557 lines
15 KiB
YAML
557 lines
15 KiB
YAML
---
|
|
# ------------------------------------------------------------------------------
|
|
# FILE: cluster/applications/monitoring/llama-swap-dashboard.yaml
|
|
# DESCRIPTION: Custom Grafana dashboard for llama-swap GPU/LLM monitoring.
|
|
# Uses llama-swap native metrics (llamaswap_* prefix).
|
|
#
|
|
# USAGE: Reconciled by ArgoCD. Picked up by Grafana sidecar via label:
|
|
# grafana_dashboard: "1"
|
|
# Reference: Ciro Luciotta homelab monitoring pattern (adapted)
|
|
# Updated: 2026-08-18 — metric names corrected for llama-swap v250
|
|
# ------------------------------------------------------------------------------
|
|
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: dashboard-llama-swap
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
app.kubernetes.io/part-of: monitoring
|
|
data:
|
|
llama-swap.json: |
|
|
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": "-- Grafana --",
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"editable": true,
|
|
"gnetId": null,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "MiB",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
},
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"max": 24576,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 23000
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 24000
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 1,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"last",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "right"
|
|
},
|
|
"tooltip": {
|
|
"mode": "single"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llamaswap_gpu_memory_used_bytes{job=\"llama-swap\"} / 1048576",
|
|
"interval": "",
|
|
"legendFormat": "VRAM Used",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU VRAM Usage (MiB)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.8
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 0.92
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.95
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"values": false,
|
|
"fields": "",
|
|
"calcs": [
|
|
"lastNotNull"
|
|
]
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llamaswap_gpu_memory_util_percent{job=\"llama-swap\"}",
|
|
"interval": "",
|
|
"legendFormat": "{{ model }}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Memory Utilization %",
|
|
"type": "gauge"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "%",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
},
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": true,
|
|
"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": 8
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "right"
|
|
},
|
|
"tooltip": {
|
|
"mode": "single"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llamaswap_gpu_util_percent{job=\"llama-swap\"}",
|
|
"interval": "",
|
|
"legendFormat": "{{ model }}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Utilization %",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "%",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
},
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": true,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 3
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"unit": "percent"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "right"
|
|
},
|
|
"tooltip": {
|
|
"mode": "single"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "avg(llamaswap_cpu_util_percent{job=\"llama-swap\"})",
|
|
"interval": "",
|
|
"legendFormat": "{{ model }}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "CPU Utilization %",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "W",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
},
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": true,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "watt"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "right"
|
|
},
|
|
"tooltip": {
|
|
"mode": "single"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llamaswap_gpu_power_draw_watts{job=\"llama-swap\"}",
|
|
"interval": "",
|
|
"legendFormat": "{{ model }} (tokens/min)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Power Draw (W)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "load",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 100,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
},
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"spanNulls": true,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "single"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llamaswap_load_average{interval=\"5m\"}",
|
|
"interval": "",
|
|
"legendFormat": "p95 latency",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "llamaswap_load_average{interval=\"5m\"}",
|
|
"interval": "",
|
|
"legendFormat": "p99 latency",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "System Load Average (5m)",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 27,
|
|
"style": "dark",
|
|
"tags": [
|
|
"llm",
|
|
"llama-swap",
|
|
"gpu-monitoring",
|
|
"ciro-luciotta"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-24h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "llama-swap GPU/LLM Monitoring",
|
|
"uid": "llama-swap-monitor",
|
|
"version": 1
|
|
}
|