From 7d673cbee9041d760b83eadb8002be3bbe4ed32d Mon Sep 17 00:00:00 2001
From: Erich Blume <blume.erich@gmail.com>
Date: Sat, 17 Jan 2026 21:09:20 -0800
Subject: [PATCH] Add zot_metrics role for Prometheus monitoring

Collects zot_up metric via textfile collector every 60 seconds.
Additional metrics can be added later if zot exposes them.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 ansible/playbooks/indri.yml                   |  2 +
 ansible/roles/zot_metrics/defaults/main.yml   |  6 +++
 ansible/roles/zot_metrics/handlers/main.yml   |  6 +++
 ansible/roles/zot_metrics/tasks/main.yml      | 43 +++++++++++++++++++
 .../templates/zot-metrics.plist.j2            | 21 +++++++++
 .../zot_metrics/templates/zot-metrics.sh.j2   | 25 +++++++++++
 6 files changed, 103 insertions(+)
 create mode 100644 ansible/roles/zot_metrics/defaults/main.yml
 create mode 100644 ansible/roles/zot_metrics/handlers/main.yml
 create mode 100644 ansible/roles/zot_metrics/tasks/main.yml
 create mode 100644 ansible/roles/zot_metrics/templates/zot-metrics.plist.j2
 create mode 100644 ansible/roles/zot_metrics/templates/zot-metrics.sh.j2

diff --git a/ansible/playbooks/indri.yml b/ansible/playbooks/indri.yml
index 5796b52..570b60f 100644
--- a/ansible/playbooks/indri.yml
+++ b/ansible/playbooks/indri.yml
@@ -101,6 +101,8 @@
       tags: devpi_metrics
     - role: zot
       tags: zot
+    - role: zot_metrics
+      tags: zot_metrics
     - role: plex_metrics
       tags: plex_metrics
     - role: postgresql
diff --git a/ansible/roles/zot_metrics/defaults/main.yml b/ansible/roles/zot_metrics/defaults/main.yml
new file mode 100644
index 0000000..3280b20
--- /dev/null
+++ b/ansible/roles/zot_metrics/defaults/main.yml
@@ -0,0 +1,6 @@
+---
+zot_metrics_url: http://localhost:5050/v2/_catalog
+zot_metrics_dir: /opt/homebrew/var/node_exporter/textfile
+zot_metrics_script: /Users/erichblume/bin/zot-metrics
+zot_metrics_interval: 60  # seconds between metric collection
+zot_metrics_log_dir: /opt/homebrew/var/log
diff --git a/ansible/roles/zot_metrics/handlers/main.yml b/ansible/roles/zot_metrics/handlers/main.yml
new file mode 100644
index 0000000..44fe49b
--- /dev/null
+++ b/ansible/roles/zot_metrics/handlers/main.yml
@@ -0,0 +1,6 @@
+---
+- name: Reload zot-metrics
+  ansible.builtin.shell: |
+    launchctl unload ~/Library/LaunchAgents/mcquack.eblume.zot-metrics.plist 2>/dev/null || true
+    launchctl load ~/Library/LaunchAgents/mcquack.eblume.zot-metrics.plist
+  changed_when: true
diff --git a/ansible/roles/zot_metrics/tasks/main.yml b/ansible/roles/zot_metrics/tasks/main.yml
new file mode 100644
index 0000000..9b43125
--- /dev/null
+++ b/ansible/roles/zot_metrics/tasks/main.yml
@@ -0,0 +1,43 @@
+---
+- name: Ensure metrics directory exists
+  ansible.builtin.file:
+    path: "{{ zot_metrics_dir }}"
+    state: directory
+    mode: '0755'
+
+- name: Ensure log directory exists
+  ansible.builtin.file:
+    path: "{{ zot_metrics_log_dir }}"
+    state: directory
+    mode: '0755'
+
+- name: Ensure bin directory exists
+  ansible.builtin.file:
+    path: "{{ zot_metrics_script | dirname }}"
+    state: directory
+    mode: '0755'
+
+- name: Deploy zot-metrics script
+  ansible.builtin.template:
+    src: zot-metrics.sh.j2
+    dest: "{{ zot_metrics_script }}"
+    mode: '0755'
+
+- name: Deploy zot-metrics LaunchAgent plist
+  ansible.builtin.template:
+    src: zot-metrics.plist.j2
+    dest: ~/Library/LaunchAgents/mcquack.eblume.zot-metrics.plist
+    mode: '0644'
+  notify: Reload zot-metrics
+
+- name: Check if zot-metrics LaunchAgent is loaded
+  ansible.builtin.command: launchctl list mcquack.eblume.zot-metrics
+  register: zot_metrics_launchctl_check
+  changed_when: false
+  failed_when: false
+
+- name: Load zot-metrics LaunchAgent if not loaded
+  ansible.builtin.command: launchctl load ~/Library/LaunchAgents/mcquack.eblume.zot-metrics.plist
+  when: zot_metrics_launchctl_check.rc != 0
+  changed_when: true
+  failed_when: false
diff --git a/ansible/roles/zot_metrics/templates/zot-metrics.plist.j2 b/ansible/roles/zot_metrics/templates/zot-metrics.plist.j2
new file mode 100644
index 0000000..6efae24
--- /dev/null
+++ b/ansible/roles/zot_metrics/templates/zot-metrics.plist.j2
@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- {{ ansible_managed }} -->
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>Label</key>
+	<string>mcquack.eblume.zot-metrics</string>
+	<key>ProgramArguments</key>
+	<array>
+		<string>{{ zot_metrics_script }}</string>
+	</array>
+	<key>StartInterval</key>
+	<integer>{{ zot_metrics_interval }}</integer>
+	<key>RunAtLoad</key>
+	<true/>
+	<key>StandardErrorPath</key>
+	<string>{{ zot_metrics_log_dir }}/mcquack.zot-metrics.err.log</string>
+	<key>StandardOutPath</key>
+	<string>{{ zot_metrics_log_dir }}/mcquack.zot-metrics.out.log</string>
+</dict>
+</plist>
diff --git a/ansible/roles/zot_metrics/templates/zot-metrics.sh.j2 b/ansible/roles/zot_metrics/templates/zot-metrics.sh.j2
new file mode 100644
index 0000000..24aaffd
--- /dev/null
+++ b/ansible/roles/zot_metrics/templates/zot-metrics.sh.j2
@@ -0,0 +1,25 @@
+#!/bin/bash
+# {{ ansible_managed }}
+# Collects Zot registry metrics for node_exporter textfile collector
+
+set -euo pipefail
+
+METRICS_URL="{{ zot_metrics_url }}"
+OUTPUT_FILE="{{ zot_metrics_dir }}/zot.prom"
+TEMP_FILE="${OUTPUT_FILE}.tmp"
+
+# Start output file with header
+cat > "$TEMP_FILE" << 'HEADER'
+# HELP zot_up Zot registry is up and responding
+# TYPE zot_up gauge
+HEADER
+
+# Check if zot is up
+if curl -sf "$METRICS_URL" > /dev/null 2>&1; then
+    echo "zot_up 1" >> "$TEMP_FILE"
+else
+    echo "zot_up 0" >> "$TEMP_FILE"
+fi
+
+# Atomic move
+mv "$TEMP_FILE" "$OUTPUT_FILE"