chore(deps): update docker docker tag to v29.9.1

Reviewed-on: #48
Reviewed-by: fauno <fauno@sutty.coop.ar>

.env.sample

@@ -133,6 +133,3 @@ SECRET_BASIC_AUTH_VERSION=v1
 
 # Node memory usage alert will trigger when memory usage is above the given number in percent
 #ALERT_NODE_MEMORY_USAGE=85
-
-# Traefik apdex alert will trigger when the apdex score of a service drops below the given number. Services receiving fewer than 10 requests per 10m are ignored
-#ALERT_TRAEFIK_APDEX=0.5

README.md

@@ -174,7 +174,6 @@ It is possible to enable the following alerts, by uncommenting the corresponding
 
 - node disk space: `ALERT_NODE_DISK_SPACE_LEFT`
 - node memory usage: `ALERT_NODE_MEMORY_USAGE`
-- traefik apdex: `ALERT_TRAEFIK_APDEX`
 
 ## smart monitoring
 

abra.sh

@@ -9,8 +9,7 @@ export LOKI_YML_VERSION=v3
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
-export GF_ALERTS_NODE_VERSION=v3
-export GF_ALERTS_TRAEFIK_VERSION=v1
+export GF_ALERTS_NODE_VERSION=v4
 export CONFIG_ALLOY_VERSION=v3
 
 # migrates secrets from old names to new names by reading values from the

alerts/node.yml.tmpl

@@ -87,7 +87,7 @@ groups:
           datasourceUid: PBFA97CFB590B2093
           model:
             editorMode: code
-            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
+            expr: 100 - ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100)
             instant: true
             intervalMs: 1000
             legendFormat: __auto

alerts/traefik.yml.tmpl

@@ -1,81 +0,0 @@
-apiVersion: 1
-
-# List of alert rule UIDs that should be deleted
-deleteRules:
-  {{ if not (env "ALERT_TRAEFIK_APDEX") }}
-  - orgId: 1
-    uid: coopcloud_traefik_apdex
-  {{ end }}
-
-groups:
-- orgId: 1
-  name: traefik
-  folder: recipes
-  interval: 5m
-  rules:
-    {{ if (env "ALERT_TRAEFIK_APDEX") }}
-    - uid: coopcloud_traefik_apdex
-      title: Apdex
-      condition: B
-      data:
-        - refId: A
-          relativeTimeRange:
-            from: 600
-            to: 0
-          datasourceUid: PBFA97CFB590B2093
-          model:
-            editorMode: code
-            # apdex = (satisfied + tolerating / 2) / total, which reduces to
-            # (le=0.3 + le=1.2) / 2 / total because the le=1.2 bucket is
-            # cumulative and therefore already contains the satisfied requests.
-            # services with less than 10 requests per 10m are ignored.
-            expr: |-
-              ((sum(rate(traefik_service_request_duration_seconds_bucket{le="0.3",code="200"}[5m])) by (service) +
-               sum(rate(traefik_service_request_duration_seconds_bucket{le="1.2",code="200"}[5m])) by (service)) / 2 /
-               sum(rate(traefik_service_request_duration_seconds_count{code="200"}[5m])) by (service))
-              and on(service)
-              (
-                sum(increase(traefik_service_request_duration_seconds_count{code="200"}[10m])) by (service) >= 10
-              )
-            instant: true
-            intervalMs: 1000
-            legendFormat: __auto
-            maxDataPoints: 43200
-            range: false
-            refId: A
-        - refId: B
-          relativeTimeRange:
-            from: 600
-            to: 0
-          datasourceUid: __expr__
-          model:
-            conditions:
-                - evaluator:
-                    params:
-                        - {{ env "ALERT_TRAEFIK_APDEX" }}
-                    type: lt
-                  operator:
-                    type: and
-                  query:
-                    params: []
-                  reducer:
-                    params: []
-                    type: avg
-                  type: query
-            datasource:
-                type: __expr__
-                uid: __expr__
-            expression: A
-            intervalMs: 1000
-            maxDataPoints: 43200
-            refId: B
-            type: threshold
-      noDataState: OK
-      execErrState: Error
-      for: 10m
-      annotations:
-        description: ""
-        runbook_url: ""
-        summary: Apdex for {{`{{ $labels.service }}`}} is below {{ env "ALERT_TRAEFIK_APDEX" }} (currently at {{`{{ printf "%.2f" (index $values "A").Value }}`}})
-      isPaused: false
-    {{ end }}

compose.docker-events.yml

@@ -1,7 +1,7 @@
 version: "3.8"
 services:
   docker-events:
-    image: docker:29.8.1-cli
+    image: docker:29.9.1-cli
     command: >
       docker events
       --format '{{json .}}'

compose.grafana.yml

@@ -24,8 +24,6 @@ services:
         target: /var/lib/grafana/dashboards/backup.json
       - source: gf_alerts_node
         target: /etc/grafana/provisioning/alerting/node.yml
-      - source: gf_alerts_traefik
-        target: /etc/grafana/provisioning/alerting/traefik.yml
     networks:
       - proxy
       - internal
@@ -36,7 +34,6 @@ services:
       - GF_INSTALL_PLUGINS
       - ALERT_NODE_DISK_SPACE_LEFT
       - ALERT_NODE_MEMORY_USAGE
-      - ALERT_TRAEFIK_APDEX
     deploy:
       labels:
         - "traefik.enable=true"
@@ -80,10 +77,6 @@ configs:
     template_driver: golang
     name: ${STACK_NAME}_gf_alerts_node_${GF_ALERTS_NODE_VERSION}
     file: alerts/node.yml.tmpl
-  gf_alerts_traefik:
-    template_driver: golang
-    name: ${STACK_NAME}_gf_alerts_traefik_${GF_ALERTS_TRAEFIK_VERSION}
-    file: alerts/traefik.yml.tmpl
 
 volumes:
   grafana-data: