f657e2c0ba
End-to-end webhook flow is proven on this NC instance (NodeCreated + NodeWritten both fired and dispatched scan_folder on a PUT test), so the watchfiles-based polling layer is no longer needed. - scanner.start_initial_scan no longer queues watch_folders on boot. - scan.watch_folders kept as a one-line no-op shim so any leftover apply_async in flight from the previous deploy doesn't crash a worker. Will be deleted entirely after the queue drains. - celery.py reroutes watch_folders to the `default` queue (worker-light) so the no-op shim actually completes — the `watcher` queue is dead. - docker-compose drops the mulita-worker-watcher service. Its celery --beat responsibility (firing discard_missing_photos_beat every 30 min) moves to worker-light's command. Latency note: NC dispatches webhook events through its background-job queue, currently run by cron */5. After this commit lands you'll want to tighten cron to */1 so new uploads land in mule within ~60s instead of up to 5 min.
94 lines
3.4 KiB
Python
94 lines
3.4 KiB
Python
"""
|
|
Celery configuration and app initialization
|
|
"""
|
|
import logging
|
|
import os
|
|
|
|
from celery import Celery
|
|
from celery.signals import worker_process_init
|
|
from app.config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# Create Celery app
|
|
celery_app = Celery(
|
|
'mulita',
|
|
broker=settings.celery_broker_url,
|
|
backend=settings.celery_result_backend,
|
|
include=[
|
|
'app.tasks.scan',
|
|
'app.tasks.thumbs',
|
|
'app.tasks.vision',
|
|
'app.services.metadata', # extract_metadata lives here
|
|
]
|
|
)
|
|
|
|
# Configure Celery
|
|
celery_app.conf.update(
|
|
task_serializer='json',
|
|
accept_content=['json'],
|
|
result_serializer='json',
|
|
timezone='UTC',
|
|
enable_utc=True,
|
|
# Robust acknowledgment: keep message in broker until task succeeds.
|
|
task_acks_late=True,
|
|
task_reject_on_worker_lost=True,
|
|
# Global time limits — individual tasks can override via decorator.
|
|
task_soft_time_limit=300, # 5 min — raises SoftTimeLimitExceeded
|
|
task_time_limit=600, # 10 min — SIGKILL
|
|
# Explicit routes for every task name. Wildcard patterns don't match
|
|
# short names produced by @shared_task(name='...').
|
|
task_routes={
|
|
# Vision queue — CPU-bound binary classification
|
|
'classify_content': {'queue': 'vision'},
|
|
'vision_fanout': {'queue': 'vision'},
|
|
# High-priority queue — thumbnails & duplicates
|
|
'generate_thumbnails': {'queue': 'high'},
|
|
'regenerate_all_thumbnails': {'queue': 'high'},
|
|
'backfill_phashes': {'queue': 'high'},
|
|
'regroup_duplicates': {'queue': 'high'},
|
|
'incremental_regroup_duplicates': {'queue': 'high'},
|
|
# Low-priority queue — scans
|
|
'scan_folder': {'queue': 'low'},
|
|
'scan_all_source_roots': {'queue': 'low'},
|
|
'backfill_gps': {'queue': 'low'},
|
|
# `watch_folders` is retired (file events come from NC webhooks)
|
|
# but the task definition still exists as a no-op shim for any
|
|
# in-flight apply_async. Route it to the default queue so the
|
|
# remaining worker actually drains it.
|
|
'watch_folders': {'queue': 'default'},
|
|
'discard_missing_photos_beat': {'queue': 'low'},
|
|
},
|
|
task_default_queue='default',
|
|
task_default_exchange='default',
|
|
task_default_exchange_type='direct',
|
|
task_default_routing_key='default',
|
|
broker_connection_retry_on_startup=True,
|
|
# Periodic catch-up so external file deletions in Nextcloud get
|
|
# reflected even when the real-time watcher missed the event
|
|
# (worker restart window, mount transient, etc).
|
|
beat_schedule={
|
|
'discard-missing-photos-every-30min': {
|
|
'task': 'discard_missing_photos_beat',
|
|
'schedule': 30 * 60,
|
|
},
|
|
},
|
|
)
|
|
|
|
|
|
@worker_process_init.connect
|
|
def _warmup_vision_models(**kwargs):
|
|
"""Pre-load vision models in the worker process so the first task
|
|
doesn't pay cold-start latency. Only runs on the vision queue."""
|
|
# The worker name contains the queue — only warm up vision workers.
|
|
worker_queues = os.environ.get("CELERY_QUEUES", "")
|
|
if "vision" not in worker_queues:
|
|
# Heuristic: check the celery command line for -Q vision
|
|
import sys
|
|
if "vision" not in " ".join(sys.argv):
|
|
return
|
|
try:
|
|
from app.services.vision.registry import registry
|
|
registry.warmup()
|
|
except Exception:
|
|
logger.exception("Vision model warmup failed") |