Archived
refactor: worker 子系统全面异步化,拆掉同步转异步的桥接层
拆掉「同步调异步 / 异步桥同步」两类垫片的第二半(HTTP 线 B2 见前序提交)。 worker 侧此前是「起线程跑同步函数、函数体内部再用 asyncio.to_thread 把活塞给 另一条循环」——线程与协程互等,取消/暂停只能靠轮询。本轮把 worker 自身变成 协程,由 _start_task 直接挂到应用事件循环上,桥接层随之失去存在理由。 改动(按子系统): - music_downloader:downloader / _aria2 / _concurrency / cover / _http / __main__ 全链路协程化。per-file 锁改 asyncio.Lock;计数闸改 「active 计数 + await asyncio.sleep(0.5)」的可取消等待(原阻塞式 with 会让 已取消任务仍要等全局名额腾出,卡死并拖后腿退款);aria2p 的同步 RPC 仍经 to_thread,轮询改 asyncio.sleep;新增 core.http_client.iter_chunks,把**流式 读取期**的 aiohttp.ClientError 收敛成 UpstreamNetworkError(请求建立阶段早已 有这条路径,读取阶段此前没有,断流会绕过调用方的 UpstreamError 分类)。 删除 get_http_session / _SESSION_LOCAL。 models._RetryFromScratch 不再继承 requests.RequestException 而继承 Exception: 它是「续传起点失效、残片已清、从头重下」,既不是确定性失败 (DownloadException),也不是残片已保留的网络失败(UpstreamError),必须独立 成类且在 except 链中先于二者捕获。 - music_api:podcast.py 全部函数协程化(直链解析内部改 await NeteaseAPI.get_song_url);compat.py 删除——16 个死掉的同步门面早已 清空,文件只剩空壳。 - services:_taskcore / _zipcore / batch / downloads / podcast / tasks 协程化。 threading.Thread → loop.create_task(任务句柄字段 worker_thread → worker_task),ThreadPoolExecutor → asyncio.gather + asyncio.Semaphore, 终态函数与结算回调全部改 await;监控线程里「worker 已死」判定改 task.done()。 删除 services/streaming.py(同步流垫片,唯一消费者已迁到 core.http_client.open)。zipfile 实例仍非线程安全,故「下载」并行、 「入包」严格串行。 - web:路由层 130+ 处 to_thread 拆除——被包住的目标自己已是协程,再包一层只是 把协程丢进线程里跑一圈。tasks_registry.start_task 直接 create_task。 web/app.py 关闭段去掉 async_bridge.shutdown()(不再有第二条约循环)。 web/routers/download.py 的播客端点补上 3 处漏掉的 await (extract_podcast_ref / get_radio_detail)——漏掉时不报错、只静默返回协程对象, 靠 pyright 抓出来后修正。 留在 to_thread 上的都是**正当的阻塞卸载**:同步 SQLite 落库与账本结算、 mutagen 全量重写标签、zipfile 整段拷贝、shutil.rmtree、aria2p 的同步 RPC、 PBKDF2 的 10 万次迭代。ruff 对残留的本地元数据操作(exists/stat/os.replace/ 往 .part 顺序写分块)按「微秒级、卸载的调度开销大于操作本身」放行,pyproject 逐条注明理由。 取消/暂停仍由 threading.Event 承载:置位方是请求线程/监控线程,读取方是 worker 协程,只有「置位」与「轮询读取」两种操作,既不需要跨循环唤醒也不会卡住事件 循环——比 asyncio.Event 更省心(ASYNC110 同理按此豁免)。 测试:10 个文件的替身边界同步迁移——网络替身从 core.sync_http 的 get_http_session 换成 downloader/服务模块的 _http.open + **真实** iter_chunks (顺带钉住读取期异常收敛);`_run` 改为在独立线程里 asyncio.run(worker(...)); aria2 的假时钟从 time.sleep 换成 _POLL_INTERVAL=0;monitor 的线程句柄替身换成 done() 可控的轻量替身(asyncio.Task 的构造需要运行中的事件循环,而监控循环跑在 常驻线程里);podcast / 封面 / 结算包装等替身一律改 async。 门禁:ruff 全过 / pyright 0-0 / pytest 383 项全绿(0 失败)。 下一步 B2:auth_system 12 个模块改 aiosqlite 背板、web 层剩余 to_thread 收尾; B3:删 core/sync_http.py、core/async_bridge.py、core/http_errors.py(现仅 sync_http 自用)。
This commit is contained in:
1 parent
65adfc9089
commit
69a50c2c31
35 files changed
+1062
-1005
No files matched your search
@@ -19,6 +19,7 @@ except 分支各写一遍「结算 + 删任务目录」,正文里散着三处
|
||||
|
||||
账本口径:一律用 ``reserve_and_open`` 真预扣(与 test_single_worker.py 同理由)。
|
||||
"""
|
||||
import asyncio
|
||||
import threading
|
||||
import time
|
||||
import zipfile
|
||||
@@ -83,9 +84,9 @@ class _FakeStream:
|
||||
self.on_call = on_call
|
||||
self.calls: list[dict[str, Any]] = []
|
||||
|
||||
def __call__(self, url: str, target: Path, total_size: int,
|
||||
cancel_ev: threading.Event, task_id: str = '',
|
||||
progress_label: str = '') -> int:
|
||||
async def __call__(self, url: str, target: Path, total_size: int,
|
||||
cancel_ev: threading.Event, task_id: str = '',
|
||||
progress_label: str = '') -> int:
|
||||
self.calls.append({'url': url, 'target': Path(target),
|
||||
'total_size': total_size})
|
||||
if self.on_call is not None:
|
||||
@@ -172,13 +173,20 @@ def _register_podcast(sandbox, *, program_id: int = 777, user_id: int,
|
||||
def _install_upstream(monkeypatch, *, program: dict[str, Any] | None = None,
|
||||
url_info: dict[str, Any] | None = None,
|
||||
stream: Any = None,
|
||||
cover: Any = lambda url: b'\xff\xd8\xff cover') -> None:
|
||||
cover: Any = None) -> None:
|
||||
"""装上播客上游替身(节目详情 / 直链 / 流式下载 / 封面)。"""
|
||||
monkeypatch.setattr(podcast_svc.podcast, 'get_program_detail',
|
||||
lambda pid, cookies: program if program is not None else _program())
|
||||
monkeypatch.setattr(podcast_svc.podcast, 'resolve_episode_url',
|
||||
lambda sid, cookies, quality:
|
||||
url_info if url_info is not None else _url_info())
|
||||
async def _detail(pid: Any, cookies: Any) -> dict[str, Any]:
|
||||
return program if program is not None else _program()
|
||||
|
||||
async def _resolve(sid: Any, cookies: Any, quality: str) -> dict[str, Any]:
|
||||
return url_info if url_info is not None else _url_info()
|
||||
|
||||
monkeypatch.setattr(podcast_svc.podcast, 'get_program_detail', _detail)
|
||||
monkeypatch.setattr(podcast_svc.podcast, 'resolve_episode_url', _resolve)
|
||||
if cover is None:
|
||||
async def _default_cover(_url: str) -> bytes:
|
||||
return b'\xff\xd8\xff cover'
|
||||
cover = _default_cover
|
||||
if stream is None:
|
||||
stream = _FakeStream()
|
||||
monkeypatch.setattr(podcast_svc, '_podcast_stream_download', stream)
|
||||
@@ -186,8 +194,11 @@ def _install_upstream(monkeypatch, *, program: dict[str, Any] | None = None,
|
||||
|
||||
|
||||
def _run(task_id: str) -> threading.Thread:
|
||||
th = threading.Thread(target=podcast_svc._podcast_download_worker,
|
||||
args=(task_id,), daemon=True)
|
||||
"""把 worker 协程跑在独立线程的私有事件循环里(等价于生产的任务循环)。"""
|
||||
def _target() -> None:
|
||||
asyncio.run(podcast_svc._podcast_download_worker(task_id))
|
||||
|
||||
th = threading.Thread(target=_target, daemon=True)
|
||||
th.start()
|
||||
return th
|
||||
|
||||
@@ -332,7 +343,7 @@ def test_cover_fetch_failure_still_delivers_zip(sandbox, monkeypatch):
|
||||
"""取封面抛异常:被吞掉,ZIP 照常交付(历史行为:封面失败不炸任务)。"""
|
||||
uid = _uid()
|
||||
|
||||
def _boom(url: str) -> bytes:
|
||||
async def _boom(url: str) -> bytes:
|
||||
raise RuntimeError('cover cdn down')
|
||||
|
||||
_install_upstream(monkeypatch, cover=_boom)
|
||||
@@ -402,7 +413,7 @@ def test_unexpected_exception_uses_generic_message(sandbox, monkeypatch):
|
||||
uid = _uid()
|
||||
before = _balance()
|
||||
|
||||
def _boom(pid: Any, cookies: Any) -> dict[str, Any]:
|
||||
async def _boom(pid: Any, cookies: Any) -> dict[str, Any]:
|
||||
raise RuntimeError('upstream host=10.0.0.9 refused')
|
||||
|
||||
_install_upstream(monkeypatch)
|
||||
@@ -468,7 +479,7 @@ def test_cancel_during_zip_stage(sandbox, monkeypatch):
|
||||
before = _balance()
|
||||
holder: dict[str, Any] = {}
|
||||
|
||||
def _cancel_in_cover(url: str) -> bytes:
|
||||
async def _cancel_in_cover(url: str) -> bytes:
|
||||
holder['task']['cancel'].set()
|
||||
return b'\xff\xd8\xff cover'
|
||||
|
||||
|
||||
Reference in new issue
Block a user