forked-synapse/synapse/replication/slave/storage/account_data.py
Erik Johnston 664409b169
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
2020-06-09 16:28:57 +01:00

61 lines
2.7 KiB
Python

# -*- coding: utf-8 -*-
# Copyright 2016 OpenMarket Ltd
# Copyright 2018 New Vector Ltd
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from synapse.replication.slave.storage._base import BaseSlavedStore
from synapse.replication.slave.storage._slaved_id_tracker import SlavedIdTracker
from synapse.storage.data_stores.main.account_data import AccountDataWorkerStore
from synapse.storage.data_stores.main.tags import TagsWorkerStore
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",
"stream_id",
extra_tables=[
("room_account_data", "stream_id"),
("room_tags_revisions", "stream_id"),
],
)
super(SlavedAccountDataStore, self).__init__(database, db_conn, hs)
def get_max_account_data_stream_id(self):
return self._account_data_id_gen.get_current_token()
def process_replication_rows(self, stream_name, instance_name, token, rows):
if stream_name == "tag_account_data":
self._account_data_id_gen.advance(token)
for row in rows:
self.get_tags_for_user.invalidate((row.user_id,))
self._account_data_stream_cache.entity_has_changed(row.user_id, token)
elif stream_name == "account_data":
self._account_data_id_gen.advance(token)
for row in rows:
if not row.room_id:
self.get_global_account_data_by_type_for_user.invalidate(
(row.data_type, row.user_id)
)
self.get_account_data_for_user.invalidate((row.user_id,))
self.get_account_data_for_room.invalidate((row.user_id, row.room_id))
self.get_account_data_for_room_and_type.invalidate(
(row.user_id, row.room_id, row.data_type)
)
self._account_data_stream_cache.entity_has_changed(row.user_id, token)
return super().process_replication_rows(stream_name, instance_name, token, rows)