ClickHouse/tests/integration/test_distributed_ddl_on_cross_replication/test.py

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

172 lines
6.6 KiB
Python
Raw Normal View History

import pytest
from helpers.cluster import ClickHouseCluster
from helpers.test_tools import assert_eq_with_retry
cluster = ClickHouseCluster(__file__)
node1 = cluster.add_instance(
"node1",
main_configs=["configs/remote_servers.xml"],
2022-07-21 18:32:33 +00:00
user_configs=["configs/settings.xml"],
with_zookeeper=True,
macros={"shard": 1, "replica": 1, "shard_bk": 3, "replica_bk": 2},
)
node2 = cluster.add_instance(
"node2",
main_configs=["configs/remote_servers.xml"],
2022-07-21 18:32:33 +00:00
user_configs=["configs/settings.xml"],
with_zookeeper=True,
macros={"shard": 2, "replica": 1, "shard_bk": 1, "replica_bk": 2},
)
node3 = cluster.add_instance(
"node3",
main_configs=["configs/remote_servers.xml"],
2022-07-21 18:32:33 +00:00
user_configs=["configs/settings.xml"],
with_zookeeper=True,
macros={"shard": 3, "replica": 1, "shard_bk": 2, "replica_bk": 2},
)
@pytest.fixture(scope="module")
def started_cluster():
try:
cluster.start()
node1.query(
"""
2020-06-16 18:07:41 +00:00
CREATE DATABASE replica_1 ON CLUSTER cross_3shards_2replicas;
CREATE DATABASE replica_2 ON CLUSTER cross_3shards_2replicas;
2021-05-10 22:54:52 +00:00
CREATE TABLE replica_1.replicated_local
2020-06-16 18:07:41 +00:00
ON CLUSTER cross_3shards_2replicas (part_key Date, id UInt32, shard_id UInt32)
2021-05-10 22:54:52 +00:00
ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/replicated', '{replica}')
2020-06-16 18:07:41 +00:00
partition by part_key order by id;
2021-05-10 22:54:52 +00:00
CREATE TABLE replica_1.replicated
ON CLUSTER cross_3shards_2replicas as replica_1.replicated_local
2020-06-16 18:07:41 +00:00
ENGINE = Distributed(cross_3shards_2replicas, '', replicated_local, shard_id);
2021-05-10 22:54:52 +00:00
CREATE TABLE replica_2.replicated_local
2020-06-16 18:07:41 +00:00
ON CLUSTER cross_3shards_2replicas (part_key Date, id UInt32, shard_id UInt32)
2021-05-10 22:54:52 +00:00
ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard_bk}/replicated', '{replica_bk}')
2020-06-16 18:07:41 +00:00
partition by part_key order by id;
2021-05-10 22:54:52 +00:00
CREATE TABLE replica_2.replicated
ON CLUSTER cross_3shards_2replicas as replica_2.replicated_local
2020-06-16 18:07:41 +00:00
ENGINE = Distributed(cross_3shards_2replicas, '', replicated_local, shard_id);
"""
2020-06-16 18:07:41 +00:00
)
to_insert = """\
2017-06-16 10 0
2017-06-17 11 0
2017-06-16 20 1
2017-06-17 21 1
2017-06-16 30 2
2017-06-17 31 2
"""
node1.query(
"INSERT INTO replica_1.replicated FORMAT TSV",
stdin=to_insert,
Rename directory monitor concept into background INSERT (#55978) * Limit log frequence for "Skipping send data over distributed table" message After SYSTEM STOP DISTRIBUTED SENDS it will constantly print this message. Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename directory monitor concept into async INSERT Rename the following query settings (with preserving backward compatiblity, by keeping old name as an alias): - distributed_directory_monitor_sleep_time_ms -> distributed_async_insert_sleep_time_ms - distributed_directory_monitor_max_sleep_time_ms -> distributed_async_insert_max_sleep_time_ms - distributed_directory_monitor_batch -> distributed_async_insert_batch_inserts - distributed_directory_monitor_split_batch_on_failure -> distributed_async_insert_split_batch_on_failure Rename the following table settings (with preserving backward compatiblity, by keeping old name as an alias): - monitor_batch_inserts -> async_insert_batch - monitor_split_batch_on_failure -> async_insert_split_batch_on_failure - directory_monitor_sleep_time_ms -> async_insert_sleep_time_ms - directory_monitor_max_sleep_time_ms -> async_insert_max_sleep_time_ms And also update all the references: $ gg -e directory_monitor_ -e monitor_ tests docs | cut -d: -f1 | sort -u | xargs sed -e 's/distributed_directory_monitor_sleep_time_ms/distributed_async_insert_sleep_time_ms/g' -e 's/distributed_directory_monitor_max_sleep_time_ms/distributed_async_insert_max_sleep_time_ms/g' -e 's/distributed_directory_monitor_batch_inserts/distributed_async_insert_batch/g' -e 's/distributed_directory_monitor_split_batch_on_failure/distributed_async_insert_split_batch_on_failure/g' -e 's/monitor_batch_inserts/async_insert_batch/g' -e 's/monitor_split_batch_on_failure/async_insert_split_batch_on_failure/g' -e 's/monitor_sleep_time_ms/async_insert_sleep_time_ms/g' -e 's/monitor_max_sleep_time_ms/async_insert_max_sleep_time_ms/g' -i Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Rename async_insert for Distributed into background_insert This will avoid amigibuity between general async INSERT's and INSERT into Distributed, which are indeed background, so new term express it even better. Mostly done with: $ git di HEAD^ --name-only | xargs sed -i -e 's/distributed_async_insert/distributed_background_insert/g' -e 's/async_insert_batch/background_insert_batch/g' -e 's/async_insert_split_batch_on_failure/background_insert_split_batch_on_failure/g' -e 's/async_insert_sleep_time_ms/background_insert_sleep_time_ms/g' -e 's/async_insert_max_sleep_time_ms/background_insert_max_sleep_time_ms/g' Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> * Mark 02417_opentelemetry_insert_on_distributed_table as long CI: https://s3.amazonaws.com/clickhouse-test-reports/55978/7a6abb03a0b507e29e999cb7e04f246a119c6f28/stateless_tests_flaky_check__asan_.html Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com> --------- Signed-off-by: Azat Khuzhin <a.khuzhin@semrush.com>
2023-11-01 14:09:39 +00:00
settings={"distributed_foreground_insert": 1},
)
yield cluster
finally:
2020-06-16 18:07:41 +00:00
# pass
cluster.shutdown()
def test_alter_ddl(started_cluster):
2020-06-16 18:07:41 +00:00
node1.query(
"ALTER TABLE replica_1.replicated_local \
ON CLUSTER cross_3shards_2replicas \
UPDATE shard_id=shard_id+3 \
WHERE part_key='2017-06-16'"
)
node1.query("SYSTEM SYNC REPLICA replica_2.replicated_local;", timeout=5)
assert_eq_with_retry(
node1,
"SELECT count(*) FROM replica_2.replicated where shard_id >= 3 and part_key='2017-06-16'",
"3",
)
2020-06-16 18:07:41 +00:00
node1.query(
"ALTER TABLE replica_1.replicated_local \
ON CLUSTER cross_3shards_2replicas DELETE WHERE shard_id >=3;"
)
node1.query("SYSTEM SYNC REPLICA replica_2.replicated_local;", timeout=5)
assert_eq_with_retry(
node1, "SELECT count(*) FROM replica_2.replicated where shard_id >= 3", "0"
)
2020-06-16 18:07:41 +00:00
node2.query(
"ALTER TABLE replica_1.replicated_local ON CLUSTER cross_3shards_2replicas DROP PARTITION '2017-06-17'"
)
node2.query("SYSTEM SYNC REPLICA replica_2.replicated_local;", timeout=5)
assert_eq_with_retry(node1, "SELECT count(*) FROM replica_2.replicated", "0")
def test_atomic_database(started_cluster):
node1.query(
"""DROP DATABASE IF EXISTS replica_1 ON CLUSTER cross_3shards_2replicas;
DROP DATABASE IF EXISTS replica_2 ON CLUSTER cross_3shards_2replicas;
CREATE DATABASE replica_1 ON CLUSTER cross_3shards_2replicas ENGINE=Atomic;
CREATE DATABASE replica_2 ON CLUSTER cross_3shards_2replicas ENGINE=Atomic;"""
)
assert "It's not supported for cross replication" in node1.query_and_get_error(
"CREATE TABLE rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree ORDER BY n"
)
assert "It's not supported for cross replication" in node1.query_and_get_error(
"CREATE TABLE replica_1.rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree ORDER BY n"
)
assert "It's not supported for cross replication" in node1.query_and_get_error(
"CREATE TABLE rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree('/{shard}/{uuid}/', '{replica}') ORDER BY n"
)
assert "It's not supported for cross replication" in node1.query_and_get_error(
"CREATE TABLE replica_2.rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree('/{shard}/{uuid}/', '{replica}') ORDER BY n"
)
assert (
"For a distributed DDL on circular replicated cluster its table name must be qualified by database name"
in node1.query_and_get_error(
"CREATE TABLE rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree('/tables/{shard}/rmt/', '{replica}') ORDER BY n"
)
)
node1.query(
"CREATE TABLE replica_1.rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree('/tables/{shard}/rmt/', '{replica}') ORDER BY n"
)
node1.query(
"CREATE TABLE replica_2.rmt ON CLUSTER cross_3shards_2replicas (n UInt64, s String) ENGINE=ReplicatedMergeTree('/tables/{shard_bk}/rmt/', '{replica_bk}') ORDER BY n"
)
2021-05-10 22:54:52 +00:00
assert (
node1.query(
"SELECT countDistinct(uuid) from remote('node1,node2,node3', 'system', 'databases') WHERE uuid != '00000000-0000-0000-0000-000000000000' AND name='replica_1'"
)
== "1\n"
)
assert (
node1.query(
"SELECT countDistinct(uuid) from remote('node1,node2,node3', 'system', 'tables') WHERE uuid != '00000000-0000-0000-0000-000000000000' AND name='rmt'"
)
2021-05-10 22:54:52 +00:00
== "2\n"
)
node1.query("INSERT INTO replica_1.rmt VALUES (1, 'test')")
node2.query("SYSTEM SYNC REPLICA replica_2.rmt", timeout=5)
assert_eq_with_retry(node2, "SELECT * FROM replica_2.rmt", "1\ttest")
def test_non_query_with_table_ddl(started_cluster):
node1.query("CREATE USER A ON CLUSTER cross_3shards_2replicas")
assert node1.query("SELECT 1", user="A") == "1\n"
assert node2.query("SELECT 1", user="A") == "1\n"
node2.query("DROP USER A ON CLUSTER cross_3shards_2replicas")