From 1d1e8a5634281c4bc931527575ebf0679d6df880 Mon Sep 17 00:00:00 2001
From: "Olivier Wilkinson (reivilibre)" <oliverw@matrix.org>
Date: Fri, 10 Nov 2023 14:01:08 +0000
Subject: [PATCH 1/2] Improve performance of fetching event reports when there
 are many of them

---
 synapse/storage/databases/main/room.py | 46 ++++++++++++++++----------
 1 file changed, 29 insertions(+), 17 deletions(-)

diff --git a/synapse/storage/databases/main/room.py b/synapse/storage/databases/main/room.py
index ef26d5d9d37e..851ed83caacf 100644
--- a/synapse/storage/databases/main/room.py
+++ b/synapse/storage/databases/main/room.py
@@ -1600,25 +1600,37 @@ def _get_event_reports_paginate_txn(
             count = cast(Tuple[int], txn.fetchone())[0]
 
             sql = """
+                WITH considered_event_reports AS (
+                    SELECT
+                        er.id,
+                        er.received_ts,
+                        er.room_id,
+                        er.event_id,
+                        er.user_id,
+                        er.content,
+                        room_stats_state.canonical_alias,
+                        room_stats_state.name
+                    FROM event_reports AS er
+                    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
-                    er.id,
-                    er.received_ts,
-                    er.room_id,
-                    er.event_id,
-                    er.user_id,
-                    er.content,
+                    cer.id,
+                    cer.received_ts,
+                    cer.room_id,
+                    cer.event_id,
+                    cer.user_id,
+                    cer.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 ?
+                    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,

From 660807bb6ef5800f9668f7092276733ddf5249af Mon Sep 17 00:00:00 2001
From: "Olivier Wilkinson (reivilibre)" <oliverw@matrix.org>
Date: Fri, 10 Nov 2023 14:04:31 +0000
Subject: [PATCH 2/2] Newsfile

Signed-off-by: Olivier Wilkinson (reivilibre) <oliverw@matrix.org>
---
 changelog.d/16620.misc | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 changelog.d/16620.misc

diff --git a/changelog.d/16620.misc b/changelog.d/16620.misc
new file mode 100644
index 000000000000..e6388f3a1848
--- /dev/null
+++ b/changelog.d/16620.misc
@@ -0,0 +1 @@
+Improve the performance of fetching event reports over the admin API when there are many of them and the requester has paginated far down the list.
\ No newline at end of file