49aadd04a9
Health endpoints: - /api/health (Journal) and /health (Planner) with DB connectivity check - Docker healthchecks updated to use app health endpoints Structured logging: - Pino with JSON output in production, pretty-print in dev - Request logging middleware in Planner (method, path, status, duration) - Replaced console.log/error with structured logger in email and auth flows Prometheus metrics: - prom-client with default Node.js metrics + custom histograms/gauges - /metrics endpoints on both apps - http_request_duration, planner_active_sessions, brouter_request_duration Monitoring stack: - Prometheus, Loki, Grafana containers in docker-compose - Grafana provisioned with datasources, dashboards, and alert rules - Caddy access logging (JSON to stdout for Loki) - grafana.trails.cool with basic auth via Caddy Dashboards and alerting: - Overview: request rate, error rate, latency p50/p95/p99 - Planner: active sessions, connected clients, BRouter latency - Infrastructure: memory, CPU, event loop lag - Alerts: disk >80%, app down 2min, error rate >5% Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
57 lines
2 KiB
JSON
57 lines
2 KiB
JSON
{
|
|
"dashboard": {
|
|
"title": "trails.cool Overview",
|
|
"uid": "trails-overview",
|
|
"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(http_request_duration_seconds_count{status=~\"5..\"}[5m])) / sum(rate(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" } } }] }
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|