overview.json was missing a comma between the "Health Status" and "App Error Rate (from logs)" panel objects, making the whole file invalid JSON. Grafana's file provisioner skips dashboards that fail to parse, so the entire "trails.cool Overview" dashboard (5 panels) never loaded — a silent gap in observability. Validated with json.load. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
181 lines
4.1 KiB
JSON
181 lines
4.1 KiB
JSON
{
|
|
"title": "trails.cool Overview",
|
|
"uid": "trails-overview",
|
|
"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": "Request Rate",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(http_request_duration_seconds_count[5m])) by (job)",
|
|
"legendFormat": "{{job}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Error Rate",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(caddy_http_request_duration_seconds_count{code=~\"5..\"}[5m])) / sum(rate(caddy_http_request_duration_seconds_count[5m])) * 100",
|
|
"legendFormat": "Error %"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Latency p50 / p95 / p99",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p95"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p99"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "Health Status",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "up",
|
|
"legendFormat": "{{job}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "DOWN",
|
|
"color": "red"
|
|
},
|
|
"1": {
|
|
"text": "UP",
|
|
"color": "green"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"title": "App Error Rate (from logs)",
|
|
"description": "Error-level log entries per second from Pino (level 50=error, 60=fatal). Captures crashes and unhandled errors that metrics may miss.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"expr": "sum(rate({service=\"journal\"} |~ \"\\\"level\\\":(50|60)\" [5m])) or vector(0)",
|
|
"legendFormat": "journal"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"expr": "sum(rate({service=\"planner\"} |~ \"\\\"level\\\":(50|60)\" [5m])) or vector(0)",
|
|
"legendFormat": "planner"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 15
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|