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]>
279 lines
7.5 KiB
Python
279 lines
7.5 KiB
Python
import csv
|
|
import logging
|
|
import os
|
|
import shutil
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.config_cluster import minio_secret_key
|
|
from helpers.mock_servers import start_mock_servers
|
|
|
|
logging.getLogger().setLevel(logging.INFO)
|
|
logging.getLogger().addHandler(logging.StreamHandler())
|
|
|
|
SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
|
|
S3_DATA = []
|
|
|
|
generated_rows = 0
|
|
|
|
def create_buckets_s3(cluster):
|
|
global generated_rows
|
|
|
|
minio = cluster.minio_client
|
|
|
|
for file_number in range(100):
|
|
file_name = f"data/generated/file_{file_number}.csv"
|
|
os.makedirs(os.path.join(SCRIPT_DIR, "data/generated/"), exist_ok=True)
|
|
S3_DATA.append(file_name)
|
|
with open(os.path.join(SCRIPT_DIR, file_name), "w+", encoding="utf-8") as f:
|
|
# a String, b UInt64
|
|
data = []
|
|
|
|
# Make all files a bit different
|
|
for number in range(100 + file_number):
|
|
data.append(
|
|
["str_" + str(number + file_number) * 10, number + file_number]
|
|
)
|
|
generated_rows += 1
|
|
|
|
writer = csv.writer(f)
|
|
writer.writerows(data)
|
|
|
|
for file in S3_DATA:
|
|
minio.fput_object(
|
|
bucket_name=cluster.minio_bucket,
|
|
object_name=file,
|
|
file_path=os.path.join(SCRIPT_DIR, file),
|
|
)
|
|
for obj in minio.list_objects(cluster.minio_bucket, recursive=True):
|
|
print(obj.object_name)
|
|
|
|
|
|
def run_s3_mocks(started_cluster):
|
|
script_dir = os.path.join(os.path.dirname(__file__), "s3_mocks")
|
|
start_mock_servers(
|
|
started_cluster,
|
|
script_dir,
|
|
[
|
|
("s3_mock.py", "resolver", "8080"),
|
|
],
|
|
)
|
|
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
node1 = cluster.add_instance(
|
|
"node1",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
with_minio=True,
|
|
with_zookeeper=True,
|
|
macros={"replica": "node1"},
|
|
)
|
|
node2 = cluster.add_instance(
|
|
"node2",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
stay_alive=True,
|
|
with_zookeeper=True,
|
|
macros={"replica": "node2"},
|
|
)
|
|
node3 = cluster.add_instance(
|
|
"node3",
|
|
main_configs=["configs/cluster.xml"],
|
|
user_configs=["configs/users.xml"],
|
|
stay_alive=True,
|
|
with_zookeeper=True,
|
|
macros={"replica": "node3"},
|
|
)
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
|
|
logging.info("Starting cluster...")
|
|
cluster.start()
|
|
logging.info("Cluster started")
|
|
|
|
create_buckets_s3(cluster)
|
|
|
|
run_s3_mocks(cluster)
|
|
|
|
yield cluster
|
|
finally:
|
|
shutil.rmtree(os.path.join(SCRIPT_DIR, "data/generated/"))
|
|
cluster.shutdown()
|
|
|
|
|
|
def test_reconnect_after_nodes_restart(started_cluster):
|
|
uuid = str(uuid4())
|
|
result = node1.query(
|
|
f"""
|
|
SELECT count(*) from s3Cluster(
|
|
'cluster_simple',
|
|
'http://minio1:9001/root/data/generated/*.csv',
|
|
'minio', '{minio_secret_key}', 'CSV', 'a String, b UInt64')
|
|
"""
|
|
, query_id=uuid
|
|
)
|
|
|
|
assert result == "14950\n"
|
|
|
|
node1.query("system flush logs query_log")
|
|
|
|
assert (
|
|
node1.query(
|
|
f"""SELECT ProfileEvents['DistributedConnectionReconnectCount'] FROM system.query_log WHERE query_id = '{uuid}' and type = 'QueryFinish';"""
|
|
) == "0\n"
|
|
)
|
|
|
|
node2.restart_clickhouse()
|
|
node3.restart_clickhouse()
|
|
|
|
uuid = str(uuid4())
|
|
result = node1.query(
|
|
f"""
|
|
SELECT count(*) from s3Cluster(
|
|
'cluster_simple',
|
|
'http://minio1:9001/root/data/generated/*.csv',
|
|
'minio', '{minio_secret_key}', 'CSV', 'a String, b UInt64')
|
|
"""
|
|
,query_id=uuid
|
|
)
|
|
|
|
assert result == "14950\n"
|
|
|
|
node1.query("system flush logs query_log")
|
|
|
|
assert (
|
|
node1.query(
|
|
f"""SELECT ProfileEvents['DistributedConnectionReconnectCount'] FROM system.query_log WHERE query_id = '{uuid}' and type = 'QueryFinish';"""
|
|
) == "2\n"
|
|
)
|
|
|
|
|
|
def test_reconnect_after_nodes_restart_no_wait(started_cluster):
|
|
uuid = str(uuid4())
|
|
result = node1.query(
|
|
f"""
|
|
SELECT count(*) from s3Cluster(
|
|
'cluster_simple',
|
|
'http://minio1:9001/root/data/generated/*.csv',
|
|
'minio', '{minio_secret_key}', 'CSV', 'a String, b UInt64')
|
|
"""
|
|
, query_id=uuid
|
|
)
|
|
|
|
assert result == "14950\n"
|
|
|
|
node1.query("system flush logs query_log")
|
|
|
|
assert (
|
|
node1.query(
|
|
f"""SELECT ProfileEvents['DistributedConnectionReconnectCount'] FROM system.query_log WHERE query_id = '{uuid}' and type = 'QueryFinish';"""
|
|
) == "0\n"
|
|
)
|
|
|
|
node2.stop()
|
|
node2.start()
|
|
|
|
uuid = str(uuid4())
|
|
result = node1.query(
|
|
f"""
|
|
SELECT count(*) from s3Cluster(
|
|
'cluster_simple',
|
|
'http://minio1:9001/root/data/generated/*.csv',
|
|
'minio', '{minio_secret_key}', 'CSV', 'a String, b UInt64')
|
|
"""
|
|
,query_id=uuid
|
|
)
|
|
|
|
assert result == "14950\n"
|
|
|
|
# avoid leaving the test w/o started node, so next test will start with fully runnning cluster
|
|
node2.wait_for_start(30)
|
|
|
|
|
|
def createTable(table, missing_table):
|
|
node1.query(
|
|
f"""
|
|
CREATE TABLE {table} (a String, b UInt64)
|
|
ENGINE=ReplicatedMergeTree('/clickhouse/tables/f15b1936-ae89-416b-8626-7c88d9fbe6a3/{table}', '{{replica}}')
|
|
ORDER BY (a, b);
|
|
"""
|
|
)
|
|
node2.query(
|
|
f"""
|
|
CREATE TABLE {table} (a String, b UInt64)
|
|
ENGINE=ReplicatedMergeTree('/clickhouse/tables/f15b1936-ae89-416b-8626-7c88d9fbe6a3/{table}', '{{replica}}')
|
|
ORDER BY (a, b);
|
|
"""
|
|
)
|
|
if (not missing_table):
|
|
node3.query(
|
|
f"""
|
|
CREATE TABLE {table} (a String, b UInt64)
|
|
ENGINE=ReplicatedMergeTree('/clickhouse/tables/f15b1936-ae89-416b-8626-7c88d9fbe6a3/{table}', '{{replica}}')
|
|
ORDER BY (a, b);
|
|
"""
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"wait_restart, missing_table",
|
|
[
|
|
pytest.param(False, False),
|
|
pytest.param(False, True),
|
|
pytest.param(True, False),
|
|
pytest.param(True, True),
|
|
],
|
|
)
|
|
def test_insert_select(started_cluster, wait_restart, missing_table):
|
|
table = 't_rmt_target'
|
|
|
|
node1.query(
|
|
f"""DROP TABLE IF EXISTS {table} ON CLUSTER 'cluster_simple' SYNC;"""
|
|
)
|
|
|
|
createTable(table, missing_table);
|
|
|
|
if (wait_restart):
|
|
node2.restart_clickhouse()
|
|
else:
|
|
node2.stop()
|
|
node2.start()
|
|
|
|
uuid = str(uuid4())
|
|
node1.query(
|
|
f"""
|
|
INSERT INTO {table} SELECT * FROM s3Cluster(
|
|
'cluster_simple',
|
|
'http://minio1:9001/root/data/generated/*.csv', 'minio', '{minio_secret_key}', 'CSV','a String, b UInt64'
|
|
) SETTINGS parallel_distributed_insert_select=1;
|
|
"""
|
|
, query_id = uuid
|
|
)
|
|
|
|
if (not wait_restart):
|
|
node2.wait_for_start(30)
|
|
|
|
node1.query(f"SYSTEM SYNC REPLICA {table}")
|
|
|
|
# Check whether we inserted at least something
|
|
assert (
|
|
int(
|
|
node1.query(
|
|
f"""SELECT count(*) FROM {table};"""
|
|
).strip()
|
|
) == generated_rows
|
|
)
|
|
|
|
if (missing_table):
|
|
node1.query("SYSTEM FLUSH LOGS query_log");
|
|
assert ( node1.query(f"select ProfileEvents['DistributedConnectionMissingTable'] from system.query_log where query_id = '{uuid}' and type = 'QueryFinish'") == "1\n")
|
|
|
|
node1.query(
|
|
f"""DROP TABLE IF EXISTS {table} ON CLUSTER 'cluster_simple' SYNC;"""
|
|
)
|