ClickHouse/docs/en/getting-started/example-datasets/star-schema.md

sidebar_label	description
Star Schema Benchmark	Dataset based on the TPC-H dbgen source. The coding style and architecture follows the TPCH dbgen.

Star Schema Benchmark

Compiling dbgen:

$ git clone git@github.com:vadimtk/ssb-dbgen.git
$ cd ssb-dbgen
$ make

Generating data:

:::warning
With -s 100 dbgen generates 600 million rows (67 GB), while while -s 1000 it generates 6 billion rows (which takes a lot of time) :::

$ ./dbgen -s 1000 -T c
$ ./dbgen -s 1000 -T l
$ ./dbgen -s 1000 -T p
$ ./dbgen -s 1000 -T s

Creating tables in ClickHouse:

CREATE TABLE customer
(
        C_CUSTKEY       UInt32,
        C_NAME          String,
        C_ADDRESS       String,
        C_CITY          LowCardinality(String),
        C_NATION        LowCardinality(String),
        C_REGION        LowCardinality(String),
        C_PHONE         String,
        C_MKTSEGMENT    LowCardinality(String)
)
ENGINE = MergeTree ORDER BY (C_CUSTKEY);

CREATE TABLE lineorder
(
    LO_ORDERKEY             UInt32,
    LO_LINENUMBER           UInt8,
    LO_CUSTKEY              UInt32,
    LO_PARTKEY              UInt32,
    LO_SUPPKEY              UInt32,
    LO_ORDERDATE            Date,
    LO_ORDERPRIORITY        LowCardinality(String),
    LO_SHIPPRIORITY         UInt8,
    LO_QUANTITY             UInt8,
    LO_EXTENDEDPRICE        UInt32,
    LO_ORDTOTALPRICE        UInt32,
    LO_DISCOUNT             UInt8,
    LO_REVENUE              UInt32,
    LO_SUPPLYCOST           UInt32,
    LO_TAX                  UInt8,
    LO_COMMITDATE           Date,
    LO_SHIPMODE             LowCardinality(String)
)
ENGINE = MergeTree PARTITION BY toYear(LO_ORDERDATE) ORDER BY (LO_ORDERDATE, LO_ORDERKEY);

CREATE TABLE part
(
        P_PARTKEY       UInt32,
        P_NAME          String,
        P_MFGR          LowCardinality(String),
        P_CATEGORY      LowCardinality(String),
        P_BRAND         LowCardinality(String),
        P_COLOR         LowCardinality(String),
        P_TYPE          LowCardinality(String),
        P_SIZE          UInt8,
        P_CONTAINER     LowCardinality(String)
)
ENGINE = MergeTree ORDER BY P_PARTKEY;

CREATE TABLE supplier
(
        S_SUPPKEY       UInt32,
        S_NAME          String,
        S_ADDRESS       String,
        S_CITY          LowCardinality(String),
        S_NATION        LowCardinality(String),
        S_REGION        LowCardinality(String),
        S_PHONE         String
)
ENGINE = MergeTree ORDER BY S_SUPPKEY;

Inserting data:

$ clickhouse-client --query "INSERT INTO customer FORMAT CSV" < customer.tbl
$ clickhouse-client --query "INSERT INTO part FORMAT CSV" < part.tbl
$ clickhouse-client --query "INSERT INTO supplier FORMAT CSV" < supplier.tbl
$ clickhouse-client --query "INSERT INTO lineorder FORMAT CSV" < lineorder.tbl

Converting “star schema” to denormalized “flat schema”:

SET max_memory_usage = 20000000000;

CREATE TABLE lineorder_flat
ENGINE = MergeTree ORDER BY (LO_ORDERDATE, LO_ORDERKEY)
AS SELECT *
FROM lineorder AS l
INNER JOIN customer AS c ON c.C_CUSTKEY = l.LO_CUSTKEY
INNER JOIN supplier AS s ON s.S_SUPPKEY = l.LO_SUPPKEY
INNER JOIN part AS p ON p.P_PARTKEY = l.LO_PARTKEY;

Running the queries:

Q1.1

SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM lineorder_flat
WHERE toYear(LO_ORDERDATE) = 1993 AND LO_DISCOUNT BETWEEN 1 AND 3 AND LO_QUANTITY < 25;

Q1.2

SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM lineorder_flat
WHERE toYYYYMM(LO_ORDERDATE) = 199401 AND LO_DISCOUNT BETWEEN 4 AND 6 AND LO_QUANTITY BETWEEN 26 AND 35;

Q1.3

SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM lineorder_flat
WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994
  AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35;

Q2.1

SELECT
    sum(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM lineorder_flat
WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Q2.2

SELECT
    sum(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM lineorder_flat
WHERE P_BRAND >= 'MFGR#2221' AND P_BRAND <= 'MFGR#2228' AND S_REGION = 'ASIA'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Q2.3

SELECT
    sum(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM lineorder_flat
WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Q3.1

SELECT
    C_NATION,
    S_NATION,
    toYear(LO_ORDERDATE) AS year,
    sum(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997
GROUP BY
    C_NATION,
    S_NATION,
    year
ORDER BY
    year ASC,
    revenue DESC;

Q3.2

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    sum(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Q3.3

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    sum(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND year >= 1992 AND year <= 1997
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Q3.4

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    sum(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND toYYYYMM(LO_ORDERDATE) = 199712
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Q4.1

SELECT
    toYear(LO_ORDERDATE) AS year,
    C_NATION,
    sum(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM lineorder_flat
WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2')
GROUP BY
    year,
    C_NATION
ORDER BY
    year ASC,
    C_NATION ASC;

Q4.2

SELECT
    toYear(LO_ORDERDATE) AS year,
    S_NATION,
    P_CATEGORY,
    sum(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM lineorder_flat
WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2')
GROUP BY
    year,
    S_NATION,
    P_CATEGORY
ORDER BY
    year ASC,
    S_NATION ASC,
    P_CATEGORY ASC;

Q4.3

SELECT
    toYear(LO_ORDERDATE) AS year,
    S_CITY,
    P_BRAND,
    sum(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM lineorder_flat
WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14'
GROUP BY
    year,
    S_CITY,
    P_BRAND
ORDER BY
    year ASC,
    S_CITY ASC,
    P_BRAND ASC;

Original article