Cloud Formation example for Glue Spark Job with metrics and scheduler

Glue_Spark_job_example.yml

AWSTemplateFormatVersion: '2010-09-09'
Description: Cloud Formation example for Glue Spark Job with metrics and scheduler 

Parameters:
  ArtifactBucket:
    Description: A global deployable artefact bucket
    Type: String
    Default: artefacts
  ServiceName:
    Description: Service Name that owns the stack when created
    Type: String
    Default: awesome-service
  Environment:
    Description: Name of the environment the service is being deployed.
    Type: String
    Default: dev

Resources:
  MyGlueSparkJob:
    Type: AWS::Glue::Job
    Properties:
      Role: !Ref MyGlueSparkJobRole
      # TODO: Size your cluster accordingly - For each unit here your have 4vCPUs and 16GB RAM
      AllocatedCapacity: 5
      Command:
        Name: glueetl
        ScriptLocation: !Sub s3://${ArtifactBucket}/${ServiceName}/glue_spark_etl_job.py
      DefaultArguments:
        "--environment": !Ref Environment
        "--enable-metrics": 'true'
        "--output_bucket_uri": !Sub "s3://${ServiceName}/etl_job_results_output"
        "--input_bucketuri": !Sub "s3://${ServiceName}/etl_job_results_input"
      ExecutionProperty:
        MaxConcurrentRuns: 1
      MaxRetries: 1
      Name: !Sub ${Environment}-${ServiceName}-generator

  MyGlueSparkJobJobTrigger:
    Type: AWS::Glue::Trigger
    Properties:
      Type: SCHEDULED
      Description: DESCRIPTION_SCHEDULED
      Schedule: cron(0 0 * * ? *)
      Actions:
        - JobName: !Sub ${Environment}-${ServiceName}-generator
      Name: !Sub ${Environment}-${ServiceName}-generator-trigger

  MyGlueSparkJobRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: "2012-10-17"
        Statement:
          -
            Effect: Allow
            Principal:
              Service:
                - "glue.amazonaws.com"
            Action:
              - "sts:AssumeRole"
      Path: "/"
      Policies:
        -
          PolicyName: root
          PolicyDocument:
            Version: "2012-10-17"
            Statement:
              -
                Effect: Allow
                Action:
                  - logs:CreateLogGroup
                  - logs:CreateLogStream
                  - logs:PutLogEvents
                Resource: arn:aws:logs:*:*:*
              -
                Effect: Allow
                Action:
                  - s3:*
                Resource:
                  - Fn::ImportValue: !Sub "s3://${ServiceName}/etl_job_results_output"
                  - Fn::Join:
                    - ''
                    - - Fn::ImportValue: "s3://${ServiceName}/etl_job_results_output"
                      - '/*'
              -
                Effect: Allow
                Action:
                  - s3:*
                Resource:
                  - arn:aws:s3:::aws-glue-*/*
                  - arn:aws:s3:::*/*aws-glue-*/*
                  - arn:aws:s3:::aws-glue-*
              -
                Effect: Allow
                Action:
                  - glue:CreateDatabase
                  - glue:DeleteDatabase
                  - glue:GetDatabase
                  - glue:GetDatabases
                  - glue:UpdateDatabase
                  - glue:CreateTable
                  - glue:DeleteTable
                  - glue:BatchDeleteTable
                  - glue:UpdateTable
                  - glue:GetTable
                  - glue:GetTables
                  - glue:BatchCreatePartition
                  - glue:CreatePartition
                  - glue:DeletePartition
                  - glue:BatchDeletePartition
                  - glue:UpdatePartition
                  - glue:GetPartition
                  - glue:GetPartitions
                  - glue:BatchGetPartition
                Resource: "*"
              - Effect: Allow
                Action:
                  - 'athena:*'
                Resource: '*'
              -
                Effect: Allow
                Action:
                  - cloudwatch:*
                Resource: '*'