Another big round of refactoring and cleaning...

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

@@ -0,0 +1,21 @@
+# Health Check for Docker Containers
+
+## Description
+
+This Ansible role is designed to ensure the health of Docker containers running on a system. It includes a script that checks for unhealthy or exited Docker containers and sets up a systemd service and timer to regularly execute this check.
+
+## Files
+
+- `vars/main.yml`: Variable definitions for the script's directory.
+- `handlers/main.yml`: Handlers to reload and restart the systemd service and timer.
+- `files/sys-hlth-docker-container.sh`: The script that checks the container health.
+- `tasks/main.yml`: Tasks to create necessary directories, copy scripts, and create systemd service and timer.
+- `templates/sys-hlth-docker-container.cymais.service.j2`: Systemd service template.
+- `templates/sys-hlth-docker-container.cymais.timer.j2`: Systemd timer template.
+- `meta/main.yml`: Meta information declaring dependencies for the role.
+
+## Usage
+
+To use this role, include it in your playbook and set the `path_administrator_scripts` variable to the desired path for the health check scripts.
+
+Ensure that the `sys-alm-compose` dependency is satisfied for error notifications.

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

@@ -0,0 +1,5 @@
+- name: "reload sys-hlth-docker-container.cymais.service"
+  systemd:
+    name: sys-hlth-docker-container.cymais.service
+    enabled: yes
+    daemon_reload: yes

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

@@ -0,0 +1,24 @@
+---
+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: "CyMaIS NonCommercial License (CNCL)"
+  license_url: "https://s.veen.world/cncl"
+  min_ansible_version: "2.9"
+  platforms:
+    - name: Archlinux
+      versions: ["rolling"]
+  galaxy_tags:
+    - monitor
+    - docker
+    - containers
+    - health
+    - systemd
+  repository: "https://s.veen.world/cymais"
+  documentation: "https://s.veen.world/cymais"
+dependencies:
+  - sys-alm-compose

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

@@ -0,0 +1,36 @@
+- name: "create {{health_docker_container_folder}}"
+  file:
+    path: "{{health_docker_container_folder}}"
+    state: directory
+    mode: 0755
+  when: run_once_health_docker_container is not defined
+
+- name: create sys-hlth-docker-container.sh
+  copy:
+    src: sys-hlth-docker-container.sh
+    dest: "{{health_docker_container_folder}}sys-hlth-docker-container.sh"
+  when: run_once_health_docker_container is not defined
+
+- name: create sys-hlth-docker-container.cymais.service
+  template: 
+    src:  sys-hlth-docker-container.service.j2
+    dest: /etc/systemd/system/sys-hlth-docker-container.cymais.service
+  notify: reload sys-hlth-docker-container.cymais.service
+  when: run_once_health_docker_container is not defined
+
+- name: "set 'service_name' to '{{ role_name }}'"
+  set_fact:
+    service_name: "{{ role_name }}"
+  when: run_once_health_docker_container is not defined
+
+- name: "include role for sys-timer for {{service_name}}"
+  include_role:
+    name: sys-timer
+  vars:
+    on_calendar:  "{{on_calendar_health_docker_container}}"
+  when: run_once_health_docker_container is not defined
+
+- name: run the health_docker_container tasks once
+  set_fact:
+    run_once_health_docker_container: true
+  when: run_once_health_docker_container is not defined

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

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

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

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