Skip to content

fix: fix flaky spark processor integ #5109

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
merged 2 commits into from
Mar 27, 2025
Merged

fix: fix flaky spark processor integ #5109

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4dd472c
fix: fix flaky spark processor integ
benieric Mar 27, 2025
6484fb0
format
benieric Mar 27, 2025
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
12 changes: 4 additions & 8 deletions tests/integ/test_spark_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
SPARK_PATH = os.path.join(DATA_DIR, "spark")


@pytest.fixture(scope="module")
@pytest.fixture(scope="module", autouse=True)
def build_jar():
jar_file_path = os.path.join(SPARK_PATH, "code", "java", "hello-java-spark")
# compile java file
Expand Down Expand Up @@ -207,12 +207,10 @@ def configuration() -> list:


def test_sagemaker_pyspark_v3(
spark_v3_py_processor, spark_v3_jar_processor, sagemaker_session, configuration, build_jar
spark_v3_py_processor, spark_v3_jar_processor, sagemaker_session, configuration
):
test_sagemaker_pyspark_multinode(spark_v3_py_processor, sagemaker_session, configuration)
test_sagemaker_java_jar_multinode(
spark_v3_jar_processor, sagemaker_session, configuration, build_jar
)
test_sagemaker_java_jar_multinode(spark_v3_jar_processor, sagemaker_session, configuration)


def test_sagemaker_pyspark_multinode(spark_py_processor, sagemaker_session, configuration):
Expand Down Expand Up @@ -280,9 +278,7 @@ def test_sagemaker_pyspark_multinode(spark_py_processor, sagemaker_session, conf
assert len(output_contents) != 0


def test_sagemaker_java_jar_multinode(
spark_jar_processor, sagemaker_session, configuration, build_jar
):
def test_sagemaker_java_jar_multinode(spark_jar_processor, sagemaker_session, configuration):
"""Test SparkJarProcessor using Java application jar"""
bucket = spark_jar_processor.sagemaker_session.default_bucket()
with open(os.path.join(SPARK_PATH, "files", "data.jsonl")) as data:
Expand Down