mirror of
https://github.com/hanzoai/datastore.git
synced 2026-09-26 13:55:07 +00:00
Alexey MilovidovandClaude Opus 4.8
295ced78d1
Follow-up to #105171, which added `ruff` with a deliberately narrow, bug-class-only rule set and left the unused-name and star-import rules off pending a dedicated cleanup pass. This enables that second batch in `pyproject.toml` and fixes every violation across the tree (the bulk in integration tests): - `F401` unused-import and `F841` unused-variable: removed, preserving any side-effecting right-hand side (e.g. `result = node.query(...)` becomes `node.query(...)`). Two `try: import ...` feature probes are kept with `# noqa: F401`. - `F541` f-string-missing-placeholders: dropped the redundant `f` prefix. - `F403`/`F405` star imports: every `from module import *` is expanded into explicit imports of the names actually used, taken from each name's real origin, so stdlib/third-party names import from their real source rather than through a test "convenience bundle". The now-empty `tests/integration/helpers/kafka/common_direct.py` bundle is removed and its three remaining consumers import `_VarintBytes`/`KafkaAdminClient` directly. Eliminating the star imports surfaced a real bug the wildcard had masked from `F821`: `generate_presets.py` in `test_prometheus_protocols` called an undefined `execute_instant_query_with_http_api`; fixed to the existing `execute_query_via_http_api`. No `black`/`isort` reformatting was applied (neither is enforced in the style check), so the diff is limited to the lint fixes themselves. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
159 lines
6.2 KiB
Python
159 lines
6.2 KiB
Python
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
|
|
nodes = [
|
|
cluster.add_instance(
|
|
f"n{i}", main_configs=["configs/remote_servers.xml"], with_zookeeper=True
|
|
)
|
|
for i in (1, 2, 3, 4, 5, 6)
|
|
]
|
|
|
|
|
|
@pytest.fixture(scope="module", autouse=True)
|
|
def start_cluster():
|
|
try:
|
|
cluster.start()
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def create_tables(cluster, table_name):
|
|
# create replicated tables
|
|
for node in nodes:
|
|
node.query(f"DROP TABLE IF EXISTS {table_name} SYNC")
|
|
|
|
if cluster == "test_single_shard_multiple_replicas":
|
|
nodes[0].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r1') ORDER BY (key)"
|
|
)
|
|
nodes[1].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r2') ORDER BY (key)"
|
|
)
|
|
nodes[2].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r3') ORDER BY (key)"
|
|
)
|
|
nodes[3].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r4') ORDER BY (key)"
|
|
)
|
|
elif cluster == "test_multiple_shards_multiple_replicas":
|
|
# shard 1
|
|
nodes[0].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r1') ORDER BY (key)"
|
|
)
|
|
nodes[1].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r2') ORDER BY (key)"
|
|
)
|
|
nodes[2].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard1/{table_name}', 'r3') ORDER BY (key)"
|
|
)
|
|
# shard 2
|
|
nodes[3].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard2/{table_name}', 'r1') ORDER BY (key)"
|
|
)
|
|
nodes[4].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard2/{table_name}', 'r2') ORDER BY (key)"
|
|
)
|
|
nodes[5].query(
|
|
f"CREATE TABLE IF NOT EXISTS {table_name} (key Int64, value String) Engine=ReplicatedMergeTree('/test_parallel_replicas/shard2/{table_name}', 'r3') ORDER BY (key)"
|
|
)
|
|
else:
|
|
raise Exception(f"Unexpected cluster: {cluster}")
|
|
|
|
# create distributed table
|
|
nodes[0].query(f"DROP TABLE IF EXISTS {table_name}_d SYNC")
|
|
nodes[0].query(
|
|
f"""
|
|
CREATE TABLE {table_name}_d AS {table_name}
|
|
Engine=Distributed(
|
|
{cluster},
|
|
currentDatabase(),
|
|
{table_name},
|
|
key
|
|
)
|
|
"""
|
|
)
|
|
|
|
# populate data
|
|
nodes[0].query(
|
|
f"INSERT INTO {table_name}_d SELECT number, number FROM numbers(1000)",
|
|
settings={"distributed_foreground_insert": 1},
|
|
)
|
|
nodes[0].query(
|
|
f"INSERT INTO {table_name}_d SELECT number, number FROM numbers(2000)",
|
|
settings={"distributed_foreground_insert": 1},
|
|
)
|
|
nodes[0].query(
|
|
f"INSERT INTO {table_name}_d SELECT -number, -number FROM numbers(1000)",
|
|
settings={"distributed_foreground_insert": 1},
|
|
)
|
|
nodes[0].query(
|
|
f"INSERT INTO {table_name}_d SELECT -number, -number FROM numbers(2000)",
|
|
settings={"distributed_foreground_insert": 1},
|
|
)
|
|
nodes[0].query(
|
|
f"INSERT INTO {table_name}_d SELECT number, number FROM numbers(3)",
|
|
settings={"distributed_foreground_insert": 1},
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"cluster,max_parallel_replicas,prefer_localhost_replica",
|
|
[
|
|
pytest.param("test_single_shard_multiple_replicas", 2, 0),
|
|
pytest.param("test_single_shard_multiple_replicas", 3, 0),
|
|
pytest.param("test_single_shard_multiple_replicas", 4, 0),
|
|
pytest.param("test_single_shard_multiple_replicas", 10, 0),
|
|
pytest.param("test_single_shard_multiple_replicas", 2, 1),
|
|
pytest.param("test_single_shard_multiple_replicas", 3, 1),
|
|
pytest.param("test_single_shard_multiple_replicas", 4, 1),
|
|
pytest.param("test_single_shard_multiple_replicas", 10, 1),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 2, 0),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 3, 0),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 4, 0),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 10, 0),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 2, 1),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 3, 1),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 4, 1),
|
|
pytest.param("test_multiple_shards_multiple_replicas", 10, 1),
|
|
],
|
|
)
|
|
def test_parallel_replicas_over_distributed(
|
|
start_cluster, cluster, max_parallel_replicas, prefer_localhost_replica
|
|
):
|
|
table_name = "test_table"
|
|
create_tables(cluster, table_name)
|
|
|
|
node = nodes[0]
|
|
expected_result = "6003\t-1999\t1999\t3\n"
|
|
|
|
# sync all replicas to get consistent result
|
|
node.query(f"SYSTEM SYNC REPLICA ON CLUSTER {cluster} {table_name}")
|
|
|
|
# parallel replicas
|
|
assert (
|
|
node.query(
|
|
f"SELECT count(), min(key), max(key), sum(key) FROM {table_name}_d",
|
|
settings={
|
|
"enable_parallel_replicas": 2,
|
|
"prefer_localhost_replica": prefer_localhost_replica,
|
|
"max_parallel_replicas": max_parallel_replicas,
|
|
},
|
|
)
|
|
== expected_result
|
|
)
|
|
|
|
# w/o parallel replicas
|
|
assert (
|
|
node.query(
|
|
f"SELECT count(), min(key), max(key), sum(key) FROM {table_name}_d",
|
|
settings={
|
|
"enable_parallel_replicas": 0,
|
|
},
|
|
)
|
|
== expected_result
|
|
)
|