Monitoring optimization

bxl-rpi/apps/docker-compose.smarthome.yaml

@@ -46,6 +46,25 @@ services:
     networks:
     - smarthome
 
+  nodered:
+    container_name: nodered
+    restart: on-failure
+    image: nodered/node-red:latest
+    volumes:
+    - $DATA/nodered:/data
+    networks:
+    - smarthome
+    - external
+    labels:
+    - "traefik.enable=true"
+    - "traefik.http.routers.nodered.rule=Host(`nodered.bhasher.com`)"
+    - "traefik.http.routers.nodered.entrypoints=internalsecure"
+    - "traefik.http.services.nodered.loadbalancer.server.port=1880"
+    - "traefik.http.routers.nodered.tls=true"
+    - "traefik.http.routers.nodered.tls.certresolver=http"
+    - "traefik.http.routers.nodered.middlewares=authelia@docker"
+
+
 networks:
   smarthome:
   external:

bxl-rpi/config/dashy/config.yml

@@ -26,11 +26,11 @@ sections:
         url: https://jellyfin.bhasher.com
         statusCheckUrl: http://jellyfin:8096
         id: 0_1507_jellyfin
-      - title: Autheli
+      - title: Authelia
         icon: hl-authelia
         url: https://idp.bhasher.com
         statusCheckUrl: http://authelia:9091
-        id: 1_1507_autheli
+        id: 1_1507_authelia
       - title: Mealie
         icon: hl-mealie
         url: https://mealie.bhasher.com
@@ -122,6 +122,16 @@ sections:
         icon: hl-portainer
         url: https://portainer.lln.bhasher.com
         id: 12_1631_portainerlln
+      - title: Home assistant
+        icon: hl-home-assistant
+        url: https://hass.bhasher.com
+        statusCheckUrl: http://hass:8123
+        id: 13_1631_homeassistant
+      - title: Node-red
+        icon: hl-node-red
+        url: https://nodered.bhasher.com
+        statusCheckUrl: http://nodered:1880
+        id: 14_1631_nodered
   - name: System services
     displayData:
       sortBy: most-used
@@ -199,6 +209,12 @@ sections:
           hostname: http://pihole
           apiKey: ''
         id: 0_1062_piholestats
+    displayData:
+      sortBy: default
+      rows: 1
+      cols: 2
+      collapsed: false
+      hideForGuests: false
   - name: Random
     widgets:
       - type: joke
@@ -210,3 +226,9 @@ sections:
         options:
           comic: random
         id: 1_609_xkcdcomic
+    displayData:
+      sortBy: default
+      rows: 1
+      cols: 2
+      collapsed: false
+      hideForGuests: false

bxl-rpi/config/monitoring/prometheus.yaml

@@ -1,5 +1,5 @@
 global:
-  scrape_interval:     15s # By default, scrape targets every 15 seconds.
+  scrape_interval:     30s # By default, scrape targets every 15 seconds.
 
   # Attach these labels to any time series or alerts when communicating with
   # external systems (federation, remote storage, Alertmanager).
@@ -11,7 +11,6 @@ global:
 scrape_configs:
   # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
   - job_name: 'prometheus'
-    scrape_interval: 5s
     static_configs:
       - targets: ['localhost:9090']
 
@@ -20,21 +19,17 @@ scrape_configs:
       - targets: ["host.docker.internal:9323"] 
 
   - job_name: 'cadvisor'
-    scrape_interval: 15s
     static_configs:
           - targets: ['cadvisor:8080']
 
   - job_name: 'node-exporter'
-    scrape_interval: 15s
     static_configs:
           - targets: ['node-exporter:9100']
 
   - job_name: 'treafik'
-    scrape_interval: 15s
     static_configs:
           - targets: ['traefik:8080']
 
   - job_name: 'authelia'
-    scrape_interval: 15s
     static_configs:
           - targets: ['authelia:9959']

bxl-rpi/system/docker-compose.monitoring.yaml

@@ -3,6 +3,7 @@ services:
     container_name: prometheus
     image:  prom/prometheus:latest
     restart: unless-stopped
+    user: root
     labels:
     - "traefik.enable=true"
     - "traefik.http.routers.prom.rule=Host(`prometheus.bhasher.com`)"
@@ -66,15 +67,25 @@ services:
 
   cadvisor:
     container_name: cadvisor
-    image: gcr.io/cadvisor/cadvisor:v0.47.1
+    image: gcr.io/cadvisor/cadvisor:v0.47.0 #v0.47.1
     volumes:
     - /:/rootfs:ro
     - /var/run:/var/run:rw
     - /sys:/sys:ro
     - /var/lib/docker/:/var/lib/docker:ro
     restart: always
+    command:
+    - "--housekeeping_interval=30s"
+    - "--docker_only=true"
+    - "--disable_metrics=percpu,sched,tcp,udp,disk,diskIO,hugetlb,referenced_memory,cpu_topology,resctrl"
     networks:
     - monitoring
+    healthcheck:
+      test: wget --quiet --tries=1 --spider http://localhost:8080/healthz || exit 1
+      interval: 15s
+      timeout: 15s
+      retries: 5
+      start_period: 30s
 
   node-exporter:
     container_name: node-exporter