feat: Implement runner execution pipeline with planner dispatch and execution services
Some checks failed
Docs CI / lint-and-preview (push) Has been cancelled
Some checks failed
Docs CI / lint-and-preview (push) Has been cancelled
- Introduced RunnerBackgroundService to handle execution of runner segments. - Added RunnerExecutionService for processing segments and aggregating results. - Implemented PlannerQueueDispatchService to manage dispatching of planner messages. - Created PlannerQueueDispatcherBackgroundService for leasing and processing planner queue messages. - Developed ScannerReportClient for interacting with the scanner service. - Enhanced observability with SchedulerWorkerMetrics for tracking planner and runner performance. - Added comprehensive documentation for the new runner execution pipeline and observability metrics. - Implemented event emission for rescan activity and scanner report readiness.
This commit is contained in:
Vladimir Moushkov
261
docs/ops/scheduler-worker-grafana-dashboard.json
Normal file
261
docs/ops/scheduler-worker-grafana-dashboard.json
Normal file
@@ -0,0 +1,261 @@
|
||||
{
|
||||
"title": "Scheduler Worker – Planning & Rescan",
|
||||
"uid": "scheduler-worker-observability",
|
||||
"schemaVersion": 38,
|
||||
"version": 1,
|
||||
"editable": true,
|
||||
"timezone": "",
|
||||
"graphTooltip": 0,
|
||||
"time": {
|
||||
"from": "now-24h",
|
||||
"to": "now"
|
||||
},
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "datasource",
|
||||
"type": "datasource",
|
||||
"query": "prometheus",
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"current": {}
|
||||
},
|
||||
{
|
||||
"name": "mode",
|
||||
"label": "Mode",
|
||||
"type": "query",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"query": "label_values(scheduler_planner_runs_total, mode)",
|
||||
"refresh": 1,
|
||||
"multi": true,
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"selected": false,
|
||||
"text": "All",
|
||||
"value": ".*"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Planner Runs per Status",
|
||||
"type": "timeseries",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"displayName": "{{status}}"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "bottom"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (rate(scheduler_planner_runs_total{mode=~\"$mode\"}[5m]))",
|
||||
"legendFormat": "{{status}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "Planner Latency P95 (s)",
|
||||
"type": "timeseries",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "bottom"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, sum by (le) (rate(scheduler_planner_latency_seconds_bucket{mode=~\"$mode\"}[5m])))",
|
||||
"legendFormat": "p95",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "Runner Segments per Status",
|
||||
"type": "timeseries",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"displayName": "{{status}}"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "bottom"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (status) (rate(scheduler_runner_segments_total{mode=~\"$mode\"}[5m]))",
|
||||
"legendFormat": "{{status}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "New Findings per Severity",
|
||||
"type": "timeseries",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"displayName": "{{severity}}"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "bottom"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(scheduler_runner_delta_critical_total{mode=~\"$mode\"}[5m]))",
|
||||
"legendFormat": "critical",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(scheduler_runner_delta_high_total{mode=~\"$mode\"}[5m]))",
|
||||
"legendFormat": "high",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(scheduler_runner_delta_total{mode=~\"$mode\"}[5m]))",
|
||||
"legendFormat": "total",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "Runner Backlog by Schedule",
|
||||
"type": "table",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"displayName": "{{scheduleId}}",
|
||||
"unit": "none"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"showHeader": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max by (scheduleId) (scheduler_runner_backlog{mode=~\"$mode\"})",
|
||||
"format": "table",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "Active Runs",
|
||||
"type": "stat",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "none"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"orientation": "horizontal",
|
||||
"textMode": "value"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(scheduler_runs_active{mode=~\"$mode\"})",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user