feat: auto-start file watcher with Redis lock for live import
Re-enable the watchfiles-based folder watcher with a Redis lock to prevent multiple instances from stacking up across restarts. The watcher is now automatically dispatched on startup when scanner.watch is true (default), and only one instance runs at a time. - Redis lock (SETNX + TTL renewal) ensures single-instance execution - Graceful exit if another watcher holds the lock - New POST /maintenance/start-watcher endpoint for manual control - Fix: use settings.scanner/vision properties instead of mulita_config Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -840,4 +840,17 @@ async def trigger_backfill_phashes(current_user: User = Depends(get_current_user
|
||||
return {"status": "queued"}
|
||||
except Exception as e:
|
||||
logger.error(f"Backfill queue failed: {e}")
|
||||
return {"status": "error", "message": str(e)}
|
||||
|
||||
|
||||
@router.post("/maintenance/start-watcher")
|
||||
async def start_file_watcher(current_user: User = Depends(get_current_user)):
|
||||
"""Start the filesystem watcher. Uses a Redis lock so only one
|
||||
instance runs at a time — safe to call repeatedly."""
|
||||
from app.tasks.scan import watch_folders
|
||||
try:
|
||||
watch_folders.apply_async(countdown=2)
|
||||
return {"status": "queued"}
|
||||
except Exception as e:
|
||||
logger.error(f"Watcher queue failed: {e}")
|
||||
return {"status": "error", "message": str(e)}
|
||||
@@ -125,7 +125,7 @@ async def regroup_duplicates(
|
||||
|
||||
Idempotent — safe to call as often as you like. Returns a summary dict.
|
||||
"""
|
||||
embedder_model = settings.mulita_config.vision.embedder.name
|
||||
embedder_model = settings.vision.embedder.name
|
||||
|
||||
async with AsyncSessionLocal() as session:
|
||||
# Pull all visible photos with a phash or embedding.
|
||||
@@ -210,7 +210,7 @@ async def incremental_regroup(
|
||||
Much faster than a full regroup for post-scan updates:
|
||||
O(new × log N) via HNSW instead of O(N²).
|
||||
"""
|
||||
embedder_model = settings.mulita_config.vision.embedder.name
|
||||
embedder_model = settings.vision.embedder.name
|
||||
|
||||
async with AsyncSessionLocal() as session:
|
||||
# If no watermark, fall back to full regroup.
|
||||
|
||||
@@ -78,17 +78,26 @@ async def bootstrap_default_source_root() -> None:
|
||||
|
||||
|
||||
async def start_initial_scan():
|
||||
"""Start the initial library scan.
|
||||
"""Start the initial library scan and optionally the file watcher.
|
||||
|
||||
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".
|
||||
The file watcher uses a Redis lock to ensure only one instance runs
|
||||
across all workers, so it's safe to dispatch on every startup — only
|
||||
the first one will actually watch, the rest exit immediately.
|
||||
"""
|
||||
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}")
|
||||
|
||||
# Start the file watcher if enabled in config.
|
||||
from app.config import settings
|
||||
if settings.scanner.watch:
|
||||
try:
|
||||
from app.tasks.scan import watch_folders
|
||||
# Countdown gives the initial scan time to register source roots
|
||||
# before the watcher tries to load them.
|
||||
watch_folders.apply_async(countdown=10)
|
||||
logger.info("File watcher queued (Redis-locked, single instance)")
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not queue file watcher: {e}")
|
||||
|
||||
@@ -468,74 +468,96 @@ async def _scan_all_source_roots_async():
|
||||
logger.warning(f"Could not queue post-scan face recluster: {e}")
|
||||
|
||||
|
||||
@shared_task(name='watch_folders')
|
||||
def watch_folders():
|
||||
WATCHER_LOCK_KEY = "mulita:watch_folders:lock"
|
||||
WATCHER_LOCK_TTL = 300 # 5 min — renewed every 60s
|
||||
|
||||
|
||||
@shared_task(name='watch_folders', bind=True)
|
||||
def watch_folders(self):
|
||||
"""
|
||||
Watch folders for changes using watchfiles. Long-running task that
|
||||
monitors filesystem events under every active source root.
|
||||
|
||||
Uses a Redis lock to ensure only one instance runs across all
|
||||
workers. The lock is renewed periodically so it survives restarts
|
||||
without leaving orphan watchers.
|
||||
"""
|
||||
import redis as redis_lib
|
||||
from watchfiles import watch
|
||||
|
||||
# Read source roots from the DB instead of the (now-removed) YAML
|
||||
# config. We need both the path and the id so we can dispatch
|
||||
# scan_folder with the source_root_id when an event fires.
|
||||
roots: list[tuple[str, str]] = []
|
||||
r = redis_lib.from_url(settings.redis_url)
|
||||
|
||||
# Acquire exclusive lock — if another watcher is already running,
|
||||
# this instance exits immediately instead of stacking up.
|
||||
lock = r.lock(WATCHER_LOCK_KEY, timeout=WATCHER_LOCK_TTL)
|
||||
if not lock.acquire(blocking=False):
|
||||
logger.info("watch_folders: another instance is already running, exiting")
|
||||
return {'status': 'skipped', 'reason': 'another instance is running'}
|
||||
|
||||
try:
|
||||
async def _load_roots():
|
||||
async with AsyncSessionLocal() as session:
|
||||
result = await session.execute(
|
||||
select(SourceRoot).where(SourceRoot.is_active == True) # noqa: E712
|
||||
)
|
||||
return [
|
||||
(os.path.normpath(sr.path), sr.id)
|
||||
for sr in result.scalars().all()
|
||||
if os.path.exists(sr.path)
|
||||
]
|
||||
roots = asyncio.run(_load_roots())
|
||||
except Exception as e:
|
||||
logger.error(f"watch_folders could not load source roots: {e}")
|
||||
return
|
||||
|
||||
if not roots:
|
||||
logger.warning("No valid source roots to watch")
|
||||
return
|
||||
|
||||
paths = [p for p, _ in roots]
|
||||
logger.info(f"Starting folder watcher for: {paths}")
|
||||
|
||||
def find_source_root_for(path: str) -> Optional[str]:
|
||||
"""Return the source_root id whose path contains `path`, or None."""
|
||||
normalized = os.path.normpath(path)
|
||||
for root_path, root_id in roots:
|
||||
if normalized == root_path or normalized.startswith(root_path + os.sep):
|
||||
return root_id
|
||||
return None
|
||||
|
||||
for changes in watch(*paths):
|
||||
for change_type, filepath in changes:
|
||||
filepath = str(filepath)
|
||||
|
||||
# Check if it's a supported file type
|
||||
if Path(filepath).suffix.lower() not in SUPPORTED_EXTENSIONS:
|
||||
continue
|
||||
|
||||
if change_type == 'added' or change_type == 'modified':
|
||||
# Queue scan for the parent folder, with the source_root_id
|
||||
# resolved by ancestor lookup so scan_folder doesn't
|
||||
# auto-create a new SourceRoot for an arbitrary subdir.
|
||||
parent_dir = str(Path(filepath).parent)
|
||||
source_root_id = find_source_root_for(parent_dir)
|
||||
if source_root_id is None:
|
||||
logger.debug(
|
||||
f"watcher event for {filepath}: parent {parent_dir} "
|
||||
f"not under any active source root, ignoring"
|
||||
roots: list[tuple[str, str]] = []
|
||||
try:
|
||||
async def _load_roots():
|
||||
async with AsyncSessionLocal() as session:
|
||||
result = await session.execute(
|
||||
select(SourceRoot).where(SourceRoot.is_active == True) # noqa: E712
|
||||
)
|
||||
return [
|
||||
(os.path.normpath(sr.path), sr.id)
|
||||
for sr in result.scalars().all()
|
||||
if os.path.exists(sr.path)
|
||||
]
|
||||
roots = asyncio.run(_load_roots())
|
||||
except Exception as e:
|
||||
logger.error(f"watch_folders could not load source roots: {e}")
|
||||
return
|
||||
|
||||
if not roots:
|
||||
logger.warning("No valid source roots to watch")
|
||||
return
|
||||
|
||||
paths = [p for p, _ in roots]
|
||||
logger.info(f"Starting folder watcher for: {paths}")
|
||||
|
||||
def find_source_root_for(path: str) -> Optional[str]:
|
||||
"""Return the source_root id whose path contains `path`, or None."""
|
||||
normalized = os.path.normpath(path)
|
||||
for root_path, root_id in roots:
|
||||
if normalized == root_path or normalized.startswith(root_path + os.sep):
|
||||
return root_id
|
||||
return None
|
||||
|
||||
renew_counter = 0
|
||||
for changes in watch(*paths):
|
||||
# Renew the Redis lock periodically so it doesn't expire
|
||||
# while the watcher is idle between events.
|
||||
renew_counter += 1
|
||||
if renew_counter % 10 == 0:
|
||||
try:
|
||||
lock.extend(WATCHER_LOCK_TTL)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
for change_type, filepath in changes:
|
||||
filepath = str(filepath)
|
||||
|
||||
if Path(filepath).suffix.lower() not in SUPPORTED_EXTENSIONS:
|
||||
continue
|
||||
scan_folder.delay(parent_dir, source_root_id)
|
||||
logger.info(f"File {change_type}: {filepath}, queued scan for {parent_dir}")
|
||||
elif change_type == 'deleted':
|
||||
# Handle file deletion
|
||||
asyncio.run(handle_file_deletion(filepath))
|
||||
|
||||
if change_type == 'added' or change_type == 'modified':
|
||||
parent_dir = str(Path(filepath).parent)
|
||||
source_root_id = find_source_root_for(parent_dir)
|
||||
if source_root_id is None:
|
||||
continue
|
||||
scan_folder.delay(parent_dir, source_root_id)
|
||||
logger.info(f"File {change_type}: {filepath}, queued scan for {parent_dir}")
|
||||
elif change_type == 'deleted':
|
||||
asyncio.run(handle_file_deletion(filepath))
|
||||
finally:
|
||||
try:
|
||||
lock.release()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
async def handle_file_deletion(filepath: str):
|
||||
"""Handle deletion of a file from the filesystem"""
|
||||
|
||||
Reference in New Issue
Block a user