Simon
195f5d41f4
1) 数据装配流式+列裁剪：Repository 新增 stream_range_many_columns（只 SELECT 所需列、SQL 侧转 REAL、yield_per 分批），引擎按 required_columns 取数 （LocalEngine 仅 close+因子字段），消除 ORM/Decimal 全量物化； 2) 研究 Job 独立子进程执行（job.mode=subprocess）：python -m app.cli.run_job 在子进程内设 RLIMIT_AS 上限，OOM 归档 failed 而非拖垮 API worker； 子进程异常退出由父进程补记 failed；并发上限 2； 3) 服务启动清理：残留 queued/running Job 标记 failed（防永久 running）。 实测同款全市场回测：uvicorn worker RSS 稳定 ~220MB，任务峰值内存由 4.1GB+ 降至 ~470MB，24s 完成并归档（此前 43s 未完成即 OOM）。 新增/更新测试 96 passed，ruff 干净。
73 lines
2.6 KiB
Python
73 lines
2.6 KiB
Python
"""Job / Experiment 的 SQLAlchemy 实现（Phase 4）。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from sqlalchemy import select
|
|
from sqlalchemy.orm import Session
|
|
|
|
from app.domain.entities.research import ExperimentRecord, JobRecord
|
|
from app.infrastructure.persistence.sqlalchemy.models.jobs import ExperimentModel, JobModel
|
|
|
|
|
|
def _job_to_model(job: JobRecord) -> JobModel:
|
|
return JobModel(**job.model_dump())
|
|
|
|
|
|
class SqlAlchemyJobRepository:
|
|
def __init__(self, session: Session) -> None:
|
|
self._session = session
|
|
|
|
def create(self, job: JobRecord) -> JobRecord:
|
|
self._session.add(_job_to_model(job))
|
|
self._session.flush()
|
|
return job
|
|
|
|
def get(self, job_id: str) -> JobRecord | None:
|
|
row = self._session.get(JobModel, job_id)
|
|
return JobRecord.model_validate(row, from_attributes=True) if row else None
|
|
|
|
def update(self, job: JobRecord) -> None:
|
|
row = self._session.get(JobModel, job.id)
|
|
if row is None:
|
|
raise KeyError(f"job {job.id} 不存在")
|
|
for k, v in job.model_dump().items():
|
|
setattr(row, k, v)
|
|
|
|
def list_recent(self, kind: str | None = None, limit: int = 20) -> list[JobRecord]:
|
|
stmt = select(JobModel).order_by(JobModel.created_at.desc()).limit(limit)
|
|
if kind:
|
|
stmt = stmt.where(JobModel.kind == kind)
|
|
return [
|
|
JobRecord.model_validate(r, from_attributes=True)
|
|
for r in self._session.scalars(stmt).all()
|
|
]
|
|
|
|
def list_by_status(self, status: str, limit: int = 100) -> list[JobRecord]:
|
|
rows = self._session.scalars(
|
|
select(JobModel)
|
|
.where(JobModel.status == status)
|
|
.order_by(JobModel.created_at)
|
|
.limit(limit)
|
|
).all()
|
|
return [JobRecord.model_validate(r, from_attributes=True) for r in rows]
|
|
|
|
|
|
class SqlAlchemyExperimentRepository:
|
|
def __init__(self, session: Session) -> None:
|
|
self._session = session
|
|
|
|
def save(self, experiment: ExperimentRecord) -> ExperimentRecord:
|
|
self._session.add(ExperimentModel(**experiment.model_dump()))
|
|
self._session.flush()
|
|
return experiment
|
|
|
|
def get(self, experiment_id: str) -> ExperimentRecord | None:
|
|
row = self._session.get(ExperimentModel, experiment_id)
|
|
return ExperimentRecord.model_validate(row, from_attributes=True) if row else None
|
|
|
|
def list_recent(self, limit: int = 50) -> list[ExperimentRecord]:
|
|
rows = self._session.scalars(
|
|
select(ExperimentModel).order_by(ExperimentModel.created_at.desc()).limit(limit)
|
|
).all()
|
|
return [ExperimentRecord.model_validate(r, from_attributes=True) for r in rows]
|