ferruzzi commented on code in PR #55088:
URL: https://github.com/apache/airflow/pull/55088#discussion_r2320395163
##########
airflow-core/src/airflow/models/deadline.py:
##########
@@ -355,6 +355,31 @@ def _evaluate_with(self, *, session: Session, **kwargs:
Any) -> datetime:
return _fetch_from_db(DagRun.queued_at, session=session, **kwargs)
+ class AverageRuntimeDeadline(BaseDeadlineReference):
+ """A deadline that calculates the average runtime from past DAG
runs."""
+
+ 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
+ query = select(func.avg(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)
+ )
+
+ avg_seconds = session.execute(query).scalar()
Review Comment:
That makes sense, I can see where you are coming from. How would you feel
about an optional int with a default (I don't know, maybe 30 runs?), so the
minimal UX is simplified?
--
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]
