spark-pagerank.yml

apiVersion: "sparkoperator.k8s.io/v1beta2"
kind: SparkApplication
metadata:
  name: "pyspark-pagerank-{{ ds }}-{{ task_instance.try_number }}"
  namespace: spark-job
spec:
  type: Python
  pythonVersion: "3"
  mode: cluster
  image: "afonsoaugusto/pagerank:latest"
  imagePullPolicy: Always
  mainApplicationFile: local:///app/pagerank.py
  sparkVersion: "3.0.0"
  restartPolicy:
    type: OnFailure
    onFailureRetries: 3
    onFailureRetryInterval: 10
    onSubmissionFailureRetries: 5
    onSubmissionFailureRetryInterval: 20
  hadoopConf:
    "fs.s3a.endpoint": "http://minio.minio-operator.svc.cluster.local:9000"
  driver:
    cores: 1
    coreLimit: "1200m"
    memory: "512m"
    labels:
      version: 3.0.0
    serviceAccount: spark-spark
    envVars:
      FILE_PROCESS: "/app/pagerank_data.txt"
      RANK_TOP: "5"
  executor:
    cores: 1
    instances: 3
    memory: "512m"
    labels:
      version: 3.0.0