fix(video-render): F6 ReliableQueue 적용 (F6 part 4)
- worker.py: poll_once + ReliableQueue + startup recovery - 4 provider (sora/veo/kling/seedance) dispatch table 보존 - Dockerfile: build context=services/, _shared 포함, PYTHONPATH=/app - docker-compose.yml: video-render build context 갱신 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -54,7 +54,8 @@ services:
|
|||||||
|
|
||||||
video-render:
|
video-render:
|
||||||
build:
|
build:
|
||||||
context: ./video-render
|
context: .
|
||||||
|
dockerfile: video-render/Dockerfile
|
||||||
container_name: video-render
|
container_name: video-render
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
ports:
|
ports:
|
||||||
|
|||||||
@@ -7,10 +7,13 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
|||||||
ca-certificates \
|
ca-certificates \
|
||||||
&& rm -rf /var/lib/apt/lists/*
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
COPY requirements.txt .
|
COPY video-render/requirements.txt /app/
|
||||||
RUN pip install --no-cache-dir --timeout 600 --retries 5 -r requirements.txt
|
RUN pip install --no-cache-dir --timeout 600 --retries 5 -r requirements.txt
|
||||||
|
|
||||||
COPY . .
|
# F6: 공통 ReliableQueue 모듈 (services/_shared)
|
||||||
|
COPY _shared /app/_shared
|
||||||
|
COPY video-render/. /app/
|
||||||
|
ENV PYTHONPATH=/app
|
||||||
|
|
||||||
EXPOSE 8000
|
EXPOSE 8000
|
||||||
CMD ["python", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]
|
CMD ["python", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]
|
||||||
|
|||||||
5
services/video-render/conftest.py
Normal file
5
services/video-render/conftest.py
Normal file
@@ -0,0 +1,5 @@
|
|||||||
|
"""Make services/ root importable so `from _shared.reliable_queue import ...` works during tests."""
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||||
@@ -41,3 +41,56 @@ def test_dispatch_unknown_job_type_logs_error():
|
|||||||
args = m.call_args[0]
|
args = m.call_args[0]
|
||||||
assert args[0] == "t5"
|
assert args[0] == "t5"
|
||||||
assert args[1] == "failed"
|
assert args[1] == "failed"
|
||||||
|
|
||||||
|
|
||||||
|
# ----- F6: ReliableQueue poll_once -----
|
||||||
|
|
||||||
|
import json
|
||||||
|
from unittest.mock import AsyncMock, MagicMock
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_poll_once_acks_on_success(monkeypatch):
|
||||||
|
payload = {"task_id": "t1", "job_type": "sora_generation", "params": {}}
|
||||||
|
raw = json.dumps(payload).encode()
|
||||||
|
fake_queue = AsyncMock()
|
||||||
|
fake_queue.dequeue = AsyncMock(return_value=(payload, raw))
|
||||||
|
fake_queue.ack = AsyncMock()
|
||||||
|
fake_queue.fail = AsyncMock()
|
||||||
|
monkeypatch.setattr(worker, "_dispatch", MagicMock())
|
||||||
|
handled = await worker.poll_once(fake_queue)
|
||||||
|
assert handled is True
|
||||||
|
fake_queue.ack.assert_awaited_once_with(raw)
|
||||||
|
fake_queue.fail.assert_not_awaited()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_poll_once_calls_fail_on_dispatch_exception(monkeypatch):
|
||||||
|
payload = {"task_id": "t2", "job_type": "sora_generation", "params": {}}
|
||||||
|
raw = json.dumps(payload).encode()
|
||||||
|
fake_queue = AsyncMock()
|
||||||
|
fake_queue.dequeue = AsyncMock(return_value=(payload, raw))
|
||||||
|
fake_queue.ack = AsyncMock()
|
||||||
|
fake_queue.fail = AsyncMock()
|
||||||
|
|
||||||
|
def _boom(p):
|
||||||
|
raise RuntimeError("dispatch crash")
|
||||||
|
|
||||||
|
monkeypatch.setattr(worker, "_dispatch", _boom)
|
||||||
|
handled = await worker.poll_once(fake_queue)
|
||||||
|
assert handled is True
|
||||||
|
fake_queue.fail.assert_awaited_once_with(raw, payload)
|
||||||
|
fake_queue.ack.assert_not_awaited()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_poll_once_returns_false_on_timeout(monkeypatch):
|
||||||
|
fake_queue = AsyncMock()
|
||||||
|
fake_queue.dequeue = AsyncMock(return_value=None)
|
||||||
|
fake_queue.ack = AsyncMock()
|
||||||
|
fake_queue.fail = AsyncMock()
|
||||||
|
monkeypatch.setattr(worker, "_dispatch", MagicMock())
|
||||||
|
handled = await worker.poll_once(fake_queue)
|
||||||
|
assert handled is False
|
||||||
|
fake_queue.ack.assert_not_awaited()
|
||||||
|
fake_queue.fail.assert_not_awaited()
|
||||||
|
|||||||
@@ -1,7 +1,7 @@
|
|||||||
"""Redis BLPOP worker — queue:video-render → job_type 디스패치 → NAS webhook.
|
"""Redis ReliableQueue worker — F6 신뢰성 패턴 (BLMOVE + ack/fail + recovery).
|
||||||
|
|
||||||
queue:paused 가 set이면 대기 (task-watcher가 박재오 활동 감지 시 set).
|
queue:paused 가 set이면 대기 (task-watcher가 박재오 활동 감지 시 set).
|
||||||
Plan-B-Music worker.py 패턴 — string-based dispatch + getattr (테스트 patch 호환).
|
string-based dispatch + getattr (테스트 patch 호환).
|
||||||
"""
|
"""
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
@@ -18,6 +18,7 @@ from providers.sora import run_sora_generation
|
|||||||
from providers.veo import run_veo_generation
|
from providers.veo import run_veo_generation
|
||||||
from providers.kling import run_kling_generation
|
from providers.kling import run_kling_generation
|
||||||
from providers.seedance import run_seedance_generation
|
from providers.seedance import run_seedance_generation
|
||||||
|
from _shared.reliable_queue import ReliableQueue
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -53,25 +54,42 @@ def _dispatch(payload: dict) -> None:
|
|||||||
fn(task_id, params)
|
fn(task_id, params)
|
||||||
|
|
||||||
|
|
||||||
|
async def poll_once(queue: ReliableQueue) -> bool:
|
||||||
|
"""F6 — 1 cycle: dequeue → _dispatch → ack/fail. Returns True if a job handled."""
|
||||||
|
result = await queue.dequeue(timeout=5)
|
||||||
|
if result is None:
|
||||||
|
return False
|
||||||
|
payload, raw = result
|
||||||
|
try:
|
||||||
|
await asyncio.to_thread(_dispatch, payload)
|
||||||
|
except Exception:
|
||||||
|
logger.exception("dispatch unhandled exception task_id=%s",
|
||||||
|
payload.get("task_id"))
|
||||||
|
await queue.fail(raw, payload)
|
||||||
|
return True
|
||||||
|
await queue.ack(raw)
|
||||||
|
return True
|
||||||
|
|
||||||
|
|
||||||
async def worker_loop():
|
async def worker_loop():
|
||||||
redis = aioredis.from_url(REDIS_URL, decode_responses=False)
|
redis = aioredis.from_url(REDIS_URL, decode_responses=False)
|
||||||
logger.info("video-render worker started (queue=%s)", QUEUE_KEY)
|
queue = ReliableQueue(redis, queue_key=QUEUE_KEY)
|
||||||
|
logger.info("video-render worker started worker_id=%s queue=%s",
|
||||||
|
queue.worker_id, QUEUE_KEY)
|
||||||
|
try:
|
||||||
|
recovered = await queue.recover()
|
||||||
|
if recovered:
|
||||||
|
logger.info("recovered %d orphaned items at startup", recovered)
|
||||||
|
except Exception:
|
||||||
|
logger.exception("startup recover failed")
|
||||||
|
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
paused = await redis.get(PAUSED_KEY)
|
paused = await redis.get(PAUSED_KEY)
|
||||||
if paused == b"1":
|
if paused == b"1":
|
||||||
await asyncio.sleep(10)
|
await asyncio.sleep(10)
|
||||||
continue
|
continue
|
||||||
item = await redis.blpop(QUEUE_KEY, timeout=1)
|
await poll_once(queue)
|
||||||
if item is None:
|
|
||||||
continue
|
|
||||||
_, raw = item
|
|
||||||
try:
|
|
||||||
payload = json.loads(raw)
|
|
||||||
except json.JSONDecodeError:
|
|
||||||
logger.error("invalid queue payload: %r", raw[:200])
|
|
||||||
continue
|
|
||||||
await asyncio.to_thread(_dispatch, payload)
|
|
||||||
except asyncio.CancelledError:
|
except asyncio.CancelledError:
|
||||||
logger.info("worker_loop cancelled")
|
logger.info("worker_loop cancelled")
|
||||||
raise
|
raise
|
||||||
|
|||||||
Reference in New Issue
Block a user