def stop(self, at_exit=True, update_run_state=True):
if update_run_state:
databand_run = try_get_databand_run()
if databand_run:
root_tr = databand_run.task.current_task_run
root_tr.finished_time = utcnow()
for tr in databand_run.task_runs:
if tr.task_run_state == TaskRunState.FAILED:
root_tr.set_task_run_state(
TaskRunState.UPSTREAM_FAILED)
databand_run.set_run_state(RunState.FAILED)
break
else:
root_tr.set_task_run_state(TaskRunState.SUCCESS)
databand_run.set_run_state(RunState.SUCCESS)
logger.info(databand_run.describe.run_banner_for_finished())
self._close_all_context_managers()
if at_exit and is_airflow_enabled():
from airflow.settings import dispose_orm
dispose_orm()
def _run_file_processor(
result_channel: MultiprocessingConnection,
parent_channel: MultiprocessingConnection,
file_path: str,
pickle_dags: bool,
dag_ids: Optional[List[str]],
thread_name: str,
callback_requests: List[CallbackRequest],
) -> None:
"""
Process the given file.
:param result_channel: the connection to use for passing back the result
:type result_channel: multiprocessing.Connection
:param parent_channel: the parent end of the channel to close in the child
:type parent_channel: multiprocessing.Connection
:param file_path: the file to process
:type file_path: str
:param pickle_dags: whether to pickle the DAGs found in the file and
save them to the DB
:type pickle_dags: bool
:param dag_ids: if specified, only examine DAG ID's that are
in this list
:type dag_ids: list[str]
:param thread_name: the name to use for the process that is launched
:type thread_name: str
:param callback_requests: failure callback to execute
:type callback_requests: List[airflow.utils.callback_requests.CallbackRequest]
:return: the process that was launched
:rtype: multiprocessing.Process
"""
# This helper runs in the newly created process
log: logging.Logger = logging.getLogger("airflow.processor")
# Since we share all open FDs from the parent, we need to close the parent side of the pipe here in
# the child, else it won't get closed properly until we exit.
log.info("Closing parent pipe")
parent_channel.close()
del parent_channel
set_context(log, file_path)
setproctitle(f"airflow scheduler - DagFileProcessor {file_path}")
try:
# redirect stdout/stderr to log
with redirect_stdout(StreamLogWriter(
log, logging.INFO)), redirect_stderr(
StreamLogWriter(log,
logging.WARN)), Stats.timer() as timer:
# Re-configure the ORM engine as there are issues with multiple processes
settings.configure_orm()
# Change the thread name to differentiate log lines. This is
# really a separate process, but changing the name of the
# process doesn't work, so changing the thread name instead.
threading.current_thread().name = thread_name
log.info("Started process (PID=%s) to work on %s", os.getpid(),
file_path)
dag_file_processor = DagFileProcessor(dag_ids=dag_ids, log=log)
result: Tuple[int, int] = dag_file_processor.process_file(
file_path=file_path,
pickle_dags=pickle_dags,
callback_requests=callback_requests,
)
result_channel.send(result)
log.info("Processing %s took %.3f seconds", file_path,
timer.duration)
except Exception: # pylint: disable=broad-except
# Log exceptions through the logging framework.
log.exception("Got an exception! Propagating...")
raise
finally:
# We re-initialized the ORM within this Process above so we need to
# tear it down manually here
settings.dispose_orm()
result_channel.close()
