dtoro
db37be902e
Diagnosis: every backend restart was dispatching watch_folders.delay() unconditionally. watch_folders is an infinite-loop celery task (for changes in watch(*paths)). With CELERYD_CONCURRENCY=4 and several restarts during dev, all four worker slots ended up pinned by stale watch_folders instances, leaving zero workers free for scan_folder. The result: clicking "Scan all folders" successfully queued a task that then sat in the queue forever, the new /photos/sub folder was never walked, and the user's newly added photo never appeared. The watcher was only opportunistically useful and the user already triggers scans manually. Disabling it removes the foot-gun. Re- enabling needs: - a Redis lock so only one watcher runs at a time - or a dedicated long-running container with concurrency=1 - or a celery beat schedule with a singleton flag Until then, manual scans work. Cleared the backlog by wiping the redis broker volume so the stale watch_folders tasks are gone. Verified: post-fix, scan_folder runs in 0.12s and reports "Processed 7/7 files. Errors: 0", picking up the previously missing /photos/sub/Samuel_Colman... file. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
66 lines
2.3 KiB
Python
66 lines
2.3 KiB
Python
"""
|
|
Scanner service for initial library scan and one-time bootstrap of the
|
|
default source root on first boot.
|
|
"""
|
|
import os
|
|
import logging
|
|
from sqlalchemy import select
|
|
|
|
from app.database import AsyncSessionLocal
|
|
from app.models import SourceRoot
|
|
from app.tasks.scan import scan_all_source_roots
|
|
from app.config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# The single host → container mount path. The compose file mounts whatever
|
|
# the user set as PHOTO_DIRS at this path.
|
|
DEFAULT_LIBRARY_PATH = "/photos"
|
|
DEFAULT_LIBRARY_NAME = "Library"
|
|
|
|
|
|
async def bootstrap_default_source_root() -> None:
|
|
"""If no source roots exist in the DB, create one pointing at the default
|
|
library mount. Lets a fresh install pick up photos with zero
|
|
configuration: the user only needs to set PHOTO_DIRS in .env.
|
|
"""
|
|
if not os.path.isdir(DEFAULT_LIBRARY_PATH):
|
|
logger.warning(
|
|
f"Default library path {DEFAULT_LIBRARY_PATH} is not mounted; "
|
|
"set PHOTO_DIRS in .env and recreate the container."
|
|
)
|
|
return
|
|
|
|
async with AsyncSessionLocal() as session:
|
|
result = await session.execute(select(SourceRoot))
|
|
if result.scalars().first() is not None:
|
|
return # Already have at least one source root, leave it alone.
|
|
|
|
source_root = SourceRoot(
|
|
name=DEFAULT_LIBRARY_NAME,
|
|
path=DEFAULT_LIBRARY_PATH,
|
|
)
|
|
session.add(source_root)
|
|
await session.commit()
|
|
logger.info(
|
|
f"Bootstrapped default source root: {DEFAULT_LIBRARY_NAME} → "
|
|
f"{DEFAULT_LIBRARY_PATH}"
|
|
)
|
|
|
|
|
|
async def start_initial_scan():
|
|
"""Start the initial library scan.
|
|
|
|
NOTE: the folder watcher (watch_folders task) is intentionally NOT
|
|
dispatched here. It's an infinite loop celery task and every backend
|
|
restart was queuing a new instance, eventually pinning every worker
|
|
and starving scan_folder dispatches. Re-enabling it needs a Redis
|
|
lock or a dedicated long-running container — until then the user
|
|
triggers scans manually via "Scan all folders".
|
|
"""
|
|
try:
|
|
scan_all_source_roots.delay()
|
|
logger.info("Initial scan queued successfully")
|
|
except Exception as e:
|
|
logger.error(f"Failed to start initial scan: {e}")
|