mirror of
https://github.com/scylladb/scylladb.git
synced 2026-04-27 03:45:11 +00:00
e314158708
If we are redefining the log table, we need to ensure any dropped
columns are registered in "dropped_columns" table, otherwise clients will not
be able to read data older than now.
Includes unit test.
Should probably be backported to all CDC enabled versions.
Fixes #10473
Closes #10474
(cherry picked from commit 78350a7e1b)
61 lines
2.5 KiB
Python
61 lines
2.5 KiB
Python
# Copyright 2021-present ScyllaDB
|
|
#
|
|
# This file is part of Scylla.
|
|
#
|
|
# Scylla 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.
|
|
#
|
|
# Scylla is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Affero General Public License
|
|
# along with Scylla. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
from cassandra.cluster import ConsistencyLevel
|
|
from cassandra.query import SimpleStatement
|
|
|
|
from util import new_test_table
|
|
from nodetool import flush
|
|
|
|
def test_cdc_log_entries_use_cdc_streams(scylla_only, cql, test_keyspace):
|
|
'''Test that the stream IDs chosen for CDC log entries come from the CDC generation
|
|
whose streams are listed in the streams description table. Since this test is executed
|
|
on a single-node cluster, there is only one generation.'''
|
|
|
|
schema = "pk int primary key"
|
|
extra = " with cdc = {'enabled': true}"
|
|
with new_test_table(cql, test_keyspace, schema, extra) as table:
|
|
stmt = cql.prepare(f"insert into {table} (pk) values (?) using timeout 5m")
|
|
for i in range(100):
|
|
cql.execute(stmt, [i])
|
|
|
|
log_stream_ids = set(r[0] for r in cql.execute(f'select "cdc$stream_id" from {table}_scylla_cdc_log'))
|
|
|
|
# There should be exactly one generation, so we just select the streams
|
|
streams_desc = cql.execute(SimpleStatement(
|
|
'select streams from system_distributed.cdc_streams_descriptions_v2',
|
|
consistency_level=ConsistencyLevel.ONE))
|
|
stream_ids = set()
|
|
for entry in streams_desc:
|
|
stream_ids.update(entry.streams)
|
|
|
|
assert(log_stream_ids.issubset(stream_ids))
|
|
|
|
|
|
# Test for #10473 - reading logs (from sstable) after dropping
|
|
# column in base.
|
|
def test_cdc_alter_table_drop_column(scylla_only, cql, test_keyspace):
|
|
schema = "pk int primary key, v int"
|
|
extra = " with cdc = {'enabled': true}"
|
|
with new_test_table(cql, test_keyspace, schema, extra) as table:
|
|
cql.execute(f"insert into {table} (pk, v) values (0, 0)")
|
|
cql.execute(f"insert into {table} (pk, v) values (1, null)")
|
|
flush(cql, table)
|
|
flush(cql, table + "_scylla_cdc_log")
|
|
cql.execute(f"alter table {table} drop v")
|
|
cql.execute(f"select * from {table}_scylla_cdc_log")
|