Initial Boone stack: observability and automation baseline

2026-03-04 23:17:06 -05:00 · 2026-03-04 23:17:06 -05:00 · ba22ab548f
commit ba22ab548f
10 changed files with 392 additions and 0 deletions
--- a/.env.example
+++ b/.env.example
@ -0,0 +1,6 @@
+POSTGRES_USER=farmadmin
+POSTGRES_PASSWORD=change_this_now
+POSTGRES_DB=farm
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=change_this_now
+TZ=America/New_York
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,8 @@
+# secrets
+.env
+
+# persistent runtime data
+data/
+
+# macOS
+.DS_Store
--- a/README.md
+++ b/README.md
@ -0,0 +1,34 @@
+# Farm Control Stack
+
+This folder contains a starter central-control stack for your farm:
+- PostgreSQL (operational + business data)
+- Mosquitto MQTT (sensor/device messaging)
+- Grafana (dashboards/alerts)
+- Node-RED (automation workflows)
+- Prometheus (metrics collection)
+
+## First-run on this Mac
+1. Open `Rancher Desktop` from Applications.
+2. Complete first-run setup in the GUI.
+3. In Rancher Desktop settings, ensure Docker CLI is enabled.
+4. Open a new terminal and run:
+   ```bash
+   cd /Users/farm/blackfish/projects/farm-control
+   ./start.sh
+   ```
+
+## Default endpoints
+- Grafana: http://localhost:3000
+- Node-RED: http://localhost:1880
+- MQTT broker: `localhost:1883`
+- PostgreSQL: `localhost:5432`
+- Prometheus: http://localhost:9090
+- Mac host metrics exporter: http://localhost:9100/metrics
+
+## Mac performance metrics
+This Mac is monitored via `node_exporter` (installed with Homebrew and started as a service).
+Prometheus scrapes it at `host.docker.internal:9100`, and Grafana uses Prometheus as default datasource.
+Grafana also auto-loads a dashboard: `Mac Host Overview` (folder: `Farm Control`).
+
+## Important
+Edit `.env` and change default passwords before exposing this machine on a farm network.
--- a/docker-compose.yml
+++ b/docker-compose.yml
@ -0,0 +1,85 @@
+name: farm-control
+
+services:
+  postgres:
+    image: postgres:16-alpine
+    container_name: farm-postgres
+    restart: unless-stopped
+    env_file: .env
+    environment:
+      - POSTGRES_USER=${POSTGRES_USER}
+      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
+      - POSTGRES_DB=${POSTGRES_DB}
+      - TZ=${TZ}
+    volumes:
+      - ./data/postgres:/var/lib/postgresql/data
+    ports:
+      - "5432:5432"
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
+
+  mosquitto:
+    image: eclipse-mosquitto:2
+    container_name: farm-mqtt
+    restart: unless-stopped
+    volumes:
+      - ./mosquitto/mosquitto.conf:/mosquitto/config/mosquitto.conf:ro
+      - ./data/mosquitto:/mosquitto/data
+      - ./data/mosquitto-log:/mosquitto/log
+    ports:
+      - "1883:1883"
+
+  grafana:
+    image: grafana/grafana:11.6.0
+    container_name: farm-grafana
+    restart: unless-stopped
+    env_file: .env
+    environment:
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
+      - TZ=${TZ}
+    volumes:
+      - ./data/grafana:/var/lib/grafana
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/etc/grafana/dashboards:ro
+    ports:
+      - "3000:3000"
+    depends_on:
+      - postgres
+      - prometheus
+
+  nodered:
+    image: nodered/node-red:4.0.9
+    container_name: farm-nodered
+    restart: unless-stopped
+    environment:
+      - TZ=${TZ}
+    volumes:
+      - ./data/nodered:/data
+    ports:
+      - "1880:1880"
+    depends_on:
+      - mosquitto
+      - postgres
+
+  prometheus:
+    image: prom/prometheus:v3.2.1
+    container_name: farm-prometheus
+    restart: unless-stopped
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.path=/prometheus
+      - --storage.tsdb.retention.time=30d
+      - --storage.tsdb.retention.size=20GB
+    volumes:
+      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./data/prometheus:/prometheus
+    ports:
+      - "9090:9090"
+
+networks:
+  default:
+    name: farm-control-net
--- a/grafana/dashboards/mac-host-overview.json
+++ b/grafana/dashboards/mac-host-overview.json
@ -0,0 +1,187 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {"type": "grafana", "uid": "-- Grafana --"},
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {
+        "defaults": {"unit": "percent", "decimals": 1},
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 0, "y": 0},
+      "id": 1,
+      "options": {"colorMode": "background", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
+      "targets": [
+        {
+          "expr": "(1 - avg(rate(node_cpu_seconds_total{instance=\"$instance\",mode=\"idle\"}[5m]))) * 100",
+          "refId": "A"
+        }
+      ],
+      "title": "CPU Usage",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {
+        "defaults": {"unit": "percent", "decimals": 1},
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 6, "y": 0},
+      "id": 2,
+      "options": {"colorMode": "background", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
+      "targets": [
+        {
+          "expr": "(1 - ((node_memory_free_bytes{instance=\"$instance\"} + node_memory_inactive_bytes{instance=\"$instance\"} + node_memory_purgeable_bytes{instance=\"$instance\"}) / node_memory_total_bytes{instance=\"$instance\"})) * 100",
+          "refId": "A"
+        }
+      ],
+      "title": "Memory Usage",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {
+        "defaults": {"unit": "percent", "decimals": 1},
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 12, "y": 0},
+      "id": 3,
+      "options": {"colorMode": "background", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
+      "targets": [
+        {
+          "expr": "100 * (1 - (node_filesystem_avail_bytes{instance=\"$instance\",mountpoint=\"/\",fstype!~\"tmpfs|devfs\"} / node_filesystem_size_bytes{instance=\"$instance\",mountpoint=\"/\",fstype!~\"tmpfs|devfs\"}))",
+          "refId": "A"
+        }
+      ],
+      "title": "Root Disk Usage",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {
+        "defaults": {"unit": "none", "decimals": 2},
+        "overrides": []
+      },
+      "gridPos": {"h": 4, "w": 6, "x": 18, "y": 0},
+      "id": 4,
+      "options": {"colorMode": "background", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
+      "targets": [
+        {
+          "expr": "node_load5{instance=\"$instance\"}",
+          "refId": "A"
+        }
+      ],
+      "title": "Load (5m)",
+      "type": "stat"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {"defaults": {"unit": "percentunit", "decimals": 2}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 4},
+      "id": 5,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "targets": [
+        {"expr": "1 - avg(rate(node_cpu_seconds_total{instance=\"$instance\",mode=\"idle\"}[5m]))", "legendFormat": "used", "refId": "A"},
+        {"expr": "avg(rate(node_cpu_seconds_total{instance=\"$instance\",mode=\"idle\"}[5m]))", "legendFormat": "idle", "refId": "B"}
+      ],
+      "title": "CPU Usage (ratio)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {"defaults": {"unit": "bytes", "decimals": 2}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 4},
+      "id": 6,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "targets": [
+        {"expr": "node_memory_total_bytes{instance=\"$instance\"} - (node_memory_free_bytes{instance=\"$instance\"} + node_memory_inactive_bytes{instance=\"$instance\"} + node_memory_purgeable_bytes{instance=\"$instance\"})", "legendFormat": "used", "refId": "A"},
+        {"expr": "node_memory_free_bytes{instance=\"$instance\"} + node_memory_inactive_bytes{instance=\"$instance\"} + node_memory_purgeable_bytes{instance=\"$instance\"}", "legendFormat": "available", "refId": "B"}
+      ],
+      "title": "Memory Bytes",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {"defaults": {"unit": "Bps", "decimals": 2}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 12},
+      "id": 7,
+      "options": {"legend": {"displayMode": "table", "placement": "bottom"}, "tooltip": {"mode": "multi"}},
+      "targets": [
+        {"expr": "sum by (device) (rate(node_network_receive_bytes_total{instance=\"$instance\",device!~\"lo0|utun.*|awdl0|llw0|gif0|stf0\"}[5m]))", "legendFormat": "{{device}} rx", "refId": "A"},
+        {"expr": "sum by (device) (rate(node_network_transmit_bytes_total{instance=\"$instance\",device!~\"lo0|utun.*|awdl0|llw0|gif0|stf0\"}[5m]))", "legendFormat": "{{device}} tx", "refId": "B"}
+      ],
+      "title": "Network Throughput",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {"type": "prometheus", "uid": "$datasource"},
+      "fieldConfig": {"defaults": {"unit": "bytes", "decimals": 2}, "overrides": []},
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 12},
+      "id": 8,
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}, "tooltip": {"mode": "single"}},
+      "targets": [
+        {"expr": "node_filesystem_size_bytes{instance=\"$instance\",mountpoint=\"/\",fstype!~\"tmpfs|devfs\"}", "legendFormat": "size", "refId": "A"},
+        {"expr": "node_filesystem_avail_bytes{instance=\"$instance\",mountpoint=\"/\",fstype!~\"tmpfs|devfs\"}", "legendFormat": "available", "refId": "B"}
+      ],
+      "title": "Root Disk Bytes",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "15s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": ["farm", "mac", "host"],
+  "templating": {
+    "list": [
+      {
+        "current": {"selected": false, "text": "Prometheus", "value": "prometheus"},
+        "hide": 2,
+        "label": "datasource",
+        "name": "datasource",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "type": "datasource"
+      },
+      {
+        "current": {"selected": false, "text": "host.docker.internal:9100", "value": "host.docker.internal:9100"},
+        "datasource": {"type": "prometheus", "uid": "$datasource"},
+        "definition": "label_values(node_uname_info, instance)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "Instance",
+        "multi": false,
+        "name": "instance",
+        "options": [],
+        "query": {"qryType": 1, "query": "label_values(node_uname_info, instance)", "refId": "PromVar"},
+        "refresh": 2,
+        "sort": 1,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {"from": "now-6h", "to": "now"},
+  "timepicker": {},
+  "timezone": "",
+  "title": "Mac Host Overview",
+  "uid": "mac-host-overview",
+  "version": 1,
+  "weekStart": ""
+}
--- a/grafana/provisioning/dashboards/default.yml
+++ b/grafana/provisioning/dashboards/default.yml
@ -0,0 +1,11 @@
+apiVersion: 1
+
+providers:
+  - name: 'Farm Dashboards'
+    orgId: 1
+    folder: 'Farm Control'
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /etc/grafana/dashboards
--- a/grafana/provisioning/datasources/prometheus.yml
+++ b/grafana/provisioning/datasources/prometheus.yml
@ -0,0 +1,10 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
--- a/monitoring/prometheus/prometheus.yml
+++ b/monitoring/prometheus/prometheus.yml
@ -0,0 +1,11 @@
+global:
+  scrape_interval: 15s
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets: ['prometheus:9090']
+
+  - job_name: mac_host
+    static_configs:
+      - targets: ['host.docker.internal:9100']
--- a/mosquitto/mosquitto.conf
+++ b/mosquitto/mosquitto.conf
@ -0,0 +1,5 @@
+persistence true
+persistence_location /mosquitto/data/
+log_dest stdout
+listener 1883
+allow_anonymous true
--- a/start.sh
+++ b/start.sh
@ -0,0 +1,35 @@
+#!/usr/bin/env zsh
+set -euo pipefail
+
+RD_BIN_DIR="/Applications/Rancher Desktop.app/Contents/Resources/resources/darwin/bin"
+export PATH="$RD_BIN_DIR:$PATH"
+
+DOCKER_BIN=""
+if command -v docker >/dev/null 2>&1; then
+  DOCKER_BIN="$(command -v docker)"
+elif [ -x "$RD_BIN_DIR/docker" ]; then
+  DOCKER_BIN="$RD_BIN_DIR/docker"
+else
+  echo "docker CLI not found."
+  echo "Enable Docker CLI in Rancher Desktop Preferences > Application and reopen terminal."
+  exit 1
+fi
+
+if ! "$DOCKER_BIN" info >/dev/null 2>&1; then
+  echo "Docker runtime is not ready. Open Rancher Desktop and wait for status 'Running'."
+  exit 1
+fi
+
+cd "$(dirname "$0")"
+"$DOCKER_BIN" compose pull
+"$DOCKER_BIN" compose up -d
+"$DOCKER_BIN" compose ps
+
+cat <<MSG
+
+Farm stack started.
+- Grafana:   http://localhost:3000
+- Node-RED:  http://localhost:1880
+- MQTT:      mqtt://localhost:1883
+- Postgres:  localhost:5432
+MSG