Initial cluster configuration

ansible.cfg

@@ -0,0 +1,18 @@
+[defaults]
+inventory = inventory/hosts.yml
+remote_user = root
+host_key_checking = False
+retry_files_enabled = False
+gathering = smart
+fact_caching = jsonfile
+fact_caching_connection = /tmp/ansible_facts
+fact_caching_timeout = 86400
+stdout_callback = yaml
+forks = 10
+
+[privilege_escalation]
+become = False
+
+[ssh_connection]
+pipelining = True
+ssh_args = -o ControlMaster=auto -o ControlPersist=60s

inventory/group_vars/all.yml

@@ -0,0 +1,12 @@
+---
+ansible_python_interpreter: /usr/bin/python3
+timezone: America/New_York
+nas_ip: 192.168.1.251
+nas_media_share: /volume1/Media
+nas_downloads_share: /volume1/Downloads
+nas_docker_share: /volume1/docker
+ntfy_server: https://ntfy.3ddbrewery.com
+ntfy_autoheal_topic: autoheal-proxmox
+ntfy_watchtower_topic: watchtower-proxmox
+docker_compose_version: "3.8"
+docker_data_dir: /home/docker/appdata

inventory/hosts.yml

@@ -0,0 +1,65 @@
+all:
+  children:
+    proxmox_nodes:
+      hosts:
+        pve2:
+          ansible_host: 192.168.1.3
+          ansible_user: root
+        pve-dell:
+          ansible_host: 192.168.1.4
+          ansible_user: root
+    vms:
+      hosts:
+        replicant:
+          ansible_host: 192.168.1.80
+          ansible_user: maddox
+          ansible_become: yes
+          docker_appdata: /home/maddox/docker/appdata
+        databases:
+          ansible_host: 192.168.1.81
+          ansible_user: root
+        immich:
+          ansible_host: 192.168.1.82
+          ansible_user: root
+    lxcs:
+      hosts:
+        media-transcode:
+          ansible_host: 192.168.1.120
+          ansible_user: root
+        network-services:
+          ansible_host: 192.168.1.121
+          ansible_user: root
+        download-stack:
+          ansible_host: 192.168.1.122
+          ansible_user: root
+        docker666:
+          ansible_host: 192.168.1.123
+          ansible_user: root
+          docker_appdata: /root/docker/appdata
+        tailscale-home:
+          ansible_host: 192.168.1.124
+          ansible_user: root
+    infrastructure:
+      hosts:
+        dns-lxc:
+          ansible_host: 192.168.1.125
+          ansible_user: root
+    legacy:
+      hosts:
+        nas:
+          ansible_host: 192.168.1.251
+          ansible_user: maddox
+          ansible_port: 44822
+        alien:
+          ansible_host: 192.168.1.252
+          ansible_user: maddox
+    docker_hosts:
+      children:
+        vms:
+        lxcs:
+    all_managed:
+      children:
+        proxmox_nodes:
+        vms:
+        lxcs:
+        infrastructure:

playbooks/check-status.yml

@@ -0,0 +1,26 @@
+---
+- name: Check cluster status
+  hosts: all_managed
+  become: yes
+  gather_facts: yes
+  
+  tasks:
+    - name: Get disk usage
+      shell: df -h / | tail -1 | awk '{print $5}'
+      register: disk_usage
+      changed_when: false
+    
+    - name: Get memory usage
+      shell: free -m | awk '/^Mem:/ {printf "%.0f%%", $3/$2 * 100}'
+      register: memory_usage
+      changed_when: false
+    
+    - name: Get container count
+      shell: docker ps -q 2>/dev/null | wc -l
+      register: container_count
+      changed_when: false
+      failed_when: false
+    
+    - name: Display status
+      debug:
+        msg: "{{ inventory_hostname }}: Disk={{ disk_usage.stdout }} Mem={{ memory_usage.stdout }} Containers={{ container_count.stdout | default('N/A') }}"

playbooks/deploy-utils.yml

@@ -0,0 +1,28 @@
+---
+- name: Deploy standardized utils stack
+  hosts: docker_hosts
+  become: yes
+  gather_facts: yes
+  vars:
+    utils_path: /home/docker/appdata/utils
+    host_ip: "{{ ansible_default_ipv4.address }}"
+    host_name: "{{ inventory_hostname }}"
+  
+  tasks:
+    - name: Create utils directory
+      file:
+        path: "{{ utils_path }}"
+        state: directory
+        mode: '0755'
+    
+    - name: Create .env file
+      copy:
+        dest: "{{ utils_path }}/.env"
+        content: |
+          HOST_IP={{ host_ip }}
+          HOST_NAME={{ host_name }}
+        mode: '0600'
+    
+    - name: Display completion
+      debug:
+        msg: "Utils directory created at {{ utils_path }} for {{ inventory_hostname }}"

playbooks/docker-prune.yml

@@ -0,0 +1,19 @@
+---
+- name: Docker cleanup on all hosts
+  hosts: docker_hosts
+  become: yes
+  gather_facts: no
+  
+  tasks:
+    - name: Prune with docker CLI
+      shell: |
+        docker image prune -f
+        docker network prune -f
+        docker builder prune -f
+      register: prune_result
+      changed_when: "'Total reclaimed space' in prune_result.stdout"
+    
+    - name: Show prune output
+      debug:
+        var: prune_result.stdout_lines
+      when: prune_result.stdout_lines | length > 0

playbooks/restart-utils.yml

@@ -0,0 +1,27 @@
+---
+- name: Restart utils stack on Docker hosts
+  hosts: docker_hosts
+  become: yes
+  gather_facts: no
+  
+  tasks:
+    - name: Set utils path
+      set_fact:
+        utils_path: "{{ docker_appdata | default('/home/docker/appdata') }}/utils"
+    
+    - name: Check if utils compose file exists
+      stat:
+        path: "{{ utils_path }}/docker-compose.yml"
+      register: compose_file
+    
+    - name: Restart utils stack
+      shell: docker compose pull && docker compose up -d --force-recreate
+      args:
+        chdir: "{{ utils_path }}"
+      when: compose_file.stat.exists
+      register: restart_result
+    
+    - name: Skip if no utils stack
+      debug:
+        msg: "{{ inventory_hostname }}: No utils stack found at {{ utils_path }}"
+      when: not compose_file.stat.exists

playbooks/update-all.yml

@@ -0,0 +1,38 @@
+---
+- name: Update all Docker hosts
+  hosts: docker_hosts
+  become: yes
+  gather_facts: yes
+  vars:
+    reboot: false
+  
+  tasks:
+    - name: Update apt cache
+      apt:
+        update_cache: yes
+        cache_valid_time: 3600
+      
+    - name: Upgrade all packages
+      apt:
+        upgrade: dist
+        autoremove: yes
+        autoclean: yes
+      register: upgrade_result
+    
+    - name: Check if reboot is required
+      stat:
+        path: /var/run/reboot-required
+      register: reboot_required
+    
+    - name: Notify if reboot needed
+      debug:
+        msg: "{{ inventory_hostname }} requires a reboot"
+      when: reboot_required.stat.exists
+    
+    - name: Reboot if required and allowed
+      reboot:
+        msg: "Ansible triggered reboot after updates"
+        reboot_timeout: 300
+      when: 
+        - reboot_required.stat.exists
+        - reboot | bool