62e208d850
Adds four metrics surfaced via the existing /metrics endpoint:
- overpass_cache_events_total{result=hit|miss|coalesced}
- overpass_cache_size (gauge)
- overpass_upstream_duration_seconds (histogram)
- overpass_upstream_requests_total{status} — covers 2xx/4xx/5xx and
an explicit "error" label for network-level failures
Grafana dashboards/planner.json gets a new row:
- Upstream health (5m 2xx success ratio, red <90%, green >99%)
- Cache hit ratio
- Cache size
- Upstream p95 latency
Plus timeseries panels for cache event breakdown, upstream status
over time, and p50/p95/p99 upstream latency.
The success-rate formula uses clamp_min(..., 1) on the denominator so
it doesn't NaN when traffic is zero.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
264 lines
5.6 KiB
JSON
264 lines
5.6 KiB
JSON
{
|
|
"title": "Planner",
|
|
"uid": "trails-planner",
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"name": "Deploys",
|
|
"enable": true,
|
|
"datasource": {
|
|
"type": "grafana",
|
|
"uid": "-- Grafana --"
|
|
},
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"target": {
|
|
"limit": 100,
|
|
"matchAny": false,
|
|
"tags": [
|
|
"deploy"
|
|
],
|
|
"type": "tags"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"timezone": "browser",
|
|
"refresh": "30s",
|
|
"panels": [
|
|
{
|
|
"title": "Active Sessions",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "planner_active_sessions",
|
|
"legendFormat": "Sessions"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Connected Clients",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "planner_connected_clients",
|
|
"legendFormat": "Clients"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "BRouter Latency",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, rate(brouter_request_duration_seconds_bucket[5m]))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, rate(brouter_request_duration_seconds_bucket[5m]))",
|
|
"legendFormat": "p95"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Request Rate by Route",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(http_request_duration_seconds_count{job=\"planner\"}[5m])) by (route)",
|
|
"legendFormat": "{{route}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Overpass Upstream Health (5m success rate)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(overpass_upstream_requests_total{status=~\"2..\"}[5m])) / clamp_min(sum(rate(overpass_upstream_requests_total[5m])), 1)",
|
|
"legendFormat": "success"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "red", "value": null },
|
|
{ "color": "orange", "value": 0.9 },
|
|
{ "color": "green", "value": 0.99 }
|
|
]
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Overpass Cache Hit Ratio (5m)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 14
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(overpass_cache_events_total{result=\"hit\"}[5m])) / clamp_min(sum(rate(overpass_cache_events_total[5m])), 1)",
|
|
"legendFormat": "hit ratio"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Overpass Cache Size",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 14
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "overpass_cache_size",
|
|
"legendFormat": "entries"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Overpass Upstream p95",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 14
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(overpass_upstream_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p95"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Overpass Cache Events",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 19
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (result) (rate(overpass_cache_events_total[5m]))",
|
|
"legendFormat": "{{result}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Overpass Upstream Status",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 19
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (status) (rate(overpass_upstream_requests_total[5m]))",
|
|
"legendFormat": "{{status}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Overpass Upstream Latency",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 26
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum(rate(overpass_upstream_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(overpass_upstream_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p95"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum(rate(overpass_upstream_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p99"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|