Skip to content
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.

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

Bind engine before attempting to drop archive tables #33622

Merged
merged 1 commit into from
Aug 23, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions airflow/utils/db_cleanup.py
Original file line number Diff line number Diff line change
Expand Up @@ -194,6 +194,7 @@ def _do_delete(*, query, orm_model, skip_archive, session):
session.execute(delete)
session.commit()
if skip_archive:
metadata.bind = session.get_bind()
target_table.drop()
session.commit()
print("Finished Performing Delete")
Expand Down
29 changes: 29 additions & 0 deletions tests/utils/test_db_cleanup.py
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
_cleanup_table,
_confirm_drop_archives,
_dump_table_to_file,
_get_archived_table_names,
config_dict,
drop_archived_tables,
export_archived_records,
Expand Down Expand Up @@ -266,6 +267,34 @@ def test__cleanup_table(self, table_name, date_add_kwargs, expected_to_delete, e
else:
raise Exception("unexpected")

@pytest.mark.parametrize(
"skip_archive, expected_archives",
[param(True, 0, id="skip_archive"), param(False, 1, id="do_archive")],
)
def test__skip_archive(self, skip_archive, expected_archives):
"""
Verify that running cleanup_table with drops the archives when requested.
"""
base_date = pendulum.DateTime(2022, 1, 1, tzinfo=pendulum.timezone("UTC"))
num_tis = 10
create_tis(
base_date=base_date,
num_tis=num_tis,
)
with create_session() as session:
clean_before_date = base_date.add(days=5)
_cleanup_table(
**config_dict["dag_run"].__dict__,
clean_before_timestamp=clean_before_date,
dry_run=False,
session=session,
table_names=["dag_run"],
skip_archive=skip_archive,
)
model = config_dict["dag_run"].orm_model
assert len(session.query(model).all()) == 5
assert len(_get_archived_table_names(["dag_run"], session)) == expected_archives

def test_no_models_missing(self):
"""
1. Verify that for all tables in `airflow.models`, we either have them enabled in db cleanup,
Expand Down