Avoid event data serialization during recorder that we throw away (#41217)

We currently serialize the event data for state change events
and then replace it because we save the state in the states table.
Since the old state and new state are both contains in the event
the cost of serializing the data has a noticable impact when there
are many state changed events.

homeassistant/components/recorder/__init__.py

@@ -381,9 +381,10 @@ class Recorder(threading.Thread):
                     continue
 
             try:
-                dbevent = Events.from_event(event)
                 if event.event_type == EVENT_STATE_CHANGED:
-                    dbevent.event_data = "{}"
+                    dbevent = Events.from_event(event, event_data="{}")
+                else:
+                    dbevent = Events.from_event(event)
                 self.event_session.add(dbevent)
             except (TypeError, ValueError):
                 _LOGGER.warning("Event is not JSON serializable: %s", event)

homeassistant/components/recorder/models.py

@@ -60,11 +60,11 @@ class Events(Base):  # type: ignore
     )
 
     @staticmethod
-    def from_event(event):
+    def from_event(event, event_data=None):
         """Create an event database object from a native event."""
         return Events(
             event_type=event.event_type,
-            event_data=json.dumps(event.data, cls=JSONEncoder),
+            event_data=event_data or json.dumps(event.data, cls=JSONEncoder),
             origin=str(event.origin),
             time_fired=event.time_fired,
             context_id=event.context.id,

tests/components/recorder/test_models.py

@@ -19,6 +19,7 @@ from homeassistant.const import EVENT_STATE_CHANGED
 import homeassistant.core as ha
 from homeassistant.exceptions import InvalidEntityFormatError
 from homeassistant.util import dt
+import homeassistant.util.dt as dt_util
 
 ENGINE = None
 SESSION = None
@@ -241,3 +242,16 @@ async def test_process_timestamp_to_utc_isoformat():
         == "2016-07-09T21:31:00+00:00"
     )
     assert process_timestamp_to_utc_isoformat(None) is None
+
+
+async def test_event_to_db_model():
+    """Test we can round trip Event conversion."""
+    event = ha.Event(
+        "state_changed", {"some": "attr"}, ha.EventOrigin.local, dt_util.utcnow()
+    )
+    native = Events.from_event(event).to_native()
+    assert native == event
+
+    native = Events.from_event(event, event_data="{}").to_native()
+    event.data = {}
+    assert native == event