stress_profiles/repair_wide_rows.yaml

keyspace: stresscql
keyspace_definition: |
  CREATE KEYSPACE stresscql WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 2};

table: typestest
table_definition: |
  CREATE TABLE typestest (
        key text,
        col1 text,
        val blob,
        PRIMARY KEY(key, col1)
  ) 
    WITH compaction = { 'class':'LeveledCompactionStrategy' }
    AND compression = {'chunk_length_in_kb': '1', 'class': 'org.apache.cassandra.io.compress.LZ4Compressor'};

#
# 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
#      SEQ(min..max)                        A fixed sequence, returning values in the range min to max sequentially (starting based on seed), wrapping if necessary.
#      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: key
    size: fixed(10)
    population: fixed(1)     # the range of unique values to select for the field (default is 100Billion)
  - name: col1
    cluster: fixed(1M)
  - name: val
    size: fixed(1K)

insert:
  partitions: fixed(1)       # 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: fixed(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
queries:
   simple1:
      cql: select * from typestest where key = ? and col1 = ? LIMIT 100
      fields: samerow             # samerow or multirow (select arguments from the same row, or randomly from all rows in the partition)