Rustam Khalimov
27c7831910
ci / build-test (push) Canceled after 0s
SaaS-мониторинг Telegram: ядро (модули Cards/Kanban/Pipeline/Tenants/Settings/ Discovery, Api, Infrastructure), сервисы telegram/ai/ml/storage, фронт Vue, контракты и grpc-hosting, деплой-конфиги (dev/prod/observability/CI-раннер), Gitea Actions CI, документация (ТЗ, техдок, api-map, код-стайл, планы, бэклог). Текущее состояние: все этапы роадмапа 0–12 закрыты, сборка 5 sln 0/0, тесты 1340/130/52/38/9 зелёные.
607 lines
16 KiB
JSON
607 lines
16 KiB
JSON
{
|
||
"annotations": {
|
||
"list": []
|
||
},
|
||
"editable": true,
|
||
"graphTooltip": 1,
|
||
"id": null,
|
||
"links": [],
|
||
"panels": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Суммарная нагрузка всех deal-процессов (HTTP + gRPC) в секунду. Источник — OTel-инструментация ASP.NET Core (метрика http.server.request.duration, счётчик _count), scrape /metrics :9464.",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"color": {
|
||
"mode": "thresholds"
|
||
},
|
||
"mappings": [],
|
||
"thresholds": {
|
||
"mode": "absolute",
|
||
"steps": [
|
||
{
|
||
"color": "green",
|
||
"value": null
|
||
}
|
||
]
|
||
},
|
||
"unit": "reqps"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 5,
|
||
"w": 6,
|
||
"x": 0,
|
||
"y": 0
|
||
},
|
||
"id": 1,
|
||
"options": {
|
||
"colorMode": "value",
|
||
"graphMode": "area",
|
||
"justifyMode": "auto",
|
||
"orientation": "auto",
|
||
"reduceOptions": {
|
||
"calcs": [
|
||
"lastNotNull"
|
||
],
|
||
"fields": "",
|
||
"values": false
|
||
},
|
||
"textMode": "auto"
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum(rate(http_server_request_duration_seconds_count[$__rate_interval]))",
|
||
"legendFormat": "RPS",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "RPS (HTTP+gRPC) сейчас",
|
||
"type": "stat"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Активные непросроченные сессии пользователей тенантов и операторов (public.sessions + public.operator_sessions). Агрегат по всем тенантам — в метке нет tenantId (низкая кардинальность).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"color": {
|
||
"mode": "thresholds"
|
||
},
|
||
"mappings": [],
|
||
"thresholds": {
|
||
"mode": "absolute",
|
||
"steps": [
|
||
{
|
||
"color": "green",
|
||
"value": null
|
||
}
|
||
]
|
||
},
|
||
"unit": "short"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 5,
|
||
"w": 6,
|
||
"x": 6,
|
||
"y": 0
|
||
},
|
||
"id": 2,
|
||
"options": {
|
||
"colorMode": "value",
|
||
"graphMode": "area",
|
||
"justifyMode": "auto",
|
||
"orientation": "auto",
|
||
"reduceOptions": {
|
||
"calcs": [
|
||
"lastNotNull"
|
||
],
|
||
"fields": "",
|
||
"values": false
|
||
},
|
||
"textMode": "auto"
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "deal_sessions_active",
|
||
"legendFormat": "сессии",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "Активные сессии",
|
||
"type": "stat"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Суммарная глубина очереди пайплайна (new+filtered) по всем тенантам; считает фоновый DealMetricsCollector через PipelineProcessingService.QueueCountsAsync.",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"color": {
|
||
"mode": "thresholds"
|
||
},
|
||
"mappings": [],
|
||
"thresholds": {
|
||
"mode": "absolute",
|
||
"steps": [
|
||
{
|
||
"color": "green",
|
||
"value": null
|
||
}
|
||
]
|
||
},
|
||
"unit": "short"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 5,
|
||
"w": 6,
|
||
"x": 12,
|
||
"y": 0
|
||
},
|
||
"id": 3,
|
||
"options": {
|
||
"colorMode": "value",
|
||
"graphMode": "area",
|
||
"justifyMode": "auto",
|
||
"orientation": "auto",
|
||
"reduceOptions": {
|
||
"calcs": [
|
||
"lastNotNull"
|
||
],
|
||
"fields": "",
|
||
"values": false
|
||
},
|
||
"textMode": "auto"
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "deal_pipeline_queue_depth",
|
||
"legendFormat": "очередь",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "Очередь пайплайна",
|
||
"type": "stat"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Суммарная глубина очереди обучения ML (MlOutbox) по всем тенантам; считает фоновый DealMetricsCollector через IMlLearningStore.CountOutboxAsync. Рост при недоступности ml-service.",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"color": {
|
||
"mode": "thresholds"
|
||
},
|
||
"mappings": [],
|
||
"thresholds": {
|
||
"mode": "absolute",
|
||
"steps": [
|
||
{
|
||
"color": "green",
|
||
"value": null
|
||
}
|
||
]
|
||
},
|
||
"unit": "short"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 5,
|
||
"w": 6,
|
||
"x": 18,
|
||
"y": 0
|
||
},
|
||
"id": 4,
|
||
"options": {
|
||
"colorMode": "value",
|
||
"graphMode": "area",
|
||
"justifyMode": "auto",
|
||
"orientation": "auto",
|
||
"reduceOptions": {
|
||
"calcs": [
|
||
"lastNotNull"
|
||
],
|
||
"fields": "",
|
||
"values": false
|
||
},
|
||
"textMode": "auto"
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "deal_ml_outbox_depth",
|
||
"legendFormat": "outbox",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "Очередь ML-outbox",
|
||
"type": "stat"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "RPS по сервисам (метка service из таргетов Prometheus). Включает HTTP-запросы core и gRPC-вызовы всех 4 процессов (gRPC идёт как ASP.NET Core-запрос с route = имя метода).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "reqps"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 0,
|
||
"y": 5
|
||
},
|
||
"id": 5,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum by (service) (rate(http_server_request_duration_seconds_count[$__rate_interval]))",
|
||
"legendFormat": "{{service}}",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "RPS по сервисам",
|
||
"type": "timeseries"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "p95 длительности запроса по сервисам (OTel-гистограмма http.server.request.duration). Рост при недоступности БД/внешних вызовов (ИИ-провайдер, ml/telegram-service).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "s"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 12,
|
||
"y": 5
|
||
},
|
||
"id": 6,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "histogram_quantile(0.95, sum by (le, service) (rate(http_server_request_duration_seconds_bucket[$__rate_interval])))",
|
||
"legendFormat": "{{service}}",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "Длительность запроса p95 по сервисам",
|
||
"type": "timeseries"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Доля HTTP/gRPC-запросов с кодом ответа 5xx в секунду по сервисам (метка http_response_status_code).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "reqps"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 0,
|
||
"y": 13
|
||
},
|
||
"id": 7,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum by (service) (rate(http_server_request_duration_seconds_count{http_response_status_code=~\"5..\"}[$__rate_interval]))",
|
||
"legendFormat": "{{service}}",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "Ошибки 5xx по сервисам",
|
||
"type": "timeseries"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Токены платного ИИ (по видам prompt/completion) и оценка токенов локальных ML-вызовов, токенов/сек. Инкремент — общая с ядром точка записи token_usage_events (TokenUsageRecorder).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "short"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 12,
|
||
"y": 13
|
||
},
|
||
"id": 8,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum by (type) (rate(deal_ai_tokens_total[$__rate_interval]))",
|
||
"legendFormat": "ai/{{type}}",
|
||
"refId": "A"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum(rate(deal_ml_tokens_total[$__rate_interval]))",
|
||
"legendFormat": "ml/prompt",
|
||
"refId": "B"
|
||
}
|
||
],
|
||
"title": "Токены AI/ML, tokens/s",
|
||
"type": "timeseries"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Вызовы платного ИИ и локального ML в секунду (соответствуют событиям token_usage_events: kind=ai|ml).",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "reqps"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 0,
|
||
"y": 21
|
||
},
|
||
"id": 9,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum(rate(deal_ai_calls_total[$__rate_interval]))",
|
||
"legendFormat": "AI-вызовы",
|
||
"refId": "A"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "sum(rate(deal_ml_calls_total[$__rate_interval]))",
|
||
"legendFormat": "ML-вызовы",
|
||
"refId": "B"
|
||
}
|
||
],
|
||
"title": "Вызовы AI/ML, calls/s",
|
||
"type": "timeseries"
|
||
},
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"description": "Топ-10 типов событий аудита по частоте (метки event/actor низкокардинальные; tenantId/userId в метрики не попадают). Полная лента с актором — public.audit_log через GET /api/operator/audit.",
|
||
"fieldConfig": {
|
||
"defaults": {
|
||
"custom": {
|
||
"drawStyle": "line",
|
||
"fillOpacity": 10,
|
||
"lineWidth": 1,
|
||
"showPoints": "never"
|
||
},
|
||
"unit": "reqps"
|
||
},
|
||
"overrides": []
|
||
},
|
||
"gridPos": {
|
||
"h": 8,
|
||
"w": 12,
|
||
"x": 12,
|
||
"y": 21
|
||
},
|
||
"id": 10,
|
||
"options": {
|
||
"legend": {
|
||
"calcs": [],
|
||
"displayMode": "list",
|
||
"placement": "bottom",
|
||
"showLegend": true
|
||
},
|
||
"tooltip": {
|
||
"mode": "multi",
|
||
"sort": "desc"
|
||
}
|
||
},
|
||
"targets": [
|
||
{
|
||
"datasource": {
|
||
"type": "prometheus",
|
||
"uid": "prometheus"
|
||
},
|
||
"editorMode": "code",
|
||
"expr": "topk(10, sum by (event) (rate(deal_audit_events_total[$__rate_interval])))",
|
||
"legendFormat": "{{event}}",
|
||
"refId": "A"
|
||
}
|
||
],
|
||
"title": "События аудита по типам (top-10)",
|
||
"type": "timeseries"
|
||
}
|
||
],
|
||
"refresh": "30s",
|
||
"schemaVersion": 39,
|
||
"tags": [
|
||
"deal",
|
||
"metrics"
|
||
],
|
||
"templating": {
|
||
"list": []
|
||
},
|
||
"time": {
|
||
"from": "now-6h",
|
||
"to": "now"
|
||
},
|
||
"timepicker": {},
|
||
"timezone": "",
|
||
"title": "Deal-Metrics-Overview",
|
||
"uid": "deal-metrics",
|
||
"version": 1,
|
||
"weekStart": ""
|
||
}
|