prometheus,grafana,cadvisor: helthcheck ok healthcheck not ok: node exporter,pushgateway,alermanager

docker-compose.yml

@@ -6,12 +6,11 @@ networks:
         - subnet: 192.168.100.0/24
 
 volumes:
-    prometheus_data: {}
+  prometheus_data: {}
-    grafana_data: {}
+  grafana_data: {}
 
 services:
 
-# POUR AFFICHAGE DASHBOARD
   grafana:
     image: grafana/grafana:11.2.0
     container_name: grafana
@@ -30,8 +29,12 @@ services:
         ipv4_address: 192.168.100.10
     labels:
       org.label-schema.group: "monitoring"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
 
-# METRICS GATHERER
   prometheus:
     image: prom/prometheus:v2.54.1
     container_name: prometheus
@@ -52,8 +55,13 @@ services:
       - grafana-network
     labels:
       org.label-schema.group: "monitoring"
+    healthcheck:
+      test: ["CMD", "wget", "http://localhost:9090"]
+      interval: 10s
+      timeout: 15s
+      retries: 10
+      start_period: 40s 
 
-# FOR HOST METRICS
   nodeexporter:
     image: prom/node-exporter:v1.8.2
     container_name: nodeexporter
@@ -73,8 +81,8 @@ services:
       - grafana-network
     labels:
       org.label-schema.group: "monitoring"
+    
 
-# FOR DOCKER CONTAINERS
   cadvisor:
     image: gcr.io/cadvisor/cadvisor
     container_name: cadvisor
@@ -91,8 +99,8 @@ services:
       - grafana-network
     labels:
       org.label-schema.group: "monitoring"
+    
 
-# LOKI FOR LOGS
   loki:
     image: grafana/loki:latest
     container_name: loki
@@ -103,19 +111,22 @@ services:
       - ./loki/cert:/etc/loki/cert
       - /etc/localtime:/etc/localtime:ro
       - /etc/timezone:/etc/timezone:ro
-#    environment:
     command: -config.file=/etc/loki/config.yml -config.expand-env=true
     networks:
       - grafana-network
+    healthcheck:
+      test: wget --quiet --tries=1 --output-document=- http://localhost:3100/ready | grep -q -w ready || exit 1
+      start_period: 20s
+      interval: 10s
+      timeout: 1s
+      retries: 12  # try for 2 minutes
 
-# FOR ALERTS
   alertmanager:
     image: prom/alertmanager:v0.20.0
     container_name: alertmanager
     volumes:
       - ./alertmanager:/etc/alertmanager
     command:
-      #- '--config.file=/etc/alertmanager/config.yml'
       - '--config.file=/etc/alertmanager/alertmanager.yml'
       - '--storage.path=/alertmanager'
     restart: unless-stopped
@@ -125,6 +136,11 @@ services:
       - grafana-network
     labels:
       org.label-schema.group: "monitoring"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9093/-/ready"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
 
   pushgateway:
     image: prom/pushgateway:v1.2.0
@@ -136,3 +152,8 @@ services:
       - grafana-network
     labels:
       org.label-schema.group: "monitoring"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9091/metrics"]
+      interval: 30s
+      timeout: 5s
+      retries: 3