Skip to content

Reconnect to blocked Databricks runs in SubmitRunOperator durable retries #69195

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
amoghrajesh merged 1 commit into from
Jul 1, 2026
Merged

Reconnect to blocked Databricks runs in SubmitRunOperator durable retries #69195

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 8 additions & 1 deletion providers/databricks/src/airflow/providers/databricks/operators/databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -937,7 +937,14 @@ def get_job_status(self, external_id: JsonValue, context: Context) -> str:

def is_job_active(self, status: str) -> bool:
life_cycle_state = status.split(":", 1)[0]
return life_cycle_state in ("PENDING", "QUEUED", "RUNNING", "TERMINATING")
return life_cycle_state in (
"PENDING",
"QUEUED",
"RUNNING",
"TERMINATING",
"BLOCKED",
"WAITING_FOR_RETRY",
)

def is_job_succeeded(self, status: str) -> bool:
return status == "TERMINATED:SUCCESS"
Expand Down
19 changes: 19 additions & 0 deletions providers/databricks/tests/unit/databricks/operators/test_databricks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1718,6 +1718,23 @@ def test_reconnects_to_active_run_without_resubmitting(self, db_mock_class):
task_store.set.assert_not_called()
assert op.run_id == RUN_ID

@mock.patch("airflow.providers.databricks.operators.databricks.DatabricksHook")
def test_reconnects_to_blocked_run_without_resubmitting(self, db_mock_class):
op = DatabricksSubmitRunOperator(
task_id=TASK_ID, json={"new_cluster": NEW_CLUSTER, "notebook_task": NOTEBOOK_TASK}
)
db_mock = db_mock_class.return_value
# A gated run sits in BLOCKED; the durable retry must reconnect and wait, not resubmit.
db_mock.get_run.side_effect = [self._state("BLOCKED"), self._state("TERMINATED", "SUCCESS")]
task_store = MagicMock(spec_set=["get", "set"])
task_store.get.return_value = RUN_ID

op.execute(self._context(task_store))

db_mock.submit_run.assert_not_called()
task_store.set.assert_not_called()
assert op.run_id == RUN_ID

@mock.patch("airflow.providers.databricks.operators.databricks._handle_databricks_operator_execution")
@mock.patch("airflow.providers.databricks.operators.databricks.DatabricksHook")
def test_already_succeeded_pushes_xcoms_without_polling(self, db_mock_class, mock_poll):
Expand Down Expand Up @@ -1846,6 +1863,8 @@ def test_get_job_status_encodes_life_cycle_and_result(self, db_mock_class):
("PENDING:", True),
("QUEUED:", True),
("TERMINATING:", True),
("BLOCKED:", True),
("WAITING_FOR_RETRY:", True),
("TERMINATED:SUCCESS", False),
("TERMINATED:FAILED", False),
("SKIPPED:", False),
Expand Down
Loading