Felix FaerberandClaude Opus 4.7
7fcd9df9d3
Bind two ready-to-use dashboards at grafana.t4t-gateway.com: - Logs — All services: per-service log volume timeseries + live tail, with a service selector and a free-text search box. - Hosted-gateway API — errors & PSS inbox: error rate, ack/deliver counters, and a live tail filtered to PSS inbox traffic so the webhook fallback is observable. Datasources + dashboard providers are mounted via Docker configs from hostinger/grafana/ so they survive grafana container restarts and live in git rather than the Grafana UI. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
84 lines
2.6 KiB
JSON
84 lines
2.6 KiB
JSON
{
|
|
"title": "Hosted-gateway API — errors & PSS inbox",
|
|
"uid": "t4t-api-errors",
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"editable": true,
|
|
"refresh": "10s",
|
|
"tags": ["t4t", "api"],
|
|
"time": {"from": "now-1h", "to": "now"},
|
|
"templating": {"list": []},
|
|
"panels": [
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Errors per minute (api + worker)",
|
|
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
|
|
"datasource": {"type": "loki", "uid": "loki"},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (swarm_service) (count_over_time({swarm_service=~\"prod_(api|worker)\"} |~ \"(?i)\\\"level\\\":(50|40)\" [1m]))",
|
|
"legendFormat": "{{swarm_service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "logs", "custom": {"drawStyle": "bars", "fillOpacity": 60}}}
|
|
},
|
|
{
|
|
"type": "stat",
|
|
"title": "Acks last 15m",
|
|
"gridPos": {"h": 8, "w": 6, "x": 12, "y": 0},
|
|
"datasource": {"type": "loki", "uid": "loki"},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(count_over_time({swarm_service=\"prod_api\"} |~ \"ack received\" [15m]))",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"options": {"reduceOptions": {"calcs": ["lastNotNull"]}, "colorMode": "value", "graphMode": "area"}
|
|
},
|
|
{
|
|
"type": "stat",
|
|
"title": "Deliveries last 15m",
|
|
"gridPos": {"h": 8, "w": 6, "x": 18, "y": 0},
|
|
"datasource": {"type": "loki", "uid": "loki"},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(count_over_time({swarm_service=\"prod_api\"} |~ \"envelope dispatched\" |~ \"job_deliver\" [15m]))",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"options": {"reduceOptions": {"calcs": ["lastNotNull"]}, "colorMode": "value", "graphMode": "area"}
|
|
},
|
|
{
|
|
"type": "logs",
|
|
"title": "API — errors",
|
|
"gridPos": {"h": 14, "w": 24, "x": 0, "y": 8},
|
|
"datasource": {"type": "loki", "uid": "loki"},
|
|
"targets": [
|
|
{
|
|
"expr": "{swarm_service=~\"prod_(api|worker)\"} |~ \"(?i)\\\"level\\\":(50|40)\"",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"options": {
|
|
"showTime": true,
|
|
"wrapLogMessage": true,
|
|
"sortOrder": "Descending"
|
|
}
|
|
},
|
|
{
|
|
"type": "logs",
|
|
"title": "PSS inbox traffic",
|
|
"gridPos": {"h": 14, "w": 24, "x": 0, "y": 22},
|
|
"datasource": {"type": "loki", "uid": "loki"},
|
|
"targets": [
|
|
{
|
|
"expr": "{swarm_service=\"prod_api\"} |~ \"pss/inbox|ack received|delivered\"",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"options": {"showTime": true, "wrapLogMessage": true, "sortOrder": "Descending"}
|
|
}
|
|
]
|
|
}
|