Refactor systemctl services and categories due to alarm bugs

This commit restructures systemctl service definitions and category mappings.

Motivation: Alarm-related bugs revealed inconsistencies in service and role handling.

Preparation step: lays the groundwork for fixing the alarm issues by aligning categories, roles, and service templates.

roles/sys-ctl-hlth-docker-container/README.md

@@ -0,0 +1,26 @@
+# Docker Container Health Check
+
+## Description
+
+This role monitors the health status of Docker containers on the system. It detects containers that are either **unhealthy** or have **exited with a non-zero code**, and triggers alerts if issues are found.
+
+## Overview
+
+The role installs a health check script along with a `systemd` service and timer to run these checks at scheduled intervals.  
+If unhealthy or failed containers are detected, the configured failure notifier (via `sys-ctl-alm-compose`) is triggered.
+
+## Purpose
+
+The primary purpose of this role is to ensure that Docker-based services remain operational. By automatically monitoring container health, it enables administrators to react quickly to failures, reducing downtime and preventing unnoticed service degradation.
+
+## Features
+
+- **Automated Health Checks:** Detects containers in `unhealthy` state or exited with non-zero exit codes.
+- **Systemd Integration:** Installs a one-shot service and timer to run health checks on a schedule.
+- **Alerting Support:** Works with the [`sys-ctl-alm-compose`](../sys-ctl-alm-compose/README.md) role for failure notifications.
+- **Configurable Script Location:** Controlled via the `PATH_ADMINISTRATOR_SCRIPTS` variable.
+
+## Further Resources
+
+- [Docker Health Checks Documentation](https://docs.docker.com/engine/reference/run/#healthcheck)
+- [Systemd Timers Documentation](https://www.freedesktop.org/software/systemd/man/systemd.timer.html)

roles/sys-ctl-hlth-docker-container/files/sys-ctl-hlth-docker-container.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+docker_ps_grep_unhealthy="$(docker ps --filter health=unhealthy --format '{{.Names}}')"
+docker_ps_grep_exited="$(docker ps --filter status=exited --format '{{.ID}}')"
+
+exitcode=0
+
+if [ -n "$docker_ps_grep_unhealthy" ]; then 
+   echo "Some docker containers are unhealthy: $docker_ps_grep_unhealthy"
+   exitcode=1
+fi
+
+if [ -n "$docker_ps_grep_exited" ]; then 
+   for container_id in $docker_ps_grep_exited
+   do
+       container_exit_code="$(docker inspect "$container_id" --format='{{.State.ExitCode}}')"
+       container_name="$(docker inspect "$container_id" --format='{{.Name}}')"
+       container_name="${container_name#/}" # Entfernt das führende '/'
+       if [ "$container_exit_code" -ne "0" ]; then
+           echo "Container $container_name exited with code $container_exit_code"
+           exitcode=2
+       fi
+   done
+fi
+
+if [ "$exitcode" -ne "0" ]; then 
+   exit $exitcode
+fi
+
+echo "All docker containers are healthy."
+exit

roles/sys-ctl-hlth-docker-container/handlers/main.yml

@@ -0,0 +1,5 @@
+- name: "reload sys-ctl-hlth-docker-container service"
+  systemd:
+    name: sys-ctl-hlth-docker-container{{ SYS_SERVICE_SUFFIX }}
+    enabled: yes
+    daemon_reload: yes

roles/sys-ctl-hlth-docker-container/meta/main.yml

@@ -0,0 +1,21 @@
+galaxy_info:
+  author: "Kevin Veen-Birkenbach"
+  description: "Checks Docker containers for unhealthy or exited states and alerts on any issues."
+  company: |
+    Kevin Veen-Birkenbach  
+    Consulting & Coaching Solutions  
+    https://www.veen.world
+  license: "Infinito.Nexus NonCommercial License"
+  license_url: "https://s.infinito.nexus/license"
+  min_ansible_version: "2.9"
+  platforms:
+  - name: Archlinux
+    versions: ["rolling"]
+  galaxy_tags:
+  - monitor
+  - docker
+  - containers
+  - health
+  - systemd
+  repository: "https://s.infinito.nexus/code"
+  documentation: "https://docs.infinito.nexus"

roles/sys-ctl-hlth-docker-container/tasks/01_core.yml

@@ -0,0 +1,31 @@
+- name: Include dependency 'sys-ctl-alm-compose'
+  include_role:
+    name: sys-ctl-alm-compose
+  when: run_once_sys_ctl_alm_compose is not defined
+  
+- name: "create {{health_docker_container_folder}}"
+  file:
+    path: "{{health_docker_container_folder}}"
+    state: directory
+    mode: "0755"
+
+- name: create sys-ctl-hlth-docker-container.sh
+  copy:
+    src: sys-ctl-hlth-docker-container.sh
+    dest: "{{health_docker_container_folder}}sys-ctl-hlth-docker-container.sh"
+
+- name: create sys-ctl-hlth-docker-container{{ SYS_SERVICE_SUFFIX }}
+  template:
+    src: sys-ctl-hlth-docker-container.service.j2
+    dest: /etc/systemd/system/sys-ctl-hlth-docker-container{{ SYS_SERVICE_SUFFIX }}
+  notify: reload sys-ctl-hlth-docker-container service
+
+- name: "set 'service_name' to '{{ role_name }}'"
+  set_fact:
+    service_name: "{{ role_name }}"
+
+- name: "include role for sys-timer for {{ service_name }}"
+  include_role:
+    name: sys-timer
+  vars:
+    on_calendar: "{{SYS_SCHEDULE_HEALTH_DOCKER_CONTAINER}}"

roles/sys-ctl-hlth-docker-container/tasks/main.yml

@@ -0,0 +1,4 @@
+- block:
+    - include_tasks: 01_core.yml
+    - include_tasks: utils/run_once.yml
+  when: run_once_sys_ctl_hlth_docker_container is not defined

roles/sys-ctl-hlth-docker-container/templates/sys-ctl-hlth-docker-container.service.j2

@@ -0,0 +1,7 @@
+[Unit]
+Description=Checking docker health
+OnFailure=sys-ctl-alm-compose.{{ SOFTWARE_NAME }}@%n.service
+
+[Service]
+Type=oneshot
+ExecStart=/bin/bash {{health_docker_container_folder}}sys-ctl-hlth-docker-container.sh

roles/sys-ctl-hlth-docker-container/vars/main.yml

@@ -0,0 +1 @@
+health_docker_container_folder: '{{ PATH_ADMINISTRATOR_SCRIPTS }}sys-ctl-hlth-docker-container/'