Improve performance of fetching event reports when there are many of them

synapse/storage/databases/main/room.py

@@ -1600,6 +1600,7 @@ class RoomWorkerStore(CacheInvalidationWorkerStore):
             count = cast(Tuple[int], txn.fetchone())[0]
 
             sql = """
+                WITH considered_event_reports AS (
                     SELECT
                         er.id,
                         er.received_ts,
@@ -1607,18 +1608,29 @@ class RoomWorkerStore(CacheInvalidationWorkerStore):
                         er.event_id,
                         er.user_id,
                         er.content,
-                    events.sender,
                         room_stats_state.canonical_alias,
                         room_stats_state.name
                     FROM event_reports AS er
-                LEFT JOIN events
-                    ON events.event_id = er.event_id
                     JOIN room_stats_state
                         ON room_stats_state.room_id = er.room_id
                     {where_clause}
                     ORDER BY er.received_ts {order}
                     LIMIT ?
                     OFFSET ?
+                )
+                -- only join on `events` after the LIMIT/OFFSET has been applied
+                SELECT
+                    cer.id,
+                    cer.received_ts,
+                    cer.room_id,
+                    cer.event_id,
+                    cer.user_id,
+                    cer.content,
+                    events.sender,
+                    cer.canonical_alias,
+                    cer.name
+                FROM considered_event_reports AS cer
+                LEFT JOIN events ON events.event_id = cer.event_id
             """.format(
                 where_clause=where_clause,
                 order=order,