synapse/tests/storage/test__base.py

179 lines
5.5 KiB
Python
Raw Permalink Normal View History

#
2023-11-21 23:29:58 +03:00
# This file is licensed under the Affero General Public License (AGPL) version 3.
#
# Copyright 2015, 2016 OpenMarket Ltd
2023-11-21 23:29:58 +03:00
# Copyright (C) 2023 New Vector, Ltd
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# See the GNU Affero General Public License for more details:
# <https://www.gnu.org/licenses/agpl-3.0.html>.
#
# Originally licensed under the Apache License, Version 2.0:
# <http://www.apache.org/licenses/LICENSE-2.0>.
#
# [This file includes modifications made by New Vector Limited]
#
#
import secrets
from typing import Generator, List, Tuple, cast
from twisted.test.proto_helpers import MemoryReactor
from synapse.server import HomeServer
from synapse.util import Clock
2018-07-09 09:09:20 +03:00
from tests import unittest
class UpdateUpsertManyTests(unittest.HomeserverTestCase):
def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
self.storage = hs.get_datastores().main
2019-02-20 15:03:30 +03:00
self.table_name = "table_" + secrets.token_hex(6)
2019-02-20 15:03:30 +03:00
self.get_success(
self.storage.db_pool.runInteraction(
2019-02-20 15:03:30 +03:00
"create",
lambda x, *a: x.execute(*a),
"CREATE TABLE %s (id INTEGER, username TEXT, value TEXT)"
% (self.table_name,),
)
)
self.get_success(
self.storage.db_pool.runInteraction(
2019-02-20 15:03:30 +03:00
"index",
lambda x, *a: x.execute(*a),
"CREATE UNIQUE INDEX %sindex ON %s(id, username)"
% (self.table_name, self.table_name),
)
)
def _dump_table_to_tuple(self) -> Generator[Tuple[int, str, str], None, None]:
yield from cast(
List[Tuple[int, str, str]],
self.get_success(
self.storage.db_pool.simple_select_list(
self.table_name, None, ["id, username, value"]
)
),
)
def test_upsert_many(self) -> None:
2019-02-20 15:03:30 +03:00
"""
Upsert_many will perform the upsert operation across a batch of data.
"""
# Add some data to an empty table
key_names = ["id", "username"]
value_names = ["value"]
key_values = [[1, "user1"], [2, "user2"]]
value_values = [["hello"], ["there"]]
self.get_success(
self.storage.db_pool.runInteraction(
2019-02-20 15:03:30 +03:00
"test",
self.storage.db_pool.simple_upsert_many_txn,
2019-02-20 15:03:30 +03:00
self.table_name,
key_names,
key_values,
value_names,
value_values,
)
)
# Check results are what we expect
self.assertEqual(
set(self._dump_table_to_tuple()),
{(1, "user1", "hello"), (2, "user2", "there")},
2019-02-20 15:03:30 +03:00
)
# Update only user2
key_values = [[2, "user2"]]
value_values = [["bleb"]]
self.get_success(
self.storage.db_pool.runInteraction(
2019-02-20 15:03:30 +03:00
"test",
self.storage.db_pool.simple_upsert_many_txn,
2019-02-20 15:03:30 +03:00
self.table_name,
key_names,
key_values,
value_names,
value_values,
)
)
# Check results are what we expect
self.assertEqual(
set(self._dump_table_to_tuple()),
{(1, "user1", "hello"), (2, "user2", "bleb")},
)
Sliding Sync: Pre-populate room data for quick filtering/sorting (#17512) Pre-populate room data for quick filtering/sorting in the Sliding Sync API Spawning from https://github.com/element-hq/synapse/pull/17450#discussion_r1697335578 This PR is acting as the Synapse version `N+1` step in the gradual migration being tracked by https://github.com/element-hq/synapse/issues/17623 Adding two new database tables: - `sliding_sync_joined_rooms`: A table for storing room meta data that the local server is still participating in. The info here can be shared across all `Membership.JOIN`. Keyed on `(room_id)` and updated when the relevant room current state changes or a new event is sent in the room. - `sliding_sync_membership_snapshots`: A table for storing a snapshot of room meta data at the time of the local user's membership. Keyed on `(room_id, user_id)` and only updated when a user's membership in a room changes. Also adds background updates to populate these tables with all of the existing data. We want to have the guarantee that if a row exists in the sliding sync tables, we are able to rely on it (accurate data). And if a row doesn't exist, we use a fallback to get the same info until the background updates fill in the rows or a new event comes in triggering it to be fully inserted. This means we need a couple extra things in place until we bump `SCHEMA_COMPAT_VERSION` and run the foreground update in the `N+2` part of the gradual migration. For context on why we can't rely on the tables without these things see [1]. 1. On start-up, block until we clear out any rows for the rooms that have had events since the max-`stream_ordering` of the `sliding_sync_joined_rooms` table (compare to max-`stream_ordering` of the `events` table). For `sliding_sync_membership_snapshots`, we can compare to the max-`stream_ordering` of `local_current_membership` - This accounts for when someone downgrades their Synapse version and then upgrades it again. This will ensure that we don't have any stale/out-of-date data in the `sliding_sync_joined_rooms`/`sliding_sync_membership_snapshots` tables since any new events sent in rooms would have also needed to be written to the sliding sync tables. For example a new event needs to bump `event_stream_ordering` in `sliding_sync_joined_rooms` table or some state in the room changing (like the room name). Or another example of someone's membership changing in a room affecting `sliding_sync_membership_snapshots`. 1. Add another background update that will catch-up with any rows that were just deleted from the sliding sync tables (based on the activity in the `events`/`local_current_membership`). The rooms that need recalculating are added to the `sliding_sync_joined_rooms_to_recalculate` table. 1. Making sure rows are fully inserted. Instead of partially inserting, we need to check if the row already exists and fully insert all data if not. All of this extra functionality can be removed once the `SCHEMA_COMPAT_VERSION` is bumped with support for the new sliding sync tables so people can no longer downgrade (the `N+2` part of the gradual migration). <details> <summary><sup>[1]</sup></summary> For `sliding_sync_joined_rooms`, since we partially insert rows as state comes in, we can't rely on the existence of the row for a given `room_id`. We can't even rely on looking at whether the background update has finished. There could still be partial rows from when someone reverted their Synapse version after the background update finished, had some state changes (or new rooms), then upgraded again and more state changes happen leaving a partial row. For `sliding_sync_membership_snapshots`, we insert items as a whole except for the `forgotten` column ~~so we can rely on rows existing and just need to always use a fallback for the `forgotten` data. We can't use the `forgotten` column in the table for the same reasons above about `sliding_sync_joined_rooms`.~~ We could have an out-of-date membership from when someone reverted their Synapse version. (same problems as outlined for `sliding_sync_joined_rooms` above) Discussed in an [internal meeting](https://docs.google.com/document/d/1MnuvPkaCkT_wviSQZ6YKBjiWciCBFMd-7hxyCO-OCbQ/edit#bookmark=id.dz5x6ef4mxz7) </details> ### TODO - [x] Update `stream_ordering`/`bump_stamp` - [x] Handle remote invites - [x] Handle state resets - [x] Consider adding `sender` so we can filter `LEAVE` memberships and distinguish from kicks. - [x] We should add it to be able to tell leaves from kicks - [x] Consider adding `tombstone` state to help address https://github.com/element-hq/synapse/issues/17540 - [x] We should add it `tombstone_successor_room_id` - [x] Consider adding `forgotten` status to avoid extra lookup/table-join on `room_memberships` - [x] We should add it - [x] Background update to fill in values for all joined rooms and non-join membership - [x] Clean-up tables when room is deleted - [ ] Make sure tables are useful to our use case - First explored in https://github.com/element-hq/synapse/compare/erikj/ss_use_new_tables - Also explored in https://github.com/element-hq/synapse/commit/76b5a576eb363496315dfd39510cad7d02b0fc73 - [x] Plan for how can we use this with a fallback - See plan discussed above in main area of the issue description - Discussed in an [internal meeting](https://docs.google.com/document/d/1MnuvPkaCkT_wviSQZ6YKBjiWciCBFMd-7hxyCO-OCbQ/edit#bookmark=id.dz5x6ef4mxz7) - [x] Plan for how we can rely on this new table without a fallback - Synapse version `N+1`: (this PR) Bump `SCHEMA_VERSION` to `87`. Add new tables and background update to backfill all rows. Since this is a new table, we don't have to add any `NOT VALID` constraints and validate them when the background update completes. Read from new tables with a fallback in cases where the rows aren't filled in yet. - Synapse version `N+2`: Bump `SCHEMA_VERSION` to `88` and bump `SCHEMA_COMPAT_VERSION` to `87` because we don't want people to downgrade and miss writes while they are on an older version. Add a foreground update to finish off the backfill so we can read from new tables without the fallback. Application code can now rely on the new tables being populated. - Discussed in an [internal meeting](https://docs.google.com/document/d/1MnuvPkaCkT_wviSQZ6YKBjiWciCBFMd-7hxyCO-OCbQ/edit#bookmark=id.hh7shg4cxdhj) ### Dev notes ``` SYNAPSE_TEST_LOG_LEVEL=INFO poetry run trial tests.storage.test_events.SlidingSyncPrePopulatedTablesTestCase SYNAPSE_POSTGRES=1 SYNAPSE_POSTGRES_USER=postgres SYNAPSE_TEST_LOG_LEVEL=INFO poetry run trial tests.storage.test_events.SlidingSyncPrePopulatedTablesTestCase ``` ``` SYNAPSE_TEST_LOG_LEVEL=INFO poetry run trial tests.handlers.test_sliding_sync.FilterRoomsTestCase ``` Reference: - [Development docs on background updates and worked examples of gradual migrations ](https://github.com/element-hq/synapse/blob/1dfa59b238cee0dc62163588cc9481896c288979/docs/development/database_schema.md#background-updates) - A real example of a gradual migration: https://github.com/matrix-org/synapse/pull/15649#discussion_r1213779514 - Adding `rooms.creator` field that needed a background update to backfill data, https://github.com/matrix-org/synapse/pull/10697 - Adding `rooms.room_version` that needed a background update to backfill data, https://github.com/matrix-org/synapse/pull/6729 - Adding `room_stats_state.room_type` that needed a background update to backfill data, https://github.com/matrix-org/synapse/pull/13031 - Tables from MSC2716: `insertion_events`, `insertion_event_edges`, `insertion_event_extremities`, `batch_events` - `current_state_events` updated in `synapse/storage/databases/main/events.py` --- ``` persist_event (adds to queue) _persist_event_batch _persist_events_and_state_updates (assigns `stream_ordering` to events) _persist_events_txn _store_event_txn _update_metadata_tables_txn _store_room_members_txn _update_current_state_txn ``` --- > Concatenated Indexes [...] (also known as multi-column, composite or combined index) > > [...] key consists of multiple columns. > > We can take advantage of the fact that the first index column is always usable for searching > > *-- https://use-the-index-luke.com/sql/where-clause/the-equals-operator/concatenated-keys* --- Dealing with `portdb` (`synapse/_scripts/synapse_port_db.py`), https://github.com/element-hq/synapse/pull/17512#discussion_r1725998219 --- <details> <summary>SQL queries:</summary> Both of these are equivalent and work in SQLite and Postgres Options 1: ```sql WITH data_table (room_id, user_id, membership_event_id, membership, event_stream_ordering, {", ".join(insert_keys)}) AS ( VALUES ( ?, ?, ?, (SELECT membership FROM room_memberships WHERE event_id = ?), (SELECT stream_ordering FROM events WHERE event_id = ?), {", ".join("?" for _ in insert_values)} ) ) INSERT INTO sliding_sync_non_join_memberships (room_id, user_id, membership_event_id, membership, event_stream_ordering, {", ".join(insert_keys)}) SELECT * FROM data_table WHERE membership != ? ON CONFLICT (room_id, user_id) DO UPDATE SET membership_event_id = EXCLUDED.membership_event_id, membership = EXCLUDED.membership, event_stream_ordering = EXCLUDED.event_stream_ordering, {", ".join(f"{key} = EXCLUDED.{key}" for key in insert_keys)} ``` Option 2: ```sql INSERT INTO sliding_sync_non_join_memberships (room_id, user_id, membership_event_id, membership, event_stream_ordering, {", ".join(insert_keys)}) SELECT column1 as room_id, column2 as user_id, column3 as membership_event_id, column4 as membership, column5 as event_stream_ordering, {", ".join("column" + str(i) for i in range(6, 6 + len(insert_keys)))} FROM ( VALUES ( ?, ?, ?, (SELECT membership FROM room_memberships WHERE event_id = ?), (SELECT stream_ordering FROM events WHERE event_id = ?), {", ".join("?" for _ in insert_values)} ) ) as v WHERE membership != ? ON CONFLICT (room_id, user_id) DO UPDATE SET membership_event_id = EXCLUDED.membership_event_id, membership = EXCLUDED.membership, event_stream_ordering = EXCLUDED.event_stream_ordering, {", ".join(f"{key} = EXCLUDED.{key}" for key in insert_keys)} ``` If we don't need the `membership` condition, we could use: ```sql INSERT INTO sliding_sync_non_join_memberships (room_id, membership_event_id, user_id, membership, event_stream_ordering, {", ".join(insert_keys)}) VALUES ( ?, ?, ?, (SELECT membership FROM room_memberships WHERE event_id = ?), (SELECT stream_ordering FROM events WHERE event_id = ?), {", ".join("?" for _ in insert_values)} ) ON CONFLICT (room_id, user_id) DO UPDATE SET membership_event_id = EXCLUDED.membership_event_id, membership = EXCLUDED.membership, event_stream_ordering = EXCLUDED.event_stream_ordering, {", ".join(f"{key} = EXCLUDED.{key}" for key in insert_keys)} ``` </details> ### Pull Request Checklist <!-- Please read https://element-hq.github.io/synapse/latest/development/contributing_guide.html before submitting your pull request --> * [x] Pull request is based on the develop branch * [x] Pull request includes a [changelog file](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#changelog). The entry should: - Be a short description of your change which makes sense to users. "Fixed a bug that prevented receiving messages from other servers." instead of "Moved X method from `EventStore` to `EventWorkerStore`.". - Use markdown where necessary, mostly for `code blocks`. - End with either a period (.) or an exclamation mark (!). - Start with a capital letter. - Feel free to credit yourself, by adding a sentence "Contributed by @github_username." or "Contributed by [Your Name]." to the end of the entry. * [x] [Code style](https://element-hq.github.io/synapse/latest/code_style.html) is correct (run the [linters](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#run-the-linters)) --------- Co-authored-by: Erik Johnston <erik@matrix.org>
2024-08-29 18:09:51 +03:00
self.get_success(
self.storage.db_pool.runInteraction(
"test",
self.storage.db_pool.simple_upsert_many_txn,
self.table_name,
key_names=key_names,
key_values=[[2, "user2"]],
value_names=[],
value_values=[],
)
)
# Check results are what we expect
self.assertEqual(
set(self._dump_table_to_tuple()),
{(1, "user1", "hello"), (2, "user2", "bleb")},
)
def test_simple_update_many(self) -> None:
"""
simple_update_many performs many updates at once.
"""
# First add some data.
self.get_success(
self.storage.db_pool.simple_insert_many(
table=self.table_name,
keys=("id", "username", "value"),
values=[(1, "alice", "A"), (2, "bob", "B"), (3, "charlie", "C")],
desc="insert",
2019-02-20 15:03:30 +03:00
)
)
# Check the data made it to the table
2019-02-20 15:03:30 +03:00
self.assertEqual(
set(self._dump_table_to_tuple()),
{(1, "alice", "A"), (2, "bob", "B"), (3, "charlie", "C")},
)
# Now use simple_update_many
self.get_success(
self.storage.db_pool.simple_update_many(
table=self.table_name,
key_names=("username",),
key_values=(
("alice",),
("bob",),
("stranger",),
),
value_names=("value",),
value_values=(
("aaa!",),
("bbb!",),
("???",),
),
desc="update_many1",
)
)
# Check the table is how we expect:
# charlie has been left alone
self.assertEqual(
set(self._dump_table_to_tuple()),
{(1, "alice", "aaa!"), (2, "bob", "bbb!"), (3, "charlie", "C")},
2019-02-20 15:03:30 +03:00
)