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]>
114 lines
3.9 KiB
Python
114 lines
3.9 KiB
Python
import logging
|
|
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.blobs import wait_blobs_count_synchronization
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def cluster():
|
|
try:
|
|
cluster = ClickHouseCluster(__file__)
|
|
cluster.add_instance(
|
|
"node",
|
|
main_configs=["configs/storage_configuration.xml", "configs/ssl.xml"],
|
|
with_minio=True,
|
|
)
|
|
logging.info("Starting cluster...")
|
|
cluster.start()
|
|
logging.info("Cluster started")
|
|
|
|
yield cluster
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
# TinyLog: files: id.bin, sizes.json
|
|
# INSERT overwrites 1 file (`sizes.json`) and appends 1 file (`id.bin`), so
|
|
# files_overhead=1, files_overhead_per_insert=1
|
|
#
|
|
# Log: files: id.bin, __marks.mrk, sizes.json
|
|
# INSERT overwrites 1 file (`sizes.json`), and appends 2 files (`id.bin`, `__marks.mrk`), so
|
|
# files_overhead=1, files_overhead_per_insert=2
|
|
#
|
|
# StripeLog: files: data.bin, index.mrk, sizes.json
|
|
# INSERT overwrites 1 file (`sizes.json`), and appends 2 files (`index.mrk`, `data.bin`), so
|
|
# files_overhead=1, files_overhead_per_insert=2
|
|
@pytest.mark.parametrize(
|
|
"log_engine,files_overhead,files_overhead_per_insert",
|
|
[
|
|
pytest.param("TinyLog", 1, 1, id="TinyLog"),
|
|
pytest.param("Log", 1, 2, id="Log"),
|
|
pytest.param("StripeLog", 1, 2, id="StripeLog"),
|
|
],
|
|
)
|
|
def test_log_family_s3(cluster, log_engine, files_overhead, files_overhead_per_insert):
|
|
node = cluster.instances["node"]
|
|
|
|
node.query(
|
|
"CREATE TABLE s3_test (id UInt64) ENGINE={} SETTINGS disk = 's3'".format(
|
|
log_engine
|
|
)
|
|
)
|
|
|
|
try:
|
|
node.query("INSERT INTO s3_test SELECT number FROM numbers(5)")
|
|
assert node.query("SELECT * FROM s3_test") == "0\n1\n2\n3\n4\n"
|
|
wait_blobs_count_synchronization(cluster.minio_client, files_overhead_per_insert + files_overhead)
|
|
|
|
node.query("INSERT INTO s3_test SELECT number + 5 FROM numbers(3)")
|
|
assert (
|
|
node.query("SELECT * FROM s3_test order by id")
|
|
== "0\n1\n2\n3\n4\n5\n6\n7\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, files_overhead_per_insert * 2 + files_overhead)
|
|
|
|
node.query("INSERT INTO s3_test SELECT number + 8 FROM numbers(1)")
|
|
assert (
|
|
node.query("SELECT * FROM s3_test order by id")
|
|
== "0\n1\n2\n3\n4\n5\n6\n7\n8\n"
|
|
)
|
|
wait_blobs_count_synchronization(cluster.minio_client, files_overhead_per_insert * 3 + files_overhead)
|
|
|
|
node.query("TRUNCATE TABLE s3_test")
|
|
wait_blobs_count_synchronization(cluster.minio_client, 0)
|
|
finally:
|
|
node.query("DROP TABLE s3_test SYNC")
|
|
|
|
|
|
# Imitate case when error occurs while inserting into table.
|
|
# For examle S3::TooManyRequests.
|
|
# In that case we can update data file, but not the size file.
|
|
# So due to exception we should do truncate of the data file to undo the insert query.
|
|
# See FileChecker::repair().
|
|
def test_stripe_log_truncate(cluster):
|
|
node = cluster.instances["node"]
|
|
|
|
node.query(
|
|
"""
|
|
CREATE TABLE stripe_table (
|
|
a int
|
|
) ENGINE = StripeLog()
|
|
SETTINGS storage_policy='s3_no_retries'
|
|
"""
|
|
)
|
|
|
|
node.query("SYSTEM ENABLE FAILPOINT stripe_log_sink_write_fallpoint")
|
|
node.query(
|
|
"""
|
|
INSERT INTO stripe_table SELECT number FROM numbers(10)
|
|
""",
|
|
ignore_error=True,
|
|
)
|
|
node.query("SYSTEM DISABLE FAILPOINT stripe_log_sink_write_fallpoint")
|
|
node.query("SELECT count(*) FROM stripe_table") == "0\n"
|
|
node.query("INSERT INTO stripe_table SELECT number FROM numbers(10)")
|
|
node.query("SELECT count(*) FROM stripe_table") == "10\n"
|
|
|
|
# Make sure that everything is okey with the table after restart.
|
|
node.query("DETACH TABLE stripe_table")
|
|
node.query("ATTACH TABLE stripe_table")
|
|
|
|
assert node.query("DROP TABLE stripe_table SYNC") == ""
|