rorapp/cluster-knaster
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
bf7c137adf44946b33cea65010a1ffc0366599cd
cluster-knaster/deploy/grafana/dashboards/knaster-uebersicht.json
T
Robert RappandClaude Opus 5.5 bf7c137adf
ci / test (push) Successful in 28s
Details
infra: Compose-Stack mit Monitoring, ohne LiteLLM (Task 5.2) 
- deploy/compose/infra: Dienst litellm entfernt (D4), Router auf LITELLM_BASE_URL
  (appsrv08, Port noch offen), alle Images gepinnt, Grafana und pve-exporter
  ohne Profile, node-exporter für den LXC, Zustand über KNASTER_STATE_DIR
- Prometheus: GPU-VMs per file_sd (node, gpu), Proxmox-Knoten per IP, infra-node
- Grafana: Datasource und Dashboards provisioniert (grafana.com 10347, 1860,
  14574 sowie knaster-Übersicht)
- Alertmanager: n8n-Receiver nur vorbereitet (auskommentiert)
- Ansible: Rollen infra-stack und gpu-exporters, Playbooks monitoring.yml und
  monitoring-targets.yml, Skript monitoring-targets.py (tofu output → file_sd)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 20:22:26 +02:00

773 lines
16 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"uid": "knaster-uebersicht",
"title": "knaster – Übersicht",
"tags": [
"knaster"
],
"timezone": "browser",
"schemaVersion": 39,
"version": 1,
"editable": false,
"refresh": "30s",
"time": {
"from": "now-6h",
"to": "now"
},
"panels": [
{
"id": 1,
"type": "stat",
"title": "Proxmox-Knoten online",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "count(max by (id) (pve_up{id=~\"node/.*\"}) == 1) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 2,
"type": "stat",
"title": "Gäste laufend",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 4,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "count(max by (id) (pve_up{id=~\"(qemu|lxc)/.*\"}) == 1) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 3,
"type": "stat",
"title": "GPUs gemeldet",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 8,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "count(count by (instance, uuid) (nvidia_smi_index)) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 4,
"type": "stat",
"title": "Ziele nicht erreichbar",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "count(up{job!~\"vllm|llamacpp\"} == 0) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 5,
"type": "stat",
"title": "Aktive Alerts",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 16,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "count(ALERTS{alertstate=\"firing\"}) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 6,
"type": "stat",
"title": "Slots verfügbar",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 20,
"y": 0,
"w": 4,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "sum(knaster_slot_available) or vector(0)",
"legendFormat": ""
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 7,
"type": "stat",
"title": "Knoten",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 4,
"w": 12,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (id) (pve_up{id=~\"node/.*\"})",
"legendFormat": "{{id}}"
}
],
"fieldConfig": {
"defaults": {
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "aus",
"color": "red"
},
"1": {
"text": "an",
"color": "green"
}
}
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "green",
"value": 1
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 8,
"type": "stat",
"title": "GPU-VMs und infra (node_exporter)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 4,
"w": 12,
"h": 4
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "up{job=~\"node|infra-node\"}",
"legendFormat": "{{instance}}"
}
],
"fieldConfig": {
"defaults": {
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "aus",
"color": "red"
},
"1": {
"text": "an",
"color": "green"
}
}
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "green",
"value": 1
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 9,
"type": "timeseries",
"title": "CPU je Knoten",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 8,
"w": 12,
"h": 7
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (id) (pve_cpu_usage_ratio{id=~\"node/.*\"})",
"legendFormat": "{{id}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"min": 0,
"max": 1
},
"overrides": []
}
},
{
"id": 10,
"type": "timeseries",
"title": "RAM je Knoten",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 8,
"w": 12,
"h": 7
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (id) (pve_memory_usage_bytes{id=~\"node/.*\"}) / max by (id) (pve_memory_size_bytes{id=~\"node/.*\"})",
"legendFormat": "{{id}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"min": 0,
"max": 1
},
"overrides": []
}
},
{
"id": 11,
"type": "timeseries",
"title": "GPU-Temperatur",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 15,
"w": 8,
"h": 8
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (instance, name, uuid) (nvidia_smi_temperature_gpu)",
"legendFormat": "{{instance}} {{name}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "celsius"
},
"overrides": []
}
},
{
"id": 12,
"type": "timeseries",
"title": "GPU-Auslastung",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 8,
"y": 15,
"w": 8,
"h": 8
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (instance, name, uuid) (nvidia_smi_utilization_gpu_ratio)",
"legendFormat": "{{instance}} {{name}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"min": 0,
"max": 1
},
"overrides": []
}
},
{
"id": 13,
"type": "timeseries",
"title": "GPU-Speicher belegt",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 16,
"y": 15,
"w": 8,
"h": 8
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "max by (instance, name, uuid) (nvidia_smi_memory_used_bytes / nvidia_smi_memory_total_bytes)",
"legendFormat": "{{instance}} {{name}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"min": 0,
"max": 1
},
"overrides": []
}
},
{
"id": 14,
"type": "stat",
"title": "Slots (Router)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 0,
"y": 23,
"w": 12,
"h": 5
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "knaster_slot_available",
"legendFormat": "{{slot}}"
}
],
"fieldConfig": {
"defaults": {
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "aus",
"color": "red"
},
"1": {
"text": "an",
"color": "green"
}
}
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "green",
"value": 1
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "background",
"graphMode": "none",
"textMode": "auto"
}
},
{
"id": 15,
"type": "table",
"title": "Aktive Alerts",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"x": 12,
"y": 23,
"w": 12,
"h": 5
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"refId": "A",
"expr": "ALERTS{alertstate=\"firing\"}",
"legendFormat": "",
"instant": true,
"format": "table"
}
],
"transformations": [
{
"id": "organize",
"options": {
"excludeByName": {
"Time": true,
"Value": true,
"__name__": true,
"alertstate": true
}
}
}
]
}
],
"templating": {
"list": []
},
"annotations": {
"list": []
}
}
Reference in New Issue View Git Blame Copy Permalink