emr-etl-runner config.yml

aws:
  # Credentials can be hardcoded or set in environment variables
  access_key_id: #####
  secret_access_key: ####
  s3:
    region: us-east-1
    buckets:
      assets: s3n://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
      jsonpath_assets: s3://snowplow-hosted-assets  # If you have defined your own JSON Schemas, add the s3:// path to your own JSON Path files in your own bucket here
      log: s3n://aff-snow/snow-log
      raw:
        in:
          - s3n://aff-snow          # e.g. s3://my-in-bucket
        processing: s3n://aff-snow/snow-processing
        archive: s3n://aff-snow/snow-archive    # e.g. s3://my-archive-bucket/in
      enriched:
        good: s3n://aff-snow/enriched/good       # e.g. s3://my-out-bucket/enriched/good
        bad: s3n://aff-snow/enriched/bad        # e.g. s3://my-out-bucket/enriched/bad
        errors: s3n://aff-snow/enriched/errors     # Leave blank unless continue_on_unexpected_error: set to true below
        archive: s3n://aff-snow/enriched/archive    # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
      shredded:
        good: s3n://aff-snow/shredded/good       # e.g. s3://my-out-bucket/shredded/good
        bad: s3n://aff-snow/shredded/bad        # e.g. s3://my-out-bucket/shredded/bad
        errors: s3n://aff-snow/shredded/errors     # Leave blank unless continue_on_unexpected_error: set to true below
        archive: s3n://aff-snow/shredded/archive    # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
  emr:
    ami_version: 4.5.0      # Don't change this
    region: us-east-1        # Always set this
    jobflow_role: EMR_EC2_DefaultRole # Created using $ aws emr create-default-roles
    service_role: EMR_DefaultRole     # Created using $ aws emr create-default-roles
    placement:  # Set this if not running in VPC. Leave blank otherwise
    ec2_subnet_id: subnet-f9b69ed1 # Set this if running in VPC. Leave blank otherwise
    ec2_key_name: snowplow
    bootstrap: []           # Set this to specify custom boostrap actions. Leave empty otherwise
    software:
      hbase:                # Optional. To launch on cluster, provide version, "0.92.0", keep quotes. Leave empty otherwise.
      lingual:              # Optional. To launch on cluster, provide version, "1.1", keep quotes. Leave empty otherwise.
    # Adjust your Hadoop cluster below
    jobflow:
      master_instance_type: m1.medium
      core_instance_count: 1
      core_instance_type: m1.medium
      core_instance_ebs:    # Optional. Attach an EBS volume to each core instance.
        volume_size: 100    # Gigabytes
        volume_type: "gp2"
        volume_iops: 400    # Optional. Will only be used if volume_type is "io1"
        ebs_optimized: false # Optional. Will default to true
      task_instance_count: 0 # Increase to use spot instances
      task_instance_type: m1.medium
      task_instance_bid: 0.015 # In USD. Adjust bid, or leave blank for non-spot-priced (i.e. on-demand) task instances
    bootstrap_failure_tries: 2 # Number of times to attempt the job in the event of bootstrap failures
    additional_info:        # Optional JSON string for selecting additional features
collectors:
  format: thrift # Or 'clj-tomcat' for the Clojure Collector, or 'thrift' for Thrift records, or 'tsv/com.amazon.aws.cloudfront/wd_access_log' for Cloudfront access logs
enrich:
  job_name: johnsnow # Give your job a name
  versions:
    hadoop_enrich: 1.8.0 # Version of the Hadoop Enrichment process
    hadoop_shred: 0.10.0 # Version of the Hadoop Shredding process
    hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying process
  continue_on_unexpected_error: false # Set to 'true' (and set out_errors: above) if you don't want any exceptions thrown from ETL
  output_compression: GZIP # Compression only supported with Redshift, set to NONE if you have Postgres targets. Allowed formats: NONE, GZIP
storage:
  download:
    folder: # Postgres-only config option. Where to store the downloaded files. Leave blank for Redshift
  targets:
    - name: "johnsnow"
      type: redshift
      host: ###### # The endpoint as shown in the Redshift console
      database: ##### # Name of database
      port: #### # Default Redshift port
      table: atomic.events
      username: #####
      password: #####
      maxerror: 3 # Stop loading on first error, or increase to permit more load errors
      comprows: 200000 # Default for a 1 XL node cluster. Not used unless --include compupdate specified
      ssl_mode: disable
monitoring:
  tags: {} # Name-value pairs describing this job
  logging:
    level: DEBUG # You can optionally switch to INFO for production