a5a6bd3408
- k8s/monitoring/alert-chain-monitor.yaml - k8s/monitoring/database-alerts.yaml - ops/grafana/ Grafana dashboards - ops/signoz/ SignOz 配置 - ops/scripts/ 維運腳本 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1427 lines
34 KiB
JSON
1427 lines
34 KiB
JSON
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": {
|
|
"type": "grafana",
|
|
"uid": "-- Grafana --"
|
|
},
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"description": "NVIDIA Nemotron Tool Calling 監控儀表板 (ADR-036 / Phase 20)",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"liveNow": false,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 1,
|
|
"panels": [],
|
|
"title": "Health Overview",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [
|
|
{
|
|
"options": {
|
|
"0": {
|
|
"color": "red",
|
|
"index": 1,
|
|
"text": "OPEN"
|
|
},
|
|
"1": {
|
|
"color": "green",
|
|
"index": 0,
|
|
"text": "CLOSED"
|
|
}
|
|
},
|
|
"type": "value"
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.2.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "nvidia_circuit_breaker_state{service=\"nemotron\"}",
|
|
"legendFormat": "Circuit Breaker",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Circuit Breaker",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 10,
|
|
"x": 4,
|
|
"y": 1
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(nvidia_tool_call_requests_total[5m])) by (status)",
|
|
"legendFormat": "{{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Tool Call Request Rate",
|
|
"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": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "line"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 30
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 45
|
|
}
|
|
]
|
|
},
|
|
"unit": "s"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 10,
|
|
"x": 14,
|
|
"y": 1
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "max", "p95"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.50, sum(rate(nvidia_tool_call_latency_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "P50",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum(rate(nvidia_tool_call_latency_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "P95",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.99, sum(rate(nvidia_tool_call_latency_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "P99",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"title": "Tool Call Latency",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.05
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.1
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.2.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(nvidia_tool_call_requests_total{status=\"error\"}[5m])) / sum(rate(nvidia_tool_call_requests_total[5m]))",
|
|
"legendFormat": "Error Rate",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Error Rate",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"id": 6,
|
|
"panels": [],
|
|
"title": "Circuit Breaker Details",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "stepAfter",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [
|
|
{
|
|
"options": {
|
|
"0": {
|
|
"color": "red",
|
|
"index": 0,
|
|
"text": "OPEN"
|
|
},
|
|
"1": {
|
|
"color": "green",
|
|
"index": 1,
|
|
"text": "CLOSED"
|
|
},
|
|
"2": {
|
|
"color": "yellow",
|
|
"index": 2,
|
|
"text": "HALF-OPEN"
|
|
}
|
|
},
|
|
"type": "value"
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 10
|
|
},
|
|
"id": 7,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "nvidia_circuit_breaker_state{service=\"nemotron\"}",
|
|
"legendFormat": "State",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Circuit Breaker State 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": "bars",
|
|
"fillOpacity": 80,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 10
|
|
},
|
|
"id": 8,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["sum"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "increase(nvidia_circuit_breaker_state_changes_total[1h])",
|
|
"legendFormat": "{{from_state}} → {{to_state}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Circuit Breaker State Changes (Last Hour)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"id": 9,
|
|
"panels": [],
|
|
"title": "Fallback & Degradation",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "nvidia"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#76b900",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "gemini"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#4285f4",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "ollama"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#ff6b6b",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 17
|
|
},
|
|
"id": 10,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "sum"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(awoooi_ai_requests_total{provider=\"nvidia\"}[5m]))",
|
|
"legendFormat": "nvidia",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(awoooi_ai_requests_total{provider=\"gemini\"}[5m]))",
|
|
"legendFormat": "gemini",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(awoooi_ai_requests_total{provider=\"ollama\"}[5m]))",
|
|
"legendFormat": "ollama",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"title": "AI Provider Traffic Distribution",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
}
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "nvidia"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#76b900",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "gemini"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#4285f4",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "ollama"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#ff6b6b",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 17
|
|
},
|
|
"id": 11,
|
|
"options": {
|
|
"displayLabels": ["percent"],
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"values": ["value"]
|
|
},
|
|
"pieType": "pie",
|
|
"reduceOptions": {
|
|
"calcs": ["sum"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(increase(awoooi_ai_requests_total{provider=\"nvidia\"}[24h]))",
|
|
"legendFormat": "nvidia",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(increase(awoooi_ai_requests_total{provider=\"gemini\"}[24h]))",
|
|
"legendFormat": "gemini",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(increase(awoooi_ai_requests_total{provider=\"ollama\"}[24h]))",
|
|
"legendFormat": "ollama",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"title": "Provider Distribution (24h)",
|
|
"type": "piechart"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 10
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 50
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 17
|
|
},
|
|
"id": 12,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"pluginVersion": "10.2.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "increase(nvidia_fallback_total{target=\"gemini\"}[1h])",
|
|
"legendFormat": "→ Gemini",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "increase(nvidia_fallback_total{target=\"ollama\"}[1h])",
|
|
"legendFormat": "→ Ollama",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Fallback Count (Last Hour)",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 25
|
|
},
|
|
"id": 13,
|
|
"panels": [],
|
|
"title": "Tool Calling Details",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 80,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 26
|
|
},
|
|
"id": 14,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["sum"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "increase(nvidia_tool_calls_total[1h])",
|
|
"legendFormat": "{{tool_name}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Tool Calls by Tool Name (Last Hour)",
|
|
"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": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "line"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 5000
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10000
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 26
|
|
},
|
|
"id": 15,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["mean", "sum"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(nvidia_tokens_used_total{type=\"input\"}[5m])) * 60",
|
|
"legendFormat": "Input Tokens/min",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(nvidia_tokens_used_total{type=\"output\"}[5m])) * 60",
|
|
"legendFormat": "Output Tokens/min",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Token Usage Rate",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 34
|
|
},
|
|
"id": 16,
|
|
"panels": [],
|
|
"title": "Anomaly Frequency (ADR-037)",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "dashed"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 3
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 35
|
|
},
|
|
"id": 17,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["max", "last"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "awoooi_anomaly_frequency{service=\"nvidia-nemotron\"}",
|
|
"legendFormat": "{{alert_name}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "NVIDIA Anomaly Frequency (24h)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 80,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "REPEAT"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "yellow",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "ESCALATE"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "orange",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "PERMANENT_FIX"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "red",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 35
|
|
},
|
|
"id": 18,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": ["sum"],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "increase(awoooi_anomaly_escalation_total{service=\"nvidia-nemotron\"}[1h])",
|
|
"legendFormat": "{{level}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Escalation Events (Last Hour)",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 38,
|
|
"style": "dark",
|
|
"tags": ["nvidia", "nemotron", "tool-calling", "ai", "adr-037"],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "Asia/Taipei",
|
|
"title": "NVIDIA Nemotron Tool Calling",
|
|
"uid": "nvidia-nemotron",
|
|
"version": 1,
|
|
"weekStart": "monday"
|
|
}
|