mik-laj commented on a change in pull request #7163: [AIRFLOW-6542] add spark-on-k8s operator/hook/sensor URL: https://github.com/apache/airflow/pull/7163#discussion_r366816834
########## File path: airflow/contrib/sensors/spark_kubernetes_sensor.py ########## @@ -0,0 +1,82 @@ +# -*- coding: utf-8 -*- +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +from typing import Dict, Optional + +from kubernetes import client + +from airflow.contrib.hooks.kubernetes_hook import Kuberneteshook +from airflow.exceptions import AirflowException +from airflow.sensors.base_sensor_operator import BaseSensorOperator +from airflow.utils.decorators import apply_defaults + + +class SparkKubernetesSensor(BaseSensorOperator): + """ + checks sparkapplication state on kubernetes + :param sparkapplication_name: sparkapplication resource name + :param namespace: the kubernetes namespace where the sparkApplication reside in + :param kube_config: kubeconfig file location + :param in_cluster: if airflow runs inside kubernetes pod take configuration from inside the cluster + """ + + template_fields = ('sparkapplication_name', 'namespace', 'kube_config') + INTERMEDIATE_STATES = ('SUBMITTED', 'RUNNING',) + FAILURE_STATES = ('FAILED', 'SUBMISSION_FAILED', 'UNKNOWN') + SUCCESS_STATES = 'COMPLETED' + + @apply_defaults + def __init__(self, + sparkapplication_name: str, + namespace: str = 'default', + kube_config: Optional[str] = None, + in_cluster: bool = False, + *args, **kwargs): + super().__init__(*args, **kwargs) + self.sparkapplication_name = sparkapplication_name + self.namespace = namespace + self.kube_config = kube_config + self.in_cluster = in_cluster + self.api_client = Kuberneteshook( Review comment: Maybe it's worth moving it to the pre_execute method? The constructor is called by every worker repeatedly when each task is started. It really should be low cost. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
