Add dedicated RAID alert category and monitor

CONFIG.en.md

@@ -33,7 +33,7 @@ This project uses `config.yaml`. Start from `config.example.yaml`.
   - `end` (string): End time `HH:MM` (e.g. `08:00`).
   - `allow_critical` (bool): Allow critical alerts during quiet hours.
 - `auto_mute` (list): Per-category auto mutes by time window.
-  - `category` (string): load/disk/smart/ssl/docker/test.
+  - `category` (string): load/disk/smart/raid/ssl/docker/test.
   - `start` (string): Start `HH:MM`.
   - `end` (string): End `HH:MM` (can wrap over midnight).
 - `auto_mute_on_high_load_sec` (int): auto-mute `load` category for N seconds on critical load (0 disables).
@@ -42,6 +42,9 @@ This project uses `config.yaml`. Start from `config.example.yaml`.
 - `smart_interval_sec` (int): SMART poll interval.
 - `smart_cooldown_sec` (int): SMART alert cooldown.
 - `smart_temp_warn` (int): SMART temperature warning (C).
+- `raid_enabled` (bool): Enable md RAID polling (`/proc/mdstat`).
+- `raid_interval_sec` (int): RAID poll interval.
+- `raid_cooldown_sec` (int): RAID alert cooldown.
 
 ## disk_report
 

CONFIG.md

@@ -33,7 +33,7 @@
   - `end` (string): конец, формат `HH:MM` (например `08:00`).
   - `allow_critical` (bool): слать критичные алерты в тишину.
 - `auto_mute` (list): авто‑мьюты по категориям и времени.
-  - `category` (string): load/disk/smart/ssl/docker/test.
+  - `category` (string): load/disk/smart/raid/ssl/docker/test.
   - `start` (string): начало `HH:MM`.
   - `end` (string): конец `HH:MM` (интервал может пересекать ночь).
 - `auto_mute_on_high_load_sec` (int): при critical load автоматически мьютить категорию `load` на N секунд (0 — выкл).
@@ -42,6 +42,9 @@
 - `smart_interval_sec` (int): интервал SMART.
 - `smart_cooldown_sec` (int): кулдаун SMART.
 - `smart_temp_warn` (int): порог температуры (C).
+- `raid_enabled` (bool): RAID проверки (`/proc/mdstat`).
+- `raid_interval_sec` (int): интервал RAID.
+- `raid_cooldown_sec` (int): кулдаун RAID алертов.
 
 ## disk_report
 

config.example.yaml

@@ -43,6 +43,9 @@ alerts:
   smart_interval_sec: 3600
   smart_cooldown_sec: 21600
   smart_temp_warn: 50
+  raid_enabled: true
+  raid_interval_sec: 300
+  raid_cooldown_sec: 1800
 
 disk_report:
   threshold: 90

handlers/alerts_admin.py

@@ -16,7 +16,7 @@ HELP_TEXT = (
     "/alerts unmute <category> - unmute category\n"
     "/alerts list - show active mutes\n"
     "/alerts recent [hours] - show incidents log (default 24h)\n"
-    "Categories: load, disk, smart, ssl, docker, test\n"
+    "Categories: load, disk, smart, raid, ssl, docker, test\n"
 )
 
 

handlers/help.py

@@ -24,7 +24,7 @@ HELP_PAGES = [
         "• `/alerts mute <cat> <minutes>` / `/alerts unmute <cat>` / `/alerts list`\n"
         "• `/alerts recent [hours]`\n"
         "Шорткаты: `/alerts_list`, `/alerts_recent`, `/alerts_mute_load` (60м).\n"
-        "Категории: load, disk, smart, ssl, docker, test.\n"
+        "Категории: load, disk, smart, raid, ssl, docker, test.\n"
         "Quiet hours: `alerts.quiet_hours` для не‑критичных.\n"
         "Авто-мьют: `alerts.auto_mute` со слотами времени.\n"
         "Только красные load: `alerts.load_only_critical: true`.\n"

main.py

@@ -5,7 +5,7 @@ from datetime import datetime
 from app import bot, dp, cfg, ADMIN_ID, ADMIN_IDS
 from keyboards import menu_kb
 from services.docker import discover_containers, docker_watchdog
-from services.alerts import monitor_resources, monitor_smart
+from services.alerts import monitor_resources, monitor_smart, monitor_raid
 from services.metrics import MetricsStore, start_sampler
 from services.queue import worker as queue_worker, configure as queue_configure
 from services.notify import notify
@@ -82,6 +82,8 @@ async def main():
         asyncio.create_task(monitor_resources(cfg, notify, bot, ADMIN_ID))
     if cfg.get("alerts", {}).get("smart_enabled", True):
         asyncio.create_task(monitor_smart(cfg, notify, bot, ADMIN_ID))
+    if cfg.get("alerts", {}).get("raid_enabled", True):
+        asyncio.create_task(monitor_raid(cfg, notify, bot, ADMIN_ID))
     if cfg.get("npmplus", {}).get("alerts", {}).get("enabled", True):
         asyncio.create_task(monitor_ssl(cfg, notify, bot, ADMIN_ID))
     if cfg.get("external_checks", {}).get("enabled", True):

services/alerts.py

@@ -1,7 +1,7 @@
 import asyncio
 import time
 import psutil
-from system_checks import list_disks, smart_health, disk_temperature
+from system_checks import list_disks, smart_health, disk_temperature, list_md_arrays, md_array_status
 from services.system import worst_disk_usage
 from services.disk_report import build_disk_report
 
@@ -130,3 +130,54 @@ async def monitor_smart(cfg, notify, bot, chat_id):
                     continue
 
         await asyncio.sleep(interval)
+
+
+async def monitor_raid(cfg, notify, bot, chat_id):
+    alerts_cfg = cfg.get("alerts", {})
+    interval = int(alerts_cfg.get("raid_interval_sec", 300))
+    cooldown = int(alerts_cfg.get("raid_cooldown_sec", 1800))
+    notify_recovery = bool(alerts_cfg.get("notify_recovery", True))
+
+    last_sent: dict[str, float] = {}
+    bad_state: dict[str, bool] = {}
+
+    while True:
+        now = time.time()
+        for dev in list_md_arrays():
+            status = md_array_status(dev)
+            lower = status.lower()
+            level = None
+            key_suffix = None
+            if "inactive" in lower:
+                level = "critical"
+                key_suffix = "inactive"
+            elif "degraded" in lower:
+                level = "warn"
+                key_suffix = "degraded"
+
+            if level:
+                if not bad_state.get(dev) or (now - last_sent.get(dev, 0.0) >= cooldown):
+                    icon = "🔴" if level == "critical" else "🟡"
+                    await notify(
+                        bot,
+                        chat_id,
+                        f"{icon} RAID {dev}: {status}",
+                        level=level,
+                        key=f"raid_{key_suffix}:{dev}",
+                        category="raid",
+                    )
+                    last_sent[dev] = now
+                bad_state[dev] = True
+            else:
+                if bad_state.get(dev) and notify_recovery:
+                    await notify(
+                        bot,
+                        chat_id,
+                        f"🟢 RAID {dev}: {status}",
+                        level="info",
+                        key=f"raid_ok:{dev}",
+                        category="raid",
+                    )
+                bad_state[dev] = False
+
+        await asyncio.sleep(interval)