Ansible/DevOpsLab
Template
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat: Завершена реализация универсальной лаборатории

Browse Source 
- Добавлена полная поддержка Istio service mesh с Kiali
- Интегрированы Helm charts (nginx, prometheus-stack)
- Созданы Grafana дашборды для Istio мониторинга
- Добавлен HTML генератор отчетов с красивым дизайном
- Созданы скрипты для снапшотов и восстановления
- Добавлена поддержка Istio Bookinfo demo
- Обновлена документация с полным описанием возможностей

Компоненты:
- Istio с Telemetry и Traffic Policy
- Prometheus + Grafana с автопровижинингом дашбордов
- HTML отчеты с анализом статусов
- Снапшоты и восстановление состояния
- Полная интеграция с Kubernetes

Автор: Сергей Антропов
Сайт: https://devops.org.ru
This commit is contained in:
Sergey Antropoff
2025-10-22 13:08:55 +03:00
parent b4881da7c5
commit 33ada54c12
13 changed files with 712 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
files/grafana/dashboards/istio-overview.json Normal file
View File

@@ -0,0 +1,69 @@
{
"id": null,
"uid": "istio-overview",
"title": "Istio • Overview",
"schemaVersion": 36,
"version": 1,
"timezone": "browser",
"tags": ["istio", "sre", "mesh"],
"panels": [
{
"type": "stat",
"title": "Global RPS",
"gridPos": {"h": 4, "w": 6, "x": 0, "y": 0},
"targets": [
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\"}[5m]))",
"legendFormat": "rps"
}
]
},
{
"type": "stat",
"title": "Success Rate",
"gridPos": {"h": 4, "w": 6, "x": 6, "y": 0},
"targets": [
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\",response_code!~\"5..\"}[5m])) / sum(rate(istio_requests_total{reporter=\"destination\"}[5m]))",
"legendFormat": "success"
}
],
"options": {"reduceOptions":{"calcs":["lastNotNull"]},"colorMode":"value","graphMode":"none"},
"fieldConfig":{"defaults":{"unit":"percentunit","min":0,"max":1}}
},
{
"type": "timeseries",
"title": "Latency (ms) p50/p95/p99",
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 4},
"targets": [
{
"expr": "histogram_quantile(0.5, sum(rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\"}[5m])) by (le))",
"legendFormat": "p50"
},
{
"expr": "histogram_quantile(0.95, sum(rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\"}[5m])) by (le))",
"legendFormat": "p95"
},
{
"expr": "histogram_quantile(0.99, sum(rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\"}[5m])) by (le))",
"legendFormat": "p99"
}
],
"fieldConfig":{"defaults":{"unit":"ms"}}
},
{
"type": "timeseries",
"title": "RPS by Workload",
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 12},
"targets": [
{
"expr": "sum by (destination_workload) (rate(istio_requests_total{reporter=\"destination\"}[5m]))",
"legendFormat": "{{destination_workload}}"
}
]
}
],
"templating": {
"list": []
}
}

80
files/grafana/dashboards/service-sli.json Normal file
View File

@@ -0,0 +1,80 @@
{
"id": null,
"uid": "service-sli",
"title": "Service • SLI",
"schemaVersion": 36,
"version": 1,
"timezone": "browser",
"tags": ["istio", "sre", "sli"],
"templating": {
"list": [
{
"name": "namespace",
"type": "query",
"datasource": "${DS_PROMETHEUS}",
"query": "label_values(istio_requests_total, destination_namespace)",
"refresh": 1
},
{
"name": "workload",
"type": "query",
"datasource": "${DS_PROMETHEUS}",
"query": "label_values(istio_requests_total{destination_namespace=\"$namespace\"}, destination_workload)",
"refresh": 1
}
]
},
"panels": [
{
"type": "stat",
"title": "Success Rate",
"gridPos": {"h": 4, "w": 6, "x": 0, "y": 0},
"targets": [
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\",response_code!~\"5..\"}[5m])) / sum(rate(istio_requests_total{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\"}[5m]))",
"legendFormat": "success"
}
],
"fieldConfig":{"defaults":{"unit":"percentunit","min":0,"max":1}}
},
{
"type": "timeseries",
"title": "Latency (ms) p50/p95/p99",
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 4},
"targets": [
{
"expr": "histogram_quantile(0.5, sum by (le) (rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\"}[5m])))",
"legendFormat": "p50"
},
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\"}[5m])))",
"legendFormat": "p95"
},
{
"expr": "histogram_quantile(0.99, sum by (le) (rate(istio_request_duration_milliseconds_bucket{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\"}[5m])))",
"legendFormat": "p99"
}
],
"fieldConfig":{"defaults":{"unit":"ms"}}
},
{
"type": "timeseries",
"title": "RPS (2xx/4xx/5xx)",
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 12},
"targets": [
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\",response_code=~\"2..\"}[5m]))",
"legendFormat": "2xx"
},
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\",response_code=~\"4..\"}[5m]))",
"legendFormat": "4xx"
},
{
"expr": "sum(rate(istio_requests_total{reporter=\"destination\",destination_namespace=\"$namespace\",destination_workload=\"$workload\",response_code=~\"5..\"}[5m]))",
"legendFormat": "5xx"
}
]
}
]
}