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.
411 lines
11 KiB
JSON
411 lines
11 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "HTTP-ответы 5xx по путям (access-лог core, поле StatusCode). Ручка, отдающая 5xx, обычно соответствует исключению ниже (в той же панели логов).",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 60,
|
|
"lineWidth": 1,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 1,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum by (Path) (count_over_time({service=\"core\"} | json | StatusCode >= 500 [1m]))",
|
|
"legendFormat": "{{Path}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "HTTP 5xx по путям (core), /мин",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "Строки с необработанным исключением (Serilog-поле \"@x\") по deal-процессам. Каждое такое событие пишется access-логом/аудитом и означает баг либо недоступную зависимость.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 60,
|
|
"lineWidth": 1,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum by (service) (count_over_time({service=~\"core|telegram-service|ai-service|ml-service\"} |~ \"\\\"@x\\\":\\\"\" [1m]))",
|
|
"legendFormat": "{{service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Исключения по сервисам, /мин",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "Строки уровня Error/Fatal (Serilog-поле @l) по deal-процессам. Дополняет панель исключений: ловит и логированные, но не брошенные ошибки.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"lineWidth": 1,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum by (service) (count_over_time({service=~\"core|telegram-service|ai-service|ml-service\"} |~ \"@l\\\":\\\"(Error|Fatal)\" [1m]))",
|
|
"legendFormat": "{{service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Error/Fatal по сервисам, /мин",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "gRPC-вызовы с не-OK статусом (access-лог RpcCallLoggingInterceptor: поля RpcMethod/GrpcStatus). Cancelled/DeadlineExceeded — клиентские отмены, Unavailable/Unknown — сбои. gRPC-health не логируется.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 60,
|
|
"lineWidth": 1,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum by (service) (count_over_time({service=~\"core|telegram-service|ai-service|ml-service\"} |= \"gRPC \" | json | GrpcStatus != \"OK\" [1m]))",
|
|
"legendFormat": "{{service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "gRPC-вызовы с ошибкой по сервисам, /мин",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "Суммарно Error/Fatal по всем deal-процессам за 5 минут; >0 — повод открыть панель логов ниже.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum(count_over_time({service=~\"core|telegram-service|ai-service|ml-service\"} |~ \"@l\\\":\\\"(Error|Fatal)\" [5m]))",
|
|
"legendFormat": "ошибок за 5м",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Error/Fatal за 5 мин (все сервисы)",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "HTTP 5xx (core) за последний час.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum(count_over_time({service=\"core\"} | json | StatusCode >= 500 [1h]))",
|
|
"legendFormat": "HTTP 5xx за 1ч",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "HTTP 5xx за 1 час (core)",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"description": "Строки Error/Fatal и записи с исключением (\"@x\") по всем deal-процессам. Разверните строку для текста исключения и стека.",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 21
|
|
},
|
|
"id": 7,
|
|
"options": {
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true,
|
|
"showTime": true,
|
|
"sortOrder": "Descending",
|
|
"wrapLogMessage": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "{service=~\"core|telegram-service|ai-service|ml-service\"} |~ \"@l\\\":\\\"(Error|Fatal)\"",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "{service=~\"core|telegram-service|ai-service|ml-service\"} |~ \"\\\"@x\\\":\\\"\"",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Лента ошибок и исключений",
|
|
"type": "logs"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"deal"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "Deal-Errors",
|
|
"uid": "deal-errors",
|
|
"version": 1,
|
|
"weekStart": ""
|
|
}
|