42d1420f9c
[Phase 0 Reset]
- 清除舊版 app/、alembic/versions/、雜亂測試腳本
- 新 requirements.txt (移除 caldav/redis/keycloak-lib，加入 apscheduler/croniter/docker/paramiko/ping3/dnspython)
[Phase 1 資料庫]
- 9 張資料表 SQLAlchemy Models：tenants / accounts / schedules / schedule_logs /
tenant_schedule_results / account_schedule_results / servers / server_status_logs / system_status_logs
- Alembic migration 001_create_all_tables (已套用到 10.1.0.20:5433/virtual_mis)
- seed.py：schedules 初始 3 筆 / servers 初始 4 筆
[Phase 2 CRUD API]
- GET/POST/PUT/DELETE: /api/v1/tenants / accounts / servers / schedules
- /api/v1/system-status
- 帳號編碼自動產生 (prefix + seq_no 4碼左補0)
- 燈號 (lights) 從最新排程結果取得
[Phase 3 Watchdog]
- APScheduler interval 3分鐘，原子 UPDATE status=Going 防重複執行
- 手動觸發 API: POST /api/v1/schedules/{id}/run
[Phase 4 Service Clients]
- KeycloakClient：vmis-admin realm，REST API (不用 python-keycloak)
- MailClient：Docker Mailserver @ 10.1.0.254:8080，含 MX DNS 驗證
- DockerClient：docker-py 本機 + paramiko SSH 遠端 compose
- NextcloudClient：OCS API user/quota
- SystemChecker：功能驗證 (traefik routers>0 / keycloak token / SMTP EHLO / DB SELECT 1 / ping)
[TDD]
- 37 tests / 37 passed (2.11s)
- SQLite in-memory + StaticPool，無需外部 DB
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
95 lines
3.6 KiB
Python
95 lines
3.6 KiB
Python
"""
|
||
Schedule 3 — 系統狀態（每日 08:00）
|
||
Part A: 基礎設施服務功能驗證（traefik/keycloak/mail/db）
|
||
Part B: 伺服器 ping 檢查
|
||
"""
|
||
import logging
|
||
from datetime import datetime
|
||
from sqlalchemy.orm import Session
|
||
|
||
from app.models.server import SystemStatusLog, ServerStatusLog, Server
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
# Fixed 8 services: environment × service_name
|
||
SERVICES = [
|
||
{"environment": "test", "service_name": "traefik",
|
||
"service_desc": "測試環境反向代理", "host": "localhost", "port": 8080},
|
||
{"environment": "test", "service_name": "keycloak",
|
||
"service_desc": "測試環境 SSO",
|
||
"url": "https://auth.lab.taipei", "realm": "master"},
|
||
{"environment": "test", "service_name": "mail",
|
||
"service_desc": "測試環境 Mail Server", "host": "localhost", "port": 587},
|
||
{"environment": "test", "service_name": "db",
|
||
"service_desc": "10.1.0.20:5433 PostgreSQL",
|
||
"db_host": "10.1.0.20", "db_port": 5433},
|
||
{"environment": "prod", "service_name": "traefik",
|
||
"service_desc": "正式環境反向代理", "host": "localhost", "port": 8080},
|
||
{"environment": "prod", "service_name": "keycloak",
|
||
"service_desc": "正式環境 SSO",
|
||
"url": "https://auth.ease.taipei", "realm": "master"},
|
||
{"environment": "prod", "service_name": "mail",
|
||
"service_desc": "正式環境 Mail Server", "host": "10.1.0.254", "port": 587},
|
||
{"environment": "prod", "service_name": "db",
|
||
"service_desc": "10.1.0.254:5432 PostgreSQL",
|
||
"db_host": "10.1.0.254", "db_port": 5432},
|
||
]
|
||
|
||
|
||
def run_system_status(schedule_log_id: int, db: Session):
|
||
from app.services.system_checker import SystemChecker
|
||
checker = SystemChecker()
|
||
|
||
# Part A: Infrastructure services
|
||
for svc in SERVICES:
|
||
result = False
|
||
fail_reason = None
|
||
try:
|
||
if svc["service_name"] == "traefik":
|
||
result = checker.check_traefik(svc["host"], svc["port"])
|
||
elif svc["service_name"] == "keycloak":
|
||
result = checker.check_keycloak(svc["url"], svc["realm"])
|
||
elif svc["service_name"] == "mail":
|
||
result = checker.check_smtp(svc["host"], svc["port"])
|
||
elif svc["service_name"] == "db":
|
||
result = checker.check_postgres(svc["db_host"], svc["db_port"])
|
||
except Exception as e:
|
||
result = False
|
||
fail_reason = str(e)
|
||
|
||
db.add(SystemStatusLog(
|
||
schedule_log_id=schedule_log_id,
|
||
environment=svc["environment"],
|
||
service_name=svc["service_name"],
|
||
service_desc=svc["service_desc"],
|
||
result=result,
|
||
fail_reason=fail_reason,
|
||
recorded_at=datetime.utcnow(),
|
||
))
|
||
|
||
# Part B: Server ping
|
||
servers = db.query(Server).filter(Server.is_active == True).order_by(Server.sort_order).all()
|
||
for server in servers:
|
||
response_time = None
|
||
fail_reason = None
|
||
try:
|
||
response_time = checker.ping_server(server.ip_address)
|
||
result = response_time is not None
|
||
if not result:
|
||
fail_reason = "No response"
|
||
except Exception as e:
|
||
result = False
|
||
fail_reason = str(e)
|
||
|
||
db.add(ServerStatusLog(
|
||
schedule_log_id=schedule_log_id,
|
||
server_id=server.id,
|
||
result=result,
|
||
response_time=response_time,
|
||
fail_reason=fail_reason,
|
||
recorded_at=datetime.utcnow(),
|
||
))
|
||
|
||
db.commit()
|
||
logger.info(f"System status check done: {len(SERVICES)} services + {len(servers)} servers")
|