Added proper initialization sequence in the queue manager:

Sequential component initialization
Coordination through an _initialized event
Consistent lock hierarchy with _global_lock
Updated the base cog to properly initialize components:
Added timeout handling for queue manager initialization
Ensures queue manager is fully initialized before starting queue processing
Added proper error handling and cleanup
Established consistent lock ordering:
Global Lock -> Queue Lock -> Processing Lock
Prevents circular wait conditions
Each component respects the lock hierarchy
Improved task coordination:
Sequential initialization of components
Proper waiting for initialization before starting operations
Timeout handling for all async operations

videoarchiver/core/base.py

@@ -386,7 +386,20 @@ class VideoArchiver(GroupCog):
                 max_history_age=86400,
                 persistence_path=str(queue_path),
             )
-            logger.info("Queue manager initialized")
+            
+            # Initialize queue manager with timeout
+            try:
+                await asyncio.wait_for(
+                    self.queue_manager.initialize(),
+                    timeout=INIT_TIMEOUT
+                )
+                logger.info("Queue manager initialized successfully")
+            except asyncio.TimeoutError:
+                logger.error("Queue manager initialization timed out")
+                raise ProcessingError("Queue manager initialization timed out")
+            except Exception as e:
+                logger.error(f"Queue manager initialization failed: {e}")
+                raise
 
             # Initialize processor with queue manager and shared FFmpeg manager
             self.processor = VideoProcessor(
@@ -429,6 +442,7 @@ class VideoArchiver(GroupCog):
                 logger.warning("Update checker start timed out")
 
             # Start queue processing as a background task
+            # Only start after queue manager is fully initialized
             self._queue_task = asyncio.create_task(
                 self.queue_manager.process_queue(self.processor.process_video)
             )

videoarchiver/queue/manager.py

@@ -48,12 +48,14 @@ class EnhancedVideoQueueManager:
         self._channel_queues: Dict[int, Set[str]] = {}
         self._active_tasks: Set[asyncio.Task] = set()
         
-        # Locks
+        # Locks - Establish consistent ordering
-        self._queue_lock = asyncio.Lock()
+        self._global_lock = asyncio.Lock()  # Primary lock for coordinating all operations
-        self._processing_lock = asyncio.Lock()
+        self._queue_lock = asyncio.Lock()   # Secondary lock for queue operations
+        self._processing_lock = asyncio.Lock()  # Tertiary lock for processing operations
         
         # State
         self._shutdown = False
+        self._initialized = asyncio.Event()
         self.metrics = QueueMetrics()
 
         # Components
@@ -68,12 +70,17 @@ class EnhancedVideoQueueManager:
             max_history_age=max_history_age
         )
 
-        # Initialize tasks
+    async def initialize(self) -> None:
-        self._init_tasks()
+        """Initialize the queue manager components sequentially"""
+        try:
+            async with self._global_lock:
+                logger.info("Starting queue manager initialization...")
                 
-    def _init_tasks(self) -> None:
+                # Load persisted state first if available
-        """Initialize background tasks"""
+                if self.persistence:
-        # Start monitoring
+                    await self._load_persisted_state()
+                
+                # Start monitoring task
                 monitor_task = asyncio.create_task(
                     self.monitor.start_monitoring(
                         self._queue,
@@ -85,7 +92,10 @@ class EnhancedVideoQueueManager:
                 self._active_tasks.add(monitor_task)
                 logger.info("Queue monitoring started")
 
-        # Start cleanup
+                # Brief pause to allow monitor to initialize
+                await asyncio.sleep(0.1)
+                
+                # Start cleanup task
                 cleanup_task = asyncio.create_task(
                     self.cleaner.start_cleanup(
                         self._queue,
@@ -101,20 +111,28 @@ class EnhancedVideoQueueManager:
                 self._active_tasks.add(cleanup_task)
                 logger.info("Queue cleanup started")
 
-        # Load persisted state if available
+                # Signal initialization complete
-        if self.persistence:
+                self._initialized.set()
-            self._load_persisted_state()
+                logger.info("Queue manager initialization completed")
 
-    def _load_persisted_state(self) -> None:
+        except Exception as e:
+            logger.error(f"Failed to initialize queue manager: {e}")
+            self._shutdown = True
+            raise
+
+    async def _load_persisted_state(self) -> None:
         """Load persisted queue state"""
         try:
             state = self.persistence.load_queue_state()
             if state:
+                async with self._queue_lock:
                     self._queue = state["queue"]
-                self._processing = state["processing"]
                     self._completed = state["completed"]
                     self._failed = state["failed"]
                 
+                async with self._processing_lock:
+                    self._processing = state["processing"]
+
                 # Update metrics
                 metrics_data = state.get("metrics", {})
                 self.metrics.total_processed = metrics_data.get("total_processed", 0)
@@ -133,28 +151,32 @@ class EnhancedVideoQueueManager:
         self,
         processor: Callable[[QueueItem], Tuple[bool, Optional[str]]]
     ) -> None:
-        """Process items in the queue
+        """Process items in the queue"""
+        # Wait for initialization to complete
+        await self._initialized.wait()
         
-        Args:
-            processor: Function that processes queue items
-        """
         logger.info("Queue processor started")
         last_persist_time = time.time()
-        persist_interval = 60  # Persist state every 60 seconds instead of every operation
+        persist_interval = 60  # Persist state every 60 seconds
         
         while not self._shutdown:
             try:
-                # Process items in batches to avoid blocking
+                items = []
+                # Use global lock for coordination
+                async with self._global_lock:
+                    # Then acquire specific locks in order
                     async with self._queue_lock:
                         # Get up to 5 items from queue
-                    items = []
                         while len(items) < 5 and self._queue:
                             item = self._queue.pop(0)
-                        self._processing[item.url] = item
                             items.append(item)
                     
+                    if items:
+                        async with self._processing_lock:
+                            for item in items:
+                                self._processing[item.url] = item
+
                 if not items:
-                    # Use shorter sleep when queue is empty and yield control
                     await asyncio.sleep(0.1)
                     continue
 
@@ -164,30 +186,20 @@ class EnhancedVideoQueueManager:
                     task = asyncio.create_task(self._process_item(processor, item))
                     tasks.append(task)
                 
-                # Wait for all tasks to complete
                 await asyncio.gather(*tasks, return_exceptions=True)
 
                 # Persist state if interval has passed
                 current_time = time.time()
                 if self.persistence and (current_time - last_persist_time) >= persist_interval:
-                    await self.persistence.persist_queue_state(
+                    await self._persist_state()
-                        self._queue,
-                        self._processing,
-                        self._completed,
-                        self._failed,
-                        self.metrics
-                    )
                     last_persist_time = current_time
 
             except Exception as e:
                 logger.error(f"Critical error in queue processor: {e}")
-                await asyncio.sleep(0.1)  # Brief pause on error before retrying
+                await asyncio.sleep(0.1)
 
-            # Yield control after each batch
             await asyncio.sleep(0)
 
-        logger.info("Queue processor stopped")
-
     async def _process_item(
         self,
         processor: Callable[[QueueItem], Tuple[bool, Optional[str]]],
@@ -195,21 +207,22 @@ class EnhancedVideoQueueManager:
     ) -> None:
         """Process a single queue item"""
         try:
-            # Process the item
             logger.info(f"Processing queue item: {item.url}")
-            item.start_processing()  # Start processing tracking
+            item.start_processing()
-            self.metrics.last_activity_time = time.time()  # Update activity time
+            self.metrics.last_activity_time = time.time()
             
             success, error = await processor(item)
             
-            # Update metrics and status
+            async with self._global_lock:
                 async with self._processing_lock:
-                item.finish_processing(success, error)  # Update item status
+                    item.finish_processing(success, error)
+                    self._processing.pop(item.url, None)
                     
                     if success:
                         self._completed[item.url] = item
                         logger.info(f"Successfully processed: {item.url}")
                     else:
+                        async with self._queue_lock:
                             if item.retry_count < self.max_retries:
                                 item.retry_count += 1
                                 item.status = "pending"
@@ -221,9 +234,6 @@ class EnhancedVideoQueueManager:
                                 self._failed[item.url] = item
                                 logger.error(f"Failed after {self.max_retries} attempts: {item.url}")
                     
-                self._processing.pop(item.url, None)
-                
-                # Update metrics
                     self.metrics.update(
                         processing_time=item.processing_time,
                         success=success,
@@ -232,16 +242,34 @@ class EnhancedVideoQueueManager:
 
         except Exception as e:
             logger.error(f"Error processing {item.url}: {e}")
+            async with self._global_lock:
                 async with self._processing_lock:
                     item.finish_processing(False, str(e))
-                self._failed[item.url] = item
                     self._processing.pop(item.url, None)
+                    self._failed[item.url] = item
                     self.metrics.update(
                         processing_time=item.processing_time,
                         success=False,
                         error=str(e)
                     )
 
+    async def _persist_state(self) -> None:
+        """Persist current state to storage"""
+        if not self.persistence:
+            return
+            
+        try:
+            async with self._global_lock:
+                await self.persistence.persist_queue_state(
+                    self._queue,
+                    self._processing,
+                    self._completed,
+                    self._failed,
+                    self.metrics
+                )
+        except Exception as e:
+            logger.error(f"Failed to persist state: {e}")
+
     async def add_to_queue(
         self,
         url: str,
@@ -255,7 +283,10 @@ class EnhancedVideoQueueManager:
         if self._shutdown:
             raise QueueError("Queue manager is shutting down")
 
+        await self._initialized.wait()
+
         try:
+            async with self._global_lock:
                 async with self._queue_lock:
                     if len(self._queue) >= self.max_queue_size:
                         raise QueueError("Queue is full")
@@ -270,7 +301,6 @@ class EnhancedVideoQueueManager:
                         priority=priority,
                     )
 
-                # Add to tracking
                     if guild_id not in self._guild_queues:
                         self._guild_queues[guild_id] = set()
                     self._guild_queues[guild_id].add(url)
@@ -279,21 +309,13 @@ class EnhancedVideoQueueManager:
                         self._channel_queues[channel_id] = set()
                     self._channel_queues[channel_id].add(url)
 
-                # Add to queue with priority
                     self._queue.append(item)
                     self._queue.sort(key=lambda x: (-x.priority, x.added_at))
 
-                # Update activity time
                     self.metrics.last_activity_time = time.time()
 
                     if self.persistence:
-                    await self.persistence.persist_queue_state(
+                        await self._persist_state()
-                        self._queue,
-                        self._processing,
-                        self._completed,
-                        self._failed,
-                        self.metrics
-                    )
 
                     logger.info(f"Added to queue: {url} (priority: {priority})")
                     return True
@@ -350,38 +372,6 @@ class EnhancedVideoQueueManager:
                 },
             }
 
-    async def clear_guild_queue(self, guild_id: int) -> int:
-        """Clear all queue items for a guild"""
-        if self._shutdown:
-            raise QueueError("Queue manager is shutting down")
-
-        try:
-            cleared = await self.cleaner.clear_guild_queue(
-                guild_id,
-                self._queue,
-                self._processing,
-                self._completed,
-                self._failed,
-                self._guild_queues,
-                self._channel_queues,
-                self._queue_lock
-            )
-
-            if self.persistence:
-                await self.persistence.persist_queue_state(
-                    self._queue,
-                    self._processing,
-                    self._completed,
-                    self._failed,
-                    self.metrics
-                )
-
-            return cleared
-
-        except Exception as e:
-            logger.error(f"Error clearing guild queue: {e}")
-            raise QueueError(f"Failed to clear guild queue: {str(e)}")
-
     async def cleanup(self) -> None:
         """Clean up resources and stop queue processing"""
         try:
@@ -399,8 +389,9 @@ class EnhancedVideoQueueManager:
 
             await asyncio.gather(*self._active_tasks, return_exceptions=True)
 
+            async with self._global_lock:
                 # Move processing items back to queue
-            async with self._queue_lock:
+                async with self._processing_lock:
                     for url, item in self._processing.items():
                         if item.retry_count < self.max_retries:
                             item.status = "pending"
@@ -413,13 +404,7 @@ class EnhancedVideoQueueManager:
 
                 # Final state persistence
                 if self.persistence:
-                await self.persistence.persist_queue_state(
+                    await self._persist_state()
-                    self._queue,
-                    self._processing,
-                    self._completed,
-                    self._failed,
-                    self.metrics
-                )
 
                 # Clear collections
                 self._queue.clear()