XW-AIOT/iot-device-management-service
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

增强：工单创建增加重试机制（最多2次重试）

Browse Source 
IoT ops 服务偶发 500 异常（auto_complete 后状态污染），
添加 3s/6s 间隔重试，避免暂时性故障导致工单丢失。
This commit is contained in:
16337
2026-03-31 09:37:33 +08:00
parent 9513951b1b
commit 93148fe85b
1 changed files with 33 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
app/services/work_order_client.py
View File

@@ -132,28 +132,43 @@ class WorkOrderClient:
body_json = json.dumps(body, ensure_ascii=False, separators=(",", ":"))
try:
headers = self._build_headers(body_json)
url = f"{self._base_url}/open-api/ops/security/order/create"
logger.info(f"创建工单请求: url={url}, body={body_json}")
max_retries = 2
for attempt in range(max_retries + 1):
try:
headers = self._build_headers(body_json)
url = f"{self._base_url}/open-api/ops/security/order/create"
if attempt == 0:
logger.info(f"创建工单请求: url={url}, body={body_json}")
async with httpx.AsyncClient(timeout=self._timeout) as client:
resp = await client.post(url, content=body_json, headers=headers)
data = resp.json()
async with httpx.AsyncClient(timeout=self._timeout) as client:
resp = await client.post(url, content=body_json, headers=headers)
data = resp.json()
if data.get("code") != 0:
logger.error(f"创建工单失败: status={resp.status_code}, resp={data}, body={body_json}")
if data.get("code") != 0:
if attempt < max_retries:
import asyncio
wait = (attempt + 1) * 3
logger.warning(f"创建工单失败(第{attempt+1}次), {wait}s后重试: code={data.get('code')}, msg={data.get('msg')}")
await asyncio.sleep(wait)
continue
logger.error(f"创建工单失败(已重试{max_retries}次): status={resp.status_code}, resp={data}, body={body_json}")
return None
# API 返回 {"code":0, "data": 1234567890} — data 直接是 orderId
order_id = str(data.get("data", ""))
logger.info(f"工单已创建: orderId={order_id}, alarmId={alarm_id}" + (f" (第{attempt+1}次尝试)" if attempt > 0 else ""))
return order_id
except Exception as e:
if attempt < max_retries:
import asyncio
wait = (attempt + 1) * 3
logger.warning(f"创建工单异常(第{attempt+1}次), {wait}s后重试: {e}")
await asyncio.sleep(wait)
continue
logger.error(f"创建工单异常(已重试{max_retries}次): {e}")
return None
# API 返回 {"code":0, "data": 1234567890} — data 直接是 orderId
order_id = str(data.get("data", ""))
logger.info(f"工单已创建: orderId={order_id}, alarmId={alarm_id}")
return order_id
except Exception as e:
logger.error(f"创建工单异常: {e}")
return None
async def auto_complete_order(
self,
order_id: str,