After updates

This commit is contained in:
Ryan Shpeherd
2026-09-08 13:51:31 -04:00
parent baa7ded329
commit 83f980f7f8
5 changed files with 409 additions and 11 deletions
+24 -1
View File
@@ -8,6 +8,7 @@ Initializes all components and starts the processing pipeline.
import logging
import signal
import sys
import threading
import time
from pathlib import Path
@@ -18,6 +19,7 @@ from config_loader import get_config
from db_connector import DBConnector
from logging_config import setup_logging
from orchestrator import WorkerPool
from scanner import DirectoryScanner
logger = logging.getLogger(__name__)
@@ -84,7 +86,27 @@ def main():
except ImportError:
logger.warning("PyTorch not installed. GPU features disabled.")
logger.info("Worker initialization complete. Starting processing loop...")
# Initialize the directory scanner.
# It scans the permanent storage location in place (no staging/copy step),
# periodically discovering new/removed video files and queueing any that
# have not been scanned yet as PENDING for the worker pool to pick up.
storage_config = config.get_section("storage")
scanner_config = config.get_section("scanner")
scanner = DirectoryScanner(
db_connector=db,
config=config.data,
input_path=storage_config.get("input_path", "/data/input"),
scan_interval=int(scanner_config.get("scan_interval_seconds", 60)),
walker_threads=int(scanner_config.get("walker_threads", 8)),
)
logger.info("Worker initialization complete. Starting scanner and processing loop...")
# Run the scanner in a background thread (its start() is a blocking loop).
scanner_thread = threading.Thread(
target=scanner.start, name="directory-scanner", daemon=True
)
scanner_thread.start()
pool = WorkerPool(db, config.data, max_workers=1)
@@ -93,6 +115,7 @@ def main():
except KeyboardInterrupt:
logger.info("Worker shutting down.")
pool.stop()
scanner.stop()
if __name__ == "__main__":
+157 -9
View File
@@ -10,9 +10,12 @@ import hashlib
import json
import logging
import os
import socket
import threading
import time
import uuid
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timezone
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Dict, List, Optional, Tuple
@@ -54,29 +57,164 @@ class DirectoryScanner:
self._total_files_modified = 0
self._total_files_unscannable = 0
# Single-instance guard: prevents overlapping scans both within this
# process (threading lock) and across replicas (DB lock with a lease).
self._instance_id = f"{socket.gethostname()}-{os.getpid()}-{uuid.uuid4().hex[:8]}"
self._lock_name = "directory_scanner"
self._lock_lease_seconds = int(
config.get("scanner", {}).get("lock_lease_seconds", 21600)
)
self._heartbeat_every = int(
config.get("scanner", {}).get("heartbeat_interval_files", 500)
)
self._scan_lock = threading.Lock()
self._lock_table_ensured = False
def start(self):
"""Start the scanner loop."""
"""Start the scanner loop.
Each cycle is guarded so that at most one scan runs at a time:
- an in-process threading lock prevents re-entrant scans, and
- a DB lock (with a lease) prevents overlapping scans across replicas.
A long-running scan keeps its lease alive via heartbeats, so the next
scheduled tick (or another replica) waits instead of starting a second
parallel scan.
"""
self._running = True
logger.info("Scanner starting: input_path=%s interval=%ds threads=%d",
self.input_path, self.scan_interval, self.walker_threads)
logger.info(
"Scanner starting: input_path=%s interval=%ds threads=%d instance=%s",
self.input_path, self.scan_interval, self.walker_threads, self._instance_id,
)
while self._running:
# In-process re-entrancy guard: never run two scans at once.
if not self._scan_lock.acquire(blocking=False):
logger.warning("A scan is already in progress; skipping this cycle.")
self._sleep_interval()
continue
try:
self._run_scan()
if self.acquire_lock():
try:
self._run_scan()
finally:
self.release_lock()
else:
logger.info(
"Scanner lock held by another instance; skipping this cycle."
)
except Exception as e:
logger.error("Scanner error: %s", e, exc_info=True)
finally:
self._scan_lock.release()
# Sleep until next scan
for _ in range(self.scan_interval):
if not self._running:
break
time.sleep(1)
self._sleep_interval()
def _sleep_interval(self):
"""Sleep for the scan interval, waking early if stopped."""
for _ in range(self.scan_interval):
if not self._running:
break
time.sleep(1)
def stop(self):
"""Stop the scanner."""
self._running = False
logger.info("Scanner stopping. Total scans: %d", self._scan_count)
# ------------------------------------------------------------------
# Single-instance lock (cross-process / cross-replica guard)
# ------------------------------------------------------------------
def _ensure_lock_table(self):
"""Create the scanner_lock table if it does not already exist."""
if self._lock_table_ensured:
return
self.db.execute(
"""CREATE TABLE IF NOT EXISTS scanner_lock (
lock_name VARCHAR(64) PRIMARY KEY,
owner VARCHAR(128) NOT NULL,
locked_at DATETIME NOT NULL,
lease_seconds INT NOT NULL DEFAULT 21600
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci"""
)
self._lock_table_ensured = True
def acquire_lock(self) -> bool:
"""Attempt to acquire the cross-process scanner lock.
Returns True if this instance now owns the lock, False otherwise.
A stale lock (held longer than the lease) is taken over so a crashed
scanner does not block scanning forever.
"""
try:
self._ensure_lock_table()
except Exception as e:
logger.warning("Could not ensure scanner_lock table: %s", e)
return True # fail-open: keep scanning rather than block entirely
now = datetime.now(timezone.utc).replace(tzinfo=None)
# 1) Try to insert a fresh lock row.
try:
self.db.execute(
"""INSERT INTO scanner_lock (lock_name, owner, locked_at, lease_seconds)
VALUES (%s, %s, %s, %s)""",
(self._lock_name, self._instance_id, now, self._lock_lease_seconds),
transaction=True,
)
logger.info("Acquired scanner lock (fresh). owner=%s", self._instance_id)
return True
except Exception:
# Row already exists -> fall through to steal-if-stale.
pass
# 2) Take over the lock if it is stale or already ours.
stale_before = now - timedelta(seconds=self._lock_lease_seconds)
try:
affected = self.db.execute(
"""UPDATE scanner_lock
SET owner = %s, locked_at = %s
WHERE lock_name = %s
AND (owner = %s OR locked_at < %s)""",
(self._instance_id, now, self._lock_name, self._instance_id, stale_before),
transaction=True,
)
if affected and affected > 0:
logger.info("Acquired scanner lock (stale takeover). owner=%s",
self._instance_id)
return True
except Exception as e:
logger.warning("Failed to check scanner lock: %s", e)
return True # fail-open
logger.info("Scanner lock held by another instance; not acquiring.")
return False
def release_lock(self):
"""Release the scanner lock if we own it."""
try:
self.db.execute(
"""DELETE FROM scanner_lock WHERE lock_name = %s AND owner = %s""",
(self._lock_name, self._instance_id),
transaction=True,
)
except Exception as e:
logger.warning("Failed to release scanner lock: %s", e)
def _heartbeat(self):
"""Refresh the lock lease so a long-running scan is not stolen."""
try:
now = datetime.now(timezone.utc).replace(tzinfo=None)
self.db.execute(
"""UPDATE scanner_lock SET locked_at = %s
WHERE lock_name = %s AND owner = %s""",
(now, self._lock_name, self._instance_id),
transaction=True,
)
except Exception as e:
logger.debug("Scanner lock heartbeat failed: %s", e)
def _run_scan(self):
"""Execute a single scan cycle."""
scan_start = time.time()
@@ -181,6 +319,7 @@ class DirectoryScanner:
def _process_files_batch(self, files: List[Path]) -> List[dict]:
"""Process a batch of files in parallel."""
results = []
processed = 0
with ThreadPoolExecutor(max_workers=self.walker_threads) as executor:
future_to_file = {
@@ -201,6 +340,11 @@ class DirectoryScanner:
"error_message": str(e),
})
processed += 1
# Keep the single-instance lock alive during long scans.
if self._heartbeat_every and processed % self._heartbeat_every == 0:
self._heartbeat()
return results
def _process_single_file(self, file_path: Path) -> dict:
@@ -384,6 +528,10 @@ class DirectoryScanner:
"total_files_new": self._total_files_new,
"total_files_modified": self._total_files_modified,
"total_files_unscannable": self._total_files_unscannable,
"instance_id": self._instance_id,
"scan_interval_seconds": self.scan_interval,
"lock_lease_seconds": self._lock_lease_seconds,
"scan_in_progress": self._scan_lock.locked(),
"input_path": str(self.input_path),
"is_running": self._running,
}