feat(monitoring): add Portal-1 and Vultr dashboards
treefmt / nix fmt (pull_request) Successful in 5s
pytest / pytest (pull_request) Successful in 30s
test ebook search / test-ebook-search (pull_request) Successful in 34s
build_systems / build-brain (pull_request) Successful in 49s
build_systems / build-bob (pull_request) Successful in 50s
build_systems / build-rhapsody-in-green (pull_request) Successful in 1m2s
build_systems / build-jeeves (pull_request) Successful in 2m14s

- scrape Portal-1 node metrics over Tailscale
- add a hardened Vultr billing and bandwidth exporter
- provision host health and infrastructure cost dashboards
This commit is contained in:
2026-08-27 17:49:56 -04:00
parent d95b8b99ce
commit bdf67e96f0
7 changed files with 2005 additions and 0 deletions
@@ -0,0 +1,798 @@
{
"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": false,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "green",
"value": 1
}
]
},
"mappings": [
{
"options": {
"0": {
"color": "red",
"index": 1,
"text": "Offline"
},
"1": {
"color": "green",
"index": 0,
"text": "Online"
}
},
"type": "value"
}
]
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 4,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "up{job=\"node\",instance=\"portal-1\"}",
"instant": true,
"legendFormat": "",
"range": false,
"refId": "A"
}
],
"title": "Node Exporter",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 4,
"y": 0
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - avg(rate(node_cpu_seconds_total{job=\"node\",instance=\"portal-1\",mode=\"idle\"}[5m])))",
"instant": true,
"legendFormat": "",
"range": false,
"refId": "A"
}
],
"title": "CPU Used",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 9,
"y": 0
},
"id": 3,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - (node_memory_MemAvailable_bytes{job=\"node\",instance=\"portal-1\"} / node_memory_MemTotal_bytes{job=\"node\",instance=\"portal-1\"}))",
"instant": true,
"legendFormat": "",
"range": false,
"refId": "A"
}
],
"title": "RAM Used",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 14,
"y": 0
},
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - (node_filesystem_avail_bytes{job=\"node\",instance=\"portal-1\",mountpoint=\"/\",fstype!=\"\"} / node_filesystem_size_bytes{job=\"node\",instance=\"portal-1\",mountpoint=\"/\",fstype!=\"\"}))",
"instant": true,
"legendFormat": "",
"range": false,
"refId": "A"
}
],
"title": "Root Filesystem Used",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 5,
"w": 5,
"x": 19,
"y": 0
},
"id": 5,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto",
"wideLayout": true
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "node_load1{job=\"node\",instance=\"portal-1\"}",
"instant": true,
"legendFormat": "",
"range": false,
"refId": "A"
}
],
"title": "Load (1m)",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 5
},
"id": 6,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - avg(rate(node_cpu_seconds_total{job=\"node\",instance=\"portal-1\",mode=\"idle\"}[5m])))",
"instant": false,
"legendFormat": "CPU used",
"range": true,
"refId": "A"
}
],
"title": "CPU Usage",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 5
},
"id": 7,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - (node_memory_MemAvailable_bytes{job=\"node\",instance=\"portal-1\"} / node_memory_MemTotal_bytes{job=\"node\",instance=\"portal-1\"}))",
"instant": false,
"legendFormat": "RAM used",
"range": true,
"refId": "A"
}
],
"title": "RAM Usage",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 70
},
{
"color": "red",
"value": 90
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 13
},
"id": 8,
"options": {
"cellHeight": "sm",
"showHeader": true,
"sortBy": [
{
"desc": true,
"displayName": "Value"
}
]
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (1 - (node_filesystem_avail_bytes{job=\"node\",instance=\"portal-1\",fstype!~\"tmpfs|devtmpfs|overlay|squashfs\",mountpoint!~\"/run.*\"} / node_filesystem_size_bytes{job=\"node\",instance=\"portal-1\",fstype!~\"tmpfs|devtmpfs|overlay|squashfs\",mountpoint!~\"/run.*\"}))",
"format": "table",
"instant": true,
"legendFormat": "{{mountpoint}}",
"range": false,
"refId": "A"
}
],
"title": "Filesystem Usage",
"type": "table"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 13
},
"id": 9,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_disk_read_bytes_total{job=\"node\",instance=\"portal-1\",device!~\"loop.*|ram.*|fd.*\"}[5m]))",
"instant": false,
"legendFormat": "read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_disk_written_bytes_total{job=\"node\",instance=\"portal-1\",device!~\"loop.*|ram.*|fd.*\"}[5m]))",
"instant": false,
"legendFormat": "write",
"range": true,
"refId": "B"
}
],
"title": "Disk Throughput",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "iops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 21
},
"id": 10,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_disk_reads_completed_total{job=\"node\",instance=\"portal-1\",device!~\"loop.*|ram.*|fd.*\"}[5m]))",
"instant": false,
"legendFormat": "reads",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_disk_writes_completed_total{job=\"node\",instance=\"portal-1\",device!~\"loop.*|ram.*|fd.*\"}[5m]))",
"instant": false,
"legendFormat": "writes",
"range": true,
"refId": "B"
}
],
"title": "Disk Operations",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 21
},
"id": 11,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_network_receive_bytes_total{job=\"node\",instance=\"portal-1\",device!=\"lo\"}[5m]))",
"instant": false,
"legendFormat": "received",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "sum(rate(node_network_transmit_bytes_total{job=\"node\",instance=\"portal-1\",device!=\"lo\"}[5m]))",
"instant": false,
"legendFormat": "sent",
"range": true,
"refId": "B"
}
],
"title": "Network Traffic",
"type": "timeseries"
}
],
"refresh": "30s",
"schemaVersion": 39,
"tags": [
"monitoring",
"portal-1",
"vultr"
],
"templating": {
"list": []
},
"time": {
"from": "now-24h",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "Portal-1 Host",
"uid": "portal-1-host",
"version": 1,
"weekStart": ""
}