spark-job/localconfig-auto-discover.yaml

# This is how many parts we split the full token range in.
# Each of these splits is then compared between the clusters
splits: 10000

# Number of buckets - splits / buckets should be under 100k to avoid wide partitions when storing the metadata
buckets: 100

# global rate limit - this is how many q/s you think the target clusters can handle
rate_limit: 10000

# optional job id - if restarting a job, set the correct job_id here to avoid re-diffing old splits
# job_id: 4e2c6c6b-bed7-4c4e-bd4c-28bef89c3cef

# Fetch size to use for the query fetching the tokens in the cluster
token_scan_fetch_size: 1000
# Fetch size to use for the queries fetching the rows of each partition
partition_read_fetch_size: 1000

read_timeout_millis: 10000
reverse_read_probability: 0.5
consistency_level: ALL
metadata_options:
  keyspace: cassandradiff
  replication: "{'class':'SimpleStrategy', 'replication_factor':'1'}"
  ttl: 31536000
  should_init: true
cluster_config:
  source:
    impl: "org.apache.cassandra.diff.ContactPointsClusterProvider"
    name: "local_test_1"
    contact_points: "127.0.0.1"
    port: "9042"
    dc: "datacenter1"
  target:
    impl: "org.apache.cassandra.diff.ContactPointsClusterProvider"
    name: "local_test_2"
    contact_points: "127.0.0.1"
    port: "9043"
    dc: "datacenter1"
  metadata:
    impl: "org.apache.cassandra.diff.ContactPointsClusterProvider"
    name: "local_test"
    contact_points: "127.0.0.1"
    port: "9042"
    dc: "datacenter1"