#!/usr/bin/env bash
#
# Homelab monitoring, Part 2: Every VM, the NAS and the Wi-Fi
# https://www.zadran.net/guides/homelab-monitoring-2-proxmox-truenas-unifi
# Generated from the guide, last updated 2026-10-13.
#
# NO WARRANTY. This script is provided as is. You are responsible for
# understanding what it does before running it, and for the consequences.
# Take a backup first. See https://www.zadran.net/disclaimer
#
# Destructive steps are left commented out on purpose -- uncomment them
# only once you have understood what they do.
#
# Where the guide writes a file with <<'EOF' and your values are in it,
# this script uses <<EOF so that they expand. Every other $, ` and \
# gets a backslash, so the rest comes out exactly as the guide shows it.

set -euo pipefail

# ---- Set these for your environment ----
# From Part 1
CTID='140'
# The IP of your Proxmox server
PVE_IP='192.168.1.2'
# Same name as in Part 1
PVE_NAME='pve'
# The IP of your TrueNAS
NAS_IP='192.168.1.10'
# A pool that is always available
POOL='tank'
# UniFi OS Server :11443, or https://<gateway IP>
UNIFI_URL='https://192.168.1.15:11443'

pveum user add prometheus@pve --comment "Monitoring (read-only)"
pveum acl modify / --users prometheus@pve --roles PVEAuditor
pveum user token add prometheus@pve exporter --privsep 0

pct enter ${CTID}        # from the Proxmox host shell
nano /opt/monitoring/prometheus/pve.yml

# >> By hand: the guide has a yaml block here, to type or paste into
# >> a file or a form. It is not a command, so it is not in this script.

cat > /opt/monitoring/compose.override.yaml <<'EOF'
services:
  pve-exporter:
    image: prompve/prometheus-pve-exporter:latest
    container_name: pve-exporter
    restart: unless-stopped
    volumes:
      - ./prometheus/pve.yml:/etc/prometheus/pve.yml:ro
EOF

cat >> /opt/monitoring/prometheus/prometheus.yml <<EOF

  - job_name: pve
    metrics_path: /pve
    params:
      cluster: ['1']
      node: ['1']
    static_configs:
      - targets: ['${PVE_IP}']
        labels:
          module: ${PVE_NAME}
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [module]
        target_label: __param_module
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: pve-exporter:9221
EOF

cd /opt/monitoring && docker compose up -d
curl -s -X POST localhost:9090/-/reload && echo "reload OK"

mkdir -p /mnt/${POOL}/apps/node-exporter/textfile
chown -R 568:568 /mnt/${POOL}/apps/node-exporter
chmod 755 /mnt/${POOL}/apps/node-exporter /mnt/${POOL}/apps/node-exporter/textfile

cat > /mnt/${POOL}/apps/node-exporter/zpool-metrics.sh <<EOF
#!/bin/bash
# ZFS pool size, usage and health for node_exporter's textfile collector
DIR=/mnt/${POOL}/apps/node-exporter/textfile
TMP=\$(mktemp "\$DIR/.zpool.XXXXXX")
zpool list -Hp -o name,size,alloc,free,cap,health | while read -r name size alloc free cap health; do
  echo "zpool_size_bytes{pool=\\"\$name\\"} \$size"
  echo "zpool_allocated_bytes{pool=\\"\$name\\"} \$alloc"
  echo "zpool_free_bytes{pool=\\"\$name\\"} \$free"
  echo "zpool_capacity_percent{pool=\\"\$name\\"} \${cap%\\%}"
  echo "zpool_healthy{pool=\\"\$name\\",state=\\"\$health\\"} \$([ "\$health" = ONLINE ] && echo 1 || echo 0)"
done | sort > "\$TMP"
chmod 644 "\$TMP" && mv "\$TMP" "\$DIR/zpool.prom"
EOF
bash /mnt/${POOL}/apps/node-exporter/zpool-metrics.sh && cat /mnt/${POOL}/apps/node-exporter/textfile/zpool.prom

# >> By hand: the guide has a yaml block here, to type or paste into
# >> a file or a form. It is not a command, so it is not in this script.

curl -s http://${NAS_IP}:9100/metrics | grep '^zpool_'

nano /opt/monitoring/prometheus/prometheus.yml

# >> By hand: the guide has a yaml block here, to type or paste into
# >> a file or a form. It is not a command, so it is not in this script.

curl -s -X POST localhost:9090/-/reload && echo "reload OK"

nano /opt/monitoring/.env

cat >> /opt/monitoring/compose.override.yaml <<EOF

  unpoller:
    image: ghcr.io/unpoller/unpoller:latest
    container_name: unpoller
    restart: unless-stopped
    environment:
      - UP_UNIFI_DEFAULT_URL=${UNIFI_URL}
      - UP_UNIFI_DEFAULT_USER=unpoller
      - UP_UNIFI_DEFAULT_PASS=\${UNPOLLER_PASSWORD}
      - UP_UNIFI_DEFAULT_VERIFY_SSL=false
      - UP_UNIFI_DEFAULT_SAVE_SITES=true
      - UP_UNIFI_DEFAULT_SAVE_DPI=false
      - UP_INFLUXDB_DISABLE=true
      - UP_PROMETHEUS_DISABLE=false
      - UP_PROMETHEUS_NAMESPACE=unpoller
EOF

cat >> /opt/monitoring/prometheus/prometheus.yml <<'EOF'

  - job_name: unpoller
    static_configs:
      - targets: ['unpoller:9130']
EOF

cd /opt/monitoring && docker compose up -d
curl -s -X POST localhost:9090/-/reload && echo "reload OK"
sleep 40
docker compose logs unpoller --since 1m | tail -5

curl -s 'localhost:9090/api/v1/targets?state=active' |
  jq -r '.data.activeTargets[] | "\(.health)\t\(.labels.job)\t\(.labels.host // .labels.instance)"' | sort -k2 | column -t