feat(orchestrator): pool 异步化(ProcessPoolExecutor spawn + stage 追踪)

This commit is contained in:
2026-07-06 18:19:24 +08:00
parent 48a9058cb2
commit 66aa27e807
3 changed files with 54 additions and 1 deletions
+20
View File
@@ -2,6 +2,8 @@
Task pool for managing multiple tasks in memory
Provides task storage and status tracking (not actual multiprocessing)
"""
from concurrent.futures import ProcessPoolExecutor, Future
from multiprocessing import get_context
from .task import Task, TaskState
@@ -12,6 +14,9 @@ class TaskPool:
"""Initialize task pool with maximum workers"""
self.max_workers = max_workers
self._tasks: dict[str, Task] = {}
self.executor = ProcessPoolExecutor(
max_workers=max_workers, mp_context=get_context("spawn")
)
def submit(self, task_id: str, task_type: str) -> Task:
"""Submit a new task to the pool"""
@@ -19,11 +24,26 @@ class TaskPool:
self._tasks[task_id] = task
return task
def submit_work(self, task_id: str, func, *args) -> Future:
"""Submit work to the process pool executor"""
return self.executor.submit(func, *args)
def update_stage(self, task_id: str, stage: str):
"""Update the stage of a task"""
t = self._tasks.get(task_id)
if t:
t.stage = stage
def get_status(self, task_id: str) -> TaskState | None:
"""Get task status by ID"""
task = self._tasks.get(task_id)
return task.status if task else None
def get_stage(self, task_id: str) -> str | None:
"""Get task stage by ID"""
t = self._tasks.get(task_id)
return t.stage if t else None
def get_task(self, task_id: str) -> Task | None:
"""Get task object by ID"""
return self._tasks.get(task_id)
+1
View File
@@ -22,6 +22,7 @@ class Task:
status: TaskState = TaskState.PENDING
result_id: int | None = None
error_msg: str | None = None
stage: str = "" # Current stage (数据加载/算因子/回测中...)
def start(self):
"""Transition from PENDING to RUNNING"""
+33 -1
View File
@@ -59,4 +59,36 @@ class TestTaskPool:
task2 = pool.submit(task_id="test_2", task_type="test")
assert len(pool._tasks) == 2
assert pool.get_status("test_1") == TaskState.PENDING
assert pool.get_status("test_2") == TaskState.PENDING
assert pool.get_status("test_2") == TaskState.PENDING
class TestTaskPoolStageAndAsync:
"""Test TaskPool stage tracking and async execution (Task 3)"""
def test_task_has_stage_field(self):
"""Test Task has stage field with default empty string"""
from sanguo_orchestrator.task import Task
t = Task(task_id="t1", task_type="cta")
assert t.stage == ""
def test_pool_submit_work_returns_future(self):
"""Test submit_work() returns Future from executor"""
from unittest.mock import MagicMock
from sanguo_orchestrator.pool import TaskPool
pool = TaskPool(max_workers=2)
pool.executor = MagicMock() # mock executor to avoid spawning real processes
mock_future = MagicMock()
pool.executor.submit.return_value = mock_future
fut = pool.submit_work("t1", func=lambda: 1)
assert fut is mock_future
pool.executor.submit.assert_called_once()
def test_pool_update_and_get_stage(self):
"""Test update_stage() and get_stage() methods"""
from sanguo_orchestrator.pool import TaskPool
from sanguo_orchestrator.task import Task
pool = TaskPool(max_workers=2)
pool.submit("t1", "cta")
pool.update_stage("t1", "回测中")
assert pool.get_stage("t1") == "回测中"
assert pool.get_task("t1").stage == "回测中"