Movses AslanyanandClaude Sonnet 5.5
fef735c922
Dashboards: observability/dashboards/generate.py (Grafana Foundation SDK) writes k8s/grafana/dashboards/*.json -- a RED dashboard per HTTP service and a system overview -- shipped through a file provider and configMapGenerators, so `kubectl apply -k k8s/` rebuilds them. Verified by deleting Grafana and its volume and re-applying. Adds tracesToMetrics to the Tempo datasource. Alerts: Prometheus rule files delivering to Alertmanager, under a labels/annotations contract enforced by observability/alerts/check_contract.py, with runbooks in docs/runbooks/. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
116 lines
2.3 KiB
JSON
116 lines
2.3 KiB
JSON
{
|
|
"annotations": {},
|
|
"editable": false,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 0,
|
|
"panels": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "tempo"
|
|
},
|
|
"gridPos": {
|
|
"h": 12,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"repeatDirection": "h",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "tempo"
|
|
},
|
|
"filters": [],
|
|
"queryType": "serviceMap",
|
|
"refId": "graph"
|
|
}
|
|
],
|
|
"title": "Service graph",
|
|
"transparent": false,
|
|
"type": "nodeGraph"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 12
|
|
},
|
|
"repeatDirection": "h",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "ledgerline_stream_lag",
|
|
"legendFormat": "{{consumer_group}}",
|
|
"refId": "lag"
|
|
}
|
|
],
|
|
"title": "Stream consumer lag",
|
|
"transparent": false,
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 12
|
|
},
|
|
"repeatDirection": "h",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (service, pool) (ledgerline_db_pool_in_use)",
|
|
"legendFormat": "{{service}} / {{pool}}",
|
|
"refId": "pool"
|
|
}
|
|
],
|
|
"title": "DB pool connections in use",
|
|
"transparent": false,
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"refresh": "15s",
|
|
"schemaVersion": 41,
|
|
"tags": [
|
|
"generated",
|
|
"overview"
|
|
],
|
|
"templating": {},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timezone": "browser",
|
|
"title": "System overview",
|
|
"uid": "overview"
|
|
}
|