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]>
125 lines
3.7 KiB
Python
125 lines
3.7 KiB
Python
|
|
import pytest
|
|
|
|
from helpers.cluster import ClickHouseCluster
|
|
from helpers.client import QueryRuntimeException
|
|
|
|
cluster = ClickHouseCluster(__file__)
|
|
node1 = cluster.add_instance(
|
|
"node1", main_configs=["configs/jemalloc_global_profiler.xml"], stay_alive=True
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def started_cluster():
|
|
try:
|
|
cluster.start()
|
|
yield cluster
|
|
|
|
finally:
|
|
cluster.shutdown()
|
|
|
|
|
|
def set_config(config, value):
|
|
node1.replace_in_config(
|
|
"/etc/clickhouse-server/config.d/jemalloc_global_profiler.xml",
|
|
f"{config}>.",
|
|
f"{config}>{value}",
|
|
)
|
|
|
|
|
|
def is_global_profiler_active():
|
|
return int(
|
|
node1.query(
|
|
"SELECT value FROM system.asynchronous_metrics WHERE metric = 'jemalloc.prof.thread_active_init'"
|
|
).strip()
|
|
)
|
|
|
|
|
|
def has_jemalloc_sample_in_trace_log(extra_query_condition=""):
|
|
node1.query("SYSTEM FLUSH LOGS")
|
|
return int(
|
|
node1.query(
|
|
f"SELECT count() > 0 FROM system.trace_log WHERE trace_type = 'JemallocSample' {extra_query_condition}"
|
|
).strip()
|
|
)
|
|
|
|
|
|
def test_jemalloc_global_profiler(started_cluster):
|
|
# default open
|
|
if node1.is_built_with_sanitizer() or node1.is_built_with_llvm_coverage():
|
|
pytest.skip("Disabled for sanitizers and llvm coverage builds")
|
|
|
|
set_config("jemalloc_enable_global_profiler", "0")
|
|
set_config("jemalloc_collect_global_profile_samples_in_trace_log", "0")
|
|
node1.restart_clickhouse()
|
|
|
|
try:
|
|
node1.query("TRUNCATE system.trace_log")
|
|
except QueryRuntimeException as e:
|
|
assert e.returncode == 60 # UNKNOWN_TABLE
|
|
|
|
assert is_global_profiler_active() == 0
|
|
assert has_jemalloc_sample_in_trace_log() == 0
|
|
|
|
set_config("jemalloc_enable_global_profiler", "1")
|
|
node1.restart_clickhouse()
|
|
|
|
assert is_global_profiler_active() == 1
|
|
assert has_jemalloc_sample_in_trace_log() == 0
|
|
|
|
# we enable collecting samples to trace_log for specific query only
|
|
profiled_query_id = "test_jemalloc_query_profiler"
|
|
node1.query(
|
|
"SELECT * FROM numbers(1000000) ORDER BY number",
|
|
settings={
|
|
"max_bytes_ratio_before_external_sort": 0,
|
|
"jemalloc_enable_profiler": 0,
|
|
"jemalloc_collect_profile_samples_in_trace_log": 1,
|
|
},
|
|
query_id=profiled_query_id,
|
|
)
|
|
|
|
def assert_only_traces_from_query(query_id):
|
|
assert (
|
|
has_jemalloc_sample_in_trace_log(
|
|
extra_query_condition=f"AND query_id = '{query_id}'"
|
|
)
|
|
== 1
|
|
)
|
|
# we can deallocate outside query some allocations we did in the query
|
|
assert (
|
|
has_jemalloc_sample_in_trace_log(
|
|
extra_query_condition=f"AND query_id != '{query_id}' AND size > 0"
|
|
)
|
|
== 0
|
|
)
|
|
|
|
assert_only_traces_from_query(profiled_query_id)
|
|
|
|
set_config("jemalloc_collect_global_profile_samples_in_trace_log", "1")
|
|
node1.restart_clickhouse()
|
|
|
|
assert is_global_profiler_active() == 1
|
|
assert has_jemalloc_sample_in_trace_log() == 1
|
|
|
|
set_config("jemalloc_enable_global_profiler", "0")
|
|
node1.restart_clickhouse()
|
|
assert is_global_profiler_active() == 0
|
|
|
|
node1.query("TRUNCATE system.trace_log")
|
|
|
|
# we enable jemalloc profiler for query but rely on global config to collect samples to trace_log
|
|
profiled_query_id = "test_jemalloc_query_profiler"
|
|
node1.query(
|
|
"SELECT * FROM numbers(1000000) ORDER BY number",
|
|
settings={
|
|
"max_bytes_ratio_before_external_sort": 0,
|
|
"jemalloc_enable_profiler": 1,
|
|
"jemalloc_collect_profile_samples_in_trace_log": 0,
|
|
},
|
|
query_id=profiled_query_id,
|
|
)
|
|
|
|
assert_only_traces_from_query(profiled_query_id)
|