some small changes

.env.sample

@@ -1,9 +1,8 @@
 TYPE=monitoring-ng
 LETS_ENCRYPT_ENV=production
 COMPOSE_FILE=compose.yml
-DOMAIN=monitoring.example.com
+DOMAIN=monitoring-ng.example.com
 TIMEOUT=120
-ENABLE_BACKUPS=true
 
 ## Enable this secret for Promtail / Prometheus
 # SECRET_BASIC_AUTH_VERSION=v1
@@ -17,10 +16,6 @@ ENABLE_BACKUPS=true
 ## Prometheus
 # COMPOSE_FILE="$COMPOSE_FILE:compose.prometheus.yml"
 # PROMETHEUS_RETENTION_TIME=1y
-#
-## Prometheus Pushgateway
-# COMPOSE_FILE="$COMPOSE_FILE:compose.pushgateway.yml"
-#
 ## Loki
 # Loki Server
 #
@@ -41,16 +36,16 @@ ENABLE_BACKUPS=true
 ## Grafana
 #
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana.yml"
-# GF_SERVER_ROOT_URL=https://monitoring.example.com
+# GF_SERVER_ROOT_URL=https://${DOMAIN}
 # SECRET_GRAFANA_ADMIN_PASSWORD_VERSION=v1
 #
 ## Single-Sign-On with OIDC
 # OIDC_ENABLED=1
 # SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION=v1
 # OIDC_CLIENT_ID=grafana
-# OIDC_AUTH_URL="https://authentik.example.com/application/o/authorize/"
-# OIDC_API_URL="https://authentik.example.com/application/o/userinfo/"
-# OIDC_TOKEN_URL="https://authentik.example.com/application/o/token/"
+# OIDC_AUTH_URL="https://sso.example.com/auth/realms/autonomic/protocol/openid-connect/auth"
+# OIDC_API_URL="https://sso.example.com/auth/realms/autonomic/protocol/openid-connect/userinfo"
+# OIDC_TOKEN_URL="https://sso.example.com/auth/realms/autonomic/protocol/openid-connect/token"
 #
 ## Additional grafana settings (unlikely to require editing)
 # GF_SECURITY_ALLOW_EMBEDDING=1

README.md

@@ -36,7 +36,7 @@ Where gathering.org is the node you want to gather metrics from.
   SECRET_USERSFILE_VERSION=v1
   ```
   - Generate userslist with httpasswd hashed password
-    `abra app secret insert traefik.gathering.org userslist v1 'admin:<hashed-secret>'`
+    `abra app secret insert traefik.gathering.org usersfile v1 'admin:<hashed-secret>'`
     make sure there is no whitespace in between `admin:<hashed-secret>`, it seems to break stuff...
   - `abra app deploy -f traefik`
 1. `abra app new monitoring-ng`
@@ -54,16 +54,16 @@ Where gathering.org is the node you want to gather metrics from.
    - monitoring.example.org
    - prometheus.monitoring.example.org
    - loki.monitoring.example.org
-2. Setup monitoring stack
+1. Setup monitoring stack
    - `abra app new monitoring-ng`
    - `abra app config monitoring.example.org`
       Uncomment all the stuff
-   - `abra app secret insert monitoring.example.org basic_auth v1 <secret>`
+   - `abra app secret insert monitoring.example.org basic_auth_admin_password v1 <secret>`
       this needs the plaintext traefik basic-auth secret, not the hashed one!
    - `abra app secret ls monitoring.example.org`
    - `abra app deploy monitoring.example.org`
-3. Add scrape config to prometheus
-  - `abra app cmd monitoring.example.org prometheus gathering.org`
+1. add scrape config to prometheus
+  - `abra app cmd monitoring.example.org prometheus add_node gathering.org`
   - or manually
     ```
     cp scrape-config.example.yml gathering.org.yml
@@ -101,18 +101,8 @@ $ echo '{
 $ systemctl restart docker.service
 ```
 
-## Setup Push Gateway
 
-1. Enable in the env fiöle by uncommenting the following lines:
-```
-## Prometheus Pushgateway
-# COMPOSE_FILE="$COMPOSE_FILE:compose.pushgateway.yml"
-```
-2. `abra app deploy monitoring.example.org`
 
-This will expose the pushgateway at `https://pushgateway.${DOMAIN}`.
-It is secured behind the same basic auth as the other services.
-After that you need to add the `pushgateway.${DOMAIN}` to the scare config.
 
 ## Post-setup guide
 

abra.sh

@@ -12,7 +12,6 @@ export PROMETHEUS_YML_VERSION=v2
 # creates a default prometheus scrape config for a given node
 add_node(){
   name=$1
-  add_domain "$name" "$name:8082"
   add_domain "$name" "node.monitoring.$name"
   add_domain "$name" "cadvisor.monitoring.$name"
   cat "/prometheus/scrape_configs/$name.yml"

compose.grafana.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:10.4.14
+    image: grafana/grafana:10.2.3
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:
@@ -62,19 +62,19 @@ configs:
     name: ${STACK_NAME}_grafana_custom_ini_${GRAFANA_CUSTOM_INI_VERSION}
     file: grafana_custom.ini
   grafana_datasources_yml:
-    name: ${STACK_NAME}_g_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION}
+    name: ${STACK_NAME}_grafana_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION}
     file: grafana-datasources.yml
   grafana_dashboards_yml:
-    name: ${STACK_NAME}_g_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION}
+    name: ${STACK_NAME}_grafana_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION}
     file: grafana-dashboards.yml
   grafana_swarm_dashboard_json:
-    name: ${STACK_NAME}_g_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_grafana_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION}
     file: grafana-swarm-dashboard.json
   grafana_stacks_dashboard_json:
-    name: ${STACK_NAME}_g_stacks_dashboard_json_${GRAFANA_STACKS_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_grafana_stacks_dashboard_json_${GRAFANA_STACKS_DASHBOARD_JSON_VERSION}
     file: grafana-stacks-dashboard.json
   grafana_traefik_dashboard_json:
-    name: ${STACK_NAME}_g_traefik_dashboard_json_${GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_grafana_traefik_dashboard_json_${GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION}
     file: grafana-traefik-dashboard.json
 
 volumes:

compose.loki.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   loki:
-    image: grafana/loki:2.9.11
+    image: grafana/loki:2.9.3
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - proxy

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v2.55.1
+    image: prom/prometheus:v2.48.1
     secrets:
       - basic_auth
     volumes:

compose.promtail.yml

@@ -2,7 +2,7 @@ version: "3.8"
 
 services:
   promtail:
-    image: grafana/promtail:2.9.11
+    image: grafana/promtail:2.9.3
     volumes:
       - /var/log:/var/log:ro
       - /var/run/docker.sock:/var/run/docker.sock

compose.pushgateway.yml

@@ -1,25 +0,0 @@
-version: '3.8'
-
-services:
-  pushgateway:
-    image: prom/pushgateway:v1.10.0
-    command:
-      - '--web.listen-address=:9191'
-      - '--push.disable-consistency-check'
-      - '--persistence.interval=5m'
-    ports:
-      - 9191:9191
-    networks:
-      - internal
-      - proxy
-    deploy:
-      restart_policy:
-        condition: on-failure
-      labels:
-        - "traefik.enable=true"
-        - "traefik.http.services.${STACK_NAME}-pushgateway.loadbalancer.server.port=9191"
-        - "traefik.http.routers.${STACK_NAME}-pushgateway.rule=Host(`pushgateway.${DOMAIN}`)"
-        - "traefik.http.routers.${STACK_NAME}-pushgateway.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}-pushgateway.tls=true"
-        - "traefik.http.routers.${STACK_NAME}-pushgateway.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - "traefik.http.routers.${STACK_NAME}-pushgateway.middlewares=basicauth@file"

compose.yml

@@ -3,7 +3,7 @@ version: "3.8"
 
 services:
   app:
-    image: prom/node-exporter:v1.8.1
+    image: prom/node-exporter:v1.7.0
     user: root
     environment:
       - NODE_ID={{.Node.ID}}
@@ -30,7 +30,6 @@ services:
       restart_policy:
         condition: on-failure
       labels:
-        - "backupbot.backup=${ENABLE_BACKUPS:-true}"
         - "traefik.enable=true"
         - "traefik.http.services.${STACK_NAME}-node.loadbalancer.server.port=9100"
         - "traefik.http.routers.${STACK_NAME}-node.rule=Host(`node.${DOMAIN}`)"
@@ -38,11 +37,11 @@ services:
         - "traefik.http.routers.${STACK_NAME}-node.tls=true"
         - "traefik.http.routers.${STACK_NAME}-node.tls.certresolver=${LETS_ENCRYPT_ENV}"
         - "traefik.http.routers.${STACK_NAME}-node.middlewares=basicauth@file"
-        - "coop-cloud.${STACK_NAME}.version=1.3.0+v1.8.1"
+        - "coop-cloud.${STACK_NAME}.version=1.0.0+v1.7.0"
         - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-120}"
 
   cadvisor:
-    image: gcr.io/cadvisor/cadvisor:v0.49.2
+    image: gcr.io/cadvisor/cadvisor:v0.47.2
     command:
       - "-logtostderr"
       - "--enable_metrics=cpu,cpuLoad,disk,diskIO,process,memory,network"

scrape-config.example.yml

@@ -1,4 +1,3 @@
 - targets:
-  - 'example.org:8082'
   - 'node.monitoring.example.org'
   - 'cadvisor.monitoring.example.org'