blob: 13987e0abf5c72c9ec834a787b4b20f350948c1b [file] [log] [blame]
# Copied from https://gist.github.com/tjake/8995058fed11d9921e31
### DML ###
# Keyspace Name
keyspace: stresscql
# The CQL for creating a keyspace (optional if it already exists)
keyspace_definition: |
CREATE KEYSPACE stresscql WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 3};
# Table name
table: blogposts
# The CQL for creating a table you wish to stress (optional if it already exists)
table_definition: |
CREATE TABLE blogposts (
domain text,
published_date timeuuid,
url text,
author text,
title text,
body text,
PRIMARY KEY(domain, published_date)
) WITH CLUSTERING ORDER BY (published_date DESC)
AND compaction = { 'class':'LeveledCompactionStrategy' }
AND comment='A table to hold blog posts'
### Column Distribution Specifications ###
columnspec:
- name: domain
size: gaussian(5..100) #domain names are relatively short
population: uniform(1..10M) #10M possible domains to pick from
- name: published_date
cluster: fixed(1000) #under each domain we will have max 1000 posts
- name: url
size: uniform(30..300)
- name: title #titles shouldn't go beyond 200 chars
size: gaussian(10..200)
- name: author
size: uniform(5..20) #author names should be short
- name: body
size: gaussian(100..5000) #the body of the blog post can be long
### Batch Ratio Distribution Specifications ###
insert:
partitions: fixed(1) # Our partition key is the domain so only insert one per batch
select: fixed(1)/1000 # We have 1000 posts per domain so 1/1000 will allow 1 post per batch
batchtype: UNLOGGED # Unlogged batches
#
# A list of queries you wish to run against the schema
#
queries:
singlepost:
cql: select * from blogposts where domain = ? LIMIT 1
fields: samerow
timeline:
cql: select url, title, published_date from blogposts where domain = ? LIMIT 10
fields: samerow