
"y": 4,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT s.site_name AS \"Site\", max(r.timestamp) AS \"Dernier relevé\", round(extract(epoch FROM now() - max(r.timestamp)) / 60) AS \"Âge (min)\"\nFROM site AS s\nLEFT JOIN reading AS r ON r.site_id = s.site_id AND r.timestamp > now() - interval '7 days'\nGROUP BY s.site_name\nORDER BY 3 DESC NULLS FIRST",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {},
"overrides": []
},
"options": {
"showHeader": true
},
"description": "Un site sans relevé depuis sept jours apparaît vide, en tête de liste."
},
{
"id": 6,
"type": "table",
"title": "Dérive du modèle, dernier rapport",
"gridPos": {
"x": 12,
"y": 4,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT DISTINCT ON (d.site_id) coalesce(s.site_name, 'Tout le parc') AS \"Site\", d.status AS \"Statut\", round(d.mae::numeric, 2) AS \"MAE\", round(d.reference_mae::numeric, 2) AS \"MAE de référence\", round(d.bias::numeric, 2) AS \"Biais\", d.computed_at AS \"Calculé le\"\nFROM drift_report AS d\nLEFT JOIN site AS s ON s.site_id = d.site_id\nORDER BY d.site_id, d.computed_at DESC",
"format": "table",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {},
"overrides": []
},
"options": {
"showHeader": true
},
"description": "Une ligne par site, plus la ligne globale (ADR 0013)."
},
{
"id": 7,
"type": "timeseries",
"title": "Consommation par site",
"gridPos": {
"x": 0,
"y": 12,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT $__timeGroupAlias(r.timestamp, $__interval), s.site_name AS metric, avg(r.consumption_kw) AS value\nFROM reading AS r\nJOIN site AS s ON s.site_id = r.site_id\nWHERE $__timeFilter(r.timestamp)\nGROUP BY 1, 2\nORDER BY 1",
"format": "time_series",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "kwatt"
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 8,
"type": "timeseries",
"title": "Relevés ingérés par heure",
"gridPos": {
"x": 12,
"y": 12,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT time_bucket('1 hour', timestamp) AS time, count(*) AS \"Relevés\"\nFROM reading\nWHERE $__timeFilter(timestamp)\nGROUP BY 1\nORDER BY 1",
"format": "time_series",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 9,
"type": "timeseries",
"title": "Alertes par sévérité",
"gridPos": {
"x": 0,
"y": 20,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT time_bucket('1 hour', timestamp) AS time, severity AS metric, count(*) AS value\nFROM alert\nWHERE $__timeFilter(timestamp)\nGROUP BY 1, 2\nORDER BY 1",
"format": "time_series",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 10,
"type": "timeseries",
"title": "Erreur absolue moyenne du modèle",
"gridPos": {
"x": 12,
"y": 20,
"w": 12,
"h": 8
},
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "grafana-postgresql-datasource",
"uid": "timescaledb"
},
"rawSql": "SELECT d.computed_at AS time, coalesce(s.site_name, 'Tout le parc') AS metric, d.mae AS value\nFROM drift_report AS d\nLEFT JOIN site AS s ON s.site_id = d.site_id\nWHERE $__timeFilter(d.computed_at)\nORDER BY 1",
"format": "time_series",
"rawQuery": true,
"editorMode": "code"
}
],
"fieldConfig": {
"defaults": {
"unit": "kwatt"
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
}
]
}