add file

.env.sample

@@ -39,20 +39,20 @@ 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_KEY_VERSION=v1
+# SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION=v1
 #
 ## Grafana
 #
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana.yml"
-# GF_SERVER_ROOT_URL=https://monitoring.example.com
-# SECRET_GF_ADMINPASSWD_VERSION=v1
-## Seperate domain for Grafana
-#GRAFANA_DOMAIN=grafana.example.com
+## GRAFANA_DOMAIN needs to be set. change it for a different domain
+#GRAFANA_DOMAIN=$DOMAIN
+# GF_SERVER_ROOT_URL=https://${GRAFANA_DOMAIN}
+# SECRET_GRAFANA_ADMIN_PASSWORD_VERSION=v1
 #
 ## Single-Sign-On with OIDC
 # COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"
 # OIDC_ENABLED=1
-# SECRET_GF_OIDC_SECRET_VERSION=v1
+# 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/"
@@ -69,12 +69,12 @@ ENABLE_BACKUPS=true
 # GF_SMTP_ENABLED=true
 # GF_SMTP_FROM_ADDRESS=grafana@example.com
 # GF_SMTP_SKIP_VERIFY=false
-# SECRET_GF_SMTP_PASSWD_VERSION=v1
+# SECRET_GRAFANA_SMTP_PASSWORD_VERSION=v1
 #
 
 ## Grafana Matrix Contact Point (optional)
 #COMPOSE_FILE="$COMPOSE_FILE:compose.matrix-alertmanager-receiver.yml"
-#SECRET_MATRIX_TOKEN_VERSION=v1
+#SECRET_MATRIX_ACCESS_TOKEN_VERSION=v1
 #GF_MATRIX_USER_ID="<user-id>"
 #GF_MATRIX_ROOM_ID="<room-id>"
 #GF_MATRIX_HOMESERVER_URL="<homeserver-url>"
@@ -85,3 +85,5 @@ ENABLE_BACKUPS=true
 #ALERT_BACKUP_NOT_SUCCESSFULL_ENABLED=true
 #ALERT_NODE_DISK_SPACE_ENABLED=true
 #ALERT_NODE_MEMORY_USAGE_ENABLED=true
+#ALERT_RESTIC_CHECK_FAILED_ENABLED=true
+#ALERT_RESTIC_OUTDATED_BACKUP_ENABLED=true

README.md

@@ -145,7 +145,7 @@ 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_token v1
+abra app secret insert monitoring.marx.klasse-methode.it matrix_access_token v1
 ```
 
 3. Set required configurations:

abra.sh

@@ -1,122 +1,28 @@
 export ENTRYPOINT_VERSION=v1
-export GF_DATASOURCES_VERSION=v1
-export GF_DASHBOARDS_VERSION=v2
-export GF_SWARM_DASH_VERSION=v2
-export GF_STACKS_DASH_VERSION=v2
-export GF_TRAEFIK_DASH_VERSION=v2
-export GF_BACKUP_DASH_VERSION=v1
-export GF_CUSTOM_INI_VERSION=v4
+export GRAFANA_DATASOURCES_YML_VERSION=v1
+export GRAFANA_DASHBOARDS_YML_VERSION=v2
+export GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v2
+export GRAFANA_STACKS_DASHBOARD_JSON_VERSION=v2
+export GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION=v2
+export GRAFANA_BACKUP_DASHBOARD_JSON_VERSION=v1
+export GRAFANA_CUSTOM_INI_VERSION=v4
 export PROMTAIL_YML_VERSION=v3
-export LOKI_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 GRAFANA_ALERTS_RESTIC_VERSION=v2
 
 # creates a default prometheus scrape config for a given node
 add_node(){
   name=$1
-  add_domain "$name" "metrics.traefik.$name"
+  add_domain "$name" "$name:8082"
   add_domain "$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_token" }}"
+  access-token: "{{ secret "matrix_access_token" }}"
   room-mapping:
     matrixroom: "{{ env "GF_MATRIX_ROOM_ID" }}"
 

alerts/restic.yml.tmpl

@@ -0,0 +1,191 @@
+apiVersion: 1
+
+deleteRules:
+  {{ if ne (env "ALERT_RESTIC_CHECK_FAILED_ENABLED") "true" }}
+  - orgId: 1
+    uid: ffglj6egxy8e8c
+  {{ end }}
+  {{ if ne (env "ALERT_RESTIC_OUTDATED_BACKUP_ENABLED") "true" }}
+  - orgId: 1
+    uid: ffgljntkp9ce8b
+  {{ end }}
+
+groups:
+    - orgId: 1
+      name: restic
+      folder: restic
+      interval: 5m
+      rules:
+      {{ if eq (env "ALERT_RESTIC_CHECK_FAILED_ENABLED") "true" }}
+        - uid: ffglj6egxy8e8c
+          title: Restic Check Failed
+          condition: C
+          data:
+            - refId: A
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: prometheus
+              model:
+                disableTextWrap: false
+                editorMode: builder
+                expr: restic_check_success
+                fullMetaSearch: false
+                includeNullMetadata: true
+                instant: true
+                intervalMs: 1000
+                legendFormat: __auto
+                maxDataPoints: 43200
+                range: false
+                refId: A
+                useBackend: false
+            - refId: B
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params: []
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - B
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: A
+                intervalMs: 1000
+                maxDataPoints: 43200
+                reducer: last
+                refId: B
+                type: reduce
+            - refId: C
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params:
+                            - 1
+                            - 0
+                        type: lt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - C
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: B
+                intervalMs: 1000
+                maxDataPoints: 43200
+                refId: C
+                type: threshold
+          noDataState: Alerting
+          execErrState: Error
+          for: 5m
+          annotations: {}
+          labels: {}
+          isPaused: false
+        {{ end }}
+        {{ if eq (env "ALERT_RESTIC_OUTDATED_BACKUP_ENABLED") "true" }}
+        - uid: ffgljntkp9ce8b
+          title: Restic Outdated Backup
+          condition: C
+          data:
+            - refId: A
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: prometheus
+              model:
+                disableTextWrap: false
+                editorMode: builder
+                expr: time() - max by(instance) (restic_backup_timestamp)
+                fullMetaSearch: false
+                includeNullMetadata: true
+                instant: true
+                intervalMs: 1000
+                legendFormat: __auto
+                maxDataPoints: 43200
+                range: false
+                refId: A
+                useBackend: false
+            - refId: B
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params: []
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - B
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: A
+                intervalMs: 1000
+                maxDataPoints: 43200
+                reducer: last
+                refId: B
+                type: reduce
+            - refId: C
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params:
+                            - 93600
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - C
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: B
+                intervalMs: 1000
+                maxDataPoints: 43200
+                refId: C
+                type: threshold
+          noDataState: NoData
+          execErrState: Error
+          for: 5m
+          annotations: {}
+          labels: {}
+          isPaused: false
+        {{ end }}

compose.grafana-oidc.yml

@@ -3,7 +3,7 @@ version: '3.8'
 services:
   grafana:
     secrets:
-      - gf_oidc_secret
+      - grafana_oidc_client_secret
     environment:
       - OIDC_API_URL
       - OIDC_AUTH_URL
@@ -12,6 +12,6 @@ services:
       - OIDC_TOKEN_URL
 
 secrets:
-  gf_oidc_secret:
+  grafana_oidc_client_secret:
     external: true
-    name: ${STACK_NAME}_gf_oidc_secret_${SECRET_GF_OIDC_SECRET_VERSION}
+    name: ${STACK_NAME}_grafana_oidc_client_secret_${SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION}

compose.grafana-smtp.yml

@@ -3,16 +3,16 @@ version: '3.8'
 services:
   grafana:
     secrets:
-      - gf_smtp_passwd
+      - grafana_smtp_password
     environment:
       - GF_SMTP_HOST
       - GF_SMTP_USER
-      - GF_SMTP_PASSWORD__FILE=/run/secrets/gf_smtp_passwd
+      - GF_SMTP_PASSWORD__FILE=/run/secrets/grafana_smtp_password
       - GF_SMTP_ENABLED
       - GF_SMTP_FROM_ADDRESS
       - GF_SMTP_SKIP_VERIFY
 
 secrets:
-  gf_smtp_passwd:
+  grafana_smtp_password:
     external: true
-    name: ${STACK_NAME}_gf_smtp_passwd_${SECRET_GF_SMTP_PASSWD_VERSION}
+    name: ${STACK_NAME}_grafana_smtp_password_${SECRET_GRAFANA_SMTP_PASSWORD_VERSION}

compose.grafana.yml

@@ -2,44 +2,49 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:12.4.0
+    image: grafana/grafana:10.4.14
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:
-      - gf_adminpasswd
+      - grafana_admin_password
     configs:
-      - source: gf_custom_ini
+      - source: grafana_custom_ini
         target: /etc/grafana/grafana.ini
-      - source: gf_datasources
+      - source: grafana_datasources_yml
         target: /etc/grafana/provisioning/datasources/datasources.yml
-      - source: gf_dashboards
+      - source: grafana_dashboards_yml
         target: /etc/grafana/provisioning/dashboards/dashboards.yml
-      - source: gf_swarm_dash
+      - source: grafana_swarm_dashboard_json
         target: /var/lib/grafana/dashboards/docker-swarm-nodes.json
-      - source: gf_stacks_dash
+      - source: grafana_stacks_dashboard_json
         target: /var/lib/grafana/dashboards/docker-swarm-stacks.json
-      - source: gf_traefik_dash
+      - source: grafana_traefik_dashboard_json
         target: /var/lib/grafana/dashboards/traefik.json
-      - source: gf_backup_dash
+      - source: grafana_backup_dashboard_json
         target: /var/lib/grafana/dashboards/backup.json
       - source: gf_alerts_node
         target: /etc/grafana/provisioning/alerting/node.yml
+      - source: gf_alerts_restic
+        target: /etc/grafana/provisioning/alerting/restic.yml
     networks:
       - proxy
       - internal
     environment:
       - GF_SERVER_ROOT_URL
-      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/gf_adminpasswd
+      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
       - GF_SECURITY_ALLOW_EMBEDDING
       - GF_INSTALL_PLUGINS
       - ALERT_NODE_DISK_SPACE_ENABLED
       - ALERT_NODE_MEMORY_USAGE_ENABLED
+      - ALERT_RESTIC_CHECK_FAILED_ENABLED
+      - ALERT_RESTIC_OUTDATED_BACKUP_ENABLED
+      - DOMAIN
     deploy:
       labels:
         - "traefik.enable=true"
         - "traefik.docker.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.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_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}"
@@ -51,38 +56,42 @@ services:
       start_period: 10s
 
 configs:
-  gf_custom_ini:
+  grafana_custom_ini:
     template_driver: golang
-    name: ${STACK_NAME}_gf_custom_ini_${GF_CUSTOM_INI_VERSION}
+    name: ${STACK_NAME}_grafana_custom_ini_${GRAFANA_CUSTOM_INI_VERSION}
     file: grafana_custom.ini
-  gf_datasources:
-    name: ${STACK_NAME}_gf_datasources_${GF_DATASOURCES_VERSION}
+  grafana_datasources_yml:
+    name: ${STACK_NAME}_g_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION}
     file: grafana-datasources.yml
-  gf_dashboards:
-    name: ${STACK_NAME}_gf_dashboards_${GF_DASHBOARDS_VERSION}
+  grafana_dashboards_yml:
+    name: ${STACK_NAME}_g_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION}
     file: grafana-dashboards.yml
-  gf_swarm_dash:
-    name: ${STACK_NAME}_gf_swarm_dash_${GF_SWARM_DASH_VERSION}
+  grafana_swarm_dashboard_json:
+    name: ${STACK_NAME}_g_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION}
     file: grafana-swarm-dashboard.json
-  gf_stacks_dash:
-    name: ${STACK_NAME}_gf_stacks_dash_${GF_STACKS_DASH_VERSION}
+  grafana_stacks_dashboard_json:
+    name: ${STACK_NAME}_g_stacks_dashboard_json_${GRAFANA_STACKS_DASHBOARD_JSON_VERSION}
     file: grafana-stacks-dashboard.json
-  gf_traefik_dash:
-    name: ${STACK_NAME}_gf_traefik_dash_${GF_TRAEFIK_DASH_VERSION}
+  grafana_traefik_dashboard_json:
+    name: ${STACK_NAME}_g_traefik_dashboard_json_${GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION}
     file: grafana-traefik-dashboard.json
-  gf_backup_dash:
-    name: ${STACK_NAME}_gf_backup_dash_${GF_BACKUP_DASH_VERSION}
+  grafana_backup_dashboard_json:
+    name: ${STACK_NAME}_g_backup_dashboard_json_${GRAFANA_BACKUP_DASHBOARD_JSON_VERSION}
     file: grafana-backup-dashboard.json
   gf_alerts_node:
     template_driver: golang
     name: ${STACK_NAME}_gf_alerts_node_${GRAFANA_ALERTS_NODE_VERSION}
     file: alerts/node.yml.tmpl
+  gf_alerts_restic:
+    template_driver: golang
+    name: ${STACK_NAME}_gf_alerts_restiv_${GRAFANA_ALERTS_RESTIC_VERSION}
+    file: alerts/restic.yml.tmpl
 
 volumes:
   grafana-data:
 
 
 secrets:
-  gf_adminpasswd:
+  grafana_admin_password:
     external: true
-    name: ${STACK_NAME}_gf_adminpasswd_${SECRET_GF_ADMINPASSWD_VERSION}
+    name: ${STACK_NAME}_grafana_admin_password_${SECRET_GRAFANA_ADMIN_PASSWORD_VERSION}

compose.loki.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   loki:
-    image: grafana/loki:3.6.7
+    image: grafana/loki:2.9.11
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - proxy
@@ -12,7 +12,7 @@ services:
     volumes:
       - loki-data:/loki
     # secrets:
-    #   - loki_aws_key
+    #   - loki_aws_secret_access_key
     environment:
       - LOKI_ACCESS_KEY_ID
       - LOKI_AWS_ENDPOINT
@@ -47,6 +47,6 @@ volumes:
   loki-data:
 
 # secrets:
-#   loki_aws_key:
+#   loki_aws_secret_access_key:
 #     external: true
-#     name: ${STACK_NAME}_loki_aws_key_${SECRET_LOKI_AWS_KEY_VERSION}
+#     name: ${STACK_NAME}_loki_aws_secret_access_key_${SECRET_LOKI_AWS_SECRET_ACCESS_KEY_VERSION}

compose.matrix-alertmanager-receiver.yml

@@ -2,9 +2,9 @@ version: '3.8'
 
 services:
   matrix-alertmanager-receiver:
-    image: metio/matrix-alertmanager-receiver:2026.2.25
+    image: metio/matrix-alertmanager-receiver:2025.2.9
     secrets:
-      - matrix_token
+      - matrix_access_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_token:
+  matrix_access_token:
     external: true
-    name: ${STACK_NAME}_matrix_token_${SECRET_MATRIX_TOKEN_VERSION}
+    name: ${STACK_NAME}_matrix_access_token_${SECRET_MATRIX_ACCESS_TOKEN_VERSION}

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v3.10.0
+    image: prom/prometheus:v2.55.1
     secrets:
       - basic_auth
     volumes:
@@ -39,3 +39,8 @@ configs:
 
 volumes:
   prometheus-data:
+
+secrets:
+  basic_auth:
+    external: true
+    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

compose.promtail.yml

@@ -2,7 +2,7 @@ version: "3.8"
 
 services:
   promtail:
-    image: grafana/promtail:3.6.7
+    image: grafana/promtail:2.9.11
     volumes:
       - /var/log:/var/log:ro
       - /var/run/docker.sock:/var/run/docker.sock
@@ -27,4 +27,4 @@ configs:
 secrets:
   basic_auth:
     external: true
-    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}
+    name: ${STACK_NAME}_basic_auth_${SECRET_BASIC_AUTH_VERSION}

compose.pushgateway.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   pushgateway:
-    image: prom/pushgateway:v1.11.2
+    image: prom/pushgateway:v1.10.0
     command:
       - '--web.listen-address=:9191'
       - '--push.disable-consistency-check'

compose.yml

@@ -3,7 +3,7 @@ version: "3.8"
 
 services:
   app:
-    image: prom/node-exporter:v1.10.2
+    image: prom/node-exporter:v1.8.1
     user: root
     environment:
       - NODE_ID={{.Node.ID}}
@@ -43,7 +43,7 @@ services:
         - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT}"
 
   cadvisor:
-    image: gcr.io/cadvisor/cadvisor:v0.55.1
+    image: gcr.io/cadvisor/cadvisor:v0.49.2
     command:
       - "-logtostderr"
       - "--enable_metrics=cpu,cpuLoad,disk,diskIO,process,memory,network"

grafana-dashboards.yml

@@ -11,13 +11,3 @@ providers:
     options:
       path: /var/lib/grafana/dashboards
       foldersFromFilesStructure: true
-  - name: 'default-alert-provider'
-    orgId: 1
-    folder: 'default-alerts'
-    type: file
-    disableDeletion: false
-    updateIntervalSeconds: 10
-    allowUiUpdates: true
-    options:
-      path: /var/lib/grafana/alerts
-      foldersFromFilesStructure: true

grafana-datasources.yml

@@ -3,6 +3,7 @@ apiVersion: 1
 datasources:
   - name: Prometheus
     type: prometheus
+    uid: prometheus
     access: proxy
     orgId: 1
     url: http://prometheus:9090
@@ -10,6 +11,7 @@ datasources:
     editable: false
   - name: Loki
     type: loki
+    uid: loki
     access: proxy
     orgId: 1
     url: http://loki:3100

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 "gf_oidc_secret" }}
+client_secret = {{ secret "grafana_oidc_client_secret" }}
 auth_url = {{ env "OIDC_AUTH_URL" }}
 token_url = {{ env "OIDC_TOKEN_URL" }}
 api_url = {{ env "OIDC_API_URL" }}

loki.yml.tmpl

@@ -34,6 +34,7 @@ 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"
 
@@ -52,7 +53,7 @@ schema_config:
     - from: 2020-10-24
       store: boltdb-shipper
       object_store: filesystem
-      schema: v13
+      schema: v11
       index:
         prefix: index_
         period: 24h
@@ -62,6 +63,7 @@ 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 }}
@@ -70,6 +72,7 @@ schema_config:
   configs:
   - from: 2020-11-25
     store: boltdb-shipper
+    object_store: aws
     schema: v11
     index:
       prefix: index_
@@ -86,7 +89,7 @@ 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_key" }}
+   secret_access_key: {{ secret "loki_aws_secret_access_key" }}
    bucketnames: {{ env "LOKI_BUCKET_NAMES" }}
    insecure: false
    sse_encryption: false
@@ -100,24 +103,19 @@ 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
@@ -125,6 +123,9 @@ 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

release/next

@@ -5,8 +5,3 @@ 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:
-  - 'metrics.traefik.example.org'
+  - 'example.org:8082'
   - 'node.monitoring.example.org'
   - 'cadvisor.monitoring.example.org'