#
# This is an example YAML profile for cassandra-stress
#
# insert data
# cassandra-stress user profile=/home/jake/stress1.yaml ops(insert=1)
#
# read, using query simple1:
# cassandra-stress profile=/home/jake/stress1.yaml ops(simple1=1)
#
# mixed workload (90/10)
# cassandra-stress user profile=/home/jake/stress1.yaml ops(insert=1,simple1=9)


#
# Keyspace info
#
keyspace: stresscql

#
# The CQL for creating a keyspace (optional if it already exists)
#
keyspace_definition: |
  CREATE KEYSPACE stresscql WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};

#
# Table info
#
table: typestest

#
# The CQL for creating a table you wish to stress (optional if it already exists)
#
table_definition: |
  CREATE TABLE typestest (
        name text,
        choice boolean,
        date timestamp,
        address inet,
        dbl double,
        lval bigint,
        ival int,
        uid timeuuid,
        value blob,
        PRIMARY KEY((name,choice), date, address, dbl, lval, ival, uid)
  ) 
    WITH compaction = { 'class':'LeveledCompactionStrategy' }
#    AND compression = { 'sstable_compression' : '' }
#    AND comment='A table of many types to test wide rows'

#
# Optional meta information on the generated columns in the above table
# The min and max only apply to text and blob types
# The distribution field represents the total unique population
# distribution of that column across rows.  Supported types are
# 
#      EXP(min..max)                        An exponential distribution over the range [min..max]
#      EXTREME(min..max,shape)              An extreme value (Weibull) distribution over the range [min..max]
#      GAUSSIAN(min..max,stdvrng)           A gaussian/normal distribution, where mean=(min+max)/2, and stdev is (mean-min)/stdvrng
#      GAUSSIAN(min..max,mean,stdev)        A gaussian/normal distribution, with explicitly defined mean and stdev
#      UNIFORM(min..max)                    A uniform distribution over the range [min, max]
#      FIXED(val)                           A fixed distribution, always returning the same value
#      Aliases: extr, gauss, normal, norm, weibull
#
#      If preceded by ~, the distribution is inverted
#
# Defaults for all columns are size: uniform(4..8), population: uniform(1..100B), cluster: fixed(1)
#
columnspec:
  - name: name
    size: uniform(1..10)
    population: uniform(1..10)     # the range of unique values to select for the field (default is 100Billion)
  - name: date
    cluster: uniform(20..40)
  - name: lval
    population: gaussian(1..1000)
    cluster: uniform(1..4)

insert:
  partitions: uniform(1..50)       # number of unique partitions to update in a single operation
                                  # if batchcount > 1, multiple batches will be used but all partitions will
                                  # occur in all batches (unless they finish early); only the row counts will vary
  batchtype: LOGGED               # type of batch to use
  select: uniform(1..10)/10       # uniform chance any single generated CQL row will be visited in a partition;
                                  # generated for each partition independently, each time we visit it

#
# A list of queries you wish to run against the schema
#
queries:
   simple1:
      cql: select * from typestest where name = ? and choice = ? LIMIT 100
      fields: samerow             # samerow or multirow (select arguments from the same row, or randomly from all rows in the partition)
   range1:
      cql: select * from typestest where name = ? and choice = ? and date >= ? LIMIT 100
      fields: multirow            # samerow or multirow (select arguments from the same row, or randomly from all rows in the partition)


#
# A list of bulk read queries that analytics tools may perform against the schema
# Each query will sweep an entire token range, page by page.
#
token_range_queries:
  all_columns_tr_query:
    columns: '*'
    page_size: 5000

  value_tr_query:
    columns: value