fix: harden single-machine load handling

server/topic.go

@@ -1348,7 +1348,9 @@ func (t *Topic) saveAndBroadcastMessage(msg *ClientComMessage, asUid types.Uid,
 	if t.cat == types.TopicCatGrp && msg.sess != nil && msg.sess.authLvl != auth.LevelRoot &&
 		store.GroupBusiness != nil && store.Store != nil && store.Store.IsOpen() {
 		access := pud.modeWant & pud.modeGiven
+		started := time.Now()
 		canPost, err := store.GroupBusiness.CanPost(t.tenantID, t.name, asUid, access.IsAdmin(), msg.Timestamp)
+		immetrics.ObserveMessagePublishStage("group", "permission_check", started, err)
 		if err != nil {
 			logs.Warn.Printf("topic[%s]: failed to check group mute policy: %v", t.name, err)
 			msg.sess.queueOut(ErrUnknown(msg.Id, t.original(asUid), msg.Timestamp))
@@ -1457,8 +1459,10 @@ func (t *Topic) saveAndBroadcastMessage(msg *ClientComMessage, asUid types.Uid,
 	// Tell the plugins that a message was accepted for delivery
 	pluginMessage(t.tenantID, data.Data, plgActCreate)
 
+	fanoutStarted := time.Now()
 	t.broadcastToSessions(data)
 	publishRealtimeTopicMessage(t.name, data)
+	immetrics.ObserveMessagePublishStage(kind, "realtime_fanout", fanoutStarted, nil)
 
 	// sendPush will update unread message count and send push notification.
 	if pushRcpt := t.pushForData(asUid, data.Data, markedReadBySender); pushRcpt != nil {