Files
homelab/kubernetes/apps/monitoring/dashboards/node-overview.json
T
k.rennerandClaude Opus 4.7 366bbb0bed monitoring(dashboards): delete dead dashboards + repoint legacy datasource
Phase 1 of the dashboard triage.

Deleted (no current data source, no plan to wire one):
- unifi-overview (unpoller removed after UDM crash)
- caddy-overview (Caddy retired 2026-05-09)
- docker-overview (Docker host era done; workloads on K8s)
- log-explorer (legacy host log shipping not in scope)
- dns-overview (dns-servers job lives but a dedicated dashboard isn't worth keeping; Explore tab covers ad-hoc)

Repointed datasource from `prometheus-legacy` to `prometheus` (the
legacy LXC 227 Prom is retired):
- node-overview, node-metrics — show K8s nodes only (legacy host
  node-exporters were never re-scraped post-migration)
- infrastructure-overview — generic up{} + node_* metrics work on K8s
- proxmox-cluster — pve-exporter is now in-cluster (commit 33b452a)

Also deletes DASHBOARD-MIGRATION.md (the migration cut-over completed
with VM 109 retirement on 2026-05-09).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 09:56:21 +02:00

231 lines
13 KiB
JSON

{
"annotations": {"list": []},
"description": "System metrics from all nodes",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}},
"overrides": []
},
"gridPos": {"h": 4, "w": 4, "x": 0, "y": 0},
"id": 1,
"options": {"colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "count(up{job=\"node\"} == 1)", "refId": "A"}],
"title": "Nodes Online",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 60}, {"color": "red", "value": 80}]}, "unit": "percent"},
"overrides": []
},
"gridPos": {"h": 4, "w": 5, "x": 4, "y": 0},
"id": 2,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["mean"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "avg(100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100))", "refId": "A"}],
"title": "Avg CPU Usage",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 70}, {"color": "red", "value": 85}]}, "unit": "percent"},
"overrides": []
},
"gridPos": {"h": 4, "w": 5, "x": 9, "y": 0},
"id": 3,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["mean"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "avg((1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100)", "refId": "A"}],
"title": "Avg Memory Usage",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 70}, {"color": "red", "value": 85}]}, "unit": "percent"},
"overrides": []
},
"gridPos": {"h": 4, "w": 5, "x": 14, "y": 0},
"id": 4,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["mean"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "avg((1 - (node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"})) * 100)", "refId": "A"}],
"title": "Avg Disk Usage",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}]}},
"overrides": []
},
"gridPos": {"h": 4, "w": 5, "x": 19, "y": 0},
"id": 5,
"options": {"colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "count(up{job=\"node\"} == 0)", "refId": "A"}],
"title": "Nodes Down",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 60}, {"color": "red", "value": 80}]},
"unit": "percent"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 4},
"id": 6,
"options": {"displayMode": "lcd", "minVizHeight": 10, "minVizWidth": 0, "orientation": "horizontal", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "showUnfilled": true},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)", "legendFormat": "{{instance}}", "refId": "A"}],
"title": "CPU Usage by Node",
"type": "bargauge"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 70}, {"color": "red", "value": 85}]},
"unit": "percent"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 4},
"id": 7,
"options": {"displayMode": "lcd", "minVizHeight": 10, "minVizWidth": 0, "orientation": "horizontal", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "showUnfilled": true},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100", "legendFormat": "{{instance}}", "refId": "A"}],
"title": "Memory Usage by Node",
"type": "bargauge"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 20, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
"unit": "percent"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 12},
"id": 8,
"options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)", "legendFormat": "{{instance}}", "refId": "A"}],
"title": "CPU Usage Over Time",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 20, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 12},
"id": 9,
"options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes", "legendFormat": "{{instance}}", "refId": "A"}],
"title": "Memory Usage Over Time",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 20, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 20},
"id": 10,
"options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(rate(node_network_receive_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\"}[5m])) by (instance)", "legendFormat": "{{instance}} rx", "refId": "A"},
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "-sum(rate(node_network_transmit_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\"}[5m])) by (instance)", "legendFormat": "{{instance}} tx", "refId": "B"}
],
"title": "Network I/O",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 20, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 20},
"id": 11,
"options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(rate(node_disk_read_bytes_total[5m])) by (instance)", "legendFormat": "{{instance}} read", "refId": "A"},
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "-sum(rate(node_disk_written_bytes_total[5m])) by (instance)", "legendFormat": "{{instance}} write", "refId": "B"}
],
"title": "Disk I/O",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 70}, {"color": "red", "value": 85}]},
"unit": "percent"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 24, "x": 0, "y": 28},
"id": 12,
"options": {"displayMode": "lcd", "minVizHeight": 10, "minVizWidth": 0, "orientation": "horizontal", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "showUnfilled": true},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "(1 - (node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"})) * 100", "legendFormat": "{{instance}}", "refId": "A"}],
"title": "Disk Usage by Node",
"type": "bargauge"
}
],
"refresh": "30s",
"schemaVersion": 38,
"style": "dark",
"tags": ["homelab", "nodes", "infrastructure"],
"templating": {"list": []},
"time": {"from": "now-1h", "to": "now"},
"timepicker": {},
"timezone": "",
"title": "Node Overview",
"uid": "node-overview",
"version": 1,
"weekStart": ""
}