partly or unimplemented features - now implemented
This commit is contained in:
master
493
devops/telemetry/dashboards/stella-ops-gateway-performance.json
Normal file
493
devops/telemetry/dashboards/stella-ops-gateway-performance.json
Normal file
@@ -0,0 +1,493 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "Stella Ops Gateway (StellaRouter) — Performance Curve Modeling & k6 Metrics",
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 2,
|
||||
"id": null,
|
||||
"iteration": 1738972800000,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"id": 1,
|
||||
"panels": [],
|
||||
"title": "Gateway Overview",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 2 },
|
||||
{ "color": "red", "value": 5 }
|
||||
]
|
||||
},
|
||||
"unit": "ms"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
|
||||
"id": 2,
|
||||
"options": {
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P50",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Routing Latency P50",
|
||||
"type": "gauge"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 3 },
|
||||
{ "color": "red", "value": 5 }
|
||||
]
|
||||
},
|
||||
"unit": "ms"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 1 },
|
||||
"id": 3,
|
||||
"options": {
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P99",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Routing Latency P99",
|
||||
"type": "gauge"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "red", "value": 0.01 }
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 1 },
|
||||
"id": 4,
|
||||
"options": {
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(gateway_errors_total{job=\"gateway\"}[$__rate_interval])) / sum(rate(gateway_requests_total{job=\"gateway\"}[$__rate_interval]))",
|
||||
"legendFormat": "Error Rate",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Error Rate",
|
||||
"type": "gauge"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 40000 },
|
||||
{ "color": "red", "value": 50000 }
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 1 },
|
||||
"id": 5,
|
||||
"options": {
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(gateway_requests_total{job=\"gateway\"}[$__rate_interval]))",
|
||||
"legendFormat": "RPS",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests Per Second",
|
||||
"type": "gauge"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
|
||||
"id": 10,
|
||||
"panels": [],
|
||||
"title": "Latency Distribution",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"spanNulls": false
|
||||
},
|
||||
"unit": "ms"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
|
||||
"id": 11,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P50",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.90, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P90",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P95",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "P99",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"title": "Request Latency Percentiles (Overall)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10
|
||||
},
|
||||
"unit": "ms"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
|
||||
"id": 12,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(gateway_request_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le, service))",
|
||||
"legendFormat": "{{service}} P99",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "P99 Latency by Service",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
|
||||
"id": 20,
|
||||
"panels": [],
|
||||
"title": "Throughput & Rate Limiting",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 15
|
||||
},
|
||||
"unit": "reqps"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 },
|
||||
"id": 21,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(gateway_requests_total{job=\"gateway\"}[$__rate_interval])) by (service)",
|
||||
"legendFormat": "{{service}}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(gateway_requests_total{job=\"gateway\"}[$__rate_interval]))",
|
||||
"legendFormat": "Total",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "RPS by Service",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "bars",
|
||||
"lineWidth": 1,
|
||||
"fillOpacity": 80
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
|
||||
"id": 22,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(gateway_ratelimit_total{job=\"gateway\"}[$__rate_interval])) by (route)",
|
||||
"legendFormat": "{{route}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Rate-Limited Requests by Route",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
|
||||
"id": 30,
|
||||
"panels": [],
|
||||
"title": "Pipeline Breakdown",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"stacking": { "mode": "none" }
|
||||
},
|
||||
"unit": "ms"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 24 },
|
||||
"id": 31,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(gateway_auth_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "Auth P95",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(gateway_routing_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "Routing P95",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum(rate(gateway_transport_duration_bucket{job=\"gateway\"}[$__rate_interval])) by (le))",
|
||||
"legendFormat": "Transport P95",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"title": "P95 Latency Breakdown (Auth / Routing / Transport)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 20,
|
||||
"stacking": { "mode": "normal" }
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 24 },
|
||||
"id": 32,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(gateway_errors_total{job=\"gateway\"}[$__rate_interval])) by (status)",
|
||||
"legendFormat": "{{status}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Errors by Status Code",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 32 },
|
||||
"id": 40,
|
||||
"panels": [],
|
||||
"title": "Connections & Resources",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 33 },
|
||||
"id": 41,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gateway_active_connections{job=\"gateway\"}",
|
||||
"legendFormat": "Active Connections",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "gateway_registered_endpoints{job=\"gateway\"}",
|
||||
"legendFormat": "Registered Endpoints",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Active Connections & Endpoints",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "${datasource}",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineInterpolation": "smooth",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10
|
||||
},
|
||||
"unit": "decbytes"
|
||||
}
|
||||
},
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 33 },
|
||||
"id": 42,
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } },
|
||||
"targets": [
|
||||
{
|
||||
"expr": "process_resident_memory_bytes{job=\"gateway\"}",
|
||||
"legendFormat": "Resident Memory",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "process_virtual_memory_bytes{job=\"gateway\"}",
|
||||
"legendFormat": "Virtual Memory",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "dotnet_gc_heap_size_bytes{job=\"gateway\"}",
|
||||
"legendFormat": "GC Heap",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 36,
|
||||
"style": "dark",
|
||||
"tags": ["stella-ops", "gateway", "performance", "k6"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": { "selected": false, "text": "Prometheus", "value": "Prometheus" },
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"name": "datasource",
|
||||
"options": [],
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
"type": "datasource"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": { "from": "now-1h", "to": "now" },
|
||||
"timepicker": {},
|
||||
"timezone": "utc",
|
||||
"title": "Stella Ops Gateway — Performance Curve Modeling",
|
||||
"uid": "stella-ops-gateway-performance",
|
||||
"version": 1
|
||||
}
|
||||
Reference in New Issue
Block a user