ashb commented on a change in pull request #15112:
URL: https://github.com/apache/airflow/pull/15112#discussion_r605081483
##########
File path: tests/utils/test_dag_processing.py
##########
@@ -521,17 +523,93 @@ def test_dag_with_system_exit(self):
manager._run_parsing_loop()
+ result = None
while parent_pipe.poll(timeout=None):
result = parent_pipe.recv()
if isinstance(result, DagParsingStat) and result.done:
break
# Three files in folder should be processed
- assert len(result.file_paths) == 3
+ assert result.num_file_paths == 3
with create_session() as session:
assert session.query(DagModel).get(dag_id) is not None
+ @conf_vars({('core', 'load_examples'): 'False'})
+ @pytest.mark.backend("mysql", "postgres")
+ def test_pipe_full_deadlock(self):
+ dag_filepath = TEST_DAG_FOLDER / "test_scheduler_dags.py"
+
+ child_pipe, parent_pipe = multiprocessing.Pipe()
+
+ # Shrink the buffers to exacerbate the problem!
+ for fd in (parent_pipe.fileno(),):
+ sock = socket.socket(fileno=fd)
+ sock.setsockopt(socket.SOL_SOCKET, socket.SO_SNDBUF, 1024)
+ sock.setsockopt(socket.SOL_SOCKET, socket.SO_RCVBUF, 1024)
+ sock.detach()
+
+ exit_event = threading.Event()
+
+ # To test this behaviour we need something that continually fills the
+ # parent pipe's bufffer (and keeps it full).
+ def keep_pipe_full(pipe, exit_event):
+ import logging
+
+ n = 0
+ while True:
+ if exit_event.is_set():
+ break
+
+ req = CallbackRequest(str(dag_filepath))
+ try:
+ logging.debug("Sending CallbackRequests %d", n + 1)
+ pipe.send(req)
+ except TypeError:
+ # This is actually the error you get when the parent pipe
+ # is closed! Nicely handled, eh?
+ break
+ except OSError:
+ break
+ n += 1
+ logging.debug(" Sent %d CallbackRequests", n)
+
+ thread = threading.Thread(target=keep_pipe_full, args=(parent_pipe,
exit_event))
+
+ fake_processors = []
+
+ def fake_processor_factory(*args, **kwargs):
+ nonlocal fake_processors
+ processor =
FakeDagFileProcessorRunner._fake_dag_processor_factory(*args, **kwargs)
+ fake_processors.append(processor)
+ return processor
+
+ manager = DagFileProcessorManager(
+ dag_directory=dag_filepath,
+ dag_ids=[],
+ # A reasonable large number to ensure that we trigger the deadlock
+ max_runs=100,
+ processor_factory=fake_processor_factory,
+ processor_timeout=timedelta(seconds=5),
+ signal_conn=child_pipe,
+ pickle_dags=False,
+ async_mode=True,
+ )
+
+ try:
+ thread.start()
+
+ # If this completes without hanging, then the test is good!
+ manager._run_parsing_loop()
Review comment:
https://github.com/apache/airflow/pull/15112/commits/5e7405f5574b36e8bc9cf8df0d0d788ba7238ad4
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
