Lock ZMQ sockets shared across threads (#24607)

* lock zmq sockets shared across threads

Several zmq sockets were used from more than one thread at a time, which zmq does not allow. In the embeddings process, GenAI review and object description threads shared one requestor, so overlapping calls silently dropped the second write and could eventually leave a thread waiting forever on a reply that had already arrived, after which nothing was saved until restart. The API's embeddings requestor had the same problem, concurrent config publishes could mix the topic of one update with the payload of another, and the webpush config subscribers were drained from every publishing thread, which could abort the process. Each socket now has a lock. The embeddings requestor lock does not wait, so an overlapping call still returns empty right away instead of stalling the API behind a slow reply.

* add test

frigate/comms/config_updater.py

@@ -1,6 +1,7 @@
 """Facilitates communication between processes."""
 
 import multiprocessing as mp
+import threading
 from _pickle import UnpicklingError
 from multiprocessing.synchronize import Event as MpEvent
 from typing import Any
@@ -18,11 +19,13 @@ class ConfigPublisher:
         self.socket = self.context.socket(zmq.PUB)
         self.socket.bind(SOCKET_PUB_SUB)
         self.stop_event: MpEvent = mp.Event()
+        self.lock = threading.Lock()
 
     def publish(self, topic: str, payload: Any) -> None:
         """There is no communication back to the processes."""
-        self.socket.send_string(topic, flags=zmq.SNDMORE)
-        self.socket.send_pyobj(payload)
+        with self.lock:
+            self.socket.send_string(topic, flags=zmq.SNDMORE)
+            self.socket.send_pyobj(payload)
 
     def stop(self) -> None:
         self.stop_event.set()

frigate/comms/embeddings_updater.py

@@ -1,6 +1,7 @@
 """Facilitates communication between processes."""
 
 import logging
+import threading
 from collections.abc import Callable
 from enum import Enum
 from typing import Any
@@ -78,14 +79,21 @@ class EmbeddingsRequestor:
         self.context = zmq.Context()
         self.socket = self.context.socket(zmq.REQ)
         self.socket.connect(SOCKET_REP_REQ)
+        self.lock = threading.Lock()
 
     def send_data(self, topic: str, data: Any) -> Any:
         """Sends data and then waits for reply."""
+        # an overlapping call fails fast so a slow reply can't stall the API
+        if not self.lock.acquire(blocking=False):
+            return ""
+
         try:
             self.socket.send_json((topic, data))
             return self.socket.recv_json()
         except zmq.ZMQError:
             return ""
+        finally:
+            self.lock.release()
 
     def stop(self) -> None:
         self.socket.close()

frigate/comms/inter_process.py

@@ -73,14 +73,16 @@ class InterProcessRequestor:
         self.context = zmq.Context()
         self.socket = self.context.socket(zmq.REQ)
         self.socket.connect(SOCKET_REP_REQ)
+        self.lock = threading.Lock()
 
     def send_data(self, topic: str, data: Any) -> Any:
         """Sends data and then waits for reply."""
-        try:
-            self.socket.send_json((topic, data))
-            return self.socket.recv_json()
-        except zmq.ZMQError:
-            return ""
+        with self.lock:
+            try:
+                self.socket.send_json((topic, data))
+                return self.socket.recv_json()
+            except zmq.ZMQError:
+                return ""
 
     def stop(self) -> None:
         self.socket.close(linger=0)

frigate/comms/webpush.py

@@ -70,6 +70,7 @@ class WebPushClient(Communicator):
             for c in self.config.cameras.values()
         }
         self.suspension_broadcaster: Callable[[str, Any, bool], None] | None = None
+        self.config_lock = threading.Lock()
         self.last_camera_notification_time: dict[str, float] = {
             c.name: 0  # type: ignore[misc]
             for c in self.config.cameras.values()
@@ -205,29 +206,30 @@ class WebPushClient(Communicator):
 
     def publish(self, topic: str, payload: Any, retain: bool = False) -> None:
         """Wrapper for publishing when client is in valid state."""
-        # check for updated global config (notifications, auth)
-        while True:
-            config_topic, config_payload = (
-                self.global_config_subscriber.check_for_update()
-            )
-            if config_topic is None:
-                break
-            if config_topic == "config/notifications" and config_payload:
-                self.config.notifications = config_payload
-            elif config_topic == "config/auth":
-                if isinstance(config_payload, AuthConfig):
-                    self.config.auth = config_payload
+        with self.config_lock:
+            # check for updated global config (notifications, auth)
+            while True:
+                config_topic, config_payload = (
+                    self.global_config_subscriber.check_for_update()
+                )
+                if config_topic is None:
+                    break
+                if config_topic == "config/notifications" and config_payload:
+                    self.config.notifications = config_payload
+                elif config_topic == "config/auth":
+                    if isinstance(config_payload, AuthConfig):
+                        self.config.auth = config_payload
+                    self._refresh_user_cameras()
+
+            updates = self.config_subscriber.check_for_updates()
+
+            if "add" in updates:
+                for camera in updates["add"]:
+                    self.suspended_cameras[camera] = 0
+                    self.last_camera_notification_time[camera] = 0
+
                 self._refresh_user_cameras()
 
-        updates = self.config_subscriber.check_for_updates()
-
-        if "add" in updates:
-            for camera in updates["add"]:
-                self.suspended_cameras[camera] = 0
-                self.last_camera_notification_time[camera] = 0
-
-            self._refresh_user_cameras()
-
         if topic == "reviews":
             decoded = json.loads(payload)
             camera = decoded["before"]["camera"]