ferruzzi commented on code in PR #55088:
URL: https://github.com/apache/airflow/pull/55088#discussion_r2337780668
##########
airflow-core/src/airflow/models/deadline.py:
##########
@@ -366,6 +366,64 @@ def _evaluate_with(self, *, session: Session, **kwargs:
Any) -> datetime:
return _fetch_from_db(DagRun.queued_at, session=session, **kwargs)
+ @dataclass
+ class AverageRuntimeDeadline(BaseDeadlineReference):
+ """A deadline that calculates the average runtime from past DAG
runs."""
+
+ limit: int
+ required_kwargs = {"dag_id"}
+
+ @provide_session
+ def _evaluate_with(self, *, session: Session, **kwargs: Any) ->
datetime:
+ from airflow.models import DagRun
+
+ dag_id = kwargs["dag_id"]
+
+ # Query for completed DAG runs with both start and end dates
+ # Order by logical_date descending to get most recent runs first
+ query = (
+ select(func.extract("epoch", DagRun.end_date -
DagRun.start_date))
+ .filter(DagRun.dag_id == dag_id,
DagRun.start_date.isnot(None), DagRun.end_date.isnot(None))
+ .order_by(DagRun.logical_date.desc())
+ )
+
+ # Apply limit
+ query = query.limit(self.limit)
+
+ # Get all durations and calculate average
+ durations = session.execute(query).scalars().all()
+
+ if len(durations) < self.limit:
+ logger.warning(
+ "Only %d completed DAG runs found for dag_id: %s (need
%d), using 24 hour default",
+ len(durations),
+ dag_id,
+ self.limit,
+ )
+ avg_seconds = 48 * 3600 # 48 hours as default
Review Comment:
Maybe I'm missing something, in L398 you say "using 24 hour default" but
here you are setting it to 48 hours?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
