Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- :logging:
- :level: DEBUG # You can optionally switch to INFO for production
- :aws:
- :access_key_id: "xxx"
- :secret_access_key: "xxx"
- :s3:
- :region: "us-east-1"
- :buckets:
- :assets: s3://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
- :log: s3://prod-snowplow-logs
- :raw:
- :in: s3://prod-snowplow-logs
- :processing: s3://prod-snowplow-out/processing
- :archive: s3://prod-snowplow-archive/raw # e.g. s3://my-archive-bucket/raw
- :enriched:
- :good: s3://prod-snowplow-out/enriched/good # e.g. s3://my-out-bucket/enriched/good
- :bad: s3://prod-snowplow-out/enriched/bad # e.g. s3://my-out-bucket/enriched/bad
- :errors: # Leave blank unless :continue_on_unexpected_error: set to true below
- :shredded:
- :good: s3://prod-snowplow-out/shredded/good # e.g. s3://my-out-bucket/shredded/good
- :bad: s3://prod-snowplow-out/shredded/bad # e.g. s3://my-out-bucket/shredded/bad
- :errors: # Leave blank unless :continue_on_unexpected_error: set to true below
- :emr:
- :ami_version: 2.4.2 # Choose as per http://docs.aws.amazon.com/ElasticMapReduce/latest/DeveloperGuide/emr-plan-ami.html
- :region: "us-east-1" # Always set this
- :placement: "us-east-1a" # Set this if not running in VPC. Leave blank otherwise
- :ec2_subnet_id: # Set this if running in VPC. Leave blank otherwise
- :ec2_key_name: "napa"
- :software:
- :hbase: # To launch on cluster, provide version, "0.92.0", keep quotes
- :lingual: # To launch on cluster, provide version, "1.1", keep quotes
- # Adjust your Hadoop cluster below
- :jobflow:
- :master_instance_type: m1.small
- :core_instance_count: 2
- :core_instance_type: m1.small
- :task_instance_count: 0 # Increase to use spot instances
- :task_instance_type: m1.small
- :task_instance_bid: 0.015 # In USD. Adjust bid, or leave blank for non-spot-priced (i.e. on-demand) task instances
- :etl:
- :job_name: Snowplow ETL # Give your job a name
- :versions:
- :hadoop_enrich: 0.6.0 # Version of the Hadoop Enrichment process
- :hadoop_shred: 0.2.0 # Version of the Hadoop Shredding process
- :collector_format: cloudfront # Or 'clj-tomcat' for the Clojure Collector
- :continue_on_unexpected_error: false # Set to 'true' (and set :out_errors: above) if you don't want any exceptions thrown from ETL
- :iglu:
- :schema: iglu:com.snowplowanalytics.iglu/resolver-config/jsonschema/1-0-0
- :data:
- :cache_size: 500
- :repositories:
- - :name: "Iglu Central"
- :priority: 0
- :vendor_prefixes:
- - com.snowplowanalytics
- :connection:
- :http:
- :uri: http://iglucentral.com
- - :name: "Sonicbids"
- :priority: 0
- :vendor_prefixes:
- - com.sonicbids
- :connection:
- :http:
- :uri: http://s3.amazonaws.com/prod-snowplow-s3.napa.sonicbids.com/
Advertisement
Add Comment
Please, Sign In to add comment