Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
75 lines (74 sloc) 3.81 KB
aws:
# Credentials can be hardcoded or set in environment variables
access_key_id: <%= ENV['AWS_SNOWPLOW_ACCESS_KEY'] %>
secret_access_key: <%= ENV['AWS_SNOWPLOW_SECRET_KEY'] %>
s3:
region: ADD HERE
buckets:
assets: s3://snowplow-hosted-assets # DO NOT CHANGE unless you are hosting the jarfiles etc yourself in your own bucket
jsonpath_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: ADD HERE
encrypted: false
enriched:
good: ADD HERE # e.g. s3://my-out-bucket/enriched/good
archive: ADD HERE # Where to archive enriched events to, e.g. s3://my-archive-bucket/enriched
stream: ADD HERE # S3 Loader's output folder with enriched data. If present raw buckets will be discarded
shredded:
good: ADD HERE # e.g. s3://my-out-bucket/shredded/good
bad: ADD HERE # e.g. s3://my-out-bucket/shredded/bad
errors: ADD HERE # Leave blank unless :continue_on_unexpected_error: set to true below
archive: ADD HERE # Where to archive shredded events to, e.g. s3://my-archive-bucket/shredded
consolidate_shredded_output: false # Whether to combine files when copying from hdfs to s3
emr:
ami_version: 5.9.0
region: ADD HERE # 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: ADD HERE # Set this if not running in VPC. Leave blank otherwise
ec2_subnet_id: ADD HERE # Set this if running in VPC. Leave blank otherwise
ec2_key_name: ADD HERE
security_configuration: ADD HERE # Specify your EMR security configuration if needed. Leave blank otherwise
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:
job_name: Snowplow ETL # Give your job a name
master_instance_type: m1.medium
core_instance_count: 2
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: 3 # Number of times to attempt the job in the event of bootstrap failures
configuration:
yarn-site:
yarn.resourcemanager.am.max-attempts: "1"
spark:
maximizeResourceAllocation: "true"
additional_info: # Optional JSON string for selecting additional features
enrich:
versions:
spark_enrich: 1.17.0 # Version of the Spark Enrichment process
output_compression: GZIP # Stream mode supports only GZIP
storage:
versions:
rdb_loader: 0.14.0
rdb_shredder: 0.13.1 # Version of the Spark Shredding process
hadoop_elasticsearch: 0.1.0 # Version of the Hadoop to Elasticsearch copying process
monitoring:
tags: {} # Name-value pairs describing this job
logging:
level: DEBUG # You can optionally switch to INFO for production
snowplow:
method: get
app_id: ADD HERE # e.g. snowplow
collector: ADD HERE # e.g. d3rkrsqld9gmqf.cloudfront.net
protocol: http
port: 80
You can’t perform that action at this time.