def next_dagrun_info(
self,
*,
last_automated_data_interval: Optional[DataInterval],
restriction: TimeRestriction,
) -> Optional[DagRunInfo]:
earliest = restriction.earliest
if not restriction.catchup:
earliest = self._skip_to_latest(earliest)
elif earliest is not None:
earliest = self._align(earliest)
if last_automated_data_interval is None:
# First run; schedule the run at the first available time matching
# the schedule, and retrospectively create a data interval for it.
if earliest is None:
return None
start = earliest
else: # There's a previous run.
if earliest is not None:
# Catchup is False or DAG has new start date in the future.
# Make sure we get the later one.
start = max(last_automated_data_interval.end, earliest)
else:
# Data interval starts from the end of the previous interval.
start = last_automated_data_interval.end
if restriction.latest is not None and start > restriction.latest:
return None
end = self._get_next(start)
return DagRunInfo.interval(start=start, end=end)
def next_dagrun_info(
self,
*,
last_automated_data_interval: Optional[DataInterval],
restriction: TimeRestriction,
) -> Optional[DagRunInfo]:
if last_automated_data_interval is not None: # There was a previous run on the regular schedule.
last_start = last_automated_data_interval.start
last_start_weekday = last_start.weekday()
if 0 <= last_start_weekday < 4: # Last run on Monday through Thursday -- next is tomorrow.
delta = timedelta(days=1)
else: # Last run on Friday -- skip to next Monday.
delta = timedelta(days=(7 - last_start_weekday))
next_start = DateTime.combine((last_start + delta).date(), Time.min).replace(tzinfo=UTC)
else: # This is the first ever run on the regular schedule.
next_start = restriction.earliest
if next_start is None: # No start_date. Don't schedule.
return None
if not restriction.catchup:
# If the DAG has catchup=False, today is the earliest to consider.
next_start = max(next_start, DateTime.combine(Date.today(), Time.min).replace(tzinfo=UTC))
elif next_start.time() != Time.min:
# If earliest does not fall on midnight, skip to the next day.
next_day = next_start.date() + timedelta(days=1)
next_start = DateTime.combine(next_day, Time.min).replace(tzinfo=UTC)
next_start_weekday = next_start.weekday()
if next_start_weekday in (5, 6): # If next start is in the weekend, go to next Monday.
delta = timedelta(days=(7 - next_start_weekday))
next_start = next_start + delta
if restriction.latest is not None and next_start > restriction.latest:
return None # Over the DAG's scheduled end; don't schedule.
return DagRunInfo.interval(start=next_start, end=(next_start + timedelta(days=1)))
def next_dagrun_info(
self,
last_automated_dagrun: Optional[DateTime],
restriction: TimeRestriction,
) -> Optional[DagRunInfo]:
if last_automated_dagrun is not None:
return None # Already run, no more scheduling.
if restriction.earliest is None: # No start date, won't run.
return None
# "@once" always schedule to the start_date determined by the DAG and
# tasks, regardless of catchup or not. This has been the case since 1.10
# and we're inheriting it. See AIRFLOW-1928.
run_after = restriction.earliest
if restriction.latest is not None and run_after > restriction.latest:
return None
return DagRunInfo.exact(run_after)
def next_dagrun_info(
self,
*,
last_automated_data_interval: Optional[DataInterval],
restriction: TimeRestriction,
) -> Optional[DagRunInfo]:
if last_automated_data_interval is None:
next_event = self.event_dates[0]
else:
future_dates = itertools.dropwhile(
lambda when: when <= last_automated_data_interval.end, self.event_dates # type: ignore
)
next_event = next(future_dates, None) # type: ignore
if next_event is None:
return None
return DagRunInfo.exact(next_event)
def next_dagrun_info(
self,
last_automated_dagrun: Optional[DateTime],
restriction: TimeRestriction,
) -> Optional[DagRunInfo]:
earliest = restriction.earliest
if not restriction.catchup:
earliest = self._schedule.skip_to_latest(earliest)
if last_automated_dagrun is None:
# First run; schedule the run at the first available time matching
# the schedule, and retrospectively create a data interval for it.
if earliest is None:
return None
start = self._schedule.align(earliest)
else:
# There's a previous run. Create a data interval starting from when
# the end of the previous interval.
start = self._schedule.get_next(last_automated_dagrun)
if restriction.latest is not None and start > restriction.latest:
return None
end = self._schedule.get_next(start)
return DagRunInfo.interval(start=start, end=end)
def next_dagrun_info(
self,
*,
last_automated_data_interval: DataInterval | None,
restriction: TimeRestriction,
) -> DagRunInfo | None:
if restriction.catchup:
if last_automated_data_interval is None:
if restriction.earliest is None:
return None
next_start_time = self._align_to_next(restriction.earliest)
else:
next_start_time = self._get_next(
last_automated_data_interval.end)
else:
current_time = DateTime.utcnow()
if restriction.earliest is not None and current_time < restriction.earliest:
next_start_time = self._align_to_next(restriction.earliest)
else:
next_start_time = self._align_to_next(current_time)
if restriction.latest is not None and restriction.latest < next_start_time:
return None
return DagRunInfo.interval(next_start_time - self._interval,
next_start_time)
def _execute(self, session=None):
"""
Initializes all components required to run a dag for a specified date range and
calls helper method to execute the tasks.
"""
ti_status = BackfillJob._DagRunTaskStatus()
start_date = self.bf_start_date
# Get DagRun schedule between the start/end dates, which will turn into dag runs.
dagrun_start_date = timezone.coerce_datetime(start_date)
if self.bf_end_date is None:
dagrun_end_date = pendulum.now(timezone.utc)
else:
dagrun_end_date = pendulum.instance(self.bf_end_date)
dagrun_infos = list(
self.dag.iter_dagrun_infos_between(dagrun_start_date,
dagrun_end_date))
if self.run_backwards:
tasks_that_depend_on_past = [
t.task_id for t in self.dag.task_dict.values()
if t.depends_on_past
]
if tasks_that_depend_on_past:
raise AirflowException(
f'You cannot backfill backwards because one or more '
f'tasks depend_on_past: {",".join(tasks_that_depend_on_past)}'
)
dagrun_infos = dagrun_infos[::-1]
if not dagrun_infos:
if not self.run_at_least_once:
self.log.info(
"No run dates were found for the given dates and dag interval."
)
return
dagrun_infos = [
DagRunInfo.interval(dagrun_start_date, dagrun_end_date)
]
# picklin'
pickle_id = None
if not self.donot_pickle and self.executor_class not in (
executor_constants.LOCAL_EXECUTOR,
executor_constants.SEQUENTIAL_EXECUTOR,
executor_constants.DASK_EXECUTOR,
):
pickle = DagPickle(self.dag)
session.add(pickle)
session.commit()
pickle_id = pickle.id
executor = self.executor
executor.job_id = "backfill"
executor.start()
ti_status.total_runs = len(dagrun_infos) # total dag runs in backfill
try:
remaining_dates = ti_status.total_runs
while remaining_dates > 0:
dagrun_infos_to_process = [
dagrun_info for dagrun_info in dagrun_infos
if dagrun_info.logical_date not in
ti_status.executed_dag_run_dates
]
self._execute_dagruns(
dagrun_infos=dagrun_infos_to_process,
ti_status=ti_status,
executor=executor,
pickle_id=pickle_id,
start_date=start_date,
session=session,
)
remaining_dates = ti_status.total_runs - len(
ti_status.executed_dag_run_dates)
err = self._collect_errors(ti_status=ti_status,
session=session)
if err:
raise BackfillUnfinished(err, ti_status)
if remaining_dates > 0:
self.log.info(
"max_active_runs limit for dag %s has been reached "
" - waiting for other dag runs to finish",
self.dag_id,
)
time.sleep(self.delay_on_limit_secs)
except (KeyboardInterrupt, SystemExit):
self.log.warning("Backfill terminated by user.")
# TODO: we will need to terminate running task instances and set the
# state to failed.
self._set_unfinished_dag_runs_to_failed(ti_status.active_runs)
finally:
session.commit()
executor.end()
self.log.info("Backfill done. Exiting.")
def _execute(self, session=None):
"""
Initializes all components required to run a dag for a specified date range and
calls helper method to execute the tasks.
"""
ti_status = BackfillJob._DagRunTaskStatus()
start_date = self.bf_start_date
# Get DagRun schedule between the start/end dates, which will turn into dag runs.
dagrun_start_date = timezone.coerce_datetime(start_date)
if self.bf_end_date is None:
dagrun_end_date = pendulum.now(timezone.utc)
else:
dagrun_end_date = pendulum.instance(self.bf_end_date)
dagrun_infos = list(
self.dag.iter_dagrun_infos_between(dagrun_start_date,
dagrun_end_date))
if self.run_backwards:
tasks_that_depend_on_past = [
t.task_id for t in self.dag.task_dict.values()
if t.depends_on_past
]
if tasks_that_depend_on_past:
raise AirflowException(
f'You cannot backfill backwards because one or more '
f'tasks depend_on_past: {",".join(tasks_that_depend_on_past)}'
)
dagrun_infos = dagrun_infos[::-1]
if not dagrun_infos:
if not self.run_at_least_once:
self.log.info(
"No run dates were found for the given dates and dag interval."
)
return
dagrun_infos = [
DagRunInfo.interval(dagrun_start_date, dagrun_end_date)
]
dag_with_subdags_ids = [d.dag_id for d in self._get_dag_with_subdags()]
running_dagruns = DagRun.find(
dag_id=dag_with_subdags_ids,
execution_start_date=self.bf_start_date,
execution_end_date=self.bf_end_date,
no_backfills=True,
state=DagRunState.RUNNING,
)
if running_dagruns:
for run in running_dagruns:
self.log.error(
"Backfill cannot be created for DagRun %s in %s, as there's already %s in a RUNNING "
"state.",
run.run_id,
run.execution_date.strftime("%Y-%m-%dT%H:%M:%S"),
run.run_type,
)
self.log.error(
"Changing DagRun into BACKFILL would cause scheduler to lose track of executing "
"tasks. Not changing DagRun type into BACKFILL, and trying insert another DagRun into "
"database would cause database constraint violation for dag_id + execution_date "
"combination. Please adjust backfill dates or wait for this DagRun to finish.",
)
return
# picklin'
pickle_id = None
if not self.donot_pickle and self.executor_class not in (
executor_constants.LOCAL_EXECUTOR,
executor_constants.SEQUENTIAL_EXECUTOR,
executor_constants.DASK_EXECUTOR,
):
pickle = DagPickle(self.dag)
session.add(pickle)
session.commit()
pickle_id = pickle.id
executor = self.executor
executor.job_id = "backfill"
executor.start()
ti_status.total_runs = len(dagrun_infos) # total dag runs in backfill
try:
remaining_dates = ti_status.total_runs
while remaining_dates > 0:
dagrun_infos_to_process = [
dagrun_info for dagrun_info in dagrun_infos
if dagrun_info.logical_date not in
ti_status.executed_dag_run_dates
]
self._execute_dagruns(
dagrun_infos=dagrun_infos_to_process,
ti_status=ti_status,
executor=executor,
pickle_id=pickle_id,
start_date=start_date,
session=session,
)
remaining_dates = ti_status.total_runs - len(
ti_status.executed_dag_run_dates)
err = self._collect_errors(ti_status=ti_status,
session=session)
if err:
if not self.continue_on_failures or ti_status.deadlocked:
raise BackfillUnfinished(err, ti_status)
if remaining_dates > 0:
self.log.info(
"max_active_runs limit for dag %s has been reached "
" - waiting for other dag runs to finish",
self.dag_id,
)
time.sleep(self.delay_on_limit_secs)
except (KeyboardInterrupt, SystemExit):
self.log.warning("Backfill terminated by user.")
# TODO: we will need to terminate running task instances and set the
# state to failed.
self._set_unfinished_dag_runs_to_failed(ti_status.active_runs)
finally:
session.commit()
executor.end()
self.log.info("Backfill done for DAG %s. Exiting.", self.dag)
