You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by GitBox <gi...@apache.org> on 2019/01/09 00:24:54 UTC
[GitHub] kaxil closed pull request #4433: [AIRFLOW-3627] Improve queries
performance in /task_stats in views.py by ~20%
kaxil closed pull request #4433: [AIRFLOW-3627] Improve queries performance in /task_stats in views.py by ~20%
URL: https://github.com/apache/airflow/pull/4433
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/airflow/www/views.py b/airflow/www/views.py
index bc8e392b3a..f62fc5eca2 100644
--- a/airflow/www/views.py
+++ b/airflow/www/views.py
@@ -590,21 +590,24 @@ def task_stats(self, session=None):
dag_ids = session.query(Dag.dag_id)
LastDagRun = (
- session.query(DagRun.dag_id, sqla.func.max(DagRun.execution_date).label('execution_date'))
- .join(Dag, Dag.dag_id == DagRun.dag_id)
- .filter(DagRun.state != State.RUNNING)
- .filter(Dag.is_active == True) # noqa: E712
- .filter(Dag.is_subdag == False) # noqa: E712
- .group_by(DagRun.dag_id)
- .subquery('last_dag_run')
+ session.query(
+ DagRun.dag_id,
+ sqla.func.max(DagRun.execution_date).label('execution_date')
+ )
+ .join(Dag, Dag.dag_id == DagRun.dag_id)
+ .filter(DagRun.state != State.RUNNING,
+ Dag.is_active,
+ Dag.is_subdag == False) # noqa: E712
+ .group_by(DagRun.dag_id)
+ .subquery('last_dag_run')
)
RunningDagRun = (
session.query(DagRun.dag_id, DagRun.execution_date)
- .join(Dag, Dag.dag_id == DagRun.dag_id)
- .filter(DagRun.state == State.RUNNING)
- .filter(Dag.is_active == True) # noqa: E712
- .filter(Dag.is_subdag == False) # noqa: E712
- .subquery('running_dag_run')
+ .join(Dag, Dag.dag_id == DagRun.dag_id)
+ .filter(DagRun.state == State.RUNNING,
+ Dag.is_active,
+ Dag.is_subdag == False) # noqa: E712
+ .subquery('running_dag_run')
)
# Select all task_instances from active dag_runs.
diff --git a/airflow/www_rbac/views.py b/airflow/www_rbac/views.py
index 3177a5540b..6a74ea1d69 100644
--- a/airflow/www_rbac/views.py
+++ b/airflow/www_rbac/views.py
@@ -333,19 +333,18 @@ def task_stats(self, session=None):
LastDagRun = (
session.query(
- DagRun.dag_id,
- sqla.func.max(DagRun.execution_date).label('execution_date'))
- .join(Dag, Dag.dag_id == DagRun.dag_id)
- .filter(DagRun.state != State.RUNNING)
- .filter(Dag.is_active == True) # noqa
- .group_by(DagRun.dag_id)
- .subquery('last_dag_run')
+ DagRun.dag_id,
+ sqla.func.max(DagRun.execution_date).label('execution_date')
+ )
+ .join(Dag, Dag.dag_id == DagRun.dag_id)
+ .filter(DagRun.state != State.RUNNING, Dag.is_active)
+ .group_by(DagRun.dag_id)
+ .subquery('last_dag_run')
)
RunningDagRun = (
session.query(DagRun.dag_id, DagRun.execution_date)
.join(Dag, Dag.dag_id == DagRun.dag_id)
- .filter(DagRun.state == State.RUNNING)
- .filter(Dag.is_active == True) # noqa
+ .filter(DagRun.state == State.RUNNING, Dag.is_active)
.subquery('running_dag_run')
)
@@ -1391,7 +1390,7 @@ def duration(self, session=None):
TF = models.TaskFail
ti_fails = (
session.query(TF)
- .filter(TF.dag_id == dag.dag_id, # noqa
+ .filter(TF.dag_id == dag.dag_id,
TF.execution_date >= min_date,
TF.execution_date <= base_date,
TF.task_id.in_([t.task_id for t in dag.tasks]))
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services