From 84ce93c12f921063bb6c59400fcf95649a1b7f45 Mon Sep 17 00:00:00 2001
From: Erik Johnston <erik@matrix.org>
Date: Thu, 12 Jan 2023 10:29:09 +0000
Subject: [PATCH] Fix race calling `/members?at=` (#14817)

Fixes #14814
---
 changelog.d/14817.bugfix                 |  1 +
 synapse/storage/databases/main/stream.py | 65 +++++++++++++++++++++---
 2 files changed, 60 insertions(+), 6 deletions(-)
 create mode 100644 changelog.d/14817.bugfix

diff --git a/changelog.d/14817.bugfix b/changelog.d/14817.bugfix
new file mode 100644
index 000000000000..bb5da7926854
--- /dev/null
+++ b/changelog.d/14817.bugfix
@@ -0,0 +1 @@
+Fix race where calling `/members` or `/state` with an `at` parameter could fail for newly created rooms, when using multiple workers.
diff --git a/synapse/storage/databases/main/stream.py b/synapse/storage/databases/main/stream.py
index cc27ec38042b..63d835053019 100644
--- a/synapse/storage/databases/main/stream.py
+++ b/synapse/storage/databases/main/stream.py
@@ -801,13 +801,66 @@ async def get_last_event_in_room_before_stream_ordering(
             before this stream ordering.
         """
 
-        last_row = await self.get_room_event_before_stream_ordering(
-            room_id=room_id,
-            stream_ordering=end_token.stream,
+        def get_last_event_in_room_before_stream_ordering_txn(
+            txn: LoggingTransaction,
+        ) -> Optional[str]:
+            # We need to handle the fact that the stream tokens can be vector
+            # clocks. We do this by getting all rows between the minimum and
+            # maximum stream ordering in the token, plus one row less than the
+            # minimum stream ordering. We then filter the results against the
+            # token and return the first row that matches.
+
+            sql = """
+                SELECT * FROM (
+                    SELECT instance_name, stream_ordering, topological_ordering, event_id
+                    FROM events
+                    LEFT JOIN rejections USING (event_id)
+                    WHERE room_id = ?
+                        AND ? < stream_ordering AND stream_ordering <= ?
+                        AND NOT outlier
+                        AND rejections.event_id IS NULL
+                    ORDER BY stream_ordering DESC
+                ) AS a
+                UNION
+                SELECT * FROM (
+                    SELECT instance_name, stream_ordering, topological_ordering, event_id
+                    FROM events
+                    LEFT JOIN rejections USING (event_id)
+                    WHERE room_id = ?
+                        AND stream_ordering <= ?
+                        AND NOT outlier
+                        AND rejections.event_id IS NULL
+                    ORDER BY stream_ordering DESC
+                    LIMIT 1
+                ) AS b
+            """
+            txn.execute(
+                sql,
+                (
+                    room_id,
+                    end_token.stream,
+                    end_token.get_max_stream_pos(),
+                    room_id,
+                    end_token.stream,
+                ),
+            )
+
+            for instance_name, stream_ordering, topological_ordering, event_id in txn:
+                if _filter_results(
+                    lower_token=None,
+                    upper_token=end_token,
+                    instance_name=instance_name,
+                    topological_ordering=topological_ordering,
+                    stream_ordering=stream_ordering,
+                ):
+                    return event_id
+
+            return None
+
+        return await self.db_pool.runInteraction(
+            "get_last_event_in_room_before_stream_ordering",
+            get_last_event_in_room_before_stream_ordering_txn,
         )
-        if last_row:
-            return last_row[2]
-        return None
 
     async def get_current_room_stream_token_for_room_id(
         self, room_id: str