Skip to content

tests(bigquery): implement robust wait loop for socket leak tests #17688

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
parthea merged 2 commits into from
Jul 13, 2026
+71 −54
Merged

tests(bigquery): implement robust wait loop for socket leak tests #17688

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9e50516
fix(bigquery): implement robust wait loop for socket leak tests
chalmerlowe Jul 9, 2026
a51872e
fix(bigquery): fix black formatting in test_magics.py
chalmerlowe Jul 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
110 changes: 59 additions & 51 deletions packages/google-cloud-bigquery/tests/system/test_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,38 +22,36 @@
import operator
import os
import pathlib
import random
import string
import time
import unittest
import uuid
import random
import string
from typing import Optional

from google.api_core.exceptions import PreconditionFailed
from google.api_core.exceptions import BadRequest
from google.api_core.exceptions import ClientError
from google.api_core.exceptions import Conflict
from google.api_core.exceptions import GoogleAPICallError
from google.api_core.exceptions import NotFound
from google.api_core.exceptions import InternalServerError
from google.api_core.exceptions import ServiceUnavailable
from google.api_core.exceptions import TooManyRequests
from google.cloud import bigquery
from google.cloud.bigquery.dataset import Dataset
from google.cloud.bigquery.dataset import DatasetReference
from google.cloud.bigquery.table import Table
import psutil
import pytest
from google.api_core.exceptions import (
BadRequest,
ClientError,
Conflict,
GoogleAPICallError,
InternalServerError,
NotFound,
PreconditionFailed,
ServiceUnavailable,
TooManyRequests,
)
from google.cloud import bigquery, storage
from google.cloud._helpers import UTC
from google.cloud.bigquery import dbapi, enums
from google.cloud import storage
from google.cloud.datacatalog_v1 import types as datacatalog_types
from google.cloud.bigquery.dataset import Dataset, DatasetReference
from google.cloud.bigquery.table import Table
from google.cloud.datacatalog_v1 import PolicyTagManagerClient
from google.cloud.resourcemanager_v3 import types as resourcemanager_types
from google.cloud.datacatalog_v1 import types as datacatalog_types
from google.cloud.resourcemanager_v3 import TagKeysClient, TagValuesClient
import psutil
import pytest
from test_utils.retry import RetryErrors
from test_utils.retry import RetryInstanceState
from test_utils.retry import RetryResult
from google.cloud.resourcemanager_v3 import types as resourcemanager_types
from test_utils.retry import RetryErrors, RetryInstanceState, RetryResult
from test_utils.system import unique_resource_id

from . import helpers
Expand Down Expand Up @@ -254,8 +252,13 @@ def test_close_releases_open_sockets(self):
import gc

gc.collect()
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
Comment on lines +255 to +260

@gemini-code-assist gemini-code-assist Bot Jul 13, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To ensure that any socket-holding objects that become eligible for garbage collection during the sleep intervals are actually collected and their sockets released, gc.collect() should be called inside the wait loop rather than only once before it.

Suggested change
for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
for _ in range(30): # Wait up to 3 seconds
gc.collect()
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)


self.assertLessEqual(conn_count_end, conn_count_start)

def test_create_dataset(self):
Expand Down Expand Up @@ -635,8 +638,7 @@ def test_create_table_with_default_value_expression(self):
self.assertEqual("FOO", row_2.get("username"))

def test_create_table_w_time_partitioning_w_clustering_fields(self):
from google.cloud.bigquery.table import TimePartitioning
from google.cloud.bigquery.table import TimePartitioningType
from google.cloud.bigquery.table import TimePartitioning, TimePartitioningType

dataset = self.temp_dataset(_make_dataset_id("create_table_tp_cf"))
table_id = "test_table"
Expand Down Expand Up @@ -964,12 +966,12 @@ def test_update_table_clustering_configuration(self):
self.assertIsNone(table3.clustering_fields, None)

def test_update_table_constraints(self):
from google.cloud.bigquery.table import TableConstraints
from google.cloud.bigquery.table import (
PrimaryKey,
ColumnReference,
ForeignKey,
PrimaryKey,
TableConstraints,
TableReference,
ColumnReference,
)

dataset = self.temp_dataset(_make_dataset_id("update_table"))
Expand Down Expand Up @@ -1128,8 +1130,7 @@ def test_insert_rows_then_dump_table(self):
self.assertEqual(sorted(row_tuples, key=by_age), sorted(ROWS, key=by_age))

def test_load_table_from_local_avro_file_then_dump_table(self):
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import SourceFormat, WriteDisposition

TABLE_NAME = "test_table_avro"
ROWS = [
Expand Down Expand Up @@ -1169,8 +1170,7 @@ def test_load_table_from_local_avro_file_then_dump_table(self):

def test_load_table_from_local_parquet_file_decimal_types(self):
from google.cloud.bigquery.enums import DecimalTargetType
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import SourceFormat, WriteDisposition

TABLE_NAME = "test_table_parquet"

Expand Down Expand Up @@ -1359,9 +1359,11 @@ def test_load_table_from_csv_w_picosecond_timestamp(self):
self.assertEqual(table.num_rows, 3)

def test_load_avro_from_uri_then_dump_table(self):
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import (
CreateDisposition,
SourceFormat,
WriteDisposition,
)

table_name = "test_table"
rows = [
Expand Down Expand Up @@ -1399,9 +1401,11 @@ def test_load_avro_from_uri_then_dump_table(self):
)

def test_load_table_from_uri_then_dump_table(self):
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import (
CreateDisposition,
SourceFormat,
WriteDisposition,
)

TABLE_ID = "test_table"
GS_URL = self._write_csv_to_storage(
Expand Down Expand Up @@ -2202,15 +2206,22 @@ def test_dbapi_connection_does_not_leak_sockets(self):
import gc

gc.collect()
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
Comment on lines +2209 to +2214

@gemini-code-assist gemini-code-assist Bot Jul 13, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To ensure that any socket-holding objects that become eligible for garbage collection during the sleep intervals are actually collected and their sockets released, gc.collect() should be called inside the wait loop rather than only once before it.

Suggested change
for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
for _ in range(30): # Wait up to 3 seconds
gc.collect()
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)


self.assertLessEqual(conn_count_end, conn_count_start)

def _load_table_for_dml(self, rows, dataset_id, table_id):
from google.cloud._testing import _NamedTemporaryFile
from google.cloud.bigquery.job import CreateDisposition
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import (
CreateDisposition,
SourceFormat,
WriteDisposition,
)

dataset = self.temp_dataset(dataset_id)
greeting = bigquery.SchemaField("greeting", "STRING", mode="NULLABLE")
Expand Down Expand Up @@ -2732,8 +2743,7 @@ def test_nested_table_to_arrow(self):
bigquery_storage = pytest.importorskip("google.cloud.bigquery_storage")
pyarrow = pytest.importorskip("pyarrow")
pyarrow.types = pytest.importorskip("pyarrow.types")
from google.cloud.bigquery.job import SourceFormat
from google.cloud.bigquery.job import WriteDisposition
from google.cloud.bigquery.job import SourceFormat, WriteDisposition

SF = bigquery.SchemaField
schema = [
Expand Down Expand Up @@ -2865,8 +2875,7 @@ def test_parameterized_types_round_trip(dataset_id: str):


def test_table_snapshots(dataset_id: str):
from google.cloud.bigquery import CopyJobConfig
from google.cloud.bigquery import OperationType
from google.cloud.bigquery import CopyJobConfig, OperationType

client = Config.CLIENT

Expand Down Expand Up @@ -2936,8 +2945,7 @@ def test_table_snapshots(dataset_id: str):


def test_table_clones(dataset_id: str):
from google.cloud.bigquery import CopyJobConfig
from google.cloud.bigquery import OperationType
from google.cloud.bigquery import CopyJobConfig, OperationType

client = Config.CLIENT

Expand Down
15 changes: 12 additions & 3 deletions packages/google-cloud-bigquery/tests/system/test_magics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,10 @@
"""System tests for Jupyter/IPython connector."""

import re
import time

import pytest
import psutil
import pytest

from . import helpers

Expand Down Expand Up @@ -71,8 +72,16 @@ def test_bigquery_magic(ipython_interactive):
with io.capture_output() as captured:
result = ip.run_cell_magic("bigquery", "--use_rest_api", sql)

conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
import gc

gc.collect()

for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
Comment on lines +79 to +84

@gemini-code-assist gemini-code-assist Bot Jul 13, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To ensure that any socket-holding objects that become eligible for garbage collection during the sleep intervals are actually collected and their sockets released, gc.collect() should be called inside the wait loop rather than only once before it.

Suggested change
for _ in range(30): # Wait up to 3 seconds
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)
for _ in range(30): # Wait up to 3 seconds
gc.collect()
conn_end = current_process.net_connections()
conn_count_end = len(conn_end)
if conn_count_end <= conn_count_start:
break
time.sleep(0.1)


lines = re.split("\n|\r", captured.stdout)
# Removes blanks & terminal code (result of display clearing)
Expand Down
Loading