From 664409b1694f102b3fd03d825ae82b31a4311560 Mon Sep 17 00:00:00 2001 From: Erik Johnston Date: Tue, 9 Jun 2020 16:28:57 +0100 Subject: Fix bug in account data replication stream. (#7656) * Ensure account data stream IDs are unique. The account data stream is shared between three tables, and the maximum allocated ID was tracked in a dedicated table. Updating the max ID happened outside the transaction that allocated the ID, leading to a race where if the server was restarted then the same ID could be allocated but the max ID failed to be updated, leading it to be reused. The ID generators have support for tracking across multiple tables, so we may as well use that instead of a dedicated table. * Fix bug in account data replication stream. If the same stream ID was used in both global and room account data then the getting updates for the replication stream would fail due to `heapq.merge(..)` trying to compare a `str` with a `None`. (This is because you'd have two rows like `(534, '!room')` and `(534, None)` from the room and global account data tables). Fix is just to order by stream ID, since we don't rely on the ordering beyond that. The bug where stream IDs can be reused should be fixed now, so this case shouldn't happen going forward. Fixes #7617 --- synapse/replication/slave/storage/account_data.py | 8 +++++++- synapse/replication/tcp/streams/_base.py | 10 ++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'synapse/replication') diff --git a/synapse/replication/slave/storage/account_data.py b/synapse/replication/slave/storage/account_data.py index 2a4f5c7cfd..9db6c62bc7 100644 --- a/synapse/replication/slave/storage/account_data.py +++ b/synapse/replication/slave/storage/account_data.py @@ -24,7 +24,13 @@ from synapse.storage.database import Database class SlavedAccountDataStore(TagsWorkerStore, AccountDataWorkerStore, BaseSlavedStore): def __init__(self, database: Database, db_conn, hs): self._account_data_id_gen = SlavedIdTracker( - db_conn, "account_data_max_stream_id", "stream_id" + db_conn, + "account_data", + "stream_id", + extra_tables=[ + ("room_account_data", "stream_id"), + ("room_tags_revisions", "stream_id"), + ], ) super(SlavedAccountDataStore, self).__init__(database, db_conn, hs) diff --git a/synapse/replication/tcp/streams/_base.py b/synapse/replication/tcp/streams/_base.py index d42aaff055..4acefc8a96 100644 --- a/synapse/replication/tcp/streams/_base.py +++ b/synapse/replication/tcp/streams/_base.py @@ -600,8 +600,14 @@ class AccountDataStream(Stream): for stream_id, user_id, room_id, account_data_type in room_results ) - # we need to return a sorted list, so merge them together. - updates = list(heapq.merge(room_rows, global_rows)) + # We need to return a sorted list, so merge them together. + # + # Note: We order only by the stream ID to work around a bug where the + # same stream ID could appear in both `global_rows` and `room_rows`, + # leading to a comparison between the data tuples. The comparison could + # fail due to attempting to compare the `room_id` which results in a + # `TypeError` from comparing a `str` vs `None`. + updates = list(heapq.merge(room_rows, global_rows, key=lambda row: row[0])) return updates, to_token, limited -- cgit 1.4.1