fix: remove port, add sni

when setting the port, alloy sends host:port as Host header and confuses
nginx

.env.sample

@@ -1,19 +1,24 @@
 TYPE=monitoring-ng
 LETS_ENCRYPT_ENV=production
 COMPOSE_FILE=compose.yml
-DOMAIN=monitoring.example.com
+DOMAIN=monitoring-ng.example.com
-TIMEOUT=120
+#TIMEOUT=120
 ENABLE_BACKUPS=true
 
-## Enable this secret for Promtail / Prometheus
+SECRET_BASIC_AUTH_VERSION=v1
-# SECRET_BASIC_AUTH_VERSION=v1
+# Enable this to send logs to a Loki server, adapt DOMAIN if server is
-#
+# remote
-# Promtail (Gathering Logs)
+# LOKI_PUSH_URL=https://loki.$DOMAIN/loki/api/v1/push
-# COMPOSE_FILE="$COMPOSE_FILE:compose.promtail.yml"
+# Enable this on SystemD hosts to read logs
-# LOKI_PUSH_URL=https://loki.monitoring.example.org/loki/api/v1/push
+# JOURNALD=1
+# Enable this on syslogd hosts and configure the syslogd to send logs to
+# Alloy on port 514/tcp
+# SYSLOG=1
+# COMPOSE_FILE="$COMPOSE_FILE:compose.syslog.yml"
 
-## Expose node and cadvisor ports instead of traefik
+# Enable this to send metrics to a Prometheus server, adapt DOMAIN if
-# COMPOSE_FILE="$COMPOSE_FILE:compose.expose-ports.yml"
+# server is remote
+# PROMETHEUS_REMOTE_WRITE_URL=https://prometheus.$DOMAIN/api/v1/write
 
 # Monitoring Server
 #
@@ -39,19 +44,18 @@ ENABLE_BACKUPS=true
 # LOKI_AWS_REGION=eu-west-1
 # LOKI_ACCESS_KEY_ID=bush-debrief-approval-robust-scraggly-molecule
 # LOKI_BUCKET_NAMES=loki
-# SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION=v1
+# SECRET_LOKI_AWS_KEY_VERSION=v1
 #
 ## Grafana
 #
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana.yml"
 # GF_SERVER_ROOT_URL=https://monitoring.example.com
-# SECRET_GRAFANA_ADMIN_PASSWORD_VERSION=v1
+# SECRET_GF_ADMINPASSWD_VERSION=v1
-## Seperate domain for Grafana
-#GRAFANA_DOMAIN=grafana.example.com
 #
 ## Single-Sign-On with OIDC
+# COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"
 # OIDC_ENABLED=1
-# SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION=v1
+# SECRET_GF_OIDC_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/"
@@ -62,17 +66,18 @@ ENABLE_BACKUPS=true
 # GF_INSTALL_PLUGINS=grafana-piechart-panel
 #
 ## grafana SMTP configuration (optional)
+# COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-smtp.yml"
 # GF_SMTP_HOST=changeme
 # GF_SMTP_USER=changme
 # GF_SMTP_ENABLED=true
 # GF_SMTP_FROM_ADDRESS=grafana@example.com
 # GF_SMTP_SKIP_VERIFY=false
-# SECRET_GRAFANA_SMTP_PASSWORD_VERSION=v1
+# SECRET_GF_SMTP_PASSWD_VERSION=v1
 #
 
 ## Grafana Matrix Contact Point (optional)
 #COMPOSE_FILE="$COMPOSE_FILE:compose.matrix-alertmanager-receiver.yml"
-#SECRET_MATRIX_ACCESS_TOKEN_VERSION=v1
+#SECRET_MATRIX_TOKEN_VERSION=v1
 #GF_MATRIX_USER_ID="<user-id>"
 #GF_MATRIX_ROOM_ID="<room-id>"
 #GF_MATRIX_HOMESERVER_URL="<homeserver-url>"
@@ -83,3 +88,9 @@ ENABLE_BACKUPS=true
 #ALERT_BACKUP_NOT_SUCCESSFULL_ENABLED=true
 #ALERT_NODE_DISK_SPACE_ENABLED=true
 #ALERT_NODE_MEMORY_USAGE_ENABLED=true
+
+# Forgejo metrics
+# SECRET_FORGEJO_METRICS_TOKEN_VERSION=v1
+# FORGEJO_METRICS_HOSTNAME=
+# FORGEJO_INSECURE_SKIP_VERIFY=false
+# COMPOSE_FILE="$COMPOSE_FILE:compose.forgejo.yml"

README.md

@@ -1,8 +1,8 @@
 # monitoring-ng
 
 Yet another monitoring stack ...
-This time its a all-in-one grafana/prometheus/loki/node_exporter/cadvisor/promtail stack.
+This time its a all-in-one grafana/prometheus/loki/alloy stack.
-It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-cloud/monitoring-lite) stack, but has everything in one recipe included now. So you can deploy monitoring instances to only gather metrics / logs (node_exporter/cadvisor/promtail) and also deploy instances with the full monitoring stack (grafana/prometheus/loki) with the same recipe and just different .env configuration.
+It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-cloud/monitoring-lite) stack, but has everything in one recipe included now. So you can deploy monitoring instances to only gather metrics / logs (alloy) and also deploy instances with the full monitoring stack (grafana/prometheus/loki) with the same recipe and just different .env configuration.
 
 
 <!-- metadata -->
@@ -47,13 +47,6 @@ Where gathering.org is the node you want to gather metrics from.
   - cadvisor.monitoring.gathering.org
   - node.monitoring.gathering.org
 
-### Expose node and cadvisor via ports instead of traefik
-
-In case you have no traefik running on the machine, you can expose the ports directly by uncommenting the following line:
-```
-# COMPOSE_FILE="$COMPOSE_FILE:compose.expose-ports.yml"
-```
-
 ## Setup Metrics Browser
 
 
@@ -145,7 +138,7 @@ COMPOSE_FILE="$COMPOSE_FILE:compose.matrix-alertmanager-receiver.yml"
 
 2. Insert the matrix access token secret:
 ```
-abra app secret insert monitoring.marx.klasse-methode.it matrix_access_token v1
+abra app secret insert monitoring.marx.klasse-methode.it matrix_token v1
 ```
 
 3. Set required configurations:

abra.sh

@@ -1,27 +1,122 @@
 export ENTRYPOINT_VERSION=v1
-export GRAFANA_DATASOURCES_YML_VERSION=v1
+export GF_DATASOURCES_VERSION=v1
-export GRAFANA_DASHBOARDS_YML_VERSION=v2
+export GF_DASHBOARDS_VERSION=v2
-export GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v2
+export GF_SWARM_DASH_VERSION=v2
-export GRAFANA_STACKS_DASHBOARD_JSON_VERSION=v2
+export GF_STACKS_DASH_VERSION=v2
-export GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION=v2
+export GF_TRAEFIK_DASH_VERSION=v2
-export GRAFANA_BACKUP_DASHBOARD_JSON_VERSION=v1
+export GF_BACKUP_DASH_VERSION=v1
-export GRAFANA_ALERTS_JSON_VERSION=v3
+export GF_CUSTOM_INI_VERSION=v4
-export GRAFANA_CUSTOM_INI_VERSION=v4
+export LOKI_YML_VERSION=v3
-export PROMTAIL_YML_VERSION=v3
-export LOKI_YML_VERSION=v2
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=e
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=a
+export GRAFANA_ALERTS_NODE_VERSION=v1c
+export CONFIG_ALLOY_VERSION=v9
 
 # creates a default prometheus scrape config for a given node
 add_node(){
   name=$1
-  add_domain "$name" "$name:8082"
+  add_domain "$name" "metrics.traefik.$name"
   add_domain "$name" "node.monitoring.$name"
   add_domain "$name" "cadvisor.monitoring.$name"
   cat "/prometheus/scrape_configs/$name.yml"
 }
 
+# migrates secrets from old names to new names by reading values from the
+# running containers on the server and re-inserting them under the new names.
+# preview changes: abra app cmd --local <app> migrate_secret_names
+# execute changes: abra app cmd --local <app> migrate_secret_names execute
+migrate_secret_names() {
+  if ! command -v jq &> /dev/null; then
+    echo "jq is required on your local machine to migrate secret names"
+    echo "It could not be found in your PATH, please install jq to proceed."
+    echo "For example: On a debian/ubuntu system, run `apt install jq`"
+    exit 1
+  fi
+
+  # Hardcoded migration mappings: old_secret_name|new_secret_name
+  MIGRATIONS="
+grafana_admin_password|gf_adminpasswd
+grafana_smtp_password|gf_smtp_passwd
+grafana_oidc_client_secret|gf_oidc_secret
+matrix_access_token|matrix_token
+loki_aws_secret_access_key|loki_aws_key
+"
+
+  # Determine which server the app is deployed on
+  SERVER=$(abra app ls -m | jq -r --arg domain "$APP_NAME" '[.[].apps[] | select(.domain == $domain) | .server] | first' 2>/dev/null)
+
+  if [ -z "$SERVER" ]; then
+    echo "Error: could not determine server for app '$APP_NAME'"
+    exit 1
+  fi
+
+  # Build a lookup table of all secrets currently mounted in this stack.
+  # Each line: <secretID> <containerID> <secretName>
+  LOOKUP=$(ssh "$SERVER" "
+    docker stack services ${STACK_NAME} --format '{{.Name}}' | while read svc; do
+      CID=\$(docker ps --no-trunc -q --filter \"name=\${svc}\" | head -1)
+      docker service inspect \"\$svc\" --format '{{json .Spec.TaskTemplate.ContainerSpec.Secrets}}' | \
+        jq -r --arg cid \"\$CID\" '.[]? | .SecretID + \" \" + \$cid + \" \" + .SecretName'
+    done | sort -k3 -r
+  " 2>/dev/null)
+
+  echo "Secret migration plan for: $APP_NAME (server: $SERVER)"
+  echo ""
+  printf "  %-24s %-8s %s\n" "OLD NAME" "FOUND" "ACTION"
+  printf "  %-24s %-8s %s\n" "--------" "-----" "------"
+
+  # Check each old name against the lookup table and display the plan
+  ANY_FOUND=false
+  while IFS='|' read -r OLD_NAME NEW_NAME; do
+    [ -z "$OLD_NAME" ] && continue
+    MATCH=$(echo "$LOOKUP" | grep " ${STACK_NAME}_${OLD_NAME}_" | head -1)
+    if [ -n "$MATCH" ]; then
+      printf "  %-24s %-8s %s\n" "$OLD_NAME" "yes" "recreate as '$NEW_NAME' version V1"
+      ANY_FOUND=true
+    else
+      printf "  %-24s %-8s %s\n" "$OLD_NAME" "no" "nothing (not found on server)"
+    fi
+  done <<< "$MIGRATIONS"
+
+  echo ""
+
+  if [ "$ANY_FOUND" = false ]; then
+    echo "No old secrets found on server. Nothing to migrate."
+    return 0
+  fi
+
+  if [ "$1" != "execute" ]; then
+    echo "To apply the above changes, run:"
+    echo "  abra app cmd --local $APP_NAME migrate_secret_names execute"
+    return 0
+  fi
+
+  # read each found secret from its container and re-insert with the new name
+  while IFS='|' read -r OLD_NAME NEW_NAME; do
+    [ -z "$OLD_NAME" ] && continue
+
+    MATCH=$(echo "$LOOKUP" | grep " ${STACK_NAME}_${OLD_NAME}_" | head -1)
+    [ -z "$MATCH" ] && continue
+
+    SECRET_ID=$(echo "$MATCH" | awk '{print $1}')
+    CID=$(echo "$MATCH" | awk '{print $2}')
+    SECRET_VALUE=$(ssh "$SERVER" "cat /var/lib/docker/containers/${CID}/mounts/secrets/${SECRET_ID} 2>/dev/null || sudo cat /var/lib/docker/containers/${CID}/mounts/secrets/${SECRET_ID} 2>/dev/null")
+
+    if [ -z "$SECRET_VALUE" ]; then
+      echo "Error: could not read value for '$OLD_NAME', skipping"
+      continue
+    fi
+
+    echo "Migrating: '$OLD_NAME' -> '$NEW_NAME' (v1)"
+    printf '%s' "$SECRET_VALUE" | abra app secret insert -C "$APP_NAME" "$NEW_NAME" v1
+    
+  done <<< "$MIGRATIONS"
+
+  echo ""
+  echo "Done."
+}
+
 # adds a domain to a scrape config or creates a new one
 add_domain(){
   name=$1

alertmanager-matrix-config.yml.tmpl

@@ -12,7 +12,7 @@ http:
 matrix:
   homeserver-url: "{{ env "GF_MATRIX_HOMESERVER_URL" }}"
   user-id: "{{ env "GF_MATRIX_USER_ID" }}"
-  access-token: "{{ secret "matrix_access_token" }}"
+  access-token: "{{ secret "matrix_token" }}"
   room-mapping:
     matrixroom: "{{ env "GF_MATRIX_ROOM_ID" }}"
 

alerts/node.yml.tmpl

@@ -0,0 +1,131 @@
+apiVersion: 1
+
+# List of alert rule UIDs that should be deleted
+deleteRules:
+  {{ if ne (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
+  - orgId: 1
+    uid: bds8bhxu97pxca
+  {{ end }}
+  {{ if ne (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
+  - orgId: 1
+    uid: ads8cswmly96oa
+  {{ end }}
+
+groups:
+- orgId: 1
+  name: node
+  folder: node
+  interval: 5m
+  rules:
+    {{ if eq (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
+    - uid: bds8bhxu97pxca
+      title: Node Disk Space
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: (node_filesystem_free_bytes{fstype="ext4"} / node_filesystem_size_bytes{fstype="ext4"}) * 100
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - 10
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 5m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Less than 10% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
+      labels:
+        "": ""
+      isPaused: false
+    {{ end }}
+    {{ if eq (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
+    - uid: ads8cswmly96oa
+      title: Node Memory Usage
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - 85
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 5m
+      annotations:
+        summary: Memory usage is above 85% on {{`{{ $labels.instance }}`}}  ({{`{{ printf "%.2f" (index $values "A").Value }}`}}%  usage)
+      isPaused: false
+    {{ end }}

compose.expose-ports.yml

@@ -1,13 +0,0 @@
----
-version: "3.8"
-
-services:
-  app:
-    ports:
-      - "9100:9100"
-    deploy:
-
-  cadvisor:
-    ports:
-      - "9101:8080"
-    deploy:

compose.forgejo.yml

@@ -0,0 +1,10 @@
+---
+version: "3.8"
+services:
+  app:
+    secrets:
+      - forgejo_token
+secrets:
+  forgejo_token:
+    external: true
+    name: ${STACK_NAME}_forgejo_token_${SECRET_FORGEJO_METRICS_TOKEN_VERSION}

compose.grafana-oidc.yml

@@ -0,0 +1,17 @@
+version: '3.8'
+
+services:
+  grafana:
+    secrets:
+      - gf_oidc_secret
+    environment:
+      - OIDC_API_URL
+      - OIDC_AUTH_URL
+      - OIDC_CLIENT_ID
+      - OIDC_ENABLED
+      - OIDC_TOKEN_URL
+
+secrets:
+  gf_oidc_secret:
+    external: true
+    name: ${STACK_NAME}_gf_oidc_secret_${SECRET_GF_OIDC_SECRET_VERSION}

compose.grafana-smtp.yml

@@ -0,0 +1,18 @@
+version: '3.8'
+
+services:
+  grafana:
+    secrets:
+      - gf_smtp_passwd
+    environment:
+      - GF_SMTP_HOST
+      - GF_SMTP_USER
+      - GF_SMTP_PASSWORD__FILE=/run/secrets/gf_smtp_passwd
+      - GF_SMTP_ENABLED
+      - GF_SMTP_FROM_ADDRESS
+      - GF_SMTP_SKIP_VERIFY
+
+secrets:
+  gf_smtp_passwd:
+    external: true
+    name: ${STACK_NAME}_gf_smtp_passwd_${SECRET_GF_SMTP_PASSWD_VERSION}

compose.grafana.yml

@@ -2,104 +2,87 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:10.4.14
+    image: grafana/grafana:12.4.3
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:
-      - grafana_admin_password
+      - gf_adminpasswd
-      - grafana_oidc_client_secret
-      - grafana_smtp_password
     configs:
-      - source: grafana_custom_ini
+      - source: gf_custom_ini
         target: /etc/grafana/grafana.ini
-      - source: grafana_datasources_yml
+      - source: gf_datasources
         target: /etc/grafana/provisioning/datasources/datasources.yml
-      - source: grafana_dashboards_yml
+      - source: gf_dashboards
         target: /etc/grafana/provisioning/dashboards/dashboards.yml
-      - source: grafana_swarm_dashboard_json
+      - source: gf_swarm_dash
         target: /var/lib/grafana/dashboards/docker-swarm-nodes.json
-      - source: grafana_stacks_dashboard_json
+      - source: gf_stacks_dash
         target: /var/lib/grafana/dashboards/docker-swarm-stacks.json
-      - source: grafana_traefik_dashboard_json
+      - source: gf_traefik_dash
         target: /var/lib/grafana/dashboards/traefik.json
-      - source: grafana_backup_dashboard_json
+      - source: gf_backup_dash
         target: /var/lib/grafana/dashboards/backup.json
-      - source: grafana_alerts_json
+      - source: gf_alerts_node
-        target: /var/lib/grafana/alerts/alerts.json
+        target: /etc/grafana/provisioning/alerting/node.yml
     networks:
       - proxy
       - internal
     environment:
       - GF_SERVER_ROOT_URL
-      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
+      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/gf_adminpasswd
-      - GF_SMTP_HOST
-      - GF_SMTP_USER
-      - GF_SMTP_PASSWORD__FILE=/run/secrets/grafana_smtp_password
-      - GF_SMTP_ENABLED
-      - GF_SMTP_FROM_ADDRESS
-      - GF_SMTP_SKIP_VERIFY
       - GF_SECURITY_ALLOW_EMBEDDING
       - GF_INSTALL_PLUGINS
-      - OIDC_API_URL
+      - ALERT_NODE_DISK_SPACE_ENABLED
-      - OIDC_AUTH_URL
+      - ALERT_NODE_MEMORY_USAGE_ENABLED
-      - OIDC_CLIENT_ID
-      - OIDC_ENABLED
-      - OIDC_TOKEN_URL
     deploy:
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
-        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN:-$DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls=true"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls.certresolver=${LETS_ENCRYPT_ENV}"
     healthcheck:
-      test: "wget -q http://localhost:3000/ -O/dev/null"
+      test: "wget -q http://localhost:3000/healthz -O/dev/null"
       interval: 5s
       timeout: 10s
       retries: 3
       start_period: 10s
 
 configs:
-  grafana_custom_ini:
+  gf_custom_ini:
     template_driver: golang
-    name: ${STACK_NAME}_grafana_custom_ini_${GRAFANA_CUSTOM_INI_VERSION}
+    name: ${STACK_NAME}_gf_custom_ini_${GF_CUSTOM_INI_VERSION}
     file: grafana_custom.ini
-  grafana_datasources_yml:
+  gf_datasources:
-    name: ${STACK_NAME}_g_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION}
+    name: ${STACK_NAME}_gf_datasources_${GF_DATASOURCES_VERSION}
     file: grafana-datasources.yml
-  grafana_dashboards_yml:
+  gf_dashboards:
-    name: ${STACK_NAME}_g_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION}
+    name: ${STACK_NAME}_gf_dashboards_${GF_DASHBOARDS_VERSION}
     file: grafana-dashboards.yml
-  grafana_swarm_dashboard_json:
+  gf_swarm_dash:
-    name: ${STACK_NAME}_g_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_gf_swarm_dash_${GF_SWARM_DASH_VERSION}
     file: grafana-swarm-dashboard.json
-  grafana_stacks_dashboard_json:
+  gf_stacks_dash:
-    name: ${STACK_NAME}_g_stacks_dashboard_json_${GRAFANA_STACKS_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_gf_stacks_dash_${GF_STACKS_DASH_VERSION}
     file: grafana-stacks-dashboard.json
-  grafana_traefik_dashboard_json:
+  gf_traefik_dash:
-    name: ${STACK_NAME}_g_traefik_dashboard_json_${GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_gf_traefik_dash_${GF_TRAEFIK_DASH_VERSION}
     file: grafana-traefik-dashboard.json
-  grafana_backup_dashboard_json:
+  gf_backup_dash:
-    name: ${STACK_NAME}_g_backup_dashboard_json_${GRAFANA_BACKUP_DASHBOARD_JSON_VERSION}
+    name: ${STACK_NAME}_gf_backup_dash_${GF_BACKUP_DASH_VERSION}
     file: grafana-backup-dashboard.json
-  grafana_alerts_json:
+  gf_alerts_node:
     template_driver: golang
-    name: ${STACK_NAME}_g_alerts_json_${GRAFANA_ALERTS_JSON_VERSION}
+    name: ${STACK_NAME}_gf_alerts_node_${GRAFANA_ALERTS_NODE_VERSION}
-    file: grafana-alerts.json.tmpl
+    file: alerts/node.yml.tmpl
 
 volumes:
   grafana-data:
 
 
 secrets:
-  grafana_admin_password:
+  gf_adminpasswd:
     external: true
-    name: ${STACK_NAME}_grafana_admin_password_${SECRET_GRAFANA_ADMIN_PASSWORD_VERSION}
+    name: ${STACK_NAME}_gf_adminpasswd_${SECRET_GF_ADMINPASSWD_VERSION}
-  grafana_oidc_client_secret:
-    external: true
-    name: ${STACK_NAME}_grafana_oidc_client_secret_${SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION}
-  grafana_smtp_password:
-    external: true
-    name: ${STACK_NAME}_grafana_smtp_password_${SECRET_GRAFANA_SMTP_PASSWORD_VERSION}

compose.loki.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   loki:
-    image: grafana/loki:2.9.11
+    image: grafana/loki:3.7.2
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - proxy
@@ -12,7 +12,7 @@ services:
     volumes:
       - loki-data:/loki
     # secrets:
-    #   - loki_aws_secret_access_key
+    #   - loki_aws_key
     environment:
       - LOKI_ACCESS_KEY_ID
       - LOKI_AWS_ENDPOINT
@@ -27,7 +27,7 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-loki.loadbalancer.server.port=3100"
         - "traefik.http.routers.${STACK_NAME}-loki.rule=Host(`loki.${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-loki.entrypoints=web-secure"
@@ -47,6 +47,6 @@ volumes:
   loki-data:
 
 # secrets:
-#   loki_aws_secret_access_key:
+#   loki_aws_key:
 #     external: true
-#     name: ${STACK_NAME}_loki_aws_secret_access_key_${SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION}
+#     name: ${STACK_NAME}_loki_aws_key_${SECRET_LOKI_AWS_KEY_VERSION}

compose.matrix-alertmanager-receiver.yml

@@ -2,9 +2,9 @@ version: '3.8'
 
 services:
   matrix-alertmanager-receiver:
-    image: metio/matrix-alertmanager-receiver:2025.2.9
+    image: metio/matrix-alertmanager-receiver:2026.2.25
     secrets:
-      - matrix_access_token
+      - matrix_token
     configs:
       - source: matrix-alertmanager-receiver-config
         target: /etc/matrix-alertmanager-receiver/config.yml
@@ -23,6 +23,6 @@ configs:
     file: alertmanager-matrix-config.yml.tmpl
 
 secrets:
-  matrix_access_token:
+  matrix_token:
     external: true
-    name: ${STACK_NAME}_matrix_access_token_${SECRET_MATRIX_ACCESS_TOKEN_VERSION}
+    name: ${STACK_NAME}_matrix_token_${SECRET_MATRIX_TOKEN_VERSION}

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v2.55.1
+    image: prom/prometheus:v3.12.0
     secrets:
       - basic_auth
     volumes:
@@ -16,6 +16,8 @@ services:
       - "--web.console.libraries=/usr/share/prometheus/console_libraries"
       - "--web.console.templates=/usr/share/prometheus/consoles"
       - "--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_TIME}"
+      - "--enable-feature=remote-write-receiver"
+      - "--web.enable-remote-write-receiver"
     networks:
       - proxy
       - internal
@@ -24,12 +26,13 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-prometheus.loadbalancer.server.port=9090"
         - "traefik.http.routers.${STACK_NAME}-prometheus.rule=Host(`prometheus.${DOMAIN}`)"
         - "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.middlewares=basicauth@file"
 
 configs:
   prometheus_yml:

compose.promtail.yml

@@ -1,30 +0,0 @@
-version: "3.8"
-
-services:
-  promtail:
-    image: grafana/promtail:2.9.11
-    volumes:
-      - /var/log:/var/log:ro
-      - /var/run/docker.sock:/var/run/docker.sock
-    command: -config.file=/etc/promtail/config.yml
-    configs:
-      - source: promtail_yml
-        target: /etc/promtail/config.yml
-    networks:
-      - internal
-    secrets:
-      - basic_auth
-    environment:
-      - DOMAIN
-      - LOKI_PUSH_URL
-
-configs:
-  promtail_yml:
-    name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
-    file: promtail.yml.tmpl
-    template_driver: golang
-
-secrets:
-  basic_auth:
-    external: true
-    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

compose.pushgateway.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   pushgateway:
-    image: prom/pushgateway:v1.10.0
+    image: prom/pushgateway:v1.11.2
     command:
       - '--web.listen-address=:9191'
       - '--push.disable-consistency-check'
@@ -17,7 +17,7 @@ services:
         condition: on-failure
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "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"

compose.syslog.yml

@@ -0,0 +1,6 @@
+---
+version: "3.8"
+services:
+  app:
+    ports:
+    - "514:514"

compose.yml

@@ -3,89 +3,46 @@ version: "3.8"
 
 services:
   app:
-    image: prom/node-exporter:v1.8.1
+    image: grafana/alloy:v1.16.1
-    user: root
+    hostname: "${DOMAIN}"
-    environment:
-      - NODE_ID={{.Node.ID}}
-    volumes:
-      - /proc:/host/proc:ro
-      - /sys:/host/sys:ro
-      - /:/rootfs:ro
-      - /etc/hostname:/etc/nodename:ro
-    command:
-      - "--path.sysfs=/host/sys"
-      - "--path.procfs=/host/proc"
-      - "--path.rootfs=/rootfs"
-      - "--collector.textfile.directory=/etc/node-exporter/"
-      - "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)"
-      - "--no-collector.ipvs"
     configs:
-      - source: entrypoint
+      - source: config_alloy
-        target: /entrypoint.sh
+        target: /etc/alloy/config.alloy
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /var/run/docker.sock:/var/run/docker.sock
+      - /sys:/sys:ro
+      - /var/lib/docker:/var/lib/docker:ro
+      - /dev:/dev:ro
+      - alloy-data:/var/lib/alloy/data
+    command:
+      - "run"
+      - "--storage.path=/var/lib/alloy/data"
+      - "/etc/alloy/config.alloy"
     networks:
       - internal
-      - proxy
+    secrets:
-    entrypoint: [ "/bin/sh", "-e", "/entrypoint.sh" ]
+      - basic_auth
     deploy:
       restart_policy:
         condition: on-failure
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
-        - "traefik.enable=true"
+        - "traefik.enable=false"
-        - "traefik.docker.network=proxy"
-        - "traefik.http.services.${STACK_NAME}-node.loadbalancer.server.port=9100"
-        - "traefik.http.routers.${STACK_NAME}-node.rule=Host(`node.${DOMAIN}`)"
-        - "traefik.http.routers.${STACK_NAME}-node.entrypoints=web-secure"
-        - "traefik.http.routers.${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=1.6.0+v1.8.1"
-        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-120}"
-
-  cadvisor:
-    image: gcr.io/cadvisor/cadvisor:v0.49.2
-    command:
-      - "-logtostderr"
-      - "--enable_metrics=cpu,cpuLoad,disk,diskIO,process,memory,network"
-      # all possible metrics: advtcp,app,cpu,cpuLoad,cpu_topology,cpuset,disk,diskIO,hugetlb,memory,memory_numa,network,oom_event,percpu,perf_event,process,referenced_memory,resctrl,sched,tcp,udp.
-      - "--housekeeping_interval=120s"
-      - "--docker_only=true"
-    volumes:
-      - /var/lib/docker/:/var/lib/docker:ro
-      - /dev/disk/:/dev/disk:ro
-      - /sys:/sys:ro
-      - /var/run:/var/run:ro
-      - /:/rootfs:ro
-    networks:
-      - internal
-      - proxy
-    deploy:
-      restart_policy:
-        condition: on-failure
-      labels:
-        - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
-        - "traefik.http.services.${STACK_NAME}-cadvisor.loadbalancer.server.port=8080"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.rule=Host(`cadvisor.${DOMAIN}`)"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.tls=true"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - "traefik.http.routers.${STACK_NAME}-cadvisor.middlewares=basicauth@file"
-    healthcheck:
-      test: wget --quiet --tries=1 --spider http://localhost:8080/healthz || exit 1
-      interval: 15s
-      timeout: 15s
-      retries: 5
-      start_period: 30s
-
 configs:
-  entrypoint:
+  config_alloy:
-    name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
+    template_driver: golang
-    file: node-exporter-entrypoint.sh
+    name: ${STACK_NAME}_config_alloy_${CONFIG_ALLOY_VERSION}
-
+    file: config.alloy.tmpl
-
-
 networks:
   proxy:
     external: true
   internal:
+volumes:
+  alloy-data:
+secrets:
+  basic_auth:
+    external: true
+    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

config.alloy.tmpl

@@ -0,0 +1,108 @@
+logging {
+  level = "info"
+  format = "logfmt"
+}
+
+discovery.docker "linux" {
+  host = "unix:///var/run/docker.sock"
+}
+
+{{ if ne (env "PROMETHEUS_REMOTE_WRITE_URL") "" }}
+prometheus.exporter.cadvisor "docker" {
+}
+
+prometheus.exporter.unix "default" {
+  include_exporter_metrics = true
+  rootfs_path = "/rootfs"
+}
+
+prometheus.scrape "default" {
+  targets = array.concat(
+    [{
+      job         = "alloy",
+      __address__ = "127.0.0.1:12345",
+    }],
+    prometheus.exporter.unix.default.targets,
+    prometheus.exporter.cadvisor.docker.targets,
+  )
+
+  forward_to = [prometheus.remote_write.prometheus.receiver]
+}
+
+{{ if ne (env "FORGEJO_METRICS_HOSTNAME") "" }}
+prometheus.scrape "forgejo" {
+  bearer_token = "{{ secret "forgejo_token" }}"
+  job_name = "forgejo"
+  scheme = "https"
+
+  targets = [{ __address__ = "{{ env "FORGEJO_METRICS_HOSTNAME" }}" }]
+  forward_to = [prometheus.remote_write.prometheus.receiver]
+
+  tls_config {
+    insecure_skip_verify = {{ env "FORGEJO_INSECURE_SKIP_VERIFY" }}
+    server_name = "{{ env "FORGEJO_METRICS_HOSTNAME" }}"
+  }
+}
+{{ end }}
+
+prometheus.remote_write "prometheus" {
+  endpoint {
+    url = "{{ env "PROMETHEUS_REMOTE_WRITE_URL" }}"
+
+    basic_auth {
+      username = "admin"
+      password = "{{ secret "basic_auth" }}"
+    }
+  }
+}
+{{ end }}
+
+{{ if ne (env "LOKI_PUSH_URL") "" }}
+loki.source.docker "docker" {
+  host       = "unix:///var/run/docker.sock"
+  targets    = discovery.docker.linux.targets
+  labels     = {"app" = "docker"}
+  forward_to = [loki.write.loki.receiver]
+}
+
+{{ if eq (env "JOURNALD") "1" }}
+loki.source.journal "journal" {
+  path = "/var/log/journal"
+  labels = { job = "{{ env "DOMAIN" }}" }
+  forward_to = [loki.write.loki.receiver]
+}
+{{ end }}
+
+{{ if eq (env "SYSLOG") "1" }}
+loki.relabel "syslog" {
+  rule {
+    action = "labelmap"
+    regex = "__syslog_(.+)"
+  }
+
+  forward_to = []
+}
+
+loki.source.syslog "syslog" {
+  listener {
+    address = "[::1]:514"
+    label_structured_data = true
+    labels = { component = "loki.source.syslog" }
+  }
+
+  relabel_rules = loki.relabel.syslog.rules
+  forward_to = [loki.write.loki.receiver]
+}
+{{ end }}
+
+loki.write "loki" {
+  endpoint {
+    url = "{{ env "LOKI_PUSH_URL" }}"
+
+    basic_auth {
+      username = "admin"
+      password = "{{ secret "basic_auth" }}"
+    }
+  }
+}
+{{ end }}

grafana-alerts.json.tmpl

@@ -216,7 +216,7 @@
               "datasourceUid": "PBFA97CFB590B2093",
               "model": {
                 "editorMode": "code",
-                "expr": "(node_filesystem_free_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} / node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"}) * 100",
+                "expr": "(node_filesystem_free_bytes{fstype=\"ext4\"} / node_filesystem_size_bytes{fstype=\"ext4\"}) * 100",
                 "instant": true,
                 "intervalMs": 1000,
                 "legendFormat": "__auto",

grafana-swarm-dashboard.json

@@ -93,7 +93,6 @@
       },
       "hideTimeOverride": true,
       "id": 2,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -107,10 +106,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -172,7 +173,6 @@
         "y": 0
       },
       "id": 1,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -186,10 +186,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -251,7 +253,6 @@
       },
       "hideTimeOverride": true,
       "id": 4,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -265,10 +266,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -335,9 +338,10 @@
         "y": 0
       },
       "id": 8,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
         "orientation": "horizontal",
         "reduceOptions": {
           "calcs": [
@@ -348,9 +352,10 @@
         },
         "showThresholdLabels": false,
         "showThresholdMarkers": true,
+        "sizing": "auto",
         "text": {}
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -405,13 +410,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -507,7 +511,6 @@
       },
       "hideTimeOverride": true,
       "id": 3,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -521,10 +524,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -585,7 +590,6 @@
       },
       "hideTimeOverride": true,
       "id": 9,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -599,10 +603,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -671,9 +677,10 @@
       },
       "hideTimeOverride": true,
       "id": 11,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
         "orientation": "horizontal",
         "reduceOptions": {
           "calcs": [
@@ -684,9 +691,10 @@
         },
         "showThresholdLabels": false,
         "showThresholdMarkers": true,
+        "sizing": "auto",
         "text": {}
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -713,7 +721,39 @@
       "fieldConfig": {
         "defaults": {
           "color": {
-            "mode": "thresholds"
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
           },
           "mappings": [
             {
@@ -747,33 +787,42 @@
           },
           "unit": "percent"
         },
-        "overrides": []
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byType",
+              "options": "time"
+            },
+            "properties": [
+              {
+                "id": "custom.axisPlacement",
+                "value": "hidden"
+              }
+            ]
+          }
+        ]
       },
       "gridPos": {
-        "h": 4,
+        "h": 6,
-        "w": 2.6666666666666665,
+        "w": 6,
         "x": 0,
         "y": 8
       },
       "id": 10,
-      "links": [],
       "maxDataPoints": 100,
-      "maxPerRow": 12,
       "options": {
-        "colorMode": "value",
+        "legend": {
-        "graphMode": "area",
+          "calcs": [],
-        "justifyMode": "auto",
+          "displayMode": "list",
-        "orientation": "horizontal",
+          "placement": "bottom",
-        "reduceOptions": {
+          "showLegend": true
-          "calcs": [
-            "last"
-          ],
-          "fields": "",
-          "values": false
         },
-        "textMode": "auto"
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "repeat": "node_id",
       "repeatDirection": "h",
       "targets": [
@@ -782,18 +831,20 @@
             "type": "prometheus",
             "uid": "PBFA97CFB590B2093"
           },
+          "editorMode": "code",
           "exemplar": true,
-          "expr": "sum((node_filesystem_free_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} / node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"}) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) / count(node_meta * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})",
+          "expr": "node_filesystem_free_bytes{fstype=\"ext4\"}  / node_filesystem_size_bytes{fstype=\"ext4\"} * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 2,
-          "legendFormat": "",
+          "legendFormat": "{{mountpoint}}",
+          "range": true,
           "refId": "A",
           "step": 20
         }
       ],
       "title": "Available Disk Space $node_id",
-      "type": "stat"
+      "type": "timeseries"
     },
     {
       "aliasColors": {},
@@ -811,7 +862,7 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 12
+        "y": 14
       },
       "hiddenSeries": false,
       "id": 14,
@@ -830,13 +881,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -900,6 +950,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -913,6 +964,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -961,12 +1013,11 @@
       },
       "gridPos": {
         "h": 7,
-        "w": 2.6666666666666665,
+        "w": 6,
         "x": 0,
-        "y": 19
+        "y": 21
       },
       "id": 15,
-      "links": [],
       "maxPerRow": 12,
       "options": {
         "legend": {
@@ -1074,7 +1125,7 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 26
+        "y": 28
       },
       "hiddenSeries": false,
       "id": 16,
@@ -1091,13 +1142,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -1178,7 +1228,7 @@
         "h": 7,
         "w": 12,
         "x": 0,
-        "y": 33
+        "y": 35
       },
       "hiddenSeries": false,
       "id": 18,
@@ -1195,7 +1245,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
@@ -1281,7 +1330,7 @@
         "h": 7,
         "w": 12,
         "x": 12,
-        "y": 33
+        "y": 35
       },
       "hiddenSeries": false,
       "id": 19,
@@ -1300,7 +1349,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
@@ -1376,7 +1424,7 @@
         "h": 7,
         "w": 18,
         "x": 0,
-        "y": 40
+        "y": 42
       },
       "hiddenSeries": false,
       "id": 12,
@@ -1397,7 +1445,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null",
       "options": {
         "alertThreshold": true
@@ -1499,10 +1546,9 @@
         "h": 7,
         "w": 6,
         "x": 18,
-        "y": 40
+        "y": 42
       },
       "id": 7,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "none",
@@ -1600,10 +1646,9 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 47
+        "y": 49
       },
       "id": 17,
-      "links": [],
       "options": {
         "legend": {
           "calcs": [],
@@ -1658,7 +1703,7 @@
         "h": 9,
         "w": 24,
         "x": 0,
-        "y": 54
+        "y": 56
       },
       "id": 30,
       "options": {
@@ -1688,8 +1733,7 @@
     }
   ],
   "refresh": "",
-  "schemaVersion": 38,
+  "schemaVersion": 39,
-  "style": "dark",
   "tags": [
     "swarmprom",
     "prometheus",
@@ -1836,6 +1880,6 @@
   "timezone": "",
   "title": "Docker Swarm Nodes",
   "uid": "BPlb-Sgik",
-  "version": 24,
+  "version": 7,
   "weekStart": ""
-}
+}

grafana_custom.ini

@@ -21,7 +21,7 @@ tls_skip_verify_insecure = false
 allow_sign_up = true
 auto_login = true
 client_id = {{ env "OIDC_CLIENT_ID" }}
-client_secret = {{ secret "grafana_oidc_client_secret" }}
+client_secret = {{ secret "gf_oidc_secret" }}
 auth_url = {{ env "OIDC_AUTH_URL" }}
 token_url = {{ env "OIDC_TOKEN_URL" }}
 api_url = {{ env "OIDC_API_URL" }}

loki.yml.tmpl

@@ -34,7 +34,6 @@ ingester:
   max_chunk_age: 1h           # All chunks will be flushed when they hit this age, default is 1h
   chunk_target_size: 1048576  # Loki will attempt to build chunks up to 1.5MB, flushing first if chunk_idle_period or max_chunk_age is reached first
   chunk_retain_period: 30s    # Must be greater than index read cache TTL if using an index cache (Default index read cache TTL is 5m)
-  max_transfer_retries: 0     # Chunk transfers disabled
   wal:
     dir: "/tmp/wal"
 
@@ -53,7 +52,7 @@ schema_config:
     - from: 2020-10-24
       store: boltdb-shipper
       object_store: filesystem
-      schema: v11
+      schema: v13
       index:
         prefix: index_
         period: 24h
@@ -63,7 +62,6 @@ storage_config:
     active_index_directory: /loki/boltdb-shipper-active
     cache_location: /loki/boltdb-shipper-cache
     cache_ttl: 24h         # Can be increased for faster performance over longer query periods, uses more disk space
-    shared_store: filesystem
   filesystem:
     directory: /loki/chunks
 {{ end }}
@@ -72,7 +70,6 @@ schema_config:
   configs:
   - from: 2020-11-25
     store: boltdb-shipper
-    object_store: aws
     schema: v11
     index:
       prefix: index_
@@ -89,7 +86,7 @@ storage_config:
    endpoint: {{ env "LOKI_AWS_ENDPOINT" }}
    region: {{ env "LOKI_AWS_REGION" }}
    access_key_id: {{ env "LOKI_ACCESS_KEY_ID" }}
-   secret_access_key: {{ secret "loki_aws_secret_access_key" }}
+   secret_access_key: {{ secret "loki_aws_key" }}
    bucketnames: {{ env "LOKI_BUCKET_NAMES" }}
    insecure: false
    sse_encryption: false
@@ -103,19 +100,24 @@ storage_config:
 
 compactor:
   working_directory: /loki/boltdb-shipper-compactor
-  shared_store: filesystem
   compaction_interval: 10m
   retention_enabled: true
   retention_delete_delay: 2h
   retention_delete_worker_count: 150
+{{ if eq (env "LOKI_STORAGE_FILESYSTEM") "1" }}
+  delete_request_store: filesystem
+{{ end }}
+{{ if eq (env "LOKI_STORAGE_S3") "1" }}
+  delete_request_store: aws
+{{ end }}
 
 limits_config:
-  enforce_metric_name: false
   reject_old_samples: true
   reject_old_samples_max_age: 168h
   retention_period: {{ env "LOKI_RETENTION_PERIOD" }}
   split_queries_by_interval: 24h
   max_query_parallelism: 100
+  allow_structured_metadata: false
 
 query_scheduler:
   max_outstanding_requests_per_tenant: 4096
@@ -123,9 +125,6 @@ query_scheduler:
 frontend:
   max_outstanding_per_tenant: 4096
 
-chunk_store_config:
-  max_look_back_period: 0s
-
 table_manager:
   retention_deletes_enabled: false
   retention_period: 0s

node-exporter-entrypoint.sh

@@ -1,11 +0,0 @@
-#!/bin/sh -e
-
-NODE_NAME=$(cat /etc/nodename)
-
-mkdir -p /etc/node-exporter
-
-echo "node_meta{node_id=\"$NODE_ID\", container_label_com_docker_swarm_node_id=\"$NODE_ID\", node_name=\"$NODE_NAME\"} 1" > /etc/node-exporter/node-meta.prom
-
-set -- /bin/node_exporter "$@"
-
-exec "$@"

promtail.yml.tmpl

@@ -1,37 +0,0 @@
-server:
-  http_listen_port: 9080
-  grpc_listen_port: 0
-
-positions:
-  filename: /tmp/positions.yaml
-
-clients:
-  - url: {{ env "LOKI_PUSH_URL" }}
-    basic_auth:
-      username: admin
-      password: {{ secret "basic_auth" }}
-    external_labels:
-      hostname: {{ env "DOMAIN" }}
-
-scrape_configs:
-- job_name: system
-  static_configs:
-  - targets:
-      - localhost
-    labels:
-      job: varlogs
-      __path__: /var/log/*log
-
-- job_name: "docker"
-  docker_sd_configs:
-    - host: "unix:///var/run/docker.sock"
-      refresh_interval: "10s"
-  relabel_configs:
-    - source_labels: ['__meta_docker_container_name']
-      target_label: "container_name"
-    - source_labels: ['__meta_docker_container_id']
-      target_label: "container_id"
-    - source_labels: ['__meta_docker_container_label_com_docker_stack_namespace']
-      target_label: "stack_namespace"
-    - source_labels: ['__meta_docker_container_label_com_docker_swarm_service_name']
-      target_label: "service_name"

release/next

@@ -0,0 +1,12 @@
+1. OIDC was moved into a seperate compose file. If you have oidc configured you need to add the following line to you .env file:
+
+COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"
+
+2. SMTP was moved into a seperate compose file. If you have smtp configured you need to add the following line to you .env file:
+
+COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-smtp.yml"
+
+3. The scrape-config.example.yml file and add_node() command were updated to use a secure endpoint for the traefik metrics instead of http. This requires an updated Traefik recipe that publishes the metrics on https.
+
+4. Secret and config names were shortened to max 14 characters to prevent going over Docker's 64 character limit when STACK_NAME and VERSION are added to it.
+When upgrading, you need to reinsert the secrets with their shorter names. Run `abra app secret list <domain>` to see which secrets aren't created on the server (because their name was shortened) and run `abra app secret insert <domain> <secret_name> v1 <value>` to reinsert them with the shorter name. Or you can use the migrate_secret_names function in abra.sh to reinsert all existing secrets with their shorter name automatically: `abra app cmd --local <domain> migrate_secret_names`

scrape-config.example.yml

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