Compare commits
44 Commits
dev-3
...
e35415d3d1
| Author | SHA1 | Date | |
|---|---|---|---|
| e35415d3d1 | |||
| 25dd64fc01 | |||
|
51c2a562fa | ||
| 4d328444bd | |||
| 804ecd6107 | |||
| d736688c62 | |||
| 1bfe772a0d | |||
| e360e5e215 | |||
| 76cb533851 | |||
| 30465e0bea | |||
| 0a73f9844e | |||
| 2ee1977956 | |||
| 220b24e867 | |||
| fb33da172a | |||
|
|
9baee2ceb7 | ||
| 60487b5488 | |||
| 07982ee0f2 | |||
| 6c51a82dce | |||
| 5e57e5214c | |||
| 8e595bf7f2 | |||
| 34b0345983 | |||
| 1dceab6479 | |||
| 0cdc40cd21 | |||
| fde1f14708 | |||
| 5a0c2d6942 | |||
| 153a7d4807 | |||
| 0944175807 | |||
| 3ee72ec48a | |||
| dd8b1c02a4 | |||
| 9e03c1f6f2 | |||
| 75cd722cc4 | |||
| 95fabdc0d1 | |||
| 8be219778c | |||
| a075ef6772 | |||
| 8595fc5886 | |||
| f7b08ae9e8 | |||
| 1eb11e454d | |||
| 14b19699c5 | |||
| 1db579797d | |||
| 9ec3f02767 | |||
| 5e10204137 | |||
| 5b8833a67f | |||
| 2661b3865e | |||
|
|
539c074e9f |
409
.cursor/rules/my-custom-rule.mdc
Normal file
409
.cursor/rules/my-custom-rule.mdc
Normal file
@@ -0,0 +1,409 @@
|
||||
---
|
||||
name: prod-project-rules
|
||||
description: Правила работы с проектом prod - инфраструктура, боты, CI/CD
|
||||
---
|
||||
|
||||
# Правила работы с проектом prod
|
||||
|
||||
## 📋 Обзор проекта
|
||||
|
||||
**prod** — проект для управления Telegram ботами и мониторинга инфраструктуры в продакшене.
|
||||
|
||||
### Основные компоненты:
|
||||
- **Инфраструктура мониторинга**: Prometheus, Grafana, Alertmanager, Uptime Kuma
|
||||
- **Telegram боты**: telegram-helper-bot, AnonBot (в отдельных поддиректориях)
|
||||
- **CI/CD**: GitHub Actions с автоматическим тестированием, созданием PR и деплоем
|
||||
- **Контейнеризация**: Docker Compose для оркестрации сервисов
|
||||
|
||||
---
|
||||
|
||||
## 🌿 Работа с ветками и Git
|
||||
|
||||
### Структура веток:
|
||||
- **`main`** — продакшен ветка, защищена, только через PR
|
||||
- **`develop`** — ветка разработки (опционально)
|
||||
- **`dev-*`** — ветки для разработки (например, `dev-4`)
|
||||
- **`feature/**`** — ветки для новых фич
|
||||
|
||||
### Workflow разработки:
|
||||
|
||||
1. **Создание ветки для разработки:**
|
||||
```bash
|
||||
git checkout -b dev-4 # или feature/my-feature
|
||||
```
|
||||
|
||||
2. **Перед коммитом - проверка качества кода:**
|
||||
```bash
|
||||
make code-quality # Проверяет форматирование, импорты, линтинг
|
||||
# Или автоматически исправить:
|
||||
make format # Исправить форматирование
|
||||
make import-fix # Исправить сортировку импортов
|
||||
```
|
||||
|
||||
3. **Коммит и пуш:**
|
||||
```bash
|
||||
git add .
|
||||
git commit -m "feat: описание изменений"
|
||||
git push -u origin dev-4
|
||||
```
|
||||
|
||||
4. **Автоматические действия после push:**
|
||||
- ✅ Запускаются тесты (Black, isort, flake8, pytest)
|
||||
- ✅ При успешных тестах автоматически создается/обновляется PR в `main`
|
||||
- ✅ Отправляется уведомление в Telegram
|
||||
|
||||
5. **После мержа PR в `main`:**
|
||||
- ✅ Автоматически запускается деплой в продакшен (`deploy.yml`)
|
||||
- ✅ Проверяются токены ботов
|
||||
- ✅ Выполняется деплой на сервер
|
||||
- ✅ Запускаются health checks и smoke tests
|
||||
- ✅ При падении smoke tests — автоматический rollback
|
||||
|
||||
---
|
||||
|
||||
## 🎨 Стандарты кода
|
||||
|
||||
### Форматирование (Black):
|
||||
- **Обязательно**: Все Python файлы должны быть отформатированы через Black
|
||||
- **Проверка**: `make format-check` или `black --check .`
|
||||
- **Исправление**: `make format` или `black .`
|
||||
- **Правила**:
|
||||
- Двойные кавычки `"` вместо одинарных `'`
|
||||
- 2 пустые строки между импортами и определениями функций/классов
|
||||
- Автоматический перенос длинных строк
|
||||
|
||||
### Сортировка импортов (isort):
|
||||
- **Обязательно**: Импорты должны быть отсортированы
|
||||
- **Проверка**: `make import-check` или `isort --check-only .`
|
||||
- **Исправление**: `make import-fix` или `isort .`
|
||||
- **Порядок**: стандартная библиотека → сторонние → локальные
|
||||
|
||||
### Линтинг (flake8):
|
||||
- **Критические ошибки** (E9, F63, F7, F82) — блокируют пайплайн
|
||||
- **Предупреждения** (F821, F822, F824) — игнорируются в CI
|
||||
- **Проверка**: `make lint-check`
|
||||
- **Исключения**: `.venv`, `venv`, `__pycache__`, `.git`
|
||||
|
||||
### Перед коммитом:
|
||||
```bash
|
||||
make code-quality # Проверяет всё сразу
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Тестирование
|
||||
|
||||
### Структура тестов:
|
||||
- **`tests/`** — тесты инфраструктуры проекта
|
||||
- **`bots/*/tests/`** — тесты ботов (в их репозиториях)
|
||||
|
||||
### Запуск тестов:
|
||||
```bash
|
||||
make test # Все тесты
|
||||
make test-infra # Только тесты инфраструктуры
|
||||
make test-coverage # С отчетом о покрытии
|
||||
make test-clean # Очистить кэш и отчеты
|
||||
```
|
||||
|
||||
### Конфигурация pytest:
|
||||
- Файл: `pytest.ini` в корне проекта
|
||||
- Автоматическое обнаружение тестов в `tests/`
|
||||
- Маркеры: `slow`, `integration`, `unit`
|
||||
- Asyncio режим: автоматический
|
||||
|
||||
### Правила написания тестов:
|
||||
- Используй описательные имена: `test_prometheus_config_is_valid`
|
||||
- Группируй связанные тесты в классы
|
||||
- Используй фикстуры для общих setup/teardown
|
||||
- Тесты должны быть независимыми и идемпотентными
|
||||
|
||||
---
|
||||
|
||||
## 🐳 Docker и контейнеризация
|
||||
|
||||
### Структура:
|
||||
- **`docker-compose.yml`** — основной файл оркестрации
|
||||
- **`Dockerfile`** — базовый образ (если нужен)
|
||||
- **`bots/*/Dockerfile`** — Dockerfile для каждого бота
|
||||
|
||||
### Сервисы в docker-compose:
|
||||
- `prometheus` — сбор метрик (порт 9090)
|
||||
- `grafana` — дашборды (порт 3000)
|
||||
- `alertmanager` — управление алертами (порт 9093)
|
||||
- `uptime-kuma` — мониторинг доступности (порт 3001)
|
||||
- `telegram-bot` — Telegram Helper Bot (порт 8080)
|
||||
- `anon-bot` — AnonBot (порт 8081)
|
||||
|
||||
### Команды:
|
||||
```bash
|
||||
make build # Собрать все контейнеры
|
||||
make up # Запустить все сервисы
|
||||
make down # Остановить все сервисы
|
||||
make restart # Перезапустить все сервисы
|
||||
make logs # Логи всех сервисов
|
||||
make logs-bot # Логи Telegram бота
|
||||
```
|
||||
|
||||
### Важные правила:
|
||||
- **Токены ботов**: Используются из GitHub Secrets через переменные окружения
|
||||
- **Формат**: `TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN:-${BOT_TOKEN}}` (Secrets имеют приоритет)
|
||||
- **Build**: Используй `docker-compose build --pull` (не `--no-cache`) для оптимизации
|
||||
- **Graceful shutdown**: `docker-compose down -t 30` для корректного завершения
|
||||
|
||||
---
|
||||
|
||||
## 🔐 Безопасность и секреты
|
||||
|
||||
### GitHub Secrets (обязательные):
|
||||
- `TELEGRAM_BOT_TOKEN` — токен Telegram Helper Bot
|
||||
- `TELEGRAM_TEST_BOT_TOKEN` — токен тестового бота (опционально)
|
||||
- `ANON_BOT_TOKEN` — токен AnonBot
|
||||
- `SSH_PRIVATE_KEY` — приватный ключ для SSH доступа к серверу
|
||||
- `SERVER_HOST`, `SERVER_USER`, `SSH_PORT` — данные сервера
|
||||
- `TELEGRAM_CHAT_ID` — ID чата для уведомлений
|
||||
|
||||
### Локальная разработка:
|
||||
- Используй `.env` файлы для локальных переменных
|
||||
- `.env` файлы в `.gitignore` — никогда не коммить!
|
||||
- Токены из Secrets имеют приоритет над `.env` в продакшене
|
||||
|
||||
### Правила:
|
||||
- ❌ **НЕ коммить** токены, пароли, секреты
|
||||
- ❌ **НЕ коммить** `.env` файлы
|
||||
- ✅ Используй `env.template` как шаблон
|
||||
- ✅ Все секреты храни в GitHub Secrets
|
||||
|
||||
---
|
||||
|
||||
## 🚀 CI/CD Pipeline
|
||||
|
||||
### Два основных workflow:
|
||||
|
||||
#### 1. `pipeline.yml` (CI):
|
||||
- **Триггер**: Push в `main`, `develop`, `dev-*`, `feature/**`
|
||||
- **Jobs**:
|
||||
- `test` — проверка качества кода и тесты
|
||||
- `create-pr` — автоматическое создание/обновление PR (только для `dev-*` и `feature/**`)
|
||||
- `rollback` — ручной откат через `workflow_dispatch`
|
||||
|
||||
#### 2. `deploy.yml` (CD):
|
||||
- **Триггер**: Мерж PR в `main`
|
||||
- **Jobs**:
|
||||
- `deploy` — деплой на сервер
|
||||
- `smoke-tests` — проверка работоспособности ботов
|
||||
- `auto-rollback` — автоматический откат при падении smoke tests
|
||||
|
||||
### Правила работы с пайплайном:
|
||||
|
||||
1. **Перед push** — всегда запускай `make code-quality` локально
|
||||
2. **После успешных тестов** — PR создастся/обновится автоматически
|
||||
3. **После мержа PR** — деплой запустится автоматически
|
||||
4. **При проблемах** — используй manual rollback через Actions → Run workflow
|
||||
|
||||
---
|
||||
|
||||
## 📁 Структура проекта
|
||||
|
||||
```
|
||||
prod/
|
||||
├── .github/workflows/ # CI/CD пайплайны
|
||||
│ ├── pipeline.yml # CI: тесты, создание PR
|
||||
│ └── deploy.yml # CD: деплой, smoke tests, rollback
|
||||
├── bots/ # Директория для ботов (submodules)
|
||||
│ ├── telegram-helper-bot/ # Telegram Helper Bot
|
||||
│ └── AnonBot/ # AnonBot
|
||||
├── infra/ # Инфраструктура
|
||||
│ ├── prometheus/ # Конфигурация Prometheus
|
||||
│ ├── grafana/ # Дашборды и provisioning Grafana
|
||||
│ ├── alertmanager/ # Конфигурация Alertmanager
|
||||
│ ├── nginx/ # Nginx конфигурация
|
||||
│ └── ansible/ # Ansible playbooks
|
||||
├── scripts/ # Скрипты развертывания
|
||||
├── tests/ # Тесты инфраструктуры
|
||||
│ └── infra/ # Тесты инфраструктуры
|
||||
├── docker-compose.yml # Docker Compose конфигурация
|
||||
├── Makefile # Команды для управления проектом
|
||||
├── pytest.ini # Конфигурация pytest
|
||||
└── README.md # Документация проекта
|
||||
```
|
||||
|
||||
### Важные файлы:
|
||||
- **`docker-compose.yml`** — основная конфигурация сервисов
|
||||
- **`Makefile`** — команды для разработки и управления
|
||||
- **`pytest.ini`** — конфигурация тестов
|
||||
- **`.gitignore`** — исключает `.env`, `.venv`, логи, кэш
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Разработка
|
||||
|
||||
### Локальная настройка:
|
||||
|
||||
1. **Клонирование и настройка:**
|
||||
```bash
|
||||
git clone <repo>
|
||||
cd prod
|
||||
cp env.template .env
|
||||
# Отредактируй .env с локальными значениями
|
||||
```
|
||||
|
||||
2. **Установка зависимостей:**
|
||||
```bash
|
||||
python3 -m venv .venv
|
||||
source .venv/bin/activate
|
||||
pip install black isort flake8 pytest
|
||||
```
|
||||
|
||||
3. **Проверка перед коммитом:**
|
||||
```bash
|
||||
make code-quality
|
||||
```
|
||||
|
||||
### Работа с ботами:
|
||||
|
||||
- Боты находятся в `bots/` как отдельные репозитории (submodules или клоны)
|
||||
- Каждый бот имеет свой Dockerfile
|
||||
- Токены ботов передаются через environment variables в docker-compose
|
||||
|
||||
---
|
||||
|
||||
## 📝 Коммиты и PR
|
||||
|
||||
### Формат коммитов:
|
||||
Используй понятные сообщения:
|
||||
```
|
||||
feat: добавлена функция X
|
||||
fix: исправлена ошибка Y
|
||||
chore: обновлены зависимости
|
||||
docs: обновлена документация
|
||||
refactor: рефакторинг модуля Z
|
||||
```
|
||||
|
||||
### Pull Request:
|
||||
- **Автоматическое создание**: Для веток `dev-*` и `feature/**` после успешных тестов
|
||||
- **Обновление**: PR автоматически обновляется при новых коммитах в той же ветке
|
||||
- **Мерж**: После мержа в `main` запускается автоматический деплой
|
||||
|
||||
---
|
||||
|
||||
## 🚨 Деплой и Rollback
|
||||
|
||||
### Автоматический деплой:
|
||||
1. Мерж PR в `main` → запуск `deploy.yml`
|
||||
2. Валидация токенов ботов
|
||||
3. Деплой на сервер (SSH)
|
||||
4. Пересборка контейнеров с `--pull`
|
||||
5. Health checks с экспоненциальным retry
|
||||
6. Smoke tests (отправка сообщений в Telegram)
|
||||
7. При успехе — обновление истории деплоев
|
||||
|
||||
### Автоматический rollback:
|
||||
- Срабатывает при падении smoke tests
|
||||
- Откатывается к последнему успешному коммиту из истории
|
||||
- Пересобираются контейнеры
|
||||
- Проверяются health checks
|
||||
|
||||
### Ручной rollback:
|
||||
- Actions → CI & CD pipeline → Run workflow
|
||||
- Выбери `rollback` и опционально укажи commit hash
|
||||
- Если commit не указан — используется последний успешный деплой
|
||||
|
||||
---
|
||||
|
||||
## 🛠️ Полезные команды Makefile
|
||||
|
||||
### Качество кода:
|
||||
```bash
|
||||
make code-quality # Все проверки (Black, isort, flake8)
|
||||
make format # Автоисправление форматирования
|
||||
make import-fix # Автоисправление импортов
|
||||
make format-diff # Показать что будет изменено
|
||||
```
|
||||
|
||||
### Docker:
|
||||
```bash
|
||||
make build # Собрать контейнеры
|
||||
make up # Запустить сервисы
|
||||
make down # Остановить сервисы
|
||||
make restart # Перезапустить
|
||||
make logs # Логи всех сервисов
|
||||
make logs-bot # Логи бота
|
||||
```
|
||||
|
||||
### Тестирование:
|
||||
```bash
|
||||
make test # Все тесты
|
||||
make test-infra # Тесты инфраструктуры
|
||||
make test-coverage # С покрытием
|
||||
make test-clean # Очистить кэш
|
||||
```
|
||||
|
||||
### Мониторинг:
|
||||
```bash
|
||||
make monitoring # Открыть Grafana
|
||||
make prometheus # Открыть Prometheus
|
||||
make status # Статус контейнеров
|
||||
make health # Health checks
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## ⚠️ Важные замечания
|
||||
|
||||
### НЕ делай:
|
||||
- ❌ Коммить `.env` файлы с секретами
|
||||
- ❌ Коммить токены ботов в код
|
||||
- ❌ Использовать `docker-compose build --no-cache` без необходимости
|
||||
- ❌ Пуш в `main` напрямую (только через PR)
|
||||
- ❌ Игнорировать ошибки форматирования перед коммитом
|
||||
|
||||
### Всегда делай:
|
||||
- ✅ Запускай `make code-quality` перед коммитом
|
||||
- ✅ Используй ветки `dev-*` или `feature/**` для разработки
|
||||
- ✅ Проверяй, что тесты проходят локально
|
||||
- ✅ Используй GitHub Secrets для токенов в продакшене
|
||||
- ✅ Проверяй логи после деплоя
|
||||
|
||||
---
|
||||
|
||||
## 📚 Дополнительные ресурсы
|
||||
|
||||
- **README.md** — основная документация проекта
|
||||
- **`.cursor/rules/release-notes-template.md`** — шаблон для Release Notes
|
||||
- **`pytest.ini`** — конфигурация тестов
|
||||
- **`Makefile`** — все доступные команды (`make help`)
|
||||
|
||||
---
|
||||
|
||||
## 🔄 Workflow схема
|
||||
|
||||
```
|
||||
1. Создание ветки (dev-* или feature/**)
|
||||
↓
|
||||
2. Разработка + локальные тесты (make code-quality)
|
||||
↓
|
||||
3. Git commit + push
|
||||
↓
|
||||
4. GitHub Actions: автоматические тесты
|
||||
↓
|
||||
5. При успехе: автоматическое создание/обновление PR
|
||||
↓
|
||||
6. Ручной review и мерж PR в main
|
||||
↓
|
||||
7. GitHub Actions: автоматический деплой
|
||||
↓
|
||||
8. Health checks + Smoke tests
|
||||
↓
|
||||
9. При успехе: ✅ Деплой завершен
|
||||
При падении: 🔄 Автоматический rollback
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 💡 Советы
|
||||
|
||||
1. **Используй Makefile** — все команды там, не запоминай длинные команды
|
||||
2. **Проверяй локально** — запускай `make code-quality` перед каждым коммитом
|
||||
3. **Следи за уведомлениями** — Telegram уведомления показывают статус деплоя
|
||||
4. **Используй правильные ветки** — `dev-*` для автоматического создания PR
|
||||
5. **Читай логи** — при проблемах смотри логи в GitHub Actions и на сервере
|
||||
124
.cursor/rules/release-notes-template.md
Normal file
124
.cursor/rules/release-notes-template.md
Normal file
@@ -0,0 +1,124 @@
|
||||
# Инструкция по оформлению Release Notes
|
||||
|
||||
## Назначение
|
||||
Этот документ описывает структуру и формат для создания файлов Release Notes (например, `docs/RELEASE_NOTES_DEV-XX.md`).
|
||||
|
||||
## Структура документа
|
||||
|
||||
### 1. Заголовок
|
||||
```markdown
|
||||
# Release Notes: [название-ветки]
|
||||
```
|
||||
|
||||
### 2. Обзор
|
||||
Краткий абзац (1-2 предложения), описывающий:
|
||||
- Количество коммитов в ветке
|
||||
- Основные направления изменений
|
||||
|
||||
**Формат:**
|
||||
```markdown
|
||||
## Обзор
|
||||
Ветка [название] содержит [N] коммитов с ключевыми улучшениями: [краткое перечисление основных изменений].
|
||||
```
|
||||
|
||||
### 3. Ключевые изменения
|
||||
Основной раздел с пронумерованными подразделами для каждого значимого изменения.
|
||||
|
||||
**Структура каждого подраздела:**
|
||||
```markdown
|
||||
### [Номер]. [Название изменения]
|
||||
|
||||
**Коммит:** `[hash]`
|
||||
|
||||
**Что сделано:**
|
||||
- [Краткое описание изменения 1]
|
||||
- [Краткое описание изменения 2]
|
||||
- [Краткое описание изменения 3]
|
||||
```
|
||||
|
||||
**Правила:**
|
||||
- Каждое изменение = отдельный подраздел
|
||||
- Название должно быть кратким и понятным
|
||||
- В разделе "Что сделано" используй маркированные списки
|
||||
- НЕ перечисляй затронутые файлы
|
||||
- НЕ указывай статистику строк кода
|
||||
- Фокусируйся на сути изменений, а не на технических деталях
|
||||
- Разделяй подразделы горизонтальной линией `---`
|
||||
|
||||
### 4. Основные достижения
|
||||
Раздел с чекбоксами, подводящий итоги релиза.
|
||||
|
||||
**Формат:**
|
||||
```markdown
|
||||
## 🎯 Основные достижения
|
||||
|
||||
✅ [Достижение 1]
|
||||
✅ [Достижение 2]
|
||||
✅ [Достижение 3]
|
||||
```
|
||||
|
||||
**Правила:**
|
||||
- Используй эмодзи ✅ для каждого достижения
|
||||
- Каждое достижение на отдельной строке
|
||||
- Краткие формулировки (3-5 слов)
|
||||
- Фокусируйся на ключевых фичах и улучшениях
|
||||
|
||||
### 5. Временная шкала разработки
|
||||
Раздел с информацией о сроках разработки.
|
||||
|
||||
**Формат:**
|
||||
```markdown
|
||||
## 📅 Временная шкала разработки
|
||||
|
||||
**Последние изменения:** [дата]
|
||||
**Основная разработка:** [период]
|
||||
**Предыдущие улучшения:** [контекст предыдущих веток/изменений]
|
||||
|
||||
**Хронология коммитов:**
|
||||
- `[hash]` - [дата и время] - [краткое описание]
|
||||
- `[hash]` - [дата и время] - [краткое описание]
|
||||
```
|
||||
|
||||
**Правила:**
|
||||
- Используй реальные даты из коммитов
|
||||
- Формат даты: "DD месяц YYYY" (например, "25 января 2026")
|
||||
- Для времени используй формат "HH:MM"
|
||||
- Хронология должна быть в хронологическом порядке (от старых к новым)
|
||||
|
||||
## Стиль написания
|
||||
|
||||
### Общие правила:
|
||||
- **Краткость**: Фокусируйся на сути, избегай избыточных деталей
|
||||
- **Ясность**: Используй простые и понятные формулировки
|
||||
- **Структурированность**: Информация должна быть легко читаемой и сканируемой
|
||||
- **Без технических деталей**: Не перечисляй файлы, классы, методы (только если это ключевая фича)
|
||||
- **Без статистики**: Не указывай количество строк кода, файлов и т.д.
|
||||
|
||||
### Язык:
|
||||
- Используй прошедшее время для описания изменений ("Добавлена", "Реализована", "Обновлена")
|
||||
- Избегай технического жаргона, если это не необходимо
|
||||
- Используй активный залог
|
||||
|
||||
### Эмодзи:
|
||||
- 🔥 для раздела "Ключевые изменения"
|
||||
- 🎯 для раздела "Основные достижения"
|
||||
- 📅 для раздела "Временная шкала разработки"
|
||||
- ✅ для чекбоксов достижений
|
||||
|
||||
## Пример использования
|
||||
|
||||
При создании Release Notes для новой ветки:
|
||||
|
||||
1. Получи список коммитов: `git log [base-branch]..[target-branch] --oneline`
|
||||
2. Для каждого значимого коммита создай подраздел в "Ключевые изменения"
|
||||
3. Собери основные достижения в раздел "Основные достижения"
|
||||
4. Добавь временную шкалу с реальными датами коммитов
|
||||
5. Проверь, что документ следует структуре и стилю
|
||||
|
||||
## Важные замечания
|
||||
|
||||
- **НЕ включай** информацию о коммитах, которые уже были в базовой ветке (master/main)
|
||||
- **НЕ перечисляй** все файлы, которые были изменены
|
||||
- **НЕ указывай** статистику строк кода
|
||||
- **Фокусируйся** на функциональных изменениях, а не на технических деталях реализации
|
||||
- Используй **реальные даты** из коммитов, а не предполагаемые
|
||||
@@ -3,6 +3,10 @@
|
||||
# Игнорируем ВСЕХ ботов - они не нужны в этом контейнере
|
||||
bots/
|
||||
|
||||
# Игнорируем логи ботов
|
||||
bots/*/logs/
|
||||
bots/*/logs/**
|
||||
|
||||
# Игнорируем ВСЕ скрытые файлы и папки (кроме .gitignore)
|
||||
.*
|
||||
!.gitignore
|
||||
@@ -45,3 +49,29 @@ data/
|
||||
*.bin
|
||||
*.dat
|
||||
*.model
|
||||
|
||||
# Игнорируем данные Docker volumes
|
||||
/var/lib/docker/volumes/
|
||||
uptime_kuma_data/
|
||||
prometheus_data/
|
||||
grafana_data/
|
||||
alertmanager_data/
|
||||
|
||||
# Игнорируем временные файлы Docker
|
||||
.docker/
|
||||
|
||||
# Игнорируем базы данных и файлы данных
|
||||
*.db
|
||||
*.db-shm
|
||||
*.db-wal
|
||||
*.sqlite
|
||||
*.sqlite3
|
||||
|
||||
# Игнорируем backup файлы
|
||||
*.backup
|
||||
*.bak
|
||||
*.old
|
||||
|
||||
# Игнорируем файлы миграций и временные скрипты
|
||||
migration.log
|
||||
fix_dates.log
|
||||
99
.github/workflows/ci.yml
vendored
Normal file
99
.github/workflows/ci.yml
vendored
Normal file
@@ -0,0 +1,99 @@
|
||||
name: CI pipeline
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ 'dev-*', 'feature/**' ]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
action:
|
||||
description: 'Action to perform'
|
||||
required: true
|
||||
type: choice
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
name: Test & Code Quality
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python 3.11
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.11'
|
||||
cache: 'pip'
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r tests/infra/requirements-test.txt
|
||||
pip install flake8 black isort mypy || true
|
||||
|
||||
- name: Code formatting check (Black)
|
||||
run: |
|
||||
echo "🔍 Checking code formatting with Black..."
|
||||
black --check . || (echo "❌ Code formatting issues found. Run 'black .' to fix." && exit 1)
|
||||
|
||||
- name: Import sorting check (isort)
|
||||
run: |
|
||||
echo "🔍 Checking import sorting with isort..."
|
||||
isort --check-only . || (echo "❌ Import sorting issues found. Run 'isort .' to fix." && exit 1)
|
||||
|
||||
- name: Linting (flake8) - Critical errors
|
||||
run: |
|
||||
echo "🔍 Running flake8 linter (critical errors only)..."
|
||||
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
|
||||
|
||||
- name: Linting (flake8) - Warnings
|
||||
run: |
|
||||
echo "🔍 Running flake8 linter (warnings)..."
|
||||
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics || true
|
||||
continue-on-error: true
|
||||
|
||||
- name: Run infrastructure tests
|
||||
run: |
|
||||
python -m pytest tests/infra/ -v --tb=short
|
||||
|
||||
- name: Validate Prometheus config
|
||||
run: |
|
||||
python -m pytest tests/infra/test_prometheus_config.py -v
|
||||
|
||||
- name: Send test success notification
|
||||
if: success()
|
||||
uses: appleboy/telegram-action@v1.0.0
|
||||
with:
|
||||
to: ${{ secrets.TELEGRAM_CHAT_ID }}
|
||||
token: ${{ secrets.TELEGRAM_BOT_TOKEN }}
|
||||
message: |
|
||||
✅ CI Tests Passed
|
||||
|
||||
📦 Repository: prod
|
||||
🌿 Branch: ${{ github.ref_name }}
|
||||
📝 Commit: ${{ github.sha }}
|
||||
👤 Author: ${{ github.actor }}
|
||||
|
||||
✅ All tests passed! Code quality checks completed successfully.
|
||||
|
||||
🔗 View details: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
||||
continue-on-error: true
|
||||
|
||||
- name: Send test failure notification
|
||||
if: failure()
|
||||
uses: appleboy/telegram-action@v1.0.0
|
||||
with:
|
||||
to: ${{ secrets.TELEGRAM_CHAT_ID }}
|
||||
token: ${{ secrets.TELEGRAM_BOT_TOKEN }}
|
||||
message: |
|
||||
❌ CI Tests Failed
|
||||
|
||||
📦 Repository: prod
|
||||
🌿 Branch: ${{ github.ref_name }}
|
||||
📝 Commit: ${{ github.sha }}
|
||||
👤 Author: ${{ github.actor }}
|
||||
|
||||
❌ Tests failed! Deployment blocked. Please fix the issues and try again.
|
||||
|
||||
🔗 View details: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
||||
continue-on-error: true
|
||||
276
.github/workflows/deploy.yml
vendored
Normal file
276
.github/workflows/deploy.yml
vendored
Normal file
@@ -0,0 +1,276 @@
|
||||
name: Deploy to Production
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ main ]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
action:
|
||||
description: 'Action to perform'
|
||||
required: true
|
||||
type: choice
|
||||
options:
|
||||
- deploy
|
||||
- rollback
|
||||
rollback_commit:
|
||||
description: 'Commit hash to rollback to (optional, uses last successful if empty)'
|
||||
required: false
|
||||
type: string
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: ubuntu-latest
|
||||
name: Deploy to Production
|
||||
if: |
|
||||
github.event_name == 'push' ||
|
||||
(github.event_name == 'workflow_dispatch' && github.event.inputs.action == 'deploy')
|
||||
concurrency:
|
||||
group: production-deploy
|
||||
cancel-in-progress: false
|
||||
environment:
|
||||
name: production
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: main
|
||||
|
||||
- name: Deploy to server
|
||||
uses: appleboy/ssh-action@v1.0.0
|
||||
with:
|
||||
host: ${{ vars.SERVER_HOST || secrets.SERVER_HOST }}
|
||||
username: ${{ vars.SERVER_USER || secrets.SERVER_USER }}
|
||||
key: ${{ secrets.SSH_PRIVATE_KEY }}
|
||||
port: ${{ vars.SSH_PORT || secrets.SSH_PORT || 22 }}
|
||||
script: |
|
||||
set -e
|
||||
export TELEGRAM_BOT_TOKEN="${{ secrets.TELEGRAM_BOT_TOKEN }}"
|
||||
export TELEGRAM_TEST_BOT_TOKEN="${{ secrets.TELEGRAM_TEST_BOT_TOKEN }}"
|
||||
export ANON_BOT_TOKEN="${{ secrets.ANON_BOT_TOKEN }}"
|
||||
|
||||
echo "🚀 Starting deployment to production..."
|
||||
|
||||
cd /home/prod
|
||||
|
||||
# Сохраняем информацию о коммите
|
||||
CURRENT_COMMIT=$(git rev-parse HEAD)
|
||||
COMMIT_MESSAGE=$(git log -1 --pretty=format:"%s" || echo "Unknown")
|
||||
COMMIT_AUTHOR=$(git log -1 --pretty=format:"%an" || echo "Unknown")
|
||||
TIMESTAMP=$(date +"%Y-%m-%d %H:%M:%S")
|
||||
|
||||
echo "📝 Current commit: $CURRENT_COMMIT"
|
||||
echo "📝 Commit message: $COMMIT_MESSAGE"
|
||||
echo "📝 Author: $COMMIT_AUTHOR"
|
||||
|
||||
# Записываем в историю деплоев
|
||||
HISTORY_FILE="/home/prod/.deploy_history.txt"
|
||||
HISTORY_SIZE="${DEPLOY_HISTORY_SIZE:-10}"
|
||||
echo "${TIMESTAMP}|${CURRENT_COMMIT}|${COMMIT_MESSAGE}|${COMMIT_AUTHOR}|deploying" >> "$HISTORY_FILE"
|
||||
tail -n "$HISTORY_SIZE" "$HISTORY_FILE" > "${HISTORY_FILE}.tmp" && mv "${HISTORY_FILE}.tmp" "$HISTORY_FILE"
|
||||
|
||||
# Обновляем код
|
||||
echo "📥 Pulling latest changes from main..."
|
||||
sudo chown -R deploy:deploy /home/prod/bots || true
|
||||
git fetch origin main
|
||||
git reset --hard origin/main
|
||||
sudo chown -R deploy:deploy /home/prod/bots || true
|
||||
|
||||
NEW_COMMIT=$(git rev-parse HEAD)
|
||||
echo "✅ Code updated: $CURRENT_COMMIT → $NEW_COMMIT"
|
||||
|
||||
# Валидация docker-compose
|
||||
echo "🔍 Validating docker-compose configuration..."
|
||||
docker-compose config > /dev/null || exit 1
|
||||
echo "✅ docker-compose.yml is valid"
|
||||
|
||||
# Проверка дискового пространства
|
||||
MIN_FREE_GB=5
|
||||
AVAILABLE_SPACE=$(df -BG /home/prod 2>/dev/null | tail -1 | awk '{print $4}' | sed 's/G//' || echo "0")
|
||||
echo "💾 Available disk space: ${AVAILABLE_SPACE}GB"
|
||||
|
||||
if [ "$AVAILABLE_SPACE" -lt "$MIN_FREE_GB" ]; then
|
||||
echo "⚠️ Insufficient disk space! Cleaning up Docker resources..."
|
||||
docker system prune -f --volumes || true
|
||||
fi
|
||||
|
||||
# Сборка и запуск контейнеров (кроме ботов для ускорения деплоя)
|
||||
echo "🔨 Rebuilding infrastructure containers (excluding bots)..."
|
||||
docker-compose stop prometheus grafana uptime-kuma alertmanager || true
|
||||
|
||||
export TELEGRAM_BOT_TOKEN TELEGRAM_TEST_BOT_TOKEN ANON_BOT_TOKEN
|
||||
docker-compose build --pull prometheus grafana uptime-kuma alertmanager
|
||||
docker-compose up -d prometheus grafana uptime-kuma alertmanager
|
||||
|
||||
echo "✅ Infrastructure containers rebuilt and started (bots remain running)"
|
||||
|
||||
- name: Update deploy history
|
||||
if: always()
|
||||
uses: appleboy/ssh-action@v1.0.0
|
||||
with:
|
||||
host: ${{ vars.SERVER_HOST || secrets.SERVER_HOST }}
|
||||
username: ${{ vars.SERVER_USER || secrets.SERVER_USER }}
|
||||
key: ${{ secrets.SSH_PRIVATE_KEY }}
|
||||
port: ${{ vars.SSH_PORT || secrets.SSH_PORT || 22 }}
|
||||
script: |
|
||||
HISTORY_FILE="/home/prod/.deploy_history.txt"
|
||||
|
||||
if [ -f "$HISTORY_FILE" ]; then
|
||||
DEPLOY_STATUS="failed"
|
||||
if [ "${{ job.status }}" = "success" ]; then
|
||||
DEPLOY_STATUS="success"
|
||||
fi
|
||||
|
||||
sed -i '$s/|deploying$/|'"$DEPLOY_STATUS"'/' "$HISTORY_FILE"
|
||||
echo "✅ Deploy history updated: $DEPLOY_STATUS"
|
||||
fi
|
||||
|
||||
- name: Send deployment notification
|
||||
if: always()
|
||||
uses: appleboy/telegram-action@v1.0.0
|
||||
with:
|
||||
to: ${{ secrets.TELEGRAM_CHAT_ID }}
|
||||
token: ${{ secrets.TELEGRAM_BOT_TOKEN }}
|
||||
message: |
|
||||
${{ job.status == 'success' && '✅' || '❌' }} Deployment: ${{ job.status }}
|
||||
|
||||
📦 Repository: prod
|
||||
🌿 Branch: main
|
||||
📝 Commit: ${{ github.event.pull_request.merge_commit_sha || github.sha }}
|
||||
👤 Author: ${{ github.event.pull_request.user.login || github.actor }}
|
||||
${{ github.event.pull_request.number && format('🔀 PR: #{0}', github.event.pull_request.number) || '' }}
|
||||
|
||||
${{ job.status == 'success' && '✅ Deployment successful! Containers started.' || '❌ Deployment failed! Check logs for details.' }}
|
||||
|
||||
🔗 View details: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
||||
continue-on-error: true
|
||||
|
||||
rollback:
|
||||
runs-on: ubuntu-latest
|
||||
name: Rollback to Previous Version
|
||||
if: |
|
||||
github.event_name == 'workflow_dispatch' &&
|
||||
github.event.inputs.action == 'rollback'
|
||||
environment:
|
||||
name: production
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: main
|
||||
|
||||
- name: Rollback on server
|
||||
uses: appleboy/ssh-action@v1.0.0
|
||||
with:
|
||||
host: ${{ vars.SERVER_HOST || secrets.SERVER_HOST }}
|
||||
username: ${{ vars.SERVER_USER || secrets.SERVER_USER }}
|
||||
key: ${{ secrets.SSH_PRIVATE_KEY }}
|
||||
port: ${{ vars.SSH_PORT || secrets.SSH_PORT || 22 }}
|
||||
script: |
|
||||
set -e
|
||||
export TELEGRAM_BOT_TOKEN="${{ secrets.TELEGRAM_BOT_TOKEN }}"
|
||||
export TELEGRAM_TEST_BOT_TOKEN="${{ secrets.TELEGRAM_TEST_BOT_TOKEN }}"
|
||||
export ANON_BOT_TOKEN="${{ secrets.ANON_BOT_TOKEN }}"
|
||||
|
||||
echo "🔄 Starting rollback..."
|
||||
|
||||
cd /home/prod
|
||||
|
||||
# Определяем коммит для отката
|
||||
ROLLBACK_COMMIT="${{ github.event.inputs.rollback_commit }}"
|
||||
HISTORY_FILE="/home/prod/.deploy_history.txt"
|
||||
|
||||
if [ -z "$ROLLBACK_COMMIT" ]; then
|
||||
echo "📝 No commit specified, finding last successful deploy..."
|
||||
if [ -f "$HISTORY_FILE" ]; then
|
||||
ROLLBACK_COMMIT=$(grep "|success$" "$HISTORY_FILE" | tail -1 | cut -d'|' -f2 || echo "")
|
||||
fi
|
||||
|
||||
if [ -z "$ROLLBACK_COMMIT" ]; then
|
||||
echo "❌ No successful deploy found in history!"
|
||||
echo "💡 Please specify commit hash manually or check deploy history"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
echo "📝 Rolling back to commit: $ROLLBACK_COMMIT"
|
||||
|
||||
# Проверяем, что коммит существует
|
||||
if ! git cat-file -e "$ROLLBACK_COMMIT" 2>/dev/null; then
|
||||
echo "❌ Commit $ROLLBACK_COMMIT not found!"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Сохраняем текущий коммит
|
||||
CURRENT_COMMIT=$(git rev-parse HEAD)
|
||||
COMMIT_MESSAGE=$(git log -1 --pretty=format:"%s" "$ROLLBACK_COMMIT" || echo "Rollback")
|
||||
TIMESTAMP=$(date +"%Y-%m-%d %H:%M:%S")
|
||||
|
||||
echo "📝 Current commit: $CURRENT_COMMIT"
|
||||
echo "📝 Target commit: $ROLLBACK_COMMIT"
|
||||
echo "📝 Commit message: $COMMIT_MESSAGE"
|
||||
|
||||
# Исправляем права перед откатом
|
||||
sudo chown -R deploy:deploy /home/prod/bots || true
|
||||
|
||||
# Откатываем код
|
||||
echo "🔄 Rolling back code..."
|
||||
git fetch origin main
|
||||
git reset --hard "$ROLLBACK_COMMIT"
|
||||
|
||||
# Исправляем права после отката
|
||||
sudo chown -R deploy:deploy /home/prod/bots || true
|
||||
|
||||
echo "✅ Code rolled back: $CURRENT_COMMIT → $ROLLBACK_COMMIT"
|
||||
|
||||
# Валидация docker-compose
|
||||
echo "🔍 Validating docker-compose configuration..."
|
||||
docker-compose config > /dev/null || exit 1
|
||||
echo "✅ docker-compose.yml is valid"
|
||||
|
||||
# Проверка дискового пространства
|
||||
MIN_FREE_GB=5
|
||||
AVAILABLE_SPACE=$(df -BG /home/prod 2>/dev/null | tail -1 | awk '{print $4}' | sed 's/G//' || echo "0")
|
||||
echo "💾 Available disk space: ${AVAILABLE_SPACE}GB"
|
||||
|
||||
if [ "$AVAILABLE_SPACE" -lt "$MIN_FREE_GB" ]; then
|
||||
echo "⚠️ Insufficient disk space! Cleaning up Docker resources..."
|
||||
docker system prune -f --volumes || true
|
||||
fi
|
||||
|
||||
# Пересобираем и запускаем контейнеры (кроме ботов для ускорения отката)
|
||||
echo "🔨 Rebuilding infrastructure containers (excluding bots)..."
|
||||
docker-compose stop prometheus grafana uptime-kuma alertmanager || true
|
||||
|
||||
export TELEGRAM_BOT_TOKEN TELEGRAM_TEST_BOT_TOKEN ANON_BOT_TOKEN
|
||||
docker-compose build --pull prometheus grafana uptime-kuma alertmanager
|
||||
docker-compose up -d prometheus grafana uptime-kuma alertmanager
|
||||
|
||||
echo "✅ Infrastructure containers rebuilt and started (bots remain running)"
|
||||
|
||||
# Записываем в историю
|
||||
echo "${TIMESTAMP}|${ROLLBACK_COMMIT}|Rollback to: ${COMMIT_MESSAGE}|github-actions|rolled_back" >> "$HISTORY_FILE"
|
||||
HISTORY_SIZE="${DEPLOY_HISTORY_SIZE:-10}"
|
||||
tail -n "$HISTORY_SIZE" "$HISTORY_FILE" > "${HISTORY_FILE}.tmp" && mv "${HISTORY_FILE}.tmp" "$HISTORY_FILE"
|
||||
|
||||
echo "✅ Rollback completed successfully"
|
||||
|
||||
- name: Send rollback notification
|
||||
if: always()
|
||||
uses: appleboy/telegram-action@v1.0.0
|
||||
with:
|
||||
to: ${{ secrets.TELEGRAM_CHAT_ID }}
|
||||
token: ${{ secrets.TELEGRAM_BOT_TOKEN }}
|
||||
message: |
|
||||
${{ job.status == 'success' && '🔄' || '❌' }} Rollback: ${{ job.status }}
|
||||
|
||||
📦 Repository: prod
|
||||
🌿 Branch: main
|
||||
📝 Rolled back to: ${{ github.event.inputs.rollback_commit || 'Last successful commit' }}
|
||||
👤 Triggered by: ${{ github.actor }}
|
||||
|
||||
${{ job.status == 'success' && '✅ Rollback completed successfully! Services restored to previous version.' || '❌ Rollback failed! Check logs for details.' }}
|
||||
|
||||
🔗 View details: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
||||
continue-on-error: true
|
||||
4
.gitignore
vendored
4
.gitignore
vendored
@@ -69,3 +69,7 @@ build/
|
||||
# Ansible inventory files (contain sensitive server info)
|
||||
infra/ansible/inventory.ini
|
||||
infra/ansible/inventory_*.ini
|
||||
|
||||
# Ansible vars files (contain passwords)
|
||||
infra/ansible/vars.yml
|
||||
infra/ansible/vars_*.yml
|
||||
@@ -1,7 +1,7 @@
|
||||
###########################################
|
||||
# Этап 1: Сборщик (Builder)
|
||||
###########################################
|
||||
FROM python:3.9-slim as builder
|
||||
FROM python:3.11.9-slim as builder
|
||||
|
||||
# Устанавливаем ТОЧНО ТОЛЬКО то, что нужно для компиляции
|
||||
RUN apt-get update && apt-get install --no-install-recommends -y \
|
||||
@@ -20,7 +20,7 @@ RUN pip install --no-cache-dir --target /install -r requirements.txt
|
||||
# Этап 2: Финальный образ (Runtime)
|
||||
###########################################
|
||||
# Используем ОЧЕНЬ легковесный базовый образ
|
||||
FROM python:3.9-alpine as runtime
|
||||
FROM python:3.11.9-alpine as runtime
|
||||
|
||||
# В Alpine Linux свои пакеты. apk вместо apt.
|
||||
# Устанавливаем минимальные рантайм-зависимости
|
||||
@@ -33,14 +33,14 @@ RUN addgroup -g 1000 app && \
|
||||
WORKDIR /app
|
||||
|
||||
# Копируем зависимости из сборщика (если есть)
|
||||
COPY --from=builder --chown=1000:1000 /install /usr/local/lib/python3.9/site-packages
|
||||
COPY --from=builder --chown=1000:1000 /install /usr/local/lib/python3.11/site-packages
|
||||
# Копируем исходный код
|
||||
COPY --chown=1000:1000 . .
|
||||
|
||||
USER 1000
|
||||
|
||||
# Важно: явно указываем Python искать зависимости в скопированной директории
|
||||
ENV PYTHONPATH="/usr/local/lib/python3.9/site-packages:${PYTHONPATH}"
|
||||
ENV PYTHONPATH="/usr/local/lib/python3.11/site-packages:${PYTHONPATH}"
|
||||
|
||||
# Оставляем базовую команду для совместимости
|
||||
CMD ["python", "-c", "print('Dockerfile готов для использования')"]
|
||||
171
Makefile
171
Makefile
@@ -1,4 +1,4 @@
|
||||
.PHONY: help build up down logs clean restart status deploy backup restore update clean-monitoring monitoring check-deps check-bot-deps check-anonBot-deps
|
||||
.PHONY: help build up down logs clean restart status deploy backup restore update clean-monitoring monitoring check-deps check-bot-deps check-anonBot-deps auth-setup auth-add-user auth-reset format-check format format-diff import-check import-fix lint-check code-quality
|
||||
|
||||
help: ## Показать справку
|
||||
@echo "🏗️ Production Infrastructure - Доступные команды:"
|
||||
@@ -9,6 +9,8 @@ help: ## Показать справку
|
||||
@echo "📊 Мониторинг:"
|
||||
@echo " Prometheus: http://localhost:9090"
|
||||
@echo " Grafana: http://localhost:3000 (admin/admin)"
|
||||
@echo " Uptime Kuma: http://localhost:3001"
|
||||
@echo " Alertmanager: http://localhost:9093"
|
||||
@echo " Server Monitor: http://localhost:9091/health"
|
||||
@echo " Bot Health: http://localhost:8080/health"
|
||||
@echo " AnonBot Health: http://localhost:8081/health"
|
||||
@@ -37,6 +39,12 @@ logs-bot: ## Показать логи Telegram бота
|
||||
logs-anonBot: ## Показать логи AnonBot
|
||||
docker-compose logs -f anon-bot
|
||||
|
||||
logs-uptime-kuma: ## Показать логи Uptime Kuma
|
||||
docker-compose logs -f uptime-kuma
|
||||
|
||||
logs-alertmanager: ## Показать логи Alertmanager
|
||||
docker-compose logs -f alertmanager
|
||||
|
||||
restart: ## Перезапустить все сервисы
|
||||
docker-compose down
|
||||
docker-compose build --no-cache
|
||||
@@ -54,6 +62,12 @@ restart-bot: ## Перезапустить только Telegram бота
|
||||
restart-anonBot: ## Перезапустить только AnonBot
|
||||
docker-compose restart anon-bot
|
||||
|
||||
restart-uptime-kuma: ## Перезапустить только Uptime Kuma
|
||||
docker-compose restart uptime-kuma
|
||||
|
||||
restart-alertmanager: ## Перезапустить только Alertmanager
|
||||
docker-compose restart alertmanager
|
||||
|
||||
status: ## Показать статус контейнеров
|
||||
docker-compose ps
|
||||
|
||||
@@ -63,6 +77,8 @@ health: ## Проверить здоровье сервисов
|
||||
@curl -f http://localhost:8081/health || echo "❌ AnonBot health check failed"
|
||||
@curl -f http://localhost:9090/-/healthy || echo "❌ Prometheus health check failed"
|
||||
@curl -f http://localhost:3000/api/health || echo "❌ Grafana health check failed"
|
||||
@curl -f http://localhost:3001 || echo "❌ Uptime Kuma health check failed"
|
||||
@curl -f http://localhost:9093/-/healthy || echo "❌ Alertmanager health check failed"
|
||||
@curl -f http://localhost:9091/health || echo "❌ Server monitor health check failed"
|
||||
|
||||
deploy: ## Полный деплой на продакшен
|
||||
@@ -98,7 +114,7 @@ clean: ## Очистить все контейнеры и образы
|
||||
|
||||
clean-monitoring: ## Очистить только данные мониторинга
|
||||
docker-compose down -v
|
||||
docker volume rm prod_prometheus_data prod_grafana_data 2>/dev/null || true
|
||||
docker volume rm prod_prometheus_data prod_grafana_data prod_uptime_kuma_data prod_alertmanager_data 2>/dev/null || true
|
||||
|
||||
security-scan: ## Сканировать образы на уязвимости
|
||||
@echo "🔍 Scanning Docker images for vulnerabilities..."
|
||||
@@ -120,6 +136,8 @@ start: build up ## Собрать и запустить все сервисы
|
||||
@echo "🏗️ Production Infrastructure запущена!"
|
||||
@echo "📊 Prometheus: http://localhost:9090"
|
||||
@echo "📈 Grafana: http://localhost:3000 (admin/admin)"
|
||||
@echo "📊 Uptime Kuma: http://localhost:3001"
|
||||
@echo "🚨 Alertmanager: http://localhost:9093"
|
||||
@echo "🤖 Bot Health: http://localhost:8080/health"
|
||||
@echo "🔒 AnonBot Health: http://localhost:8081/health"
|
||||
@echo "📡 Server Monitor: http://localhost:9091/health"
|
||||
@@ -151,16 +169,29 @@ test-all: ## Запустить все тесты в одном процессе
|
||||
|
||||
test-infra: check-deps ## Запустить тесты инфраструктуры
|
||||
@echo "🏗️ Запускаю тесты инфраструктуры..."
|
||||
@python3 -m pytest tests/infra/ -v
|
||||
@source .venv/bin/activate && python3 -m pytest tests/infra/ -v
|
||||
|
||||
test-bot: check-bot-deps ## Запустить тесты Telegram бота
|
||||
@echo "🤖 Запускаю тесты Telegram бота..."
|
||||
@cd bots/telegram-helper-bot && source .venv/bin/activate && python3 -m pytest tests/ -v
|
||||
|
||||
test-bot-coverage: check-bot-deps ## Запустить тесты Telegram бота с отчетом о покрытии
|
||||
@echo "🤖 Запускаю тесты Telegram бота..."
|
||||
@cd bots/telegram-helper-bot && source .venv/bin/activate && python3 -m pytest tests/ --cov=helper_bot --cov-report=term-missing --cov-report=html:htmlcov/bot
|
||||
@echo "📊 Отчеты о покрытии сохранены в htmlcov/"
|
||||
@echo " - Telegram бот: $(shell python3 count_tests.py | head -2 | tail -1) тестов"
|
||||
|
||||
test-anonBot: check-anonBot-deps ## Запустить тесты AnonBot
|
||||
@echo "🔒 Запускаю тесты AnonBot..."
|
||||
@cd bots/AnonBot && python3 -m pytest tests/ -v
|
||||
|
||||
|
||||
test-anonBot-coverage: check-anonBot-deps ## Запустить тесты AnonBot с отчетом о покрытии
|
||||
@echo "🔒 Запускаю тесты AnonBot..."
|
||||
@cd bots/AnonBot && python3 -m pytest tests/ --cov=. --cov-report=term-missing --cov-report=html:htmlcov/anonbot
|
||||
@echo "📊 Отчеты о покрытии сохранены в htmlcov/"
|
||||
@echo " - AnonBot: $(shell python3 count_tests.py | head -3 | tail -1) тестов"
|
||||
|
||||
test-coverage: check-deps check-bot-deps check-anonBot-deps ## Запустить все тесты с отчетом о покрытии
|
||||
@echo "📊 Запускаю все тесты с отчетом о покрытии..."
|
||||
@echo "📈 Покрытие для инфраструктуры..."
|
||||
@@ -192,6 +223,7 @@ test-clean: ## Очистить все файлы тестирования и о
|
||||
@find . -name "__pycache__" -type d -exec rm -rf {} + 2>/dev/null || true
|
||||
@echo "✅ Файлы тестирования очищены"
|
||||
|
||||
|
||||
check-ports: ## Проверить занятые порты
|
||||
@echo "🔍 Checking occupied ports..."
|
||||
@echo "Port 3000 (Grafana):"
|
||||
@@ -208,7 +240,7 @@ check-ports: ## Проверить занятые порты
|
||||
|
||||
check-deps: ## Проверить зависимости инфраструктуры
|
||||
@echo "🔍 Проверяю зависимости инфраструктуры..."
|
||||
@python3 -c "import pytest" 2>/dev/null || (echo "❌ Отсутствуют зависимости инфраструктуры. Установите: pip install pytest" && exit 1)
|
||||
@source .venv/bin/activate && python3 -c "import pytest" 2>/dev/null || (echo "❌ Отсутствуют зависимости инфраструктуры. Установите: source .venv/bin/activate && pip install pytest" && exit 1)
|
||||
@echo "✅ Зависимости инфраструктуры установлены"
|
||||
|
||||
check-bot-deps: ## Проверить зависимости Telegram бота
|
||||
@@ -242,3 +274,134 @@ reload-prometheus: ## Перезагрузить конфигурацию Promet
|
||||
reload-grafana: ## Перезагрузить конфигурацию Grafana
|
||||
@echo "🔄 Reloading Grafana configuration..."
|
||||
@docker-compose restart grafana
|
||||
|
||||
ssl-setup: ## Настроить SSL сертификаты (самоподписанный)
|
||||
@echo "🔒 Setting up self-signed SSL certificates..."
|
||||
@if [ -z "$(SERVER_IP)" ]; then echo "❌ Please set SERVER_IP variable in .env file"; exit 1; fi
|
||||
@mkdir -p /etc/letsencrypt/live/$(SERVER_IP)
|
||||
@openssl req -x509 -nodes -days 365 -newkey rsa:2048 \
|
||||
-keyout /etc/letsencrypt/live/$(SERVER_IP)/privkey.pem \
|
||||
-out /etc/letsencrypt/live/$(SERVER_IP)/fullchain.pem \
|
||||
-subj "/CN=$(SERVER_IP)"
|
||||
@echo "✅ Self-signed certificate created for $(SERVER_IP)"
|
||||
|
||||
ssl-renew: ## Обновить SSL сертификаты
|
||||
@echo "🔄 Renewing SSL certificates..."
|
||||
@sudo /usr/local/bin/ssl-renewal.sh
|
||||
|
||||
ssl-status: ## Проверить статус SSL сертификатов
|
||||
@echo "🔍 Checking SSL certificate status..."
|
||||
@sudo certbot certificates
|
||||
|
||||
uptime-kuma: ## Открыть Uptime Kuma в браузере
|
||||
@echo "📊 Opening Uptime Kuma..."
|
||||
@open http://localhost:3001 || xdg-open http://localhost:3001 || echo "Please open manually: http://localhost:3001"
|
||||
|
||||
alertmanager: ## Открыть Alertmanager в браузере
|
||||
@echo "🚨 Opening Alertmanager..."
|
||||
@open http://localhost:9093 || xdg-open http://localhost:9093 || echo "Please open manually: http://localhost:9093"
|
||||
|
||||
monitoring-all: ## Открыть все мониторинг сервисы
|
||||
@echo "📊 Opening all monitoring services..."
|
||||
@echo " - Grafana: http://localhost:3000"
|
||||
@echo " - Prometheus: http://localhost:9090"
|
||||
@echo " - Uptime Kuma: http://localhost:3001"
|
||||
@echo " - Alertmanager: http://localhost:9093"
|
||||
@open http://localhost:3000 || xdg-open http://localhost:3000 || echo "Please open manually"
|
||||
|
||||
# ========================================
|
||||
# 🔐 АВТОРИЗАЦИЯ МОНИТОРИНГА
|
||||
# ========================================
|
||||
|
||||
auth-setup: ## Настроить авторизацию для мониторинга
|
||||
@echo "🔐 Setting up monitoring authentication..."
|
||||
@sudo mkdir -p /etc/nginx/passwords
|
||||
@sudo cp scripts/generate_auth_passwords.sh /usr/local/bin/generate_auth_passwords.sh
|
||||
@sudo chmod +x /usr/local/bin/generate_auth_passwords.sh
|
||||
@echo "✅ Authentication setup complete!"
|
||||
@echo "💡 Use 'make auth-add-user' to add users"
|
||||
|
||||
auth-add-user: ## Добавить пользователя для мониторинга (make auth-add-user USER=username)
|
||||
@if [ -z "$(USER)" ]; then \
|
||||
echo "❌ Please specify USER: make auth-add-user USER=username"; \
|
||||
exit 1; \
|
||||
fi
|
||||
@echo "🔐 Adding user $(USER) for monitoring..."
|
||||
@sudo /usr/local/bin/generate_auth_passwords.sh $(USER)
|
||||
@echo "✅ User $(USER) added successfully!"
|
||||
|
||||
auth-reset: ## Сбросить пароль для пользователя (make auth-reset USER=username)
|
||||
@if [ -z "$(USER)" ]; then \
|
||||
echo "❌ Please specify USER: make auth-reset USER=username"; \
|
||||
exit 1; \
|
||||
fi
|
||||
@echo "🔐 Resetting password for user $(USER)..."
|
||||
@sudo htpasswd /etc/nginx/passwords/monitoring.htpasswd $(USER)
|
||||
@echo "✅ Password reset for user $(USER)!"
|
||||
|
||||
auth-list: ## Показать список пользователей мониторинга
|
||||
@echo "👥 Monitoring users:"
|
||||
@sudo cat /etc/nginx/passwords/monitoring.htpasswd 2>/dev/null | cut -d: -f1 || echo "❌ No users found"
|
||||
|
||||
# ========================================
|
||||
# Code Quality & Formatting
|
||||
# ========================================
|
||||
|
||||
format-check: ## Проверить форматирование кода (Black)
|
||||
@echo "🔍 Checking code formatting with Black..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m black --check . || (echo "❌ Code formatting issues found. Run 'make format' to fix." && exit 1); \
|
||||
else \
|
||||
python3 -m black --check . || (echo "❌ Code formatting issues found. Run 'make format' to fix." && exit 1); \
|
||||
fi
|
||||
@echo "✅ Code formatting is correct!"
|
||||
|
||||
format: ## Автоматически исправить форматирование кода (Black)
|
||||
@echo "🎨 Formatting code with Black..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m black .; \
|
||||
else \
|
||||
python3 -m black .; \
|
||||
fi
|
||||
@echo "✅ Code formatted!"
|
||||
|
||||
format-diff: ## Показать что будет изменено Black (без применения)
|
||||
@echo "📋 Showing Black diff (no changes applied)..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m black --diff .; \
|
||||
else \
|
||||
python3 -m black --diff .; \
|
||||
fi
|
||||
|
||||
import-check: ## Проверить сортировку импортов (isort)
|
||||
@echo "🔍 Checking import sorting with isort..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m isort --check-only . || (echo "❌ Import sorting issues found. Run 'make import-fix' to fix." && exit 1); \
|
||||
else \
|
||||
python3 -m isort --check-only . || (echo "❌ Import sorting issues found. Run 'make import-fix' to fix." && exit 1); \
|
||||
fi
|
||||
@echo "✅ Import sorting is correct!"
|
||||
|
||||
import-fix: ## Автоматически исправить сортировку импортов (isort)
|
||||
@echo "📦 Fixing import sorting with isort..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m isort .; \
|
||||
else \
|
||||
python3 -m isort .; \
|
||||
fi
|
||||
@echo "✅ Imports sorted!"
|
||||
|
||||
lint-check: ## Проверить код линтером (flake8) - только критические ошибки
|
||||
@echo "🔍 Running flake8 linter (critical errors only)..."
|
||||
@if [ -f .venv/bin/python ]; then \
|
||||
.venv/bin/python -m flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=".venv,venv,__pycache__,.git,*.pyc" || true; \
|
||||
else \
|
||||
python3 -m flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=".venv,venv,__pycache__,.git,*.pyc" || true; \
|
||||
fi
|
||||
@echo "✅ Linting check completed (non-critical warnings in dependencies ignored)!"
|
||||
|
||||
code-quality: format-check import-check lint-check ## Проверить качество кода (все проверки)
|
||||
@echo ""
|
||||
@echo "✅ All code quality checks passed!"
|
||||
@echo ""
|
||||
@echo "ℹ️ Note: F821/F822/F824 warnings in bots/ are non-critical and ignored in CI"
|
||||
|
||||
17
README.md
17
README.md
@@ -19,10 +19,6 @@ prod/
|
||||
|
||||
## 🚀 Быстрый запуск
|
||||
|
||||
### ⚠️ Важное замечание
|
||||
**Убедитесь, что вы удалили файл `docker-compose.yml` из папки `bots/telegram-helper-bot/`**
|
||||
для избежания конфликтов портов. Используйте только корневой `docker-compose.yml`.
|
||||
|
||||
### 1. Настройка переменных окружения
|
||||
|
||||
Скопируйте шаблон и настройте переменные:
|
||||
@@ -57,12 +53,25 @@ GRAFANA_ADMIN_PASSWORD=admin
|
||||
docker-compose up -d
|
||||
```
|
||||
|
||||
### 2.1 Запуск только основного бота (с зависимостями). Можно заменить на AnonBot
|
||||
|
||||
```bash
|
||||
docker-compose up -d prometheus telegram-bot
|
||||
```
|
||||
|
||||
### 3. Проверка статуса
|
||||
|
||||
```bash
|
||||
docker-compose ps
|
||||
```
|
||||
|
||||
|
||||
### 4. Перезапуск контейнера
|
||||
|
||||
```bash
|
||||
docker-compose down telegram-bot && docker-compose build --no-cache telegram-bot && docker-compose up -d telegram-bot
|
||||
```
|
||||
|
||||
## 📊 Сервисы
|
||||
|
||||
- **Prometheus** (порт 9090) - сбор метрик
|
||||
|
||||
@@ -12,18 +12,31 @@ services:
|
||||
- '--web.console.templates=/etc/prometheus/consoles'
|
||||
- '--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_DAYS:-30}d'
|
||||
- '--web.enable-lifecycle'
|
||||
- '--web.external-url=https://${SERVER_IP}/prometheus/'
|
||||
# Оптимизация памяти
|
||||
- '--storage.tsdb.max-block-duration=2h'
|
||||
- '--storage.tsdb.min-block-duration=2h'
|
||||
ports:
|
||||
- "9090:9090"
|
||||
volumes:
|
||||
- ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||||
- ./infra/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
|
||||
- prometheus_data:/prometheus
|
||||
networks:
|
||||
- bots_network
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
|
||||
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/prometheus/-/healthy"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
memory: 128M
|
||||
cpus: '0.5'
|
||||
reservations:
|
||||
memory: 64M
|
||||
cpus: '0.25'
|
||||
|
||||
# Grafana Dashboard
|
||||
grafana:
|
||||
@@ -35,9 +48,12 @@ services:
|
||||
- GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
|
||||
- GF_USERS_ALLOW_SIGN_UP=false
|
||||
- GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
|
||||
- GF_SERVER_ROOT_URL=https://${SERVER_IP:-localhost}/grafana/
|
||||
- GF_SERVER_ROOT_URL=https://${SERVER_IP}/grafana/
|
||||
- GF_SERVER_SERVE_FROM_SUB_PATH=true
|
||||
- GF_SERVER_DOMAIN=${SERVER_IP:-localhost}
|
||||
# Оптимизация памяти
|
||||
- GF_DATABASE_MAX_IDLE_CONN=2
|
||||
- GF_DATABASE_MAX_OPEN_CONN=5
|
||||
- GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH=/etc/grafana/provisioning/dashboards/node-exporter-full-dashboard.json
|
||||
ports:
|
||||
- "3000:3000"
|
||||
volumes:
|
||||
@@ -52,27 +68,64 @@ services:
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
memory: 200M
|
||||
cpus: '0.5'
|
||||
reservations:
|
||||
memory: 100M
|
||||
cpus: '0.25'
|
||||
|
||||
# Nginx Reverse Proxy
|
||||
nginx:
|
||||
image: nginx:alpine
|
||||
container_name: bots_nginx
|
||||
# Uptime Kuma Status Page
|
||||
uptime-kuma:
|
||||
image: louislam/uptime-kuma:latest
|
||||
container_name: bots_uptime_kuma
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "80:80"
|
||||
- "443:443"
|
||||
volumes:
|
||||
- ./infra/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
|
||||
- ./infra/nginx/conf.d:/etc/nginx/conf.d:ro
|
||||
- ./infra/nginx/ssl:/etc/nginx/ssl:ro
|
||||
- ./infra/nginx/.htpasswd:/etc/nginx/.htpasswd:ro
|
||||
- uptime_kuma_data:/app/data
|
||||
ports:
|
||||
- "3001:3001"
|
||||
environment:
|
||||
- UPTIME_KUMA_PORT=3001
|
||||
networks:
|
||||
- bots_network
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://localhost:3001"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 40s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
memory: 150M
|
||||
cpus: '0.5'
|
||||
reservations:
|
||||
memory: 80M
|
||||
cpus: '0.25'
|
||||
|
||||
# Alertmanager
|
||||
alertmanager:
|
||||
image: prom/alertmanager:latest
|
||||
container_name: bots_alertmanager
|
||||
restart: unless-stopped
|
||||
command:
|
||||
- '--config.file=/etc/alertmanager/alertmanager.yml'
|
||||
- '--storage.path=/alertmanager'
|
||||
- '--web.external-url=https://${SERVER_IP}/alertmanager/'
|
||||
- '--web.route-prefix=/'
|
||||
ports:
|
||||
- "9093:9093"
|
||||
volumes:
|
||||
- alertmanager_data:/alertmanager
|
||||
- ./infra/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
||||
networks:
|
||||
- bots_network
|
||||
depends_on:
|
||||
- grafana
|
||||
- prometheus
|
||||
healthcheck:
|
||||
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost/nginx-health"]
|
||||
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
@@ -95,10 +148,10 @@ services:
|
||||
- LOG_RETENTION_DAYS=${LOG_RETENTION_DAYS:-30}
|
||||
- METRICS_HOST=${METRICS_HOST:-0.0.0.0}
|
||||
- METRICS_PORT=${METRICS_PORT:-8080}
|
||||
# Telegram settings
|
||||
- TELEGRAM_BOT_TOKEN=${BOT_TOKEN}
|
||||
- TELEGRAM_LISTEN_BOT_TOKEN=${LISTEN_BOT_TOKEN}
|
||||
- TELEGRAM_TEST_BOT_TOKEN=${TEST_BOT_TOKEN}
|
||||
# Telegram settings (токены из GitHub Secrets имеют приоритет над .env)
|
||||
- TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN:-${BOT_TOKEN}}
|
||||
- TELEGRAM_LISTEN_BOT_TOKEN=${TELEGRAM_LISTEN_BOT_TOKEN:-${LISTEN_BOT_TOKEN}}
|
||||
- TELEGRAM_TEST_BOT_TOKEN=${TELEGRAM_TEST_BOT_TOKEN:-${TEST_BOT_TOKEN}}
|
||||
- TELEGRAM_PREVIEW_LINK=${PREVIEW_LINK:-false}
|
||||
- TELEGRAM_MAIN_PUBLIC=${MAIN_PUBLIC}
|
||||
- TELEGRAM_GROUP_FOR_POSTS=${GROUP_FOR_POSTS}
|
||||
@@ -152,8 +205,8 @@ services:
|
||||
- PYTHONUNBUFFERED=1
|
||||
- DOCKER_CONTAINER=true
|
||||
- LOG_LEVEL=${LOG_LEVEL:-INFO}
|
||||
# AnonBot settings
|
||||
- ANON_BOT_TOKEN=${BOT_TOKEN}
|
||||
# AnonBot settings (токен из GitHub Secrets имеет приоритет над .env)
|
||||
- ANON_BOT_TOKEN=${ANON_BOT_TOKEN:-${BOT_TOKEN}}
|
||||
- ANON_BOT_ADMINS=${ADMINS}
|
||||
- ANON_BOT_DATABASE_PATH=/app/database/anon_qna.db
|
||||
- ANON_BOT_DEBUG=${DEBUG:-false}
|
||||
@@ -194,10 +247,15 @@ volumes:
|
||||
driver: local
|
||||
grafana_data:
|
||||
driver: local
|
||||
uptime_kuma_data:
|
||||
driver: local
|
||||
alertmanager_data:
|
||||
driver: local
|
||||
|
||||
networks:
|
||||
bots_network:
|
||||
driver: bridge
|
||||
ipam:
|
||||
config:
|
||||
- subnet: 192.168.100.0/24
|
||||
- subnet: 172.20.0.0/16
|
||||
gateway: 172.20.0.1
|
||||
|
||||
17
infra/alertmanager/alertmanager-simple.yml
Normal file
17
infra/alertmanager/alertmanager-simple.yml
Normal file
@@ -0,0 +1,17 @@
|
||||
# Simplified Alertmanager Configuration
|
||||
global:
|
||||
smtp_smarthost: 'localhost:587'
|
||||
smtp_from: 'alerts@localhost'
|
||||
|
||||
route:
|
||||
group_by: ['alertname']
|
||||
group_wait: 10s
|
||||
group_interval: 10s
|
||||
repeat_interval: 1h
|
||||
receiver: 'web.hook'
|
||||
|
||||
receivers:
|
||||
- name: 'web.hook'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/'
|
||||
send_resolved: true
|
||||
119
infra/alertmanager/alertmanager.yml
Normal file
119
infra/alertmanager/alertmanager.yml
Normal file
@@ -0,0 +1,119 @@
|
||||
# Alertmanager Configuration
|
||||
# This file configures how alerts are handled and routed
|
||||
|
||||
global:
|
||||
# SMTP configuration for email notifications
|
||||
smtp_smarthost: 'localhost:587'
|
||||
smtp_from: 'alerts@{{DOMAIN}}'
|
||||
smtp_auth_username: 'alerts@{{DOMAIN}}'
|
||||
smtp_auth_password: '{{SMTP_PASSWORD}}'
|
||||
smtp_require_tls: true
|
||||
|
||||
# Resolve timeout
|
||||
resolve_timeout: 5m
|
||||
|
||||
# Templates for alert formatting
|
||||
templates:
|
||||
- '/etc/alertmanager/templates/*.tmpl'
|
||||
|
||||
# Route configuration - defines how alerts are routed
|
||||
route:
|
||||
group_by: ['alertname', 'cluster', 'service']
|
||||
group_wait: 10s
|
||||
group_interval: 10s
|
||||
repeat_interval: 1h
|
||||
receiver: 'web.hook'
|
||||
routes:
|
||||
# Critical alerts - immediate notification
|
||||
- match:
|
||||
severity: critical
|
||||
receiver: 'critical-alerts'
|
||||
group_wait: 5s
|
||||
repeat_interval: 5m
|
||||
|
||||
# Warning alerts - grouped notification
|
||||
- match:
|
||||
severity: warning
|
||||
receiver: 'warning-alerts'
|
||||
group_wait: 30s
|
||||
repeat_interval: 30m
|
||||
|
||||
# Bot-specific alerts
|
||||
- match:
|
||||
service: telegram-bot
|
||||
receiver: 'bot-alerts'
|
||||
group_wait: 10s
|
||||
repeat_interval: 15m
|
||||
|
||||
- match:
|
||||
service: anon-bot
|
||||
receiver: 'bot-alerts'
|
||||
group_wait: 10s
|
||||
repeat_interval: 15m
|
||||
|
||||
# Infrastructure alerts
|
||||
- match:
|
||||
service: prometheus
|
||||
receiver: 'infrastructure-alerts'
|
||||
group_wait: 30s
|
||||
repeat_interval: 1h
|
||||
|
||||
- match:
|
||||
service: grafana
|
||||
receiver: 'infrastructure-alerts'
|
||||
group_wait: 30s
|
||||
repeat_interval: 1h
|
||||
|
||||
- match:
|
||||
service: nginx
|
||||
receiver: 'infrastructure-alerts'
|
||||
group_wait: 30s
|
||||
repeat_interval: 1h
|
||||
|
||||
# Inhibition rules - suppress certain alerts when others are firing
|
||||
inhibit_rules:
|
||||
# Suppress warning alerts when critical alerts are firing
|
||||
- source_match:
|
||||
severity: 'critical'
|
||||
target_match:
|
||||
severity: 'warning'
|
||||
equal: ['alertname', 'cluster', 'service']
|
||||
|
||||
# Suppress individual instance alerts when the entire service is down
|
||||
- source_match:
|
||||
alertname: 'ServiceDown'
|
||||
target_match:
|
||||
alertname: 'InstanceDown'
|
||||
equal: ['service']
|
||||
|
||||
# Receiver configurations
|
||||
receivers:
|
||||
# Default webhook receiver (for testing)
|
||||
- name: 'web.hook'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/'
|
||||
send_resolved: true
|
||||
|
||||
# Critical alerts - immediate notification via webhook
|
||||
- name: 'critical-alerts'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/critical'
|
||||
send_resolved: true
|
||||
|
||||
# Warning alerts - less urgent notification
|
||||
- name: 'warning-alerts'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/warning'
|
||||
send_resolved: true
|
||||
|
||||
# Bot-specific alerts
|
||||
- name: 'bot-alerts'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/bot'
|
||||
send_resolved: true
|
||||
|
||||
# Infrastructure alerts
|
||||
- name: 'infrastructure-alerts'
|
||||
webhook_configs:
|
||||
- url: 'http://localhost:5001/infrastructure'
|
||||
send_resolved: true
|
||||
File diff suppressed because it is too large
Load Diff
529
infra/grafana/dashboards/bot-monitoring.json
Normal file
529
infra/grafana/dashboards/bot-monitoring.json
Normal file
@@ -0,0 +1,529 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(http_requests_total{job=~\"telegram-bot|anon-bot\"}[5m])",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - {{method}} {{status}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Bot Request Rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket{job=~\"telegram-bot|anon-bot\"}[5m]))",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - 95th percentile",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.50, rate(http_request_duration_seconds_bucket{job=~\"telegram-bot|anon-bot\"}[5m]))",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - 50th percentile",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Bot Response Time",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percent"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(http_requests_total{job=~\"telegram-bot|anon-bot\",status=~\"5..\"}[5m]) / rate(http_requests_total{job=~\"telegram-bot|anon-bot\"}[5m]) * 100",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - Error Rate",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Bot Error Rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "process_resident_memory_bytes{job=~\"telegram-bot|anon-bot\"}",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - Memory Usage",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Bot Memory Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "up{job=~\"telegram-bot|anon-bot\"}",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - Status",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Bot Health Status",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(process_cpu_seconds_total{job=~\"telegram-bot|anon-bot\"}[5m]) * 100",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - CPU Usage",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Bot CPU Usage",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"schemaVersion": 27,
|
||||
"style": "dark",
|
||||
"tags": ["bots", "monitoring"],
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "Bot Monitoring Dashboard",
|
||||
"uid": "bot-monitoring",
|
||||
"version": 1
|
||||
}
|
||||
523
infra/grafana/dashboards/infrastructure-monitoring.json
Normal file
523
infra/grafana/dashboards/infrastructure-monitoring.json
Normal file
@@ -0,0 +1,523 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percent"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
|
||||
"interval": "",
|
||||
"legendFormat": "CPU Usage - {{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "System CPU Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percent"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100",
|
||||
"interval": "",
|
||||
"legendFormat": "Memory Usage - {{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "System Memory Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percent"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100",
|
||||
"interval": "",
|
||||
"legendFormat": "Disk Usage - {{instance}} {{mountpoint}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Disk Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "up{job=~\"prometheus|grafana|nginx|alertmanager|uptime-kuma\"}",
|
||||
"interval": "",
|
||||
"legendFormat": "{{job}} - Status",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Service Health Status",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(nginx_http_requests_total[5m])",
|
||||
"interval": "",
|
||||
"legendFormat": "Nginx - {{status}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Nginx Request Rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": "Prometheus",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"vis": false
|
||||
},
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom"
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "container_memory_usage_bytes{name=~\"bots_.*\"}",
|
||||
"interval": "",
|
||||
"legendFormat": "{{name}} - Memory",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Container Memory Usage",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"schemaVersion": 27,
|
||||
"style": "dark",
|
||||
"tags": ["infrastructure", "monitoring"],
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "Infrastructure Monitoring Dashboard",
|
||||
"uid": "infrastructure-monitoring",
|
||||
"version": 1
|
||||
}
|
||||
16
infra/grafana/provisioning/dashboards/dashboards.yml
Normal file
16
infra/grafana/provisioning/dashboards/dashboards.yml
Normal file
@@ -0,0 +1,16 @@
|
||||
# Grafana Dashboard Provisioning Configuration
|
||||
# This file configures automatic dashboard import
|
||||
|
||||
apiVersion: 1
|
||||
|
||||
providers:
|
||||
- name: 'default'
|
||||
orgId: 1
|
||||
folder: ''
|
||||
type: file
|
||||
disableDeletion: false
|
||||
updateIntervalSeconds: 10
|
||||
allowUiUpdates: true
|
||||
options:
|
||||
path: /etc/grafana/provisioning/dashboards
|
||||
foldersFromFilesStructure: true
|
||||
@@ -4,5 +4,13 @@ datasources:
|
||||
- name: Prometheus
|
||||
type: prometheus
|
||||
access: proxy
|
||||
url: http://prometheus:9090
|
||||
url: http://prometheus:9090/prometheus
|
||||
isDefault: true
|
||||
jsonData:
|
||||
httpMethod: POST
|
||||
manageAlerts: true
|
||||
prometheusType: Prometheus
|
||||
prometheusVersion: 2.40.0
|
||||
cacheLevel: 'High'
|
||||
disableRecordingRules: false
|
||||
incrementalQueryOverlapWindow: 10m
|
||||
|
||||
77
infra/logrotate/README.md
Normal file
77
infra/logrotate/README.md
Normal file
@@ -0,0 +1,77 @@
|
||||
# Logrotate Configuration
|
||||
|
||||
Эта директория содержит конфигурационные файлы для автоматической ротации логов.
|
||||
|
||||
## Файлы
|
||||
|
||||
### `logrotate_bots.conf.j2`
|
||||
Шаблон конфигурации для логов ботов и Docker контейнеров:
|
||||
- Логи ботов в `{{ project_root }}/bots/*/logs/*.log`
|
||||
- Stderr логи ботов в `{{ project_root }}/bots/*/bot_stderr.log`
|
||||
- Docker контейнер логи в `/var/lib/docker/containers/*/*.log`
|
||||
|
||||
### `logrotate_system.conf.j2`
|
||||
Шаблон конфигурации для системных сервисов:
|
||||
- Nginx логи в `/var/log/nginx/*.log`
|
||||
- Системные логи (syslog, mail, auth, cron и др.)
|
||||
- Fail2ban логи
|
||||
- Docker daemon логи
|
||||
- Prometheus node exporter логи
|
||||
|
||||
## Переменные окружения
|
||||
|
||||
Конфигурации используют следующие переменные из `.env` файла:
|
||||
|
||||
```bash
|
||||
# Logrotate настройки
|
||||
LOGROTATE_RETENTION_DAYS=30 # Количество дней хранения логов
|
||||
LOGROTATE_COMPRESS=true # Сжатие старых логов
|
||||
LOGROTATE_DELAYCOMPRESS=true # Отложенное сжатие
|
||||
```
|
||||
|
||||
## Использование
|
||||
|
||||
Эти шаблоны автоматически применяются при запуске Ansible playbook. Они создают конфигурационные файлы в `/etc/logrotate.d/` на сервере.
|
||||
|
||||
### Ручное применение
|
||||
|
||||
Если нужно применить конфигурации вручную:
|
||||
|
||||
```bash
|
||||
# Скопировать конфигурации
|
||||
sudo cp logrotate_bots.conf.j2 /etc/logrotate.d/bots
|
||||
sudo cp logrotate_system.conf.j2 /etc/logrotate.d/system
|
||||
|
||||
# Проверить конфигурацию
|
||||
sudo logrotate -d /etc/logrotate.conf
|
||||
|
||||
# Принудительная ротация
|
||||
sudo logrotate -f /etc/logrotate.conf
|
||||
```
|
||||
|
||||
## Настройки по умолчанию
|
||||
|
||||
- **Ежедневная ротация**: все логи ротируются каждый день
|
||||
- **Сжатие**: старые логи сжимаются gzip
|
||||
- **Хранение**: 30 дней (настраивается через переменную)
|
||||
- **Автоматический перезапуск сервисов**: после ротации логов
|
||||
|
||||
## Структура логов
|
||||
|
||||
После настройки логи будут организованы следующим образом:
|
||||
|
||||
```
|
||||
/var/log/
|
||||
├── nginx/
|
||||
│ ├── access.log
|
||||
│ ├── access.log.1.gz
|
||||
│ ├── error.log
|
||||
│ └── error.log.1.gz
|
||||
└── ...
|
||||
|
||||
{{ project_root }}/bots/*/logs/
|
||||
├── bot.log
|
||||
├── bot.log.1.gz
|
||||
├── bot.log.2.gz
|
||||
└── ...
|
||||
```
|
||||
49
infra/logrotate/logrotate_bots.conf.j2
Normal file
49
infra/logrotate/logrotate_bots.conf.j2
Normal file
@@ -0,0 +1,49 @@
|
||||
# Logrotate configuration for bot applications
|
||||
# This file manages log rotation for all bot services
|
||||
|
||||
{{ project_root }}/bots/*/logs/*.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 30
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 {{ deploy_user }} {{ deploy_user }}
|
||||
postrotate
|
||||
# Restart bot services if they are running
|
||||
if [ -f /home/{{ deploy_user }}/.docker-compose-pid ]; then
|
||||
cd {{ project_root }} && docker-compose restart
|
||||
fi
|
||||
endscript
|
||||
}
|
||||
|
||||
{{ project_root }}/bots/*/bot_stderr.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 30
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 {{ deploy_user }} {{ deploy_user }}
|
||||
postrotate
|
||||
# Restart bot services if they are running
|
||||
if [ -f /home/{{ deploy_user }}/.docker-compose-pid ]; then
|
||||
cd {{ project_root }} && docker-compose restart
|
||||
fi
|
||||
endscript
|
||||
}
|
||||
|
||||
# Docker container logs
|
||||
/var/lib/docker/containers/*/*.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 root root
|
||||
postrotate
|
||||
# Reload Docker daemon
|
||||
systemctl reload docker
|
||||
endscript
|
||||
}
|
||||
100
infra/logrotate/logrotate_system.conf.j2
Normal file
100
infra/logrotate/logrotate_system.conf.j2
Normal file
@@ -0,0 +1,100 @@
|
||||
# Logrotate configuration for system services
|
||||
# This file manages log rotation for system services
|
||||
|
||||
# Nginx logs
|
||||
/var/log/nginx/*.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 30
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 www-data adm
|
||||
sharedscripts
|
||||
postrotate
|
||||
if [ -f /var/run/nginx.pid ]; then
|
||||
kill -USR1 `cat /var/run/nginx.pid`
|
||||
fi
|
||||
endscript
|
||||
}
|
||||
|
||||
# System logs
|
||||
/var/log/syslog {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 syslog adm
|
||||
postrotate
|
||||
/usr/lib/rsyslog/rsyslog-rotate
|
||||
endscript
|
||||
}
|
||||
|
||||
/var/log/mail.info
|
||||
/var/log/mail.warn
|
||||
/var/log/mail.err
|
||||
/var/log/mail.log
|
||||
/var/log/daemon.log
|
||||
/var/log/kern.log
|
||||
/var/log/auth.log
|
||||
/var/log/user.log
|
||||
/var/log/lpr.log
|
||||
/var/log/cron.log
|
||||
/var/log/debug
|
||||
/var/log/messages {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 syslog adm
|
||||
sharedscripts
|
||||
postrotate
|
||||
/usr/lib/rsyslog/rsyslog-rotate
|
||||
endscript
|
||||
}
|
||||
|
||||
# Fail2ban logs
|
||||
/var/log/fail2ban.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 root root
|
||||
postrotate
|
||||
systemctl reload fail2ban
|
||||
endscript
|
||||
}
|
||||
|
||||
# Docker daemon logs
|
||||
/var/log/docker.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 root root
|
||||
postrotate
|
||||
systemctl reload docker
|
||||
endscript
|
||||
}
|
||||
|
||||
# Prometheus node exporter logs
|
||||
/var/log/prometheus-node-exporter.log {
|
||||
daily
|
||||
missingok
|
||||
rotate 7
|
||||
compress
|
||||
delaycompress
|
||||
notifempty
|
||||
create 0644 prometheus prometheus
|
||||
postrotate
|
||||
systemctl reload prometheus-node-exporter
|
||||
endscript
|
||||
}
|
||||
104
infra/nginx/AUTH_SETUP.md
Normal file
104
infra/nginx/AUTH_SETUP.md
Normal file
@@ -0,0 +1,104 @@
|
||||
# Настройка авторизации для мониторинга
|
||||
|
||||
## Обзор
|
||||
|
||||
Добавлена HTTP Basic Authentication для следующих сервисов:
|
||||
- **Prometheus** (`/prometheus/`) - метрики и мониторинг
|
||||
- **Alertmanager** (`/alerts/` и `/api/v1/`) - управление алертами
|
||||
|
||||
## Управление паролями
|
||||
|
||||
### Автоматическая настройка через Ansible
|
||||
|
||||
При развертывании через Ansible пароли настраиваются автоматически:
|
||||
|
||||
```bash
|
||||
# Использовать пароли по умолчанию
|
||||
ansible-playbook -i inventory.ini playbook.yml
|
||||
|
||||
# Задать свои пароли
|
||||
ansible-playbook -i inventory.ini playbook.yml \
|
||||
-e monitoring_username=myuser \
|
||||
-e monitoring_password=mypassword
|
||||
```
|
||||
|
||||
### Ручная настройка
|
||||
|
||||
1. **Создать файл паролей:**
|
||||
```bash
|
||||
sudo mkdir -p /etc/nginx/passwords
|
||||
sudo htpasswd -c /etc/nginx/passwords/monitoring.htpasswd admin
|
||||
```
|
||||
|
||||
2. **Добавить дополнительных пользователей:**
|
||||
```bash
|
||||
sudo htpasswd /etc/nginx/passwords/monitoring.htpasswd username
|
||||
```
|
||||
|
||||
3. **Установить правильные права:**
|
||||
```bash
|
||||
sudo chown root:www-data /etc/nginx/passwords/monitoring.htpasswd
|
||||
sudo chmod 640 /etc/nginx/passwords/monitoring.htpasswd
|
||||
```
|
||||
|
||||
4. **Перезапустить nginx:**
|
||||
```bash
|
||||
sudo systemctl reload nginx
|
||||
```
|
||||
|
||||
### Использование скрипта генерации
|
||||
|
||||
```bash
|
||||
# Сгенерировать пароль для пользователя admin
|
||||
sudo /usr/local/bin/generate_auth_passwords.sh admin
|
||||
|
||||
# Сгенерировать пароль для другого пользователя
|
||||
sudo /usr/local/bin/generate_auth_passwords.sh myuser
|
||||
```
|
||||
|
||||
## Доступ к сервисам
|
||||
|
||||
После настройки авторизации доступ к сервисам:
|
||||
|
||||
- **Prometheus**: `https://your-server/prometheus/`
|
||||
- **Alertmanager**: `https://your-server/alerts/`
|
||||
- **Alertmanager API**: `https://your-server/api/v1/`
|
||||
|
||||
При первом обращении браузер запросит логин и пароль.
|
||||
|
||||
## Health Check endpoints
|
||||
|
||||
Следующие endpoints остаются доступными без авторизации для мониторинга:
|
||||
|
||||
- `https://your-server/prometheus/-/healthy` - проверка состояния Prometheus
|
||||
- `https://your-server/nginx-health` - проверка состояния nginx
|
||||
|
||||
## Безопасность
|
||||
|
||||
- Пароли хранятся в зашифрованном виде в файле `/etc/nginx/passwords/monitoring.htpasswd`
|
||||
- Файл доступен только для чтения пользователю root и группе www-data
|
||||
- Используется HTTPS для всех соединений
|
||||
- Настроена защита от брутфорса через fail2ban
|
||||
|
||||
## Устранение проблем
|
||||
|
||||
### Проверка конфигурации nginx
|
||||
```bash
|
||||
sudo nginx -t
|
||||
```
|
||||
|
||||
### Проверка файла паролей
|
||||
```bash
|
||||
sudo cat /etc/nginx/passwords/monitoring.htpasswd
|
||||
```
|
||||
|
||||
### Проверка логов nginx
|
||||
```bash
|
||||
sudo tail -f /var/log/nginx/error.log
|
||||
sudo tail -f /var/log/nginx/access.log
|
||||
```
|
||||
|
||||
### Сброс пароля
|
||||
```bash
|
||||
sudo htpasswd /etc/nginx/passwords/monitoring.htpasswd admin
|
||||
```
|
||||
@@ -1,32 +0,0 @@
|
||||
# Grafana reverse proxy configuration
|
||||
upstream grafana_backend {
|
||||
server grafana:3000;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
# Grafana proxy configuration
|
||||
location /grafana/ {
|
||||
proxy_pass http://grafana_backend/;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Port $server_port;
|
||||
|
||||
# WebSocket support for Grafana
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 60s;
|
||||
proxy_send_timeout 60s;
|
||||
proxy_read_timeout 60s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
proxy_busy_buffers_size 8k;
|
||||
}
|
||||
@@ -1,34 +0,0 @@
|
||||
# Prometheus reverse proxy configuration
|
||||
upstream prometheus_backend {
|
||||
server prometheus:9090;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
# Prometheus proxy configuration
|
||||
location /prometheus/ {
|
||||
proxy_pass http://prometheus_backend/;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Port $server_port;
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
proxy_busy_buffers_size 8k;
|
||||
}
|
||||
|
||||
# Health check endpoint
|
||||
location /prometheus/-/healthy {
|
||||
proxy_pass http://prometheus_backend/-/healthy;
|
||||
proxy_set_header Host $host;
|
||||
access_log off;
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
# Status page configuration (for future uptime kuma integration)
|
||||
|
||||
# Rate limiting for status page
|
||||
location /status {
|
||||
# Basic authentication for status page
|
||||
auth_basic "Status Page Access";
|
||||
auth_basic_user_file /etc/nginx/.htpasswd;
|
||||
|
||||
# Placeholder for future uptime kuma integration
|
||||
# For now, show nginx status
|
||||
access_log off;
|
||||
return 200 '{"status": "ok", "nginx": "running", "timestamp": "$time_iso8601"}';
|
||||
add_header Content-Type application/json;
|
||||
}
|
||||
|
||||
# Nginx status stub (for monitoring)
|
||||
location /nginx_status {
|
||||
stub_status on;
|
||||
access_log off;
|
||||
allow 127.0.0.1;
|
||||
allow 172.16.0.0/12; # Docker networks
|
||||
allow 192.168.0.0/16; # Private networks
|
||||
deny all;
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
user nginx;
|
||||
user www-data;
|
||||
worker_processes auto;
|
||||
error_log /var/log/nginx/error.log warn;
|
||||
pid /var/run/nginx.pid;
|
||||
@@ -63,7 +63,29 @@ http {
|
||||
ssl_session_cache shared:SSL:10m;
|
||||
ssl_session_timeout 10m;
|
||||
|
||||
# Upstream configurations
|
||||
upstream grafana_backend {
|
||||
server localhost:3000;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
upstream prometheus_backend {
|
||||
server localhost:9090;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
upstream uptime_kuma_backend {
|
||||
server localhost:3001;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
upstream alertmanager_backend {
|
||||
server localhost:9093;
|
||||
keepalive 32;
|
||||
}
|
||||
|
||||
# Main server block
|
||||
# Redirect HTTP to HTTPS
|
||||
server {
|
||||
listen 80;
|
||||
server_name _;
|
||||
@@ -74,20 +96,23 @@ http {
|
||||
listen 443 ssl http2;
|
||||
server_name _;
|
||||
|
||||
# SSL configuration
|
||||
ssl_certificate /etc/nginx/ssl/cert.pem;
|
||||
ssl_certificate_key /etc/nginx/ssl/key.pem;
|
||||
# SSL configuration (self-signed certificate)
|
||||
ssl_certificate /etc/nginx/ssl/fullchain.pem;
|
||||
ssl_certificate_key /etc/nginx/ssl/privkey.pem;
|
||||
ssl_protocols TLSv1.2 TLSv1.3;
|
||||
ssl_ciphers ECDHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-SHA256:ECDHE-RSA-AES256-SHA384;
|
||||
ssl_prefer_server_ciphers off;
|
||||
ssl_session_cache shared:SSL:10m;
|
||||
ssl_session_timeout 10m;
|
||||
|
||||
# Security headers
|
||||
add_header X-Frame-Options "SAMEORIGIN" always;
|
||||
add_header X-Content-Type-Options "nosniff" always;
|
||||
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=20 nodelay;
|
||||
|
||||
# Redirect root to Grafana
|
||||
# Root page - show simple status
|
||||
location = / {
|
||||
return 301 /grafana/;
|
||||
return 200 "Bot Infrastructure Status\n\nServices:\n- Grafana: /grafana/\n- Prometheus: /prometheus/\n- Uptime Kuma: /status/\n- Alertmanager: /alerts/\n";
|
||||
add_header Content-Type text/plain;
|
||||
}
|
||||
|
||||
# Health check endpoint
|
||||
@@ -97,7 +122,282 @@ http {
|
||||
add_header Content-Type text/plain;
|
||||
}
|
||||
|
||||
# Include location configurations
|
||||
include /etc/nginx/conf.d/*.conf;
|
||||
# Uptime Kuma status page
|
||||
location /status {
|
||||
# Rate limiting
|
||||
limit_req zone=status burst=5 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001/;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
}
|
||||
|
||||
# Uptime Kuma dashboard
|
||||
location /dashboard {
|
||||
# Rate limiting
|
||||
limit_req zone=status burst=5 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001/dashboard;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
}
|
||||
|
||||
# Uptime Kuma static assets
|
||||
location /assets/ {
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=20 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# Cache static assets
|
||||
expires 1y;
|
||||
add_header Cache-Control "public, immutable";
|
||||
}
|
||||
|
||||
# Uptime Kuma icons and manifest
|
||||
location ~ ^/(icon.*\.(png|svg)|apple-touch-icon.*\.png|manifest\.json)$ {
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=20 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# Cache static assets
|
||||
expires 1y;
|
||||
add_header Cache-Control "public, immutable";
|
||||
}
|
||||
|
||||
# Uptime Kuma WebSocket (Socket.IO)
|
||||
location /socket.io/ {
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=20 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
}
|
||||
|
||||
# Uptime Kuma API endpoints
|
||||
location /api/ {
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=10 nodelay;
|
||||
|
||||
# Proxy to Uptime Kuma
|
||||
proxy_pass http://127.0.0.1:3001;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# CORS headers
|
||||
add_header Access-Control-Allow-Origin "*" always;
|
||||
add_header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS" always;
|
||||
add_header Access-Control-Allow-Headers "DNT,User-Agent,X-Requested-With,If-Modified-Since,Cache-Control,Content-Type,Range,Authorization" always;
|
||||
|
||||
# Handle preflight requests
|
||||
if ($request_method = 'OPTIONS') {
|
||||
add_header Access-Control-Allow-Origin "*";
|
||||
add_header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS";
|
||||
add_header Access-Control-Allow-Headers "DNT,User-Agent,X-Requested-With,If-Modified-Since,Cache-Control,Content-Type,Range,Authorization";
|
||||
add_header Access-Control-Max-Age 1728000;
|
||||
add_header Content-Type "text/plain; charset=utf-8";
|
||||
add_header Content-Length 0;
|
||||
return 204;
|
||||
}
|
||||
}
|
||||
|
||||
# Grafana proxy configuration
|
||||
location /grafana/ {
|
||||
proxy_pass http://grafana_backend;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Port $server_port;
|
||||
|
||||
# WebSocket support for Grafana
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 60s;
|
||||
proxy_send_timeout 60s;
|
||||
proxy_read_timeout 60s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
proxy_busy_buffers_size 8k;
|
||||
}
|
||||
|
||||
# Prometheus proxy configuration with authentication
|
||||
location /prometheus/ {
|
||||
# HTTP Basic Authentication
|
||||
auth_basic "Prometheus Monitoring";
|
||||
auth_basic_user_file /etc/nginx/passwords/monitoring.htpasswd;
|
||||
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=10 nodelay;
|
||||
|
||||
proxy_pass http://prometheus_backend/prometheus/;
|
||||
proxy_redirect /prometheus/ /prometheus/;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Port $server_port;
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
proxy_busy_buffers_size 8k;
|
||||
}
|
||||
|
||||
# Prometheus health check endpoint
|
||||
location /prometheus/-/healthy {
|
||||
proxy_pass http://prometheus_backend/prometheus/-/healthy;
|
||||
proxy_set_header Host $host;
|
||||
access_log off;
|
||||
}
|
||||
|
||||
# Alertmanager proxy configuration with authentication
|
||||
location /alerts/ {
|
||||
# HTTP Basic Authentication
|
||||
auth_basic "Alertmanager Monitoring";
|
||||
auth_basic_user_file /etc/nginx/passwords/monitoring.htpasswd;
|
||||
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=10 nodelay;
|
||||
|
||||
# Remove trailing slash for proxy
|
||||
rewrite ^/alerts/(.*)$ /$1 break;
|
||||
|
||||
# Proxy to Alertmanager
|
||||
proxy_pass http://alertmanager_backend;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Port $server_port;
|
||||
|
||||
# Timeouts
|
||||
proxy_connect_timeout 30s;
|
||||
proxy_send_timeout 30s;
|
||||
proxy_read_timeout 30s;
|
||||
|
||||
# Buffer settings
|
||||
proxy_buffering on;
|
||||
proxy_buffer_size 4k;
|
||||
proxy_buffers 8 4k;
|
||||
proxy_busy_buffers_size 8k;
|
||||
|
||||
# Security headers
|
||||
add_header X-Frame-Options "SAMEORIGIN" always;
|
||||
add_header X-Content-Type-Options "nosniff" always;
|
||||
}
|
||||
|
||||
# Alertmanager API with authentication
|
||||
location /api/v1/ {
|
||||
# HTTP Basic Authentication
|
||||
auth_basic "Alertmanager API";
|
||||
auth_basic_user_file /etc/nginx/passwords/monitoring.htpasswd;
|
||||
|
||||
# Rate limiting
|
||||
limit_req zone=api burst=20 nodelay;
|
||||
|
||||
# Proxy to Alertmanager
|
||||
proxy_pass http://alertmanager_backend;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# CORS headers
|
||||
add_header Access-Control-Allow-Origin "*" always;
|
||||
add_header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS" always;
|
||||
add_header Access-Control-Allow-Headers "DNT,User-Agent,X-Requested-With,If-Modified-Since,Cache-Control,Content-Type,Range,Authorization" always;
|
||||
|
||||
# Handle preflight requests
|
||||
if ($request_method = 'OPTIONS') {
|
||||
add_header Access-Control-Allow-Origin "*";
|
||||
add_header Access-Control-Allow-Methods "GET, POST, PUT, DELETE, OPTIONS";
|
||||
add_header Access-Control-Allow-Headers "DNT,User-Agent,X-Requested-With,If-Modified-Since,Cache-Control,Content-Type,Range,Authorization";
|
||||
add_header Access-Control-Max-Age 1728000;
|
||||
add_header Content-Type "text/plain; charset=utf-8";
|
||||
add_header Content-Length 0;
|
||||
return 204;
|
||||
}
|
||||
}
|
||||
|
||||
# All location configurations are now integrated into this file
|
||||
}
|
||||
}
|
||||
|
||||
27
infra/nginx/ssl/letsencrypt.conf
Normal file
27
infra/nginx/ssl/letsencrypt.conf
Normal file
@@ -0,0 +1,27 @@
|
||||
# Let's Encrypt SSL Configuration
|
||||
# This file contains the SSL configuration for Let's Encrypt certificates
|
||||
|
||||
# SSL certificate paths (Let's Encrypt)
|
||||
ssl_certificate /etc/letsencrypt/live/{{DOMAIN}}/fullchain.pem;
|
||||
ssl_certificate_key /etc/letsencrypt/live/{{DOMAIN}}/privkey.pem;
|
||||
|
||||
# SSL Security Configuration
|
||||
ssl_protocols TLSv1.2 TLSv1.3;
|
||||
ssl_ciphers ECDHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-SHA256:ECDHE-RSA-AES256-SHA384:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-RSA-AES128-SHA256:ECDHE-RSA-AES256-SHA384;
|
||||
ssl_prefer_server_ciphers off;
|
||||
ssl_session_cache shared:SSL:10m;
|
||||
ssl_session_timeout 10m;
|
||||
ssl_session_tickets off;
|
||||
|
||||
# OCSP Stapling
|
||||
ssl_stapling on;
|
||||
ssl_stapling_verify on;
|
||||
ssl_trusted_certificate /etc/letsencrypt/live/{{DOMAIN}}/chain.pem;
|
||||
|
||||
# Security Headers
|
||||
add_header Strict-Transport-Security "max-age=31536000; includeSubDomains" always;
|
||||
add_header X-Frame-Options "SAMEORIGIN" always;
|
||||
add_header X-Content-Type-Options "nosniff" always;
|
||||
add_header X-XSS-Protection "1; mode=block" always;
|
||||
add_header Referrer-Policy "strict-origin-when-cross-origin" always;
|
||||
add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval'; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; font-src 'self' data:; connect-src 'self' wss: https:;" always;
|
||||
253
infra/prometheus/alert_rules.yml
Normal file
253
infra/prometheus/alert_rules.yml
Normal file
@@ -0,0 +1,253 @@
|
||||
# Prometheus Alert Rules
|
||||
# This file defines alerting rules for monitoring the bot infrastructure
|
||||
|
||||
groups:
|
||||
# Bot Health Monitoring
|
||||
- name: bot_health
|
||||
rules:
|
||||
# Telegram Bot Health
|
||||
- alert: TelegramBotDown
|
||||
expr: up{job="telegram-bot"} == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: telegram-bot
|
||||
annotations:
|
||||
summary: "Telegram Bot is down"
|
||||
description: "Telegram Bot has been down for more than 1 minute"
|
||||
runbook_url: "https://docs.example.com/runbooks/telegram-bot-down"
|
||||
|
||||
- alert: TelegramBotHighErrorRate
|
||||
expr: rate(http_requests_total{job="telegram-bot",status=~"5.."}[5m]) > 0.1
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
service: telegram-bot
|
||||
annotations:
|
||||
summary: "Telegram Bot high error rate"
|
||||
description: "Telegram Bot error rate is {{ $value }} errors per second"
|
||||
|
||||
- alert: TelegramBotHighResponseTime
|
||||
expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket{job="telegram-bot"}[5m])) > 2
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: telegram-bot
|
||||
annotations:
|
||||
summary: "Telegram Bot high response time"
|
||||
description: "95th percentile response time is {{ $value }} seconds"
|
||||
|
||||
# AnonBot Health
|
||||
- alert: AnonBotDown
|
||||
expr: up{job="anon-bot"} == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: anon-bot
|
||||
annotations:
|
||||
summary: "AnonBot is down"
|
||||
description: "AnonBot has been down for more than 1 minute"
|
||||
runbook_url: "https://docs.example.com/runbooks/anon-bot-down"
|
||||
|
||||
- alert: AnonBotHighErrorRate
|
||||
expr: rate(http_requests_total{job="anon-bot",status=~"5.."}[5m]) > 0.1
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
service: anon-bot
|
||||
annotations:
|
||||
summary: "AnonBot high error rate"
|
||||
description: "AnonBot error rate is {{ $value }} errors per second"
|
||||
|
||||
- alert: AnonBotHighResponseTime
|
||||
expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket{job="anon-bot"}[5m])) > 2
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: anon-bot
|
||||
annotations:
|
||||
summary: "AnonBot high response time"
|
||||
description: "95th percentile response time is {{ $value }} seconds"
|
||||
|
||||
# Infrastructure Health Monitoring
|
||||
- name: infrastructure_health
|
||||
rules:
|
||||
# Prometheus Health
|
||||
- alert: PrometheusDown
|
||||
expr: up{job="prometheus"} == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: prometheus
|
||||
annotations:
|
||||
summary: "Prometheus is down"
|
||||
description: "Prometheus has been down for more than 1 minute"
|
||||
|
||||
- alert: PrometheusHighMemoryUsage
|
||||
expr: (prometheus_tsdb_head_series / prometheus_tsdb_head_series_limit) > 0.8
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: prometheus
|
||||
annotations:
|
||||
summary: "Prometheus high memory usage"
|
||||
description: "Prometheus memory usage is {{ $value | humanizePercentage }} of limit"
|
||||
|
||||
# Grafana Health
|
||||
- alert: GrafanaDown
|
||||
expr: up{job="grafana"} == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: grafana
|
||||
annotations:
|
||||
summary: "Grafana is down"
|
||||
description: "Grafana has been down for more than 1 minute"
|
||||
|
||||
# Nginx Health
|
||||
- alert: NginxDown
|
||||
expr: up{job="nginx"} == 0
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: nginx
|
||||
annotations:
|
||||
summary: "Nginx is down"
|
||||
description: "Nginx has been down for more than 1 minute"
|
||||
|
||||
- alert: NginxHighErrorRate
|
||||
expr: rate(nginx_http_requests_total{status=~"5.."}[5m]) > 0.1
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
service: nginx
|
||||
annotations:
|
||||
summary: "Nginx high error rate"
|
||||
description: "Nginx error rate is {{ $value }} errors per second"
|
||||
|
||||
# System Resource Monitoring
|
||||
- name: system_resources
|
||||
rules:
|
||||
# High CPU Usage
|
||||
- alert: HighCPUUsage
|
||||
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: system
|
||||
annotations:
|
||||
summary: "High CPU usage"
|
||||
description: "CPU usage is {{ $value }}% on {{ $labels.instance }}"
|
||||
|
||||
- alert: VeryHighCPUUsage
|
||||
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 95
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
service: system
|
||||
annotations:
|
||||
summary: "Very high CPU usage"
|
||||
description: "CPU usage is {{ $value }}% on {{ $labels.instance }}"
|
||||
|
||||
# High Memory Usage
|
||||
- alert: HighMemoryUsage
|
||||
expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: system
|
||||
annotations:
|
||||
summary: "High memory usage"
|
||||
description: "Memory usage is {{ $value }}% on {{ $labels.instance }}"
|
||||
|
||||
- alert: VeryHighMemoryUsage
|
||||
expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 95
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
service: system
|
||||
annotations:
|
||||
summary: "Very high memory usage"
|
||||
description: "Memory usage is {{ $value }}% on {{ $labels.instance }}"
|
||||
|
||||
# Disk Space
|
||||
- alert: LowDiskSpace
|
||||
expr: (1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100 > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: system
|
||||
annotations:
|
||||
summary: "Low disk space"
|
||||
description: "Disk usage is {{ $value }}% on {{ $labels.instance }} ({{ $labels.mountpoint }})"
|
||||
|
||||
- alert: VeryLowDiskSpace
|
||||
expr: (1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100 > 95
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
service: system
|
||||
annotations:
|
||||
summary: "Very low disk space"
|
||||
description: "Disk usage is {{ $value }}% on {{ $labels.instance }} ({{ $labels.mountpoint }})"
|
||||
|
||||
# Docker Container Monitoring
|
||||
- name: docker_containers
|
||||
rules:
|
||||
# Container Restart
|
||||
- alert: ContainerRestarting
|
||||
expr: rate(container_start_time_seconds[10m]) > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
service: docker
|
||||
annotations:
|
||||
summary: "Container restarting"
|
||||
description: "Container {{ $labels.name }} is restarting frequently"
|
||||
|
||||
# Container High Memory Usage
|
||||
- alert: ContainerHighMemoryUsage
|
||||
expr: (container_memory_usage_bytes / container_spec_memory_limit_bytes) * 100 > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: docker
|
||||
annotations:
|
||||
summary: "Container high memory usage"
|
||||
description: "Container {{ $labels.name }} memory usage is {{ $value }}%"
|
||||
|
||||
# Container High CPU Usage
|
||||
- alert: ContainerHighCPUUsage
|
||||
expr: (rate(container_cpu_usage_seconds_total[5m]) / container_spec_cpu_quota * 100) > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: docker
|
||||
annotations:
|
||||
summary: "Container high CPU usage"
|
||||
description: "Container {{ $labels.name }} CPU usage is {{ $value }}%"
|
||||
|
||||
# Database Monitoring
|
||||
- name: database_health
|
||||
rules:
|
||||
# Database Connection Issues
|
||||
- alert: DatabaseConnectionFailed
|
||||
expr: increase(database_connection_errors_total[5m]) > 5
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
service: database
|
||||
annotations:
|
||||
summary: "Database connection failures"
|
||||
description: "{{ $value }} database connection failures in the last 5 minutes"
|
||||
|
||||
# Database High Query Time
|
||||
- alert: DatabaseHighQueryTime
|
||||
expr: histogram_quantile(0.95, rate(database_query_duration_seconds_bucket[5m])) > 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
service: database
|
||||
annotations:
|
||||
summary: "Database high query time"
|
||||
description: "95th percentile database query time is {{ $value }} seconds"
|
||||
@@ -3,8 +3,7 @@ global:
|
||||
evaluation_interval: 15s
|
||||
|
||||
rule_files:
|
||||
# - "first_rules.yml"
|
||||
# - "second_rules.yml"
|
||||
- "alert_rules.yml"
|
||||
|
||||
scrape_configs:
|
||||
- job_name: 'prometheus'
|
||||
@@ -14,7 +13,7 @@ scrape_configs:
|
||||
# Job для мониторинга Node Exporter
|
||||
- job_name: 'node'
|
||||
static_configs:
|
||||
- targets: ['172.17.0.1:9100'] # Специальное имя для доступа к хосту
|
||||
- targets: ['172.20.0.1:9100'] # Node Exporter на хосте через Docker gateway
|
||||
labels:
|
||||
instance: 'main-server'
|
||||
|
||||
@@ -46,4 +45,4 @@ alerting:
|
||||
alertmanagers:
|
||||
- static_configs:
|
||||
- targets:
|
||||
# - alertmanager:9093
|
||||
- alertmanager:9093
|
||||
|
||||
77
infra/uptime-kuma/README.md
Normal file
77
infra/uptime-kuma/README.md
Normal file
@@ -0,0 +1,77 @@
|
||||
# Uptime Kuma Configuration
|
||||
|
||||
Uptime Kuma - это статусная страница для мониторинга доступности сервисов.
|
||||
|
||||
## Доступ
|
||||
|
||||
- **Веб-интерфейс**: `https://your-domain/status/`
|
||||
- **Прямой доступ**: `http://localhost:3001` (только локально)
|
||||
|
||||
## Настройка
|
||||
|
||||
### Первоначальная настройка
|
||||
|
||||
1. Запустите сервисы:
|
||||
```bash
|
||||
make up
|
||||
```
|
||||
|
||||
2. Откройте `https://your-domain/status/`
|
||||
|
||||
3. Создайте администратора:
|
||||
- Username: `admin`
|
||||
- Password: `admin` (смените после первого входа)
|
||||
|
||||
### Мониторинг сервисов
|
||||
|
||||
Uptime Kuma автоматически настроит мониторинг следующих сервисов:
|
||||
|
||||
- **Telegram Bot**: `http://telegram-bot:8080/health`
|
||||
- **AnonBot**: `http://anon-bot:8081/health`
|
||||
- **Prometheus**: `http://prometheus:9090/-/healthy`
|
||||
- **Grafana**: `http://grafana:3000/api/health`
|
||||
- **AlertManager**: `http://alertmanager:9093/-/healthy`
|
||||
- **Nginx**: `http://nginx:80/nginx-health`
|
||||
|
||||
### Уведомления
|
||||
|
||||
Настройте уведомления в веб-интерфейсе:
|
||||
- Telegram Bot
|
||||
- Email
|
||||
- Webhook
|
||||
- Discord
|
||||
- Slack
|
||||
|
||||
## Файлы конфигурации
|
||||
|
||||
- `monitors.json` - экспорт настроенных мониторов
|
||||
- `settings.json` - настройки приложения
|
||||
- `backup/` - резервные копии конфигурации
|
||||
|
||||
## Команды управления
|
||||
|
||||
```bash
|
||||
# Показать логи
|
||||
make logs-uptime-kuma
|
||||
|
||||
# Перезапустить
|
||||
make restart-uptime-kuma
|
||||
|
||||
# Проверить статус
|
||||
make status
|
||||
```
|
||||
|
||||
## Резервное копирование
|
||||
|
||||
Конфигурация сохраняется в Docker volume `uptime_kuma_data`.
|
||||
Для резервного копирования:
|
||||
|
||||
```bash
|
||||
# Создать backup
|
||||
make backup
|
||||
|
||||
# Восстановить
|
||||
make restore FILE=backup.tar.gz
|
||||
```
|
||||
|
||||
|
||||
36
infra/uptime-kuma/backup/README.md
Normal file
36
infra/uptime-kuma/backup/README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
# Uptime Kuma Backup
|
||||
|
||||
Эта директория содержит резервные копии конфигурации Uptime Kuma.
|
||||
|
||||
## Автоматическое резервное копирование
|
||||
|
||||
Создайте скрипт для автоматического бэкапа:
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# backup-uptime-kuma.sh
|
||||
|
||||
DATE=$(date +%Y%m%d-%H%M%S)
|
||||
BACKUP_DIR="/path/to/backups"
|
||||
CONTAINER_NAME="bots_uptime_kuma"
|
||||
|
||||
# Создать backup
|
||||
docker exec $CONTAINER_NAME tar -czf /tmp/uptime-kuma-backup-$DATE.tar.gz /app/data
|
||||
|
||||
# Скопировать backup на хост
|
||||
docker cp $CONTAINER_NAME:/tmp/uptime-kuma-backup-$DATE.tar.gz $BACKUP_DIR/
|
||||
|
||||
# Очистить временные файлы
|
||||
docker exec $CONTAINER_NAME rm /tmp/uptime-kuma-backup-$DATE.tar.gz
|
||||
|
||||
echo "Backup created: $BACKUP_DIR/uptime-kuma-backup-$DATE.tar.gz"
|
||||
```
|
||||
|
||||
## Восстановление
|
||||
|
||||
```bash
|
||||
# Восстановить из backup
|
||||
docker cp backup-file.tar.gz $CONTAINER_NAME:/tmp/
|
||||
docker exec $CONTAINER_NAME tar -xzf /tmp/backup-file.tar.gz -C /
|
||||
docker restart $CONTAINER_NAME
|
||||
```
|
||||
147
infra/uptime-kuma/monitors.json
Normal file
147
infra/uptime-kuma/monitors.json
Normal file
@@ -0,0 +1,147 @@
|
||||
{
|
||||
"monitors": [
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Telegram Bot Health",
|
||||
"url": "http://telegram-bot:8080/health",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["bot", "telegram", "health"],
|
||||
"description": "Мониторинг состояния Telegram Helper Bot",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "AnonBot Health",
|
||||
"url": "http://anon-bot:8081/health",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["bot", "anon", "health"],
|
||||
"description": "Мониторинг состояния AnonBot",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"name": "Prometheus Health",
|
||||
"url": "http://prometheus:9090/-/healthy",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["monitoring", "prometheus", "health"],
|
||||
"description": "Мониторинг состояния Prometheus",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"name": "Grafana Health",
|
||||
"url": "http://grafana:3000/api/health",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["monitoring", "grafana", "health"],
|
||||
"description": "Мониторинг состояния Grafana",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"name": "AlertManager Health",
|
||||
"url": "http://alertmanager:9093/-/healthy",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["monitoring", "alertmanager", "health"],
|
||||
"description": "Мониторинг состояния AlertManager",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"name": "Nginx Health",
|
||||
"url": "http://nginx:80/nginx-health",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 60,
|
||||
"retries": 3,
|
||||
"timeout": 10,
|
||||
"keyword": "healthy",
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["infrastructure", "nginx", "health"],
|
||||
"description": "Мониторинг состояния Nginx",
|
||||
"active": true
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"name": "External Bot Status",
|
||||
"url": "https://your-domain/status/",
|
||||
"type": "http",
|
||||
"method": "GET",
|
||||
"interval": 300,
|
||||
"retries": 2,
|
||||
"timeout": 15,
|
||||
"keyword": null,
|
||||
"maxredirects": 10,
|
||||
"ignoreTls": false,
|
||||
"upsideDown": false,
|
||||
"tags": ["external", "status-page"],
|
||||
"description": "Мониторинг внешней доступности статусной страницы",
|
||||
"active": false
|
||||
}
|
||||
],
|
||||
"tags": [
|
||||
{
|
||||
"name": "bot",
|
||||
"color": "#3498db"
|
||||
},
|
||||
{
|
||||
"name": "monitoring",
|
||||
"color": "#e74c3c"
|
||||
},
|
||||
{
|
||||
"name": "infrastructure",
|
||||
"color": "#f39c12"
|
||||
},
|
||||
{
|
||||
"name": "health",
|
||||
"color": "#27ae60"
|
||||
},
|
||||
{
|
||||
"name": "external",
|
||||
"color": "#9b59b6"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
24
infra/uptime-kuma/settings.json
Normal file
24
infra/uptime-kuma/settings.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"language": "ru",
|
||||
"theme": "light",
|
||||
"timezone": "Europe/Moscow",
|
||||
"dateLocale": "ru",
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"timeFormat": "24",
|
||||
"weekStart": 1,
|
||||
"searchEngineIndex": true,
|
||||
"primaryBaseURL": "https://your-domain/status/",
|
||||
"public": true,
|
||||
"publicGroupList": true,
|
||||
"showTags": true,
|
||||
"showPoweredBy": false,
|
||||
"keepDataPeriodDays": 365,
|
||||
"retentionCheckInterval": 3600,
|
||||
"maxmindLicenseKey": "",
|
||||
"dnsCache": true,
|
||||
"dnsCacheTtl": 300,
|
||||
"trustProxy": true,
|
||||
"disableAuth": false,
|
||||
"defaultTimezone": "Europe/Moscow",
|
||||
"defaultLanguage": "ru"
|
||||
}
|
||||
109
scripts/deploy-from-github.sh
Executable file
109
scripts/deploy-from-github.sh
Executable file
@@ -0,0 +1,109 @@
|
||||
#!/bin/bash
|
||||
# Скрипт для деплоя из GitHub Actions
|
||||
# Используется на сервере для безопасного обновления
|
||||
|
||||
set -e
|
||||
|
||||
PROJECT_DIR="/home/prod"
|
||||
BACKUP_DIR="/home/prod/backups"
|
||||
LOG_FILE="/home/prod/logs/deploy.log"
|
||||
|
||||
# Создаем директории если их нет
|
||||
mkdir -p "$BACKUP_DIR"
|
||||
mkdir -p "$(dirname "$LOG_FILE")"
|
||||
|
||||
# Функция логирования
|
||||
log() {
|
||||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE"
|
||||
}
|
||||
|
||||
log "🚀 Starting deployment..."
|
||||
|
||||
# Переходим в директорию проекта
|
||||
cd "$PROJECT_DIR" || exit 1
|
||||
|
||||
# Сохраняем текущий коммит
|
||||
CURRENT_COMMIT=$(git rev-parse HEAD)
|
||||
log "Current commit: $CURRENT_COMMIT"
|
||||
|
||||
# Создаем backup конфигурации перед обновлением
|
||||
log "💾 Creating backup..."
|
||||
BACKUP_FILE="$BACKUP_DIR/backup-$(date +%Y%m%d-%H%M%S).tar.gz"
|
||||
tar -czf "$BACKUP_FILE" \
|
||||
infra/prometheus/prometheus.yml \
|
||||
infra/grafana/provisioning/ \
|
||||
docker-compose.yml \
|
||||
2>/dev/null || true
|
||||
log "Backup created: $BACKUP_FILE"
|
||||
|
||||
# Обновляем код
|
||||
log "📥 Pulling latest changes..."
|
||||
git fetch origin main
|
||||
git reset --hard origin/main
|
||||
|
||||
# Проверяем изменения
|
||||
NEW_COMMIT=$(git rev-parse HEAD)
|
||||
if [ "$CURRENT_COMMIT" = "$NEW_COMMIT" ]; then
|
||||
log "ℹ️ No new changes to deploy"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
log "✅ Code updated: $CURRENT_COMMIT → $NEW_COMMIT"
|
||||
|
||||
# Проверяем синтаксис docker-compose
|
||||
log "🔍 Validating docker-compose.yml..."
|
||||
if ! docker-compose config > /dev/null 2>&1; then
|
||||
log "❌ docker-compose.yml validation failed!"
|
||||
log "🔄 Rolling back..."
|
||||
git reset --hard "$CURRENT_COMMIT"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Перезапускаем сервисы
|
||||
log "🔄 Restarting services..."
|
||||
if command -v make &> /dev/null; then
|
||||
make restart
|
||||
else
|
||||
docker-compose down
|
||||
docker-compose up -d --build
|
||||
fi
|
||||
|
||||
# Ждем запуска сервисов
|
||||
log "⏳ Waiting for services to start..."
|
||||
sleep 20
|
||||
|
||||
# Health checks
|
||||
log "🏥 Running health checks..."
|
||||
|
||||
HEALTH_CHECK_FAILED=0
|
||||
|
||||
# Prometheus
|
||||
if curl -f http://localhost:9090/-/healthy > /dev/null 2>&1; then
|
||||
log "✅ Prometheus is healthy"
|
||||
else
|
||||
log "❌ Prometheus health check failed"
|
||||
HEALTH_CHECK_FAILED=1
|
||||
fi
|
||||
|
||||
# Grafana
|
||||
if curl -f http://localhost:3000/api/health > /dev/null 2>&1; then
|
||||
log "✅ Grafana is healthy"
|
||||
else
|
||||
log "❌ Grafana health check failed"
|
||||
HEALTH_CHECK_FAILED=1
|
||||
fi
|
||||
|
||||
# Если health check не прошел, откатываемся
|
||||
if [ $HEALTH_CHECK_FAILED -eq 1 ]; then
|
||||
log "❌ Health checks failed! Rolling back..."
|
||||
git reset --hard "$CURRENT_COMMIT"
|
||||
make restart || docker-compose restart
|
||||
log "🔄 Rollback completed"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "✅ Deployment completed successfully!"
|
||||
log "📊 Container status:"
|
||||
docker-compose ps || docker ps --filter "name=bots_"
|
||||
|
||||
exit 0
|
||||
31
scripts/generate_auth_passwords.sh
Executable file
31
scripts/generate_auth_passwords.sh
Executable file
@@ -0,0 +1,31 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Script to generate HTTP Basic Auth passwords for monitoring services
|
||||
# Usage: ./generate_auth_passwords.sh [username]
|
||||
|
||||
set -e
|
||||
|
||||
# Default username if not provided
|
||||
USERNAME=${1:-"admin"}
|
||||
|
||||
# Create passwords directory if it doesn't exist
|
||||
PASSWORDS_DIR="/etc/nginx/passwords"
|
||||
mkdir -p "$PASSWORDS_DIR"
|
||||
|
||||
# Generate random password
|
||||
PASSWORD=$(openssl rand -base64 32 | tr -d "=+/" | cut -c1-25)
|
||||
|
||||
# Create htpasswd file
|
||||
echo "Creating password file for user: $USERNAME"
|
||||
htpasswd -cb "$PASSWORDS_DIR/monitoring.htpasswd" "$USERNAME" "$PASSWORD"
|
||||
|
||||
# Set proper permissions
|
||||
chown root:www-data "$PASSWORDS_DIR/monitoring.htpasswd"
|
||||
chmod 640 "$PASSWORDS_DIR/monitoring.htpasswd"
|
||||
|
||||
echo "Password file created: $PASSWORDS_DIR/monitoring.htpasswd"
|
||||
echo "Username: $USERNAME"
|
||||
echo "Password: $PASSWORD"
|
||||
echo ""
|
||||
echo "Save this password securely!"
|
||||
echo "You can add more users with: htpasswd $PASSWORDS_DIR/monitoring.htpasswd <username>"
|
||||
163
scripts/setup-ssl.sh
Executable file
163
scripts/setup-ssl.sh
Executable file
@@ -0,0 +1,163 @@
|
||||
#!/bin/bash
|
||||
|
||||
# SSL Setup Script for Let's Encrypt
|
||||
# This script sets up SSL certificates using Let's Encrypt
|
||||
|
||||
set -e
|
||||
|
||||
# Configuration
|
||||
DOMAIN="${DOMAIN:-localhost}"
|
||||
EMAIL="${EMAIL:-admin@${DOMAIN}}"
|
||||
NGINX_CONTAINER="bots_nginx"
|
||||
CERTBOT_IMAGE="certbot/certbot:latest"
|
||||
|
||||
# Colors for output
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m' # No Color
|
||||
|
||||
# Logging function
|
||||
log() {
|
||||
echo -e "${GREEN}[$(date +'%Y-%m-%d %H:%M:%S')] $1${NC}"
|
||||
}
|
||||
|
||||
warn() {
|
||||
echo -e "${YELLOW}[$(date +'%Y-%m-%d %H:%M:%S')] WARNING: $1${NC}"
|
||||
}
|
||||
|
||||
error() {
|
||||
echo -e "${RED}[$(date +'%Y-%m-%d %H:%M:%S')] ERROR: $1${NC}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Check if running as root
|
||||
if [[ $EUID -eq 0 ]]; then
|
||||
error "This script should not be run as root for security reasons"
|
||||
fi
|
||||
|
||||
# Check if domain is localhost
|
||||
if [[ "$DOMAIN" == "localhost" ]]; then
|
||||
warn "Domain is set to localhost. Let's Encrypt certificates cannot be issued for localhost."
|
||||
warn "Please set the DOMAIN environment variable to your actual domain name."
|
||||
warn "Example: DOMAIN=example.com ./scripts/setup-ssl.sh"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check if Docker is running
|
||||
if ! docker info > /dev/null 2>&1; then
|
||||
error "Docker is not running. Please start Docker and try again."
|
||||
fi
|
||||
|
||||
# Check if nginx container is running
|
||||
if ! docker ps | grep -q "$NGINX_CONTAINER"; then
|
||||
error "Nginx container ($NGINX_CONTAINER) is not running. Please start it first with 'docker-compose up -d nginx'"
|
||||
fi
|
||||
|
||||
log "Setting up SSL certificates for domain: $DOMAIN"
|
||||
log "Email for Let's Encrypt: $EMAIL"
|
||||
|
||||
# Create necessary directories
|
||||
log "Creating Let's Encrypt directories..."
|
||||
sudo mkdir -p /etc/letsencrypt/live
|
||||
sudo mkdir -p /etc/letsencrypt/archive
|
||||
sudo mkdir -p /etc/letsencrypt/renewal
|
||||
sudo chmod 755 /etc/letsencrypt
|
||||
|
||||
# Stop nginx temporarily for certificate generation
|
||||
log "Stopping nginx container for certificate generation..."
|
||||
docker stop "$NGINX_CONTAINER" || true
|
||||
|
||||
# Generate certificate using certbot
|
||||
log "Generating SSL certificate using Let's Encrypt..."
|
||||
docker run --rm \
|
||||
-v /etc/letsencrypt:/etc/letsencrypt \
|
||||
-v /var/lib/letsencrypt:/var/lib/letsencrypt \
|
||||
-p 80:80 \
|
||||
-p 443:443 \
|
||||
"$CERTBOT_IMAGE" certonly \
|
||||
--standalone \
|
||||
--non-interactive \
|
||||
--agree-tos \
|
||||
--email "$EMAIL" \
|
||||
--domains "$DOMAIN" \
|
||||
--expand
|
||||
|
||||
# Check if certificate was generated successfully
|
||||
if [[ ! -f "/etc/letsencrypt/live/$DOMAIN/fullchain.pem" ]]; then
|
||||
error "Failed to generate SSL certificate for $DOMAIN"
|
||||
fi
|
||||
|
||||
log "SSL certificate generated successfully!"
|
||||
|
||||
# Set proper permissions
|
||||
log "Setting proper permissions for SSL certificates..."
|
||||
sudo chmod 755 /etc/letsencrypt/live
|
||||
sudo chmod 755 /etc/letsencrypt/archive
|
||||
sudo chmod 644 /etc/letsencrypt/live/"$DOMAIN"/*.pem
|
||||
sudo chmod 600 /etc/letsencrypt/live/"$DOMAIN"/privkey.pem
|
||||
|
||||
# Update nginx configuration to use Let's Encrypt certificates
|
||||
log "Updating nginx configuration..."
|
||||
if [[ -f "infra/nginx/ssl/letsencrypt.conf" ]]; then
|
||||
# Replace domain placeholder in letsencrypt.conf
|
||||
sed "s/{{DOMAIN}}/$DOMAIN/g" infra/nginx/ssl/letsencrypt.conf > /tmp/letsencrypt.conf
|
||||
sudo cp /tmp/letsencrypt.conf /etc/letsencrypt/live/"$DOMAIN"/letsencrypt.conf
|
||||
rm /tmp/letsencrypt.conf
|
||||
fi
|
||||
|
||||
# Start nginx container
|
||||
log "Starting nginx container..."
|
||||
docker start "$NGINX_CONTAINER"
|
||||
|
||||
# Wait for nginx to start
|
||||
log "Waiting for nginx to start..."
|
||||
sleep 10
|
||||
|
||||
# Test SSL certificate
|
||||
log "Testing SSL certificate..."
|
||||
if curl -k -s "https://$DOMAIN" > /dev/null; then
|
||||
log "SSL certificate is working correctly!"
|
||||
else
|
||||
warn "SSL certificate test failed. Please check nginx configuration."
|
||||
fi
|
||||
|
||||
# Set up automatic renewal
|
||||
log "Setting up automatic certificate renewal..."
|
||||
cat > /tmp/ssl-renewal.sh << EOF
|
||||
#!/bin/bash
|
||||
# SSL Certificate Renewal Script
|
||||
|
||||
set -e
|
||||
|
||||
DOMAIN="$DOMAIN"
|
||||
NGINX_CONTAINER="$NGINX_CONTAINER"
|
||||
CERTBOT_IMAGE="$CERTBOT_IMAGE"
|
||||
|
||||
# Renew certificates
|
||||
docker run --rm \\
|
||||
-v /etc/letsencrypt:/etc/letsencrypt \\
|
||||
-v /var/lib/letsencrypt:/var/lib/letsencrypt \\
|
||||
"$CERTBOT_IMAGE" renew --quiet
|
||||
|
||||
# Reload nginx
|
||||
docker exec "\$NGINX_CONTAINER" nginx -s reload
|
||||
|
||||
echo "\$(date): SSL certificates renewed successfully" >> /var/log/ssl-renewal.log
|
||||
EOF
|
||||
|
||||
sudo mv /tmp/ssl-renewal.sh /usr/local/bin/ssl-renewal.sh
|
||||
sudo chmod +x /usr/local/bin/ssl-renewal.sh
|
||||
|
||||
# Add cron job for automatic renewal (every Monday at 2 AM)
|
||||
log "Adding cron job for automatic renewal..."
|
||||
(crontab -l 2>/dev/null; echo "0 2 * * 1 /usr/local/bin/ssl-renewal.sh") | crontab -
|
||||
|
||||
log "SSL setup completed successfully!"
|
||||
log "Certificate location: /etc/letsencrypt/live/$DOMAIN/"
|
||||
log "Automatic renewal is configured to run every Monday at 2 AM"
|
||||
log "You can test the renewal manually with: sudo /usr/local/bin/ssl-renewal.sh"
|
||||
|
||||
# Display certificate information
|
||||
log "Certificate information:"
|
||||
openssl x509 -in "/etc/letsencrypt/live/$DOMAIN/fullchain.pem" -text -noout | grep -E "(Subject:|Not Before|Not After|DNS:)"
|
||||
@@ -3,12 +3,12 @@
|
||||
Тесты для конфигурации Prometheus
|
||||
"""
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
import sys
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
|
||||
|
||||
class TestPrometheusConfig:
|
||||
@@ -17,7 +17,12 @@ class TestPrometheusConfig:
|
||||
@pytest.fixture
|
||||
def prometheus_config_path(self):
|
||||
"""Путь к файлу конфигурации Prometheus"""
|
||||
return Path(__file__).parent.parent.parent / 'infra' / 'prometheus' / 'prometheus.yml'
|
||||
return (
|
||||
Path(__file__).parent.parent.parent
|
||||
/ "infra"
|
||||
/ "prometheus"
|
||||
/ "prometheus.yml"
|
||||
)
|
||||
|
||||
@pytest.fixture
|
||||
def prometheus_config(self, prometheus_config_path):
|
||||
@@ -25,100 +30,117 @@ class TestPrometheusConfig:
|
||||
if not prometheus_config_path.exists():
|
||||
pytest.skip(f"Prometheus config file not found: {prometheus_config_path}")
|
||||
|
||||
with open(prometheus_config_path, 'r', encoding='utf-8') as f:
|
||||
with open(prometheus_config_path, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f)
|
||||
|
||||
def test_config_file_exists(self, prometheus_config_path):
|
||||
"""Тест существования файла конфигурации"""
|
||||
assert prometheus_config_path.exists(), f"Prometheus config file not found: {prometheus_config_path}"
|
||||
assert (
|
||||
prometheus_config_path.exists()
|
||||
), f"Prometheus config file not found: {prometheus_config_path}"
|
||||
|
||||
def test_config_is_valid_yaml(self, prometheus_config):
|
||||
"""Тест валидности YAML конфигурации"""
|
||||
assert isinstance(prometheus_config, dict), "Config should be a valid YAML dictionary"
|
||||
assert isinstance(
|
||||
prometheus_config, dict
|
||||
), "Config should be a valid YAML dictionary"
|
||||
|
||||
def test_global_section(self, prometheus_config):
|
||||
"""Тест глобальной секции конфигурации"""
|
||||
assert 'global' in prometheus_config, "Config should have global section"
|
||||
assert "global" in prometheus_config, "Config should have global section"
|
||||
|
||||
global_config = prometheus_config['global']
|
||||
assert 'scrape_interval' in global_config, "Global section should have scrape_interval"
|
||||
assert 'evaluation_interval' in global_config, "Global section should have evaluation_interval"
|
||||
global_config = prometheus_config["global"]
|
||||
assert (
|
||||
"scrape_interval" in global_config
|
||||
), "Global section should have scrape_interval"
|
||||
assert (
|
||||
"evaluation_interval" in global_config
|
||||
), "Global section should have evaluation_interval"
|
||||
|
||||
# Проверяем значения интервалов
|
||||
assert global_config['scrape_interval'] == '15s', "Default scrape_interval should be 15s"
|
||||
assert global_config['evaluation_interval'] == '15s', "Default evaluation_interval should be 15s"
|
||||
assert (
|
||||
global_config["scrape_interval"] == "15s"
|
||||
), "Default scrape_interval should be 15s"
|
||||
assert (
|
||||
global_config["evaluation_interval"] == "15s"
|
||||
), "Default evaluation_interval should be 15s"
|
||||
|
||||
def test_scrape_configs_section(self, prometheus_config):
|
||||
"""Тест секции scrape_configs"""
|
||||
assert 'scrape_configs' in prometheus_config, "Config should have scrape_configs section"
|
||||
assert (
|
||||
"scrape_configs" in prometheus_config
|
||||
), "Config should have scrape_configs section"
|
||||
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
assert isinstance(scrape_configs, list), "scrape_configs should be a list"
|
||||
assert len(scrape_configs) >= 1, "Should have at least one scrape config"
|
||||
|
||||
def test_prometheus_job(self, prometheus_config):
|
||||
"""Тест job для самого Prometheus"""
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
# Ищем job для prometheus
|
||||
prometheus_job = None
|
||||
for job in scrape_configs:
|
||||
if job.get('job_name') == 'prometheus':
|
||||
if job.get("job_name") == "prometheus":
|
||||
prometheus_job = job
|
||||
break
|
||||
|
||||
assert prometheus_job is not None, "Should have prometheus job"
|
||||
assert 'static_configs' in prometheus_job, "Prometheus job should have static_configs"
|
||||
assert (
|
||||
"static_configs" in prometheus_job
|
||||
), "Prometheus job should have static_configs"
|
||||
|
||||
static_configs = prometheus_job['static_configs']
|
||||
static_configs = prometheus_job["static_configs"]
|
||||
assert isinstance(static_configs, list), "static_configs should be a list"
|
||||
assert len(static_configs) > 0, "Should have at least one static config"
|
||||
|
||||
# Проверяем targets
|
||||
targets = static_configs[0].get('targets', [])
|
||||
assert 'localhost:9090' in targets, "Prometheus should scrape localhost:9090"
|
||||
|
||||
targets = static_configs[0].get("targets", [])
|
||||
assert "localhost:9090" in targets, "Prometheus should scrape localhost:9090"
|
||||
|
||||
def test_telegram_bot_job(self, prometheus_config):
|
||||
"""Тест job для telegram-helper-bot"""
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
# Ищем job для telegram-helper-bot
|
||||
bot_job = None
|
||||
for job in scrape_configs:
|
||||
if job.get('job_name') == 'telegram-helper-bot':
|
||||
if job.get("job_name") == "telegram-helper-bot":
|
||||
bot_job = job
|
||||
break
|
||||
|
||||
assert bot_job is not None, "Should have telegram-helper-bot job"
|
||||
|
||||
# Проверяем основные параметры
|
||||
assert 'static_configs' in bot_job, "Bot job should have static_configs"
|
||||
assert 'metrics_path' in bot_job, "Bot job should have metrics_path"
|
||||
assert 'scrape_interval' in bot_job, "Bot job should have scrape_interval"
|
||||
assert 'scrape_timeout' in bot_job, "Bot job should have scrape_timeout"
|
||||
assert 'honor_labels' in bot_job, "Bot job should have honor_labels"
|
||||
assert "static_configs" in bot_job, "Bot job should have static_configs"
|
||||
assert "metrics_path" in bot_job, "Bot job should have metrics_path"
|
||||
assert "scrape_interval" in bot_job, "Bot job should have scrape_interval"
|
||||
assert "scrape_timeout" in bot_job, "Bot job should have scrape_timeout"
|
||||
assert "honor_labels" in bot_job, "Bot job should have honor_labels"
|
||||
|
||||
# Проверяем значения
|
||||
assert bot_job['metrics_path'] == '/metrics', "Metrics path should be /metrics"
|
||||
assert bot_job['scrape_interval'] == '15s', "Scrape interval should be 15s"
|
||||
assert bot_job['scrape_timeout'] == '10s', "Scrape timeout should be 10s"
|
||||
assert bot_job['honor_labels'] is True, "honor_labels should be True"
|
||||
assert bot_job["metrics_path"] == "/metrics", "Metrics path should be /metrics"
|
||||
assert bot_job["scrape_interval"] == "15s", "Scrape interval should be 15s"
|
||||
assert bot_job["scrape_timeout"] == "10s", "Scrape timeout should be 10s"
|
||||
assert bot_job["honor_labels"] is True, "honor_labels should be True"
|
||||
|
||||
# Проверяем static_configs
|
||||
static_configs = bot_job['static_configs']
|
||||
static_configs = bot_job["static_configs"]
|
||||
assert len(static_configs) > 0, "Should have at least one static config"
|
||||
|
||||
# Проверяем targets
|
||||
targets = static_configs[0].get('targets', [])
|
||||
assert 'bots_telegram_bot:8080' in targets, "Should scrape bots_telegram_bot:8080"
|
||||
targets = static_configs[0].get("targets", [])
|
||||
assert (
|
||||
"bots_telegram_bot:8080" in targets
|
||||
), "Should scrape bots_telegram_bot:8080"
|
||||
|
||||
# Проверяем labels
|
||||
labels = static_configs[0].get('labels', {})
|
||||
labels = static_configs[0].get("labels", {})
|
||||
expected_labels = {
|
||||
'bot_name': 'telegram-helper-bot',
|
||||
'environment': 'production',
|
||||
'service': 'telegram-bot'
|
||||
"bot_name": "telegram-helper-bot",
|
||||
"environment": "production",
|
||||
"service": "telegram-bot",
|
||||
}
|
||||
|
||||
for key, value in expected_labels.items():
|
||||
@@ -127,106 +149,144 @@ class TestPrometheusConfig:
|
||||
|
||||
def test_alerting_section(self, prometheus_config):
|
||||
"""Тест секции alerting"""
|
||||
assert 'alerting' in prometheus_config, "Config should have alerting section"
|
||||
assert "alerting" in prometheus_config, "Config should have alerting section"
|
||||
|
||||
alerting_config = prometheus_config['alerting']
|
||||
assert 'alertmanagers' in alerting_config, "Alerting section should have alertmanagers"
|
||||
alerting_config = prometheus_config["alerting"]
|
||||
assert (
|
||||
"alertmanagers" in alerting_config
|
||||
), "Alerting section should have alertmanagers"
|
||||
|
||||
alertmanagers = alerting_config['alertmanagers']
|
||||
alertmanagers = alerting_config["alertmanagers"]
|
||||
assert isinstance(alertmanagers, list), "alertmanagers should be a list"
|
||||
|
||||
# Проверяем, что alertmanager закомментирован (не активен)
|
||||
# Это нормально для тестовой среды
|
||||
# Проверяем, что alertmanager настроен правильно
|
||||
if len(alertmanagers) > 0:
|
||||
for am in alertmanagers:
|
||||
if 'static_configs' in am:
|
||||
static_configs = am['static_configs']
|
||||
if "static_configs" in am:
|
||||
static_configs = am["static_configs"]
|
||||
assert isinstance(
|
||||
static_configs, list
|
||||
), "static_configs should be a list"
|
||||
for sc in static_configs:
|
||||
if 'targets' in sc:
|
||||
targets = sc['targets']
|
||||
if "targets" in sc:
|
||||
targets = sc["targets"]
|
||||
# targets может быть None если все строки закомментированы
|
||||
if targets is not None:
|
||||
# Проверяем, что все targets закомментированы
|
||||
assert isinstance(
|
||||
targets, list
|
||||
), "targets should be a list"
|
||||
# Проверяем, что targets не пустые и имеют правильный формат
|
||||
for target in targets:
|
||||
assert target.startswith('#'), f"Alertmanager target should be commented: {target}"
|
||||
assert isinstance(
|
||||
target, str
|
||||
), f"Target should be a string: {target}"
|
||||
# Если target не закомментирован, проверяем формат
|
||||
if not target.startswith("#"):
|
||||
assert (
|
||||
":" in target
|
||||
), f"Target should have port: {target}"
|
||||
|
||||
def test_rule_files_section(self, prometheus_config):
|
||||
"""Тест секции rule_files"""
|
||||
assert 'rule_files' in prometheus_config, "Config should have rule_files section"
|
||||
assert (
|
||||
"rule_files" in prometheus_config
|
||||
), "Config should have rule_files section"
|
||||
|
||||
rule_files = prometheus_config['rule_files']
|
||||
rule_files = prometheus_config["rule_files"]
|
||||
# rule_files может быть None если все строки закомментированы
|
||||
if rule_files is not None:
|
||||
assert isinstance(rule_files, list), "rule_files should be a list"
|
||||
|
||||
# Проверяем, что все rule files закомментированы
|
||||
# Проверяем, что rule files имеют правильный формат
|
||||
for rule_file in rule_files:
|
||||
assert rule_file.startswith('#'), f"Rule file should be commented: {rule_file}"
|
||||
assert isinstance(
|
||||
rule_file, str
|
||||
), f"Rule file should be a string: {rule_file}"
|
||||
# Если rule file не закомментирован, проверяем, что это валидный путь
|
||||
if not rule_file.startswith("#"):
|
||||
assert rule_file.endswith(".yml") or rule_file.endswith(
|
||||
".yaml"
|
||||
), f"Rule file should have .yml or .yaml extension: {rule_file}"
|
||||
|
||||
def test_config_structure_consistency(self, prometheus_config):
|
||||
"""Тест консистентности структуры конфигурации"""
|
||||
# Проверяем, что все job'ы имеют одинаковую структуру
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
required_fields = ['job_name', 'static_configs']
|
||||
optional_fields = ['metrics_path', 'scrape_interval', 'scrape_timeout', 'honor_labels']
|
||||
required_fields = ["job_name", "static_configs"]
|
||||
optional_fields = [
|
||||
"metrics_path",
|
||||
"scrape_interval",
|
||||
"scrape_timeout",
|
||||
"honor_labels",
|
||||
]
|
||||
|
||||
for job in scrape_configs:
|
||||
# Проверяем обязательные поля
|
||||
for field in required_fields:
|
||||
assert field in job, f"Job {job.get('job_name', 'unknown')} missing required field: {field}"
|
||||
assert (
|
||||
field in job
|
||||
), f"Job {job.get('job_name', 'unknown')} missing required field: {field}"
|
||||
|
||||
# Проверяем, что static_configs содержит targets
|
||||
static_configs = job['static_configs']
|
||||
assert isinstance(static_configs, list), f"Job {job.get('job_name', 'unknown')} static_configs should be list"
|
||||
static_configs = job["static_configs"]
|
||||
assert isinstance(
|
||||
static_configs, list
|
||||
), f"Job {job.get('job_name', 'unknown')} static_configs should be list"
|
||||
|
||||
for static_config in static_configs:
|
||||
assert 'targets' in static_config, f"Static config should have targets"
|
||||
targets = static_config['targets']
|
||||
assert "targets" in static_config, f"Static config should have targets"
|
||||
targets = static_config["targets"]
|
||||
assert isinstance(targets, list), "Targets should be a list"
|
||||
assert len(targets) > 0, "Targets should not be empty"
|
||||
|
||||
def test_port_configurations(self, prometheus_config):
|
||||
"""Тест конфигурации портов"""
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
# Проверяем, что порты корректно настроены
|
||||
for job in scrape_configs:
|
||||
static_configs = job['static_configs']
|
||||
static_configs = job["static_configs"]
|
||||
for static_config in static_configs:
|
||||
targets = static_config['targets']
|
||||
targets = static_config["targets"]
|
||||
for target in targets:
|
||||
if ':' in target:
|
||||
host, port = target.split(':', 1)
|
||||
if ":" in target:
|
||||
host, port = target.split(":", 1)
|
||||
# Проверяем, что порт это число
|
||||
try:
|
||||
port_num = int(port)
|
||||
assert 1 <= port_num <= 65535, f"Port {port_num} out of range"
|
||||
assert (
|
||||
1 <= port_num <= 65535
|
||||
), f"Port {port_num} out of range"
|
||||
except ValueError:
|
||||
# Это может быть Docker service name без порта
|
||||
pass
|
||||
|
||||
def test_environment_labels(self, prometheus_config):
|
||||
"""Тест labels окружения"""
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
# Проверяем, что production окружение правильно помечено
|
||||
for job in scrape_configs:
|
||||
if job.get('job_name') == 'telegram-helper-bot':
|
||||
static_configs = job['static_configs']
|
||||
if job.get("job_name") == "telegram-helper-bot":
|
||||
static_configs = job["static_configs"]
|
||||
for static_config in static_configs:
|
||||
labels = static_config.get('labels', {})
|
||||
if 'environment' in labels:
|
||||
assert labels['environment'] == 'production', "Environment should be production"
|
||||
labels = static_config.get("labels", {})
|
||||
if "environment" in labels:
|
||||
assert (
|
||||
labels["environment"] == "production"
|
||||
), "Environment should be production"
|
||||
|
||||
def test_metrics_path_consistency(self, prometheus_config):
|
||||
"""Тест консистентности paths для метрик"""
|
||||
scrape_configs = prometheus_config['scrape_configs']
|
||||
scrape_configs = prometheus_config["scrape_configs"]
|
||||
|
||||
# Проверяем, что все job'ы используют /metrics
|
||||
for job in scrape_configs:
|
||||
if 'metrics_path' in job:
|
||||
assert job['metrics_path'] == '/metrics', f"Job {job.get('job_name', 'unknown')} should use /metrics path"
|
||||
if "metrics_path" in job:
|
||||
assert (
|
||||
job["metrics_path"] == "/metrics"
|
||||
), f"Job {job.get('job_name', 'unknown')} should use /metrics path"
|
||||
|
||||
|
||||
class TestPrometheusConfigValidation:
|
||||
@@ -236,73 +296,58 @@ class TestPrometheusConfigValidation:
|
||||
def sample_valid_config(self):
|
||||
"""Пример валидной конфигурации"""
|
||||
return {
|
||||
'global': {
|
||||
'scrape_interval': '15s',
|
||||
'evaluation_interval': '15s'
|
||||
},
|
||||
'scrape_configs': [
|
||||
"global": {"scrape_interval": "15s", "evaluation_interval": "15s"},
|
||||
"scrape_configs": [
|
||||
{
|
||||
'job_name': 'test',
|
||||
'static_configs': [
|
||||
{
|
||||
'targets': ['localhost:9090']
|
||||
}
|
||||
]
|
||||
"job_name": "test",
|
||||
"static_configs": [{"targets": ["localhost:9090"]}],
|
||||
}
|
||||
]
|
||||
],
|
||||
}
|
||||
|
||||
def test_minimal_valid_config(self, sample_valid_config):
|
||||
"""Тест минимальной валидной конфигурации"""
|
||||
# Проверяем, что конфигурация содержит все необходимые поля
|
||||
assert 'global' in sample_valid_config
|
||||
assert 'scrape_configs' in sample_valid_config
|
||||
assert "global" in sample_valid_config
|
||||
assert "scrape_configs" in sample_valid_config
|
||||
|
||||
global_config = sample_valid_config['global']
|
||||
assert 'scrape_interval' in global_config
|
||||
assert 'evaluation_interval' in global_config
|
||||
global_config = sample_valid_config["global"]
|
||||
assert "scrape_interval" in global_config
|
||||
assert "evaluation_interval" in global_config
|
||||
|
||||
scrape_configs = sample_valid_config['scrape_configs']
|
||||
scrape_configs = sample_valid_config["scrape_configs"]
|
||||
assert len(scrape_configs) > 0
|
||||
|
||||
for job in scrape_configs:
|
||||
assert 'job_name' in job
|
||||
assert 'static_configs' in job
|
||||
assert "job_name" in job
|
||||
assert "static_configs" in job
|
||||
|
||||
static_configs = job['static_configs']
|
||||
static_configs = job["static_configs"]
|
||||
assert len(static_configs) > 0
|
||||
|
||||
for static_config in static_configs:
|
||||
assert 'targets' in static_config
|
||||
targets = static_config['targets']
|
||||
assert "targets" in static_config
|
||||
targets = static_config["targets"]
|
||||
assert len(targets) > 0
|
||||
|
||||
def test_config_without_required_fields(self):
|
||||
"""Тест конфигурации без обязательных полей"""
|
||||
# Конфигурация без global секции
|
||||
config_without_global = {
|
||||
'scrape_configs': []
|
||||
}
|
||||
config_without_global = {"scrape_configs": []}
|
||||
|
||||
# Конфигурация без scrape_configs
|
||||
config_without_scrape = {
|
||||
'global': {
|
||||
'scrape_interval': '15s'
|
||||
}
|
||||
}
|
||||
config_without_scrape = {"global": {"scrape_interval": "15s"}}
|
||||
|
||||
# Конфигурация с пустыми scrape_configs
|
||||
config_empty_scrape = {
|
||||
'global': {
|
||||
'scrape_interval': '15s'
|
||||
},
|
||||
'scrape_configs': []
|
||||
"global": {"scrape_interval": "15s"},
|
||||
"scrape_configs": [],
|
||||
}
|
||||
|
||||
# Все эти конфигурации должны быть невалидными
|
||||
assert 'global' not in config_without_global
|
||||
assert 'scrape_configs' not in config_without_scrape
|
||||
assert len(config_empty_scrape['scrape_configs']) == 0
|
||||
assert "global" not in config_without_global
|
||||
assert "scrape_configs" not in config_without_scrape
|
||||
assert len(config_empty_scrape["scrape_configs"]) == 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -3,27 +3,35 @@
|
||||
Тест конфигурации pytest
|
||||
"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
def test_pytest_config_loaded():
|
||||
"""Проверяем, что конфигурация pytest загружена"""
|
||||
# Проверяем, что мы находимся в корневой директории проекта
|
||||
assert os.path.exists('pytest.ini'), "pytest.ini должен существовать в корне проекта"
|
||||
assert os.path.exists(
|
||||
"pytest.ini"
|
||||
), "pytest.ini должен существовать в корне проекта"
|
||||
|
||||
# Проверяем, что директория tests существует
|
||||
assert os.path.exists('tests'), "Директория tests должна существовать"
|
||||
assert os.path.exists('tests/infra'), "Директория tests/infra должна существовать"
|
||||
assert os.path.exists('tests/bot'), "Директория tests/bot должна существовать"
|
||||
assert os.path.exists("tests"), "Директория tests должна существовать"
|
||||
assert os.path.exists("tests/infra"), "Директория tests/infra должна существовать"
|
||||
assert os.path.exists("tests/bot"), "Директория tests/bot должна существовать"
|
||||
|
||||
|
||||
def test_test_structure():
|
||||
"""Проверяем структуру тестов"""
|
||||
# Проверяем наличие __init__.py файлов
|
||||
assert os.path.exists('tests/__init__.py'), "tests/__init__.py должен существовать"
|
||||
assert os.path.exists('tests/infra/__init__.py'), "tests/infra/__init__.py должен существовать"
|
||||
assert os.path.exists('tests/bot/__init__.py'), "tests/bot/__init__.py должен существовать"
|
||||
assert os.path.exists("tests/__init__.py"), "tests/__init__.py должен существовать"
|
||||
assert os.path.exists(
|
||||
"tests/infra/__init__.py"
|
||||
), "tests/infra/__init__.py должен существовать"
|
||||
assert os.path.exists(
|
||||
"tests/bot/__init__.py"
|
||||
), "tests/bot/__init__.py должен существовать"
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user