3b9361c237
- 冲突解决原则：本地权限治理(require_admin/current_user/资源ACL)与远程 op_log 日志装饰器双向保留 - platform.py: 9 处冲突，@op_log 与管理员校验叠加，避免远程丢失 require_admin 的安全回归 - logging.py: 合并 get_client_ip 与 user_id_var，X-Trace-Id 优先 + ContextVar 卫生处理 - op_log.py: 采纳远程将变量计算上移到函数顶部的结构 - compute_poller.py: 中文日志 + 失败去重限流/断连重置逻辑 - data_process.py: 保留租户归属字段 + biz_logger 成功日志
60 lines
2.4 KiB
Python
60 lines
2.4 KiB
Python
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import time
|
|
|
|
from app.core.config import get_settings
|
|
from app.core.logging import get_logger
|
|
from app.db.platform_store import get_platform_store
|
|
from app.modules.compute_gateway.sync import poll_compute_jobs_once
|
|
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
async def run_compute_poller() -> None:
|
|
settings = get_settings()
|
|
if settings.compute_mode == "simulator" or settings.compute_status_sync_mode != "polling":
|
|
logger.info("计算轮询已禁用", extra={"compute_mode": settings.compute_mode})
|
|
return
|
|
|
|
interval = max(3, settings.compute_poll_interval_seconds)
|
|
logger.info("计算轮询已启动", extra={"interval_seconds": interval})
|
|
# PlatformStore may run additive schema checks against a remote PostgreSQL
|
|
# server on first use. Keep that startup work off the Uvicorn event loop so
|
|
# health checks and normal API requests can still respond while the DB is
|
|
# unavailable or slow.
|
|
store = None
|
|
last_failure_signature = ""
|
|
last_failure_logged_at = 0.0
|
|
await asyncio.sleep(1)
|
|
while True:
|
|
try:
|
|
if store is None:
|
|
store = await asyncio.to_thread(get_platform_store)
|
|
result = await poll_compute_jobs_once(store)
|
|
if result["failed"]:
|
|
signature = "|".join(sorted({
|
|
str(item.get("error") or "")[:120]
|
|
for item in result["failed"]
|
|
}))
|
|
now = time.monotonic()
|
|
if signature != last_failure_signature or now - last_failure_logged_at >= 300:
|
|
logger.warning(
|
|
"计算轮询报告失败任务 count=%d first_error=%s",
|
|
len(result["failed"]),
|
|
signature[:500],
|
|
)
|
|
last_failure_signature = signature
|
|
last_failure_logged_at = now
|
|
elif result["synced"]:
|
|
logger.debug("计算任务状态已同步", extra={"result": result})
|
|
except asyncio.CancelledError:
|
|
logger.info("计算轮询已停止")
|
|
raise
|
|
except Exception as exc: # noqa: BLE001 - keep background polling alive
|
|
logger.exception("计算轮询执行失败", extra={"error": str(exc)})
|
|
if "store" in locals() and isinstance(exc, (ConnectionError, TimeoutError)):
|
|
store = None
|
|
await asyncio.sleep(interval)
|