ferruzzi commented on code in PR #55088:
URL: https://github.com/apache/airflow/pull/55088#discussion_r2356129905
##########
airflow-core/src/airflow/models/deadline.py:
##########
@@ -366,6 +367,76 @@ 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."""
+
+ DEFAULT_LIMIT = 10
+ limit: int
+ min_runs: int | None = None
+ required_kwargs = {"dag_id"}
+
+ def __post_init__(self):
+ if self.min_runs is None:
+ self.min_runs = self.limit
+ if self.min_runs < 1:
+ raise ValueError("min_runs must be at least 1")
+
+ @provide_session
+ def _evaluate_with(self, *, session: Session, **kwargs: Any) ->
datetime | None:
+ 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) < cast("int", self.min_runs):
+ logger.info(
+ "Only %d completed DAG runs found for dag_id: %s (need
%d), skipping deadline creation",
+ len(durations),
+ dag_id,
+ self.min_runs,
+ )
+ return None
+ 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,
+ )
+ return timezone.utcnow() + timedelta(seconds=avg_seconds)
Review Comment:
Interval is added in the base class's `evaluate_with` after the child
class's `_evaluate_with` returns. My mistake.
--
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]
