Capture current Ansible control plane state

Commit the accumulated infrastructure work that was living only in the working tree: monitoring stack, emergency access/bot, gyro allocator, grimmory, adguard, backup audit and the OpenCode agent definitions. Also ignore Python bytecode, local archives and Nix/direnv artifacts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01GTocXkGUUazHdKKd3r9k71
2026-08-26 21:39:28 +03:00
parent 4bafa7d09e
commit c676be81ec
126 changed files with 10583 additions and 44 deletions
@@ -0,0 +1,6 @@
+---
+monitoring_exporter_install_node: true
+monitoring_exporter_install_smart: false
+monitoring_exporter_textfile_dir: /var/lib/node_exporter/textfile_collector
+monitoring_exporter_node_listen_address: 0.0.0.0:9100
+monitoring_exporter_smartctl_timer: "*:0/15"
@@ -0,0 +1,9 @@
+---
+- name: reload systemd
+  ansible.builtin.systemd:
+    daemon_reload: true
+
+- name: restart node exporter
+  ansible.builtin.systemd:
+    name: prometheus-node-exporter
+    state: restarted
@@ -0,0 +1,121 @@
+---
+- name: Install Node Exporter
+  ansible.builtin.apt:
+    name: prometheus-node-exporter
+    state: present
+  when: monitoring_exporter_install_node
+
+- name: Create Node Exporter textfile directory
+  ansible.builtin.file:
+    path: "{{ monitoring_exporter_textfile_dir }}"
+    state: directory
+    owner: root
+    group: root
+    mode: "0755"
+  when: monitoring_exporter_install_node
+
+- name: Create Node Exporter systemd override directory
+  ansible.builtin.file:
+    path: /etc/systemd/system/prometheus-node-exporter.service.d
+    state: directory
+    owner: root
+    group: root
+    mode: "0755"
+  when: monitoring_exporter_install_node
+
+- name: Configure Node Exporter collectors
+  ansible.builtin.copy:
+    dest: /etc/systemd/system/prometheus-node-exporter.service.d/override.conf
+    owner: root
+    group: root
+    mode: "0644"
+    content: |
+      [Service]
+      ExecStart=
+      ExecStart=/usr/bin/prometheus-node-exporter --web.listen-address={{ monitoring_exporter_node_listen_address }} --collector.systemd --collector.textfile.directory={{ monitoring_exporter_textfile_dir }}
+  when: monitoring_exporter_install_node
+  notify:
+    - reload systemd
+    - restart node exporter
+
+- name: Ensure Node Exporter is enabled and running
+  ansible.builtin.systemd:
+    name: prometheus-node-exporter
+    enabled: true
+    state: started
+  when: monitoring_exporter_install_node
+
+- name: Install SMART Exporter dependencies
+  ansible.builtin.apt:
+    name:
+      - jq
+      - smartmontools
+    state: present
+  when: monitoring_exporter_install_smart
+
+- name: Remove obsolete SMART Exporter container unit
+  ansible.builtin.systemd:
+    name: homelab-smartctl-exporter
+    enabled: false
+    state: stopped
+  failed_when: false
+  when: monitoring_exporter_install_smart
+
+- name: Install SMART metric collection script
+  ansible.builtin.template:
+    src: smartctl-metrics.sh.j2
+    dest: /usr/local/sbin/homelab-smartctl-metrics
+    owner: root
+    group: root
+    mode: "0755"
+  when: monitoring_exporter_install_smart
+
+- name: Install SMART metric collection service
+  ansible.builtin.copy:
+    dest: /etc/systemd/system/homelab-smartctl-metrics.service
+    owner: root
+    group: root
+    mode: "0644"
+    content: |
+      [Unit]
+      Description=Publish SMART metrics for Node Exporter
+
+      [Service]
+      Type=oneshot
+      ExecStart=/usr/local/sbin/homelab-smartctl-metrics
+  when: monitoring_exporter_install_smart
+  notify: reload systemd
+
+- name: Install SMART metric collection timer
+  ansible.builtin.copy:
+    dest: /etc/systemd/system/homelab-smartctl-metrics.timer
+    owner: root
+    group: root
+    mode: "0644"
+    content: |
+      [Unit]
+      Description=Collect SMART metrics every 15 minutes
+
+      [Timer]
+      OnBootSec=2m
+      OnUnitActiveSec=15m
+      Persistent=true
+
+      [Install]
+      WantedBy=multi-user.target
+  when: monitoring_exporter_install_smart
+  notify: reload systemd
+
+- name: Enable SMART metric collection timer
+  ansible.builtin.systemd:
+    name: homelab-smartctl-metrics.timer
+    daemon_reload: true
+    enabled: true
+    state: started
+  when: monitoring_exporter_install_smart
+
+- name: Run initial SMART metric collection
+  ansible.builtin.systemd:
+    name: homelab-smartctl-metrics.service
+    state: started
+  when: monitoring_exporter_install_smart
@@ -0,0 +1,30 @@
+#!/bin/sh
+# Managed by Ansible. Export SMART health to Node Exporter's textfile collector.
+set -eu
+
+METRICS_DIR="{{ monitoring_exporter_textfile_dir }}"
+METRICS_FILE="$METRICS_DIR/homelab_smartctl.prom"
+METRICS_TMP=$(mktemp "$METRICS_FILE.XXXXXX")
+
+trap 'rm -f "$METRICS_TMP"' EXIT
+
+printf '# HELP homelab_smart_device_healthy SMART overall health (1 healthy, 0 failed)\n' >> "$METRICS_TMP"
+printf '# TYPE homelab_smart_device_healthy gauge\n' >> "$METRICS_TMP"
+
+lsblk -dn -o NAME,TYPE | while read -r name type; do
+  [ "$type" = "disk" ] || continue
+  device="/dev/$name"
+  json=$(smartctl -a -j "$device" 2>/dev/null || true)
+  [ -n "$json" ] || continue
+
+  healthy=$(printf '%s' "$json" | jq -r 'if .smart_status.passed == true then 1 else 0 end')
+  temperature=$(printf '%s' "$json" | jq -r '.temperature.current // .nvme_smart_health_information_log.temperature // empty')
+  nvme_warning=$(printf '%s' "$json" | jq -r '.nvme_smart_health_information_log.critical_warning // empty')
+
+  printf 'homelab_smart_device_healthy{device="%s"} %s\n' "$name" "$healthy" >> "$METRICS_TMP"
+  [ -z "$temperature" ] || printf 'homelab_smart_temperature_celsius{device="%s"} %s\n' "$name" "$temperature" >> "$METRICS_TMP"
+  [ -z "$nvme_warning" ] || printf 'homelab_smart_nvme_critical_warning{device="%s"} %s\n' "$name" "$nvme_warning" >> "$METRICS_TMP"
+done
+
+chmod 0644 "$METRICS_TMP"
+mv "$METRICS_TMP" "$METRICS_FILE"