k3s/monitoring/grafana-temps-dashboard.yaml
teddy 7082deaf86 monitoring: add separate all-sensors temp panel with 70°C warning line
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-10 00:02:59 +02:00

119 lines
4.4 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-dashboard-temps
namespace: monitoring
labels:
grafana_dashboard: "1"
data:
hardware-temperatures.json: |
{
"annotations": {"list": []},
"editable": true,
"graphTooltip": 0,
"links": [],
"panels": [
{
"datasource": {"type": "prometheus", "uid": "${datasource}"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"unit": "celsius",
"thresholds": {"mode": "absolute", "steps": [
{"color": "green", "value": null},
{"color": "yellow", "value": 60},
{"color": "orange", "value": 75},
{"color": "red", "value": 85}
]}
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
"id": 1,
"options": {
"colorMode": "background",
"graphMode": "area",
"orientation": "auto",
"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false},
"textMode": "auto"
},
"pluginVersion": "11.0.0",
"title": "Max temperature per host (now)",
"type": "stat",
"targets": [
{"datasource": {"type": "prometheus", "uid": "${datasource}"},
"expr": "max by (instance) (node_hwmon_temp_celsius)",
"legendFormat": "{{instance}}", "refId": "A"}
]
},
{
"datasource": {"type": "prometheus", "uid": "${datasource}"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"unit": "celsius",
"custom": {"drawStyle": "line", "lineWidth": 2, "fillOpacity": 10, "showPoints": "never", "thresholdsStyle": {"mode": "line"}},
"thresholds": {"mode": "absolute", "steps": [
{"color": "green", "value": null},
{"color": "red", "value": 70}
]}
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
"id": 2,
"options": {
"legend": {"displayMode": "table", "placement": "bottom", "calcs": ["last", "max"]},
"tooltip": {"mode": "multi"}
},
"title": "Highest temperature per host (warning line @ 70°C)",
"type": "timeseries",
"targets": [
{"datasource": {"type": "prometheus", "uid": "${datasource}"},
"expr": "max by (instance) (node_hwmon_temp_celsius)",
"legendFormat": "{{instance}}", "refId": "A"}
]
},
{
"datasource": {"type": "prometheus", "uid": "${datasource}"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"unit": "celsius",
"custom": {"drawStyle": "line", "lineWidth": 1, "fillOpacity": 5, "showPoints": "never", "thresholdsStyle": {"mode": "line"}},
"thresholds": {"mode": "absolute", "steps": [
{"color": "green", "value": null},
{"color": "red", "value": 70}
]}
},
"overrides": []
},
"gridPos": {"h": 8, "w": 24, "x": 0, "y": 8},
"id": 3,
"options": {
"legend": {"displayMode": "table", "placement": "bottom", "calcs": ["last", "max"]},
"tooltip": {"mode": "multi"}
},
"title": "All temperature sensors (warning line @ 70°C)",
"type": "timeseries",
"targets": [
{"datasource": {"type": "prometheus", "uid": "${datasource}"},
"expr": "node_hwmon_temp_celsius",
"legendFormat": "{{instance}} / {{chip}} / {{sensor}}", "refId": "A"}
]
}
],
"refresh": "30s",
"schemaVersion": 39,
"tags": ["hardware", "temperature"],
"templating": {"list": [
{"current": {}, "hide": 0, "includeAll": false, "label": "Datasource",
"multi": false, "name": "datasource", "options": [], "query": "prometheus",
"refresh": 1, "type": "datasource"}
]},
"time": {"from": "now-6h", "to": "now"},
"timezone": "Europe/Oslo",
"title": "Hardware Temperatures",
"uid": "hw-temps",
"version": 3
}