add: proxmox_vmid in the inventory

.gitignore

@@ -2,3 +2,5 @@
 **/.terraform*
 *.tfstate*
 *credentials.auto.tfvars
+# Bruno
+.bruno

ansible/opnsense/inventory.yml

@@ -0,0 +1,20 @@
+---
+all:
+  children:
+    opnsense:
+      vars:
+        ansible_connection: local
+      children:
+        opnsense_backup:
+          hosts:
+            cerbere-head2:
+              ansible_host: 192.168.88.3
+              main_role: BACKUP
+              hypervisor: TrueNAS
+        opnsense_master:
+          hosts:
+            cerbere-head1:
+              ansible_host: 192.168.88.2
+              main_role: MASTER
+              hypervisor: Proxmox
+              proxmox_vmid: 122

ansible/proxmox/update_proxmox.yml

@@ -0,0 +1,204 @@
+---
+- name: Check Proxmox VE cluster health
+  hosts: nodes
+  any_errors_fatal: true
+  become: true
+  tasks:
+
+    - delegate_to: "{{ groups['nodes'][0] }}"
+      run_once: true
+      block:
+
+        - name: Verify cluster quorum
+          ansible.builtin.command: pvecm status
+          register: quorum_status
+          changed_when: false
+          failed_when: quorum_status.stdout is not search('Quorate:\\s*Yes')
+          
+        - name: Verify Ceph health
+          ansible.builtin.command: ceph health
+          register: ceph_health
+          changed_when: false
+          failed_when: "'HEALTH_OK' not in ceph_health.stdout"
+
+      rescue:
+
+        - name: Send no ready notification
+          ansible.builtin.uri:
+            url: "{{  ntfy_url }}/{{ ntfy_topic }}"
+            method: POST
+            user: "{{ ntfy_user }}"
+            password: "{{ lookup('env', 'NTFY_PASSWORD') }}"
+            force_basic_auth: true
+            body: No updates have been rolled out
+            headers:
+              Title: "Proxmox VE Not Ready for Updates"
+              Priority: "default"
+              Tags: "x"
+          delegate_to: localhost
+          become: false
+          run_once: true
+          when: ntfy_url is defined
+
+        - ansible.builtin.fail:
+            msg: "Update aborted"
+
+
+- name: Rolling update of Proxmox VE cluster
+  hosts: nodes
+  serial: 1
+  any_errors_fatal: true
+  become: true
+  tasks:
+
+    - block:
+
+        - name: Refresh repositories
+          ansible.builtin.apt:
+            update_cache: true
+
+        - name: Check if updates are available
+          ansible.builtin.apt:
+            upgrade: dist
+          check_mode: true
+          register: apt_check
+
+        - name: Proceed if updates are available
+          when: apt_check.changed
+          block:         
+
+          - name: Get version before upgrade
+            ansible.builtin.shell: pveversion | awk -F'/' '{print $2}'
+            register: pve_old_version
+            changed_when: false
+
+          - name: Enable maintenance mode
+            ansible.builtin.command: >
+              ha-manager crm-command node-maintenance enable {{ inventory_hostname_short }}
+
+          - name: Wait for LXCs to leave node
+            ansible.builtin.shell: |
+              pct list | awk 'NR>1 && $2=="running" {count++} END {print count+0}'
+            register: lxc_count
+            changed_when: false
+            until: lxc_count.stdout | int == 0
+            retries: 60
+            delay: 15
+
+          - name: Wait for VMs to leave node
+            ansible.builtin.shell: |
+              qm list | awk 'NR>1 && $3=="running" {count++} END {print count+0}'
+            register: vm_count
+            changed_when: false
+            until: vm_count.stdout | int == 0
+            retries: 60
+            delay: 15
+
+          - name: Pause 15s 
+            ansible.builtin.pause:
+              seconds: 15
+
+          - name: Update packages
+            ansible.builtin.apt:
+              upgrade: full
+              autoremove: true
+              autoclean: true
+              
+          - name: Disable Ceph rebalancing
+            ansible.builtin.command: ceph osd set noout
+
+          - name: Reboot node
+            ansible.builtin.reboot:
+              reboot_timeout: 900
+              post_reboot_delay: 30
+              
+          - name: Enable Ceph rebalancing
+            ansible.builtin.command: ceph osd unset noout
+
+          - name: Disable maintenance mode
+            ansible.builtin.command: >
+              ha-manager crm-command node-maintenance disable {{ inventory_hostname_short }}
+
+          - name: Get version after upgrade
+            ansible.builtin.shell: pveversion | awk -F'/' '{print $2}'
+            register: pve_new_version
+            changed_when: false
+
+          - name: Save update report
+            ansible.builtin.set_fact:
+              update_report:
+                old: "{{ pve_old_version.stdout }}"
+                new: "{{ pve_new_version.stdout }}"
+
+          - name: Wait for Ceph to be healthy
+            ansible.builtin.command: ceph health
+            register: ceph_status
+            changed_when: false
+            until: "'HEALTH_OK' in ceph_status.stdout"
+            retries: 60
+            delay: 15
+            delegate_to: "{{ groups['nodes'][0] }}"
+          
+      rescue:
+
+        - name: Send failure notification
+          ansible.builtin.uri:
+            url: "{{  ntfy_url }}/{{ ntfy_topic }}"
+            method: POST
+            user: "{{ ntfy_user }}"
+            password: "{{ lookup('env', 'NTFY_PASSWORD') }}"
+            force_basic_auth: true
+            body: Update failed on {{ inventory_hostname_short }}
+            headers:
+              Title: "Proxmox VE Update Failed"
+              Priority: "high"
+              Tags: "x"
+          delegate_to: localhost
+          become: false
+          run_once: true
+          when: ntfy_url is defined
+
+        - ansible.builtin.fail:
+            msg: "Update aborted"
+
+
+- name: Send notification
+  hosts: localhost
+  tasks:
+
+    - name: Determine if updates occurred
+      ansible.builtin.set_fact:
+        updates_performed: "{{ groups['nodes'] | map('extract', hostvars) | selectattr('update_report', 'defined') | list | length > 0 }}"
+
+    - name: Send success notification
+      ansible.builtin.uri:
+        url: "{{  ntfy_url }}/{{ ntfy_topic }}"
+        method: POST
+        user: "{{ ntfy_user }}"
+        password: "{{ lookup('env', 'NTFY_PASSWORD') }}"
+        force_basic_auth: true
+        body: |
+          {% set updated_nodes = [] %}
+          {% for node in groups['nodes'] %}
+            {% if hostvars[node].update_report is defined %}
+              {% set _ = updated_nodes.append(node) %}
+            {% endif %}
+          {% endfor %}
+          {% if not updates_performed %}
+          No updates available on the cluster.
+          {% else %}
+          The following nodes were updated:
+          {% for node in updated_nodes %}
+          {% if hostvars[node].update_report.old == hostvars[node].update_report.new %}
+          - {{ hostvars[node].inventory_hostname_short }}: version {{ hostvars[node].update_report.old }} (unchanged)
+          {% else %}
+          - {{ hostvars[node].inventory_hostname_short }}: version {{ hostvars[node].update_report.old }} → {{ hostvars[node].update_report.new }}
+          {% endif %}
+          {% endfor %}
+          {% endif %}
+        headers:
+          Title: "Proxmox VE Update Report"
+          Priority: "{{ 'min' if not updates_performed else 'default' }}"
+          Tags: "white_check_mark"
+      when: ntfy_url is defined
+

opnsense/10-wan

@@ -0,0 +1,105 @@
+#!/usr/local/bin/php
+<?php
+/**
+ * Author 2025 Etienne Girault <etienne.girault@gmail.com>
+ * OPNsense CARP event script
+ * - Enables/disables the WAN interface only when needed
+ * - Avoids reapplying config when CARP triggers multiple times
+ */
+
+require_once("config.inc");
+require_once("interfaces.inc");
+require_once("util.inc");
+require_once("system.inc");
+
+// Read CARP event arguments
+$subsystem = !empty($argv[1]) ? $argv[1] : '';
+$type = !empty($argv[2]) ? $argv[2] : '';
+
+// Accept only MASTER/BACKUP events
+if (!in_array($type, ['MASTER', 'BACKUP'])) {
+    // Ignore CARP INIT, DEMOTED, etc.
+    exit(0);
+}
+
+// Validate subsystem name format, expected pattern: <ifname>@<vhid>
+if (!preg_match('/^[a-z0-9_]+@\S+$/i', $subsystem)) {
+    log_error("Malformed subsystem argument: '{$subsystem}'.");
+    exit(0);
+}
+
+// Only react to the primary VHID
+list($vhid, $iface) = explode('@', $subsystem);
+$primary_vhid = '1'; //
+
+if ($vhid !== $primary_vhid) {
+    exit(0); // ignore events from other VHIDs
+}
+
+// Interface key to manage
+$ifkey = 'wan';
+$real_if = get_real_interface('wan');
+// Fallback gateway name
+$gw_name = 'LAN_GW';
+// Determine whether WAN interface is currently enabled
+$ifkey_enabled = !empty($config['interfaces'][$ifkey]['enable']) ? true : false;
+// Lock file to prevent interface flapping
+$lock_file = '/tmp/carp_wan_disable_lock';
+$lock_default_age = 5;
+$lock_max_age = 10;
+
+// MASTER event
+if ($type === "MASTER") {
+    // Enable WAN only if it's currently disabled
+    if (!$ifkey_enabled) {
+        // Check if lock file is present
+        if (file_exists($lock_file)) {
+            $lock_age = time() - (int)file_get_contents($lock_file);
+            if ($lock_age < $lock_max_age) {
+                log_msg("CARP event: WAN disable lock present ({$lock_age}s old), waiting...");
+                $elapsed = 0;
+                while (file_exists($lock_file) && $elapsed < 5000) {
+                    usleep(500000);
+                    $elapsed += 500;
+                }
+            } else {
+                log_msg("CARP event: removing stale WAN disable lock.");
+                @unlink($lock_file);
+            }
+        }
+        log_msg("CARP event: switching to '$type', enabling interface '$ifkey'.", LOG_WARNING);
+        $config['interfaces'][$ifkey]['enable'] = '1';
+        write_config("enable interface '$ifkey' due CARP event '$type'", false);
+        interface_configure(false, $ifkey, false, false);
+    } else {
+        log_msg("CARP event: already 'MASTER' for interface '$ifkey', nothing to do.");
+    }
+
+// BACKUP event
+} else {
+    // Disable WAN only if it's currently enabled
+    if ($ifkey_enabled) {
+        log_msg("CARP event: switching to '$type', disabling interface '$ifkey'.", LOG_WARNING);
+        unset($config['interfaces'][$ifkey]['enable']);
+        write_config("disable interface '$ifkey' due CARP event '$type'", false);
+        interface_configure(false, $ifkey, false, false);
+        // Remove WAN default gateway
+        mwexec("/sbin/route delete default");
+        foreach ($config['OPNsense']['Gateways']['gateway_item'] as $gw) {
+            if ($gw['name'] === $gw_name) {
+                $gw_ip = $gw['gateway'];
+                break;
+            }
+        }
+        // Shutdown WAN interface
+        mwexec("/sbin/ifconfig {$real_if} down")
+        // Add fallback default gateway
+        mwexec("/sbin/route add default {$gw_ip}");
+        // Create lock file
+        file_put_contents($lock_file, time());
+        sleep($lock_default_age);
+        @unlink($lock_file);
+    } else {
+        log_msg("CARP event: already '$type' for interface '$ifkey', nothing to do.");
+    }
+}