ferruzzi commented on code in PR #55088:
URL: https://github.com/apache/airflow/pull/55088#discussion_r2337787877
##########
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
+ else:
+ avg_seconds = sum(durations) / len(durations)
+ logger.info(
+ "Average runtime for dag_id %s (from %d runs): %.2f
seconds",
+ dag_id,
+ len(durations),
+ avg_seconds,
+ )
+ with open("/temporary.txt", "a") as f:
+ f.write(f"Calculated average: {avg_seconds} seconds\n")
+
+ return timezone.utcnow() + timedelta(seconds=avg_seconds)
+
+ def serialize_reference(self) -> dict:
+ return {
+ ReferenceModels.REFERENCE_TYPE_FIELD: self.reference_name,
+ "limit": self.limit,
+ }
+
+ @classmethod
+ def deserialize_reference(cls, reference_data: dict):
+ return cls(limit=reference_data.get("limit", 10))
Review Comment:
IF we're going to put the default value in there, then I think it should be
a constant somewhere so it stays in sync with the actual method's default,
especially since they are in different files and would be easy to miss if we
change one later.
--
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]
