Merge remote-tracking branch 'origin/topic/awelzel/fix-flaky-terminate-while-queueing'

* origin/topic/awelzel/fix-flaky-terminate-while-queueing:
  cluster/websocket: Stop and wait for reply thread during Terminate()

CHANGES

@@ -1,3 +1,15 @@
+8.0.0-dev.50 | 2025-05-07 13:21:39 +0200
+
+  * cluster/websocket: Stop and wait for reply thread during Terminate() (Arne Welzel, Corelight)
+
+    The terminate-while-queueing test added for #4428 failed spuriously
+    indicating that sometimes WebSocket clients receive code 1000 instead of 1001.
+    This happens if the ixwebsocket server is shutdown before the reply thread had a
+    chance to process queued close messages.
+
+    Fix by signaling and waiting for the dispatcher's reply thread to terminate
+    before returning from Terminate().
+
 8.0.0-dev.46 | 2025-05-06 14:20:54 +0200
 
   * testing/btest: Fix double commented @TEST- lines (Arne Welzel, Corelight)

VERSION

@@ -1 +1 @@
-8.0.0-dev.46
+8.0.0-dev.50

src/cluster/websocket/WebSocket.cc

@@ -249,6 +249,11 @@ void WebSocketEventDispatcher::Terminate() {
     clients.clear();
 
     onloop->Close();
+
+    // Wait for the reply_msg_thread to process any outstanding
+    // WebSocketReply messages before returning.
+    reply_msg_thread->SignalStop();
+    reply_msg_thread->WaitForStop();
 }
 
 void WebSocketEventDispatcher::QueueForProcessing(WebSocketEvent&& event) {

testing/btest/cluster/websocket/terminate-while-queuing.zeek

@@ -89,7 +89,7 @@ def run(ws_url):
                     tc.send_json(wstest.build_event_v1("/test/pings/", "ping", [f"tc{idx}", i]))
                 except websockets.exceptions.ConnectionClosedOK as e:
                     print("connection closed ok")
-                    assert e.code == 1001  # Remote going away
+                    assert e.code == 1001, f"expected code 1001, got {e.code} - {e}"  # Remote going away
                     i -= 1
                     saw_closed_ok.add(idx)