fix(critical): 修复调度器静默失效、数据源缺失与前端类型错误
C1 定时任务静默失效(4 层缺陷):
- scheduler.py: croniter(expr, datetime.now) 未调用 now(),
导致 TypeError 被吞、next_run 恒为 None(最深一层)
- scheduler.py: _calc_next 非法 cron 静默吞异常 -> 改为构造期抛 ValueError
- scheduler.py: _run_loop 一次异常即永久停摆 -> 增加异常隔离
- scheduler.py: sleep(min(wait,60)) 使运行期 cron 变更最长 60s 才生效
-> 改为固定 SLEEP_TICK 轮询
- app.py / schedules.py: 3 处 register() 第 2 参误传 task 类型名
C3 EvalPage.tsx: 引用未导入的 EmptyState -> 改为已导入的 EmptyText
(tsc --noEmit 由 1 error 变为 0 error)
新增 tests/test_scheduler_registration.py: 9 项行为回归测试
This commit is contained in:
+1
-1
@@ -50,7 +50,7 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
|
||||
for s in schedules:
|
||||
leagues = s.leagues.split(",") if s.leagues else list(BZZOIRO_LEAGUE_IDS.keys())
|
||||
scheduler.register(
|
||||
s.id, s.task,
|
||||
s.id, s.cron,
|
||||
lambda sid=s.id: _run_scheduled_task(sid),
|
||||
enabled=s.enabled,
|
||||
)
|
||||
|
||||
@@ -91,8 +91,8 @@ async def create_schedule(req: ScheduleIn, db: AsyncSession = Depends(get_db_rea
|
||||
db.add(sched)
|
||||
await db.commit()
|
||||
|
||||
# 注册到调度器
|
||||
scheduler.register(req.id, req.task, lambda: _run_scheduled_task(req.id), enabled=req.enabled)
|
||||
# 注册到调度器(注意: 第 2 参是 cron 表达式,不是 task 类型名)
|
||||
scheduler.register(req.id, req.cron, lambda: _run_scheduled_task(req.id), enabled=req.enabled)
|
||||
|
||||
return {"ok": True, "id": req.id}
|
||||
|
||||
@@ -115,8 +115,8 @@ async def update_schedule(schedule_id: str, req: ScheduleUpdate, db: AsyncSessio
|
||||
sched.enabled = req.enabled
|
||||
await db.commit()
|
||||
|
||||
# 更新调度器(使用最终值)
|
||||
scheduler.register(schedule_id, sched.task, lambda: _run_scheduled_task(schedule_id), enabled=sched.enabled)
|
||||
# 更新调度器(第 2 参传 cron 表达式;使用最终值)
|
||||
scheduler.register(schedule_id, sched.cron, lambda: _run_scheduled_task(schedule_id), enabled=sched.enabled)
|
||||
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
+89
-29
@@ -14,6 +14,9 @@ logger = logging.getLogger(__name__)
|
||||
class ScheduledTask:
|
||||
"""一个定时任务。"""
|
||||
|
||||
#: 运行循环的轮询粒度(秒)。同时决定运行期 cron/next_run 变更的生效延迟上限。
|
||||
SLEEP_TICK: float = 1.0
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
task_id: str,
|
||||
@@ -28,13 +31,29 @@ class ScheduledTask:
|
||||
self.last_run: datetime | None = None
|
||||
self.next_run: datetime | None = None
|
||||
self._task: asyncio.Task | None = None
|
||||
self._calc_next()
|
||||
# 构造时立即校验 cron:非法表达式直接报错,不留给 _run_loop 静默吞掉。
|
||||
# (全量审查 C1: 传入任务类型字符串时 croniter 抛异常被吞 → 任务永不触发)
|
||||
self._calc_next(raise_on_error=True)
|
||||
|
||||
def _calc_next(self) -> None:
|
||||
def _calc_next(self, *, raise_on_error: bool = False) -> None:
|
||||
"""计算下次运行时间。
|
||||
|
||||
raise_on_error=True 时非法 cron 抛 ValueError(构造期用);
|
||||
否则仅告警并置 next_run=None(运行期容错)。
|
||||
"""
|
||||
try:
|
||||
self.next_run = croniter(self.cron, datetime.now).get_next(datetime)
|
||||
except Exception:
|
||||
# 必须调用 datetime.now():传方法对象本身会让 croniter 在
|
||||
# (start_time or now) 的算术里抛 TypeError,导致 next_run 永远为 None。
|
||||
self.next_run = croniter(self.cron, datetime.now()).get_next(datetime)
|
||||
except Exception as e:
|
||||
self.next_run = None
|
||||
msg = (
|
||||
f"任务 {self.task_id!r} 的 cron 表达式非法: {self.cron!r} ({e})。"
|
||||
"注意: 此处应为 cron 表达式(如 '0 8 * * *'),不是任务类型名。"
|
||||
)
|
||||
if raise_on_error:
|
||||
raise ValueError(msg) from e
|
||||
logger.error(msg)
|
||||
|
||||
def update(self, cron: str | None = None, enabled: bool | None = None) -> None:
|
||||
if cron is not None:
|
||||
@@ -44,27 +63,45 @@ class ScheduledTask:
|
||||
self._calc_next()
|
||||
|
||||
async def _run_loop(self) -> None:
|
||||
"""任务运行循环。
|
||||
|
||||
睡眠策略: 使用固定的短 tick(SLEEP_TICK 秒)轮询 next_run,而不是
|
||||
一次性 sleep 到 next_run。原因是运行期可通过 API 更新 cron / 手动
|
||||
调整 next_run;若按 wait_seconds 长时间沉睡,变更最长要等
|
||||
wait_seconds 才生效(实测可达 60s),表现为「改了不生效」。
|
||||
"""
|
||||
while True:
|
||||
if not self.enabled or not self.next_run:
|
||||
await asyncio.sleep(60)
|
||||
self._calc_next()
|
||||
continue
|
||||
|
||||
now = datetime.now()
|
||||
wait_seconds = (self.next_run - now).total_seconds()
|
||||
if wait_seconds > 0:
|
||||
await asyncio.sleep(min(wait_seconds, 60))
|
||||
continue
|
||||
|
||||
# 执行任务
|
||||
self.last_run = datetime.now()
|
||||
self._calc_next()
|
||||
try:
|
||||
logger.info("定时任务触发: %s (cron=%s)", self.task_id, self.cron)
|
||||
await self.fn()
|
||||
logger.info("定时任务完成: %s", self.task_id)
|
||||
if not self.enabled or not self.next_run:
|
||||
await asyncio.sleep(self.SLEEP_TICK)
|
||||
self._calc_next()
|
||||
continue
|
||||
|
||||
now = datetime.now()
|
||||
wait_seconds = (self.next_run - now).total_seconds()
|
||||
if wait_seconds > 0:
|
||||
# 短 tick 轮询,保证 next_run/cron 变更能及时被感知
|
||||
await asyncio.sleep(min(wait_seconds, self.SLEEP_TICK))
|
||||
continue
|
||||
|
||||
# 执行任务:先推进 next_run 再执行,避免任务耗时导致重复触发
|
||||
self.last_run = datetime.now()
|
||||
self._calc_next()
|
||||
try:
|
||||
logger.info("定时任务触发: %s (cron=%s)", self.task_id, self.cron)
|
||||
await self.fn()
|
||||
logger.info("定时任务完成: %s", self.task_id)
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
except Exception:
|
||||
# 单个任务失败不能终止循环,否则一次异常即永久停摆
|
||||
logger.exception("定时任务失败: %s", self.task_id)
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
except Exception:
|
||||
logger.exception("定时任务失败: %s", self.task_id)
|
||||
# 循环体自身的意外异常(如 _calc_next)也不能终止调度
|
||||
logger.exception("调度循环异常: %s", self.task_id)
|
||||
await asyncio.sleep(self.SLEEP_TICK)
|
||||
|
||||
|
||||
class DataQualityScheduler:
|
||||
@@ -152,6 +189,7 @@ class Scheduler:
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._tasks: dict[str, ScheduledTask] = {}
|
||||
self._running = False
|
||||
|
||||
def register(
|
||||
self,
|
||||
@@ -160,13 +198,31 @@ class Scheduler:
|
||||
fn: Callable[[], Coroutine],
|
||||
enabled: bool = True,
|
||||
) -> ScheduledTask:
|
||||
if task_id in self._tasks:
|
||||
self._tasks[task_id].update(cron=cron, enabled=enabled)
|
||||
return self._tasks[task_id]
|
||||
task = ScheduledTask(task_id, cron, fn, enabled)
|
||||
self._tasks[task_id] = task
|
||||
"""注册(或更新)一个定时任务。
|
||||
|
||||
若调度器已 start,新任务会立即启动其运行循环 ——
|
||||
否则运行期通过 API 新建的任务永远不会被执行(全量审查 C1 缺陷 2)。
|
||||
"""
|
||||
existing = self._tasks.get(task_id)
|
||||
if existing is not None:
|
||||
existing.update(cron=cron, enabled=enabled)
|
||||
# 更新 cron 后重新校验:改坏了要立刻报错,而不是静默失活
|
||||
existing._calc_next(raise_on_error=True)
|
||||
existing.fn = fn
|
||||
task = existing
|
||||
else:
|
||||
task = ScheduledTask(task_id, cron, fn, enabled)
|
||||
self._tasks[task_id] = task
|
||||
|
||||
if self._running:
|
||||
self._ensure_loop(task)
|
||||
return task
|
||||
|
||||
def _ensure_loop(self, task: ScheduledTask) -> None:
|
||||
"""为任务启动运行循环(幂等:已在运行则跳过)。"""
|
||||
if task._task is None or task._task.done():
|
||||
task._task = asyncio.create_task(task._run_loop())
|
||||
|
||||
def get(self, task_id: str) -> ScheduledTask | None:
|
||||
return self._tasks.get(task_id)
|
||||
|
||||
@@ -174,14 +230,18 @@ class Scheduler:
|
||||
return list(self._tasks.values())
|
||||
|
||||
def remove(self, task_id: str) -> None:
|
||||
self._tasks.pop(task_id, None)
|
||||
task = self._tasks.pop(task_id, None)
|
||||
if task is not None and task._task is not None:
|
||||
task._task.cancel()
|
||||
|
||||
async def start(self) -> None:
|
||||
self._running = True
|
||||
for task in self._tasks.values():
|
||||
task._task = asyncio.create_task(task._run_loop())
|
||||
self._ensure_loop(task)
|
||||
logger.info("定时调度器已启动, 共 %d 个任务", len(self._tasks))
|
||||
|
||||
async def stop(self) -> None:
|
||||
self._running = False
|
||||
for task in self._tasks.values():
|
||||
if task._task:
|
||||
task._task.cancel()
|
||||
|
||||
Reference in New Issue
Block a user