Johan LEROY
dc952d13aa
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
584 lines
13 KiB
JSON
584 lines
13 KiB
JSON
{
|
|
"uid": "enervision-infra",
|
|
"title": "EnerVision · Infrastructure",
|
|
"description": "Hôte (node-exporter), conteneurs (cAdvisor) et PostgreSQL (postgres-exporter). L'hôte porte la recette et la prod.",
|
|
"tags": [
|
|
"enervision"
|
|
],
|
|
"timezone": "browser",
|
|
"editable": false,
|
|
"graphTooltip": 1,
|
|
"refresh": "30s",
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "stat",
|
|
"title": "Mémoire de l'hôte",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 0,
|
|
"w": 6,
|
|
"h": 4
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes",
|
|
"legendFormat": "",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 0.8
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
},
|
|
"description": "Alerte au-delà de 90 % pendant 10 minutes."
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "stat",
|
|
"title": "Processeur de l'hôte",
|
|
"gridPos": {
|
|
"x": 6,
|
|
"y": 0,
|
|
"w": 6,
|
|
"h": 4
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))",
|
|
"legendFormat": "",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 0.7
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "stat",
|
|
"title": "Disque libre",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 0,
|
|
"w": 6,
|
|
"h": 4
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "node_filesystem_avail_bytes{mountpoint=\"/\", fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{mountpoint=\"/\", fstype!~\"tmpfs|overlay\"}",
|
|
"legendFormat": "",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 0.1
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 0.2
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "stat",
|
|
"title": "PostgreSQL",
|
|
"gridPos": {
|
|
"x": 18,
|
|
"y": 0,
|
|
"w": 6,
|
|
"h": 4
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "pg_up",
|
|
"legendFormat": "",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "Injoignable",
|
|
"color": "red"
|
|
},
|
|
"1": {
|
|
"text": "Joignable",
|
|
"color": "green"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 5,
|
|
"type": "timeseries",
|
|
"title": "Mémoire par conteneur",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 4,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (name) (container_memory_working_set_bytes{name!=\"\"})",
|
|
"legendFormat": "{{name}}",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"description": "Recette et prod partagent l'hôte : leurs conteneurs se distinguent par le préfixe du projet Compose."
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "timeseries",
|
|
"title": "Processeur par conteneur",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 4,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[5m]))",
|
|
"legendFormat": "{{name}}",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 7,
|
|
"type": "timeseries",
|
|
"title": "Mémoire de l'hôte",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 12,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes",
|
|
"legendFormat": "utilisée",
|
|
"range": true
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "node_memory_MemTotal_bytes",
|
|
"legendFormat": "totale",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"type": "timeseries",
|
|
"title": "Connexions PostgreSQL par état",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 12,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (state) (pg_stat_activity_count)",
|
|
"legendFormat": "{{state}}",
|
|
"range": true
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "max(pg_settings_max_connections)",
|
|
"legendFormat": "maximum",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 9,
|
|
"type": "timeseries",
|
|
"title": "Transactions validées par base",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 20,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (datname) (rate(pg_stat_database_xact_commit{datname!~\"template.*|postgres\"}[5m]))",
|
|
"legendFormat": "{{datname}}",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "timeseries",
|
|
"title": "Taille des bases",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 20,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "pg_database_size_bytes{datname!~\"template.*|postgres\"}",
|
|
"legendFormat": "{{datname}}",
|
|
"range": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|