Star Schema Benchmark¶

git clone https://github.com/apache/doris.git

cd doris/tools/ssb-tools

./bin/build-ssb-dbgen.sh

./bin/gen-ssb-data.sh -s 100 -c 100

export FE_HOST="xxx"
export FE_HTTP_PORT="8030"
export FE_QUERY_PORT="9030"
export USER="root"
export PASSWORD='xxx'
export DB="ssb"

./bin/create-ssb-tables.sh

$ ./bin/create-ssb-tables.sh 

mysql  Ver 8.0.34-0ubuntu0.20.04.1 for Linux on x86_64 ((Ubuntu))
FE_HOST: 127.0.0.1
FE_QUERY_PORT: 9030
USER: root
DB: ssb
Run DDL from /home/dxlab/opt/doris/tools/ssb-tools/bin/../ddl/create-ssb-tables.sql
Run DDL from /home/dxlab/opt/doris/tools/ssb-tools/bin/../ddl/create-ssb-flat-table.sql
ssb tables has been created

CREATE TABLE `lineorder_flat` (
  `LO_ORDERDATE` date NOT NULL COMMENT "",
  `LO_ORDERKEY` int(11) NOT NULL COMMENT "",
  `LO_LINENUMBER` tinyint(4) NOT NULL COMMENT "",
  `LO_CUSTKEY` int(11) NOT NULL COMMENT "",
  `LO_PARTKEY` int(11) NOT NULL COMMENT "",
  `LO_SUPPKEY` int(11) NOT NULL COMMENT "",
  `LO_ORDERPRIORITY` varchar(100) NOT NULL COMMENT "",
  `LO_SHIPPRIORITY` tinyint(4) NOT NULL COMMENT "",
  `LO_QUANTITY` tinyint(4) NOT NULL COMMENT "",
  `LO_EXTENDEDPRICE` int(11) NOT NULL COMMENT "",
  `LO_ORDTOTALPRICE` int(11) NOT NULL COMMENT "",
  `LO_DISCOUNT` tinyint(4) NOT NULL COMMENT "",
  `LO_REVENUE` int(11) NOT NULL COMMENT "",
  `LO_SUPPLYCOST` int(11) NOT NULL COMMENT "",
  `LO_TAX` tinyint(4) NOT NULL COMMENT "",
  `LO_COMMITDATE` date NOT NULL COMMENT "",
  `LO_SHIPMODE` varchar(100) NOT NULL COMMENT "",
  `C_NAME` varchar(100) NOT NULL COMMENT "",
  `C_ADDRESS` varchar(100) NOT NULL COMMENT "",
  `C_CITY` varchar(100) NOT NULL COMMENT "",
  `C_NATION` varchar(100) NOT NULL COMMENT "",
  `C_REGION` varchar(100) NOT NULL COMMENT "",
  `C_PHONE` varchar(100) NOT NULL COMMENT "",
  `C_MKTSEGMENT` varchar(100) NOT NULL COMMENT "",
  `S_NAME` varchar(100) NOT NULL COMMENT "",
  `S_ADDRESS` varchar(100) NOT NULL COMMENT "",
  `S_CITY` varchar(100) NOT NULL COMMENT "",
  `S_NATION` varchar(100) NOT NULL COMMENT "",
  `S_REGION` varchar(100) NOT NULL COMMENT "",
  `S_PHONE` varchar(100) NOT NULL COMMENT "",
  `P_NAME` varchar(100) NOT NULL COMMENT "",
  `P_MFGR` varchar(100) NOT NULL COMMENT "",執行下列腳本下載並編譯 [tpch-tools](https://github.com/apache/doris/tree/master/tools/tpch-tools) 工具。

```shell
sh build-tpch-dbgen.sh

### 導入數據

我們使用以下指令完成 SSB 測試集所有資料匯入及 SSB FLAT 寬表資料合成並匯入到表裡。


```shell
./bin/load-ssb-data.sh

select count(*) from part;
select count(*) from customer;
select count(*) from supplier;
select count(*) from dates;
select count(*) from lineorder;
select count(*) from lineorder_flat;

./bin/run-ssb-flat-queries.sh

--Q1.1
SELECT SUM(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM lineorder_flat
WHERE  LO_ORDERDATE >= 19930101  AND LO_ORDERDATE <= 19931231 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 LO_ORDERDATE >= 19940101 AND LO_ORDERDATE <= 19940131  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  weekofyear(LO_ORDERDATE) = 6 AND LO_ORDERDATE >= 19940101  AND LO_ORDERDATE <= 19941231 AND LO_DISCOUNT BETWEEN 5 AND 7  AND LO_QUANTITY BETWEEN 26 AND 35;

--Q2.1
SELECT SUM(LO_REVENUE), (LO_ORDERDATE DIV 10000) 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), (LO_ORDERDATE DIV 10000) 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), (LO_ORDERDATE DIV 10000) 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, (LO_ORDERDATE DIV 10000) AS YEAR, SUM(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND LO_ORDERDATE >= 19920101  AND LO_ORDERDATE <= 19971231
GROUP BY C_NATION, S_NATION, YEAR
ORDER BY YEAR ASC, revenue DESC;

--Q3.2
SELECT C_CITY, S_CITY, (LO_ORDERDATE DIV 10000) AS YEAR, SUM(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND LO_ORDERDATE >= 19920101 AND LO_ORDERDATE <= 19971231
GROUP BY C_CITY, S_CITY, YEAR
ORDER BY YEAR ASC, revenue DESC;

--Q3.3
SELECT C_CITY, S_CITY, (LO_ORDERDATE DIV 10000) AS YEAR, SUM(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_CITY IN ('UNITED KI1', 'UNITED KI5') AND S_CITY IN ('UNITED KI1', 'UNITED KI5') AND LO_ORDERDATE >= 19920101 AND LO_ORDERDATE <= 19971231
GROUP BY C_CITY, S_CITY, YEAR
ORDER BY YEAR ASC, revenue DESC;

--Q3.4
SELECT C_CITY, S_CITY, (LO_ORDERDATE DIV 10000) AS YEAR, SUM(LO_REVENUE) AS revenue
FROM lineorder_flat
WHERE C_CITY IN ('UNITED KI1', 'UNITED KI5') AND S_CITY IN ('UNITED KI1', 'UNITED KI5') AND LO_ORDERDATE >= 19971201  AND LO_ORDERDATE <= 19971231
GROUP BY C_CITY, S_CITY, YEAR
ORDER BY YEAR ASC, revenue DESC;

--Q4.1
SELECT (LO_ORDERDATE DIV 10000) 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 IN ('MFGR#1', 'MFGR#2')
GROUP BY YEAR, C_NATION
ORDER BY YEAR ASC, C_NATION ASC;

--Q4.2
SELECT (LO_ORDERDATE DIV 10000) 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 LO_ORDERDATE >= 19970101 AND LO_ORDERDATE <= 19981231 AND P_MFGR IN ('MFGR#1', 'MFGR#2')
GROUP BY YEAR, S_NATION, P_CATEGORY
ORDER BY YEAR ASC, S_NATION ASC, P_CATEGORY ASC;

--Q4.3
SELECT (LO_ORDERDATE DIV 10000) AS YEAR, S_CITY, P_BRAND, SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM lineorder_flat
WHERE S_NATION = 'UNITED STATES' AND LO_ORDERDATE >= 19970101 AND LO_ORDERDATE <= 19981231 AND P_CATEGORY = 'MFGR#14'
GROUP BY YEAR, S_CITY, P_BRAND
ORDER BY YEAR ASC, S_CITY ASC, P_BRAND ASC;

./bin/run-ssb-queries.sh

--Q1.1
SELECT SUM(lo_extendedprice * lo_discount) AS REVENUE
FROM lineorder, dates
WHERE
    lo_orderdate = d_datekey
    AND d_year = 1993
    AND lo_discount BETWEEN 1 AND 3
    AND lo_quantity < 25;
--Q1.2
SELECT SUM(lo_extendedprice * lo_discount) AS REVENUE
FROM lineorder, dates
WHERE
    lo_orderdate = d_datekey
    AND d_yearmonth = 'Jan1994'
    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, dates
WHERE
    lo_orderdate = d_datekey
    AND d_weeknuminyear = 6
    AND d_year = 1994
    AND lo_discount BETWEEN 5 AND 7
    AND lo_quantity BETWEEN 26 AND 35;

--Q2.1
SELECT SUM(lo_revenue), d_year, p_brand
FROM lineorder, dates, part, supplier
WHERE
    lo_orderdate = d_datekey
    AND lo_partkey = p_partkey
    AND lo_suppkey = s_suppkey
    AND p_category = 'MFGR#12'
    AND s_region = 'AMERICA'
GROUP BY d_year, p_brand
ORDER BY p_brand;

--Q2.2
SELECT SUM(lo_revenue), d_year, p_brand
FROM lineorder, dates, part, supplier
WHERE
    lo_orderdate = d_datekey
    AND lo_partkey = p_partkey
    AND lo_suppkey = s_suppkey
    AND p_brand BETWEEN 'MFGR#2221' AND 'MFGR#2228'
    AND s_region = 'ASIA'
GROUP BY d_year, p_brand
ORDER BY d_year, p_brand;

--Q2.3
SELECT SUM(lo_revenue), d_year, p_brand
FROM lineorder, dates, part, supplier
WHERE
    lo_orderdate = d_datekey
    AND lo_partkey = p_partkey
    AND lo_suppkey = s_suppkey
    AND p_brand = 'MFGR#2239'
    AND s_region = 'EUROPE'
GROUP BY d_year, p_brand
ORDER BY d_year, p_brand;

--Q3.1
SELECT
    c_nation,
    s_nation,
    d_year,
    SUM(lo_revenue) AS REVENUE
FROM customer, lineorder, supplier, dates
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_orderdate = d_datekey
    AND c_region = 'ASIA'
    AND s_region = 'ASIA'
    AND d_year >= 1992
    AND d_year <= 1997
GROUP BY c_nation, s_nation, d_year
ORDER BY d_year ASC, REVENUE DESC;

--Q3.2
SELECT
    c_city,
    s_city,
    d_year,
    SUM(lo_revenue) AS REVENUE
FROM customer, lineorder, supplier, dates
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_orderdate = d_datekey
    AND c_nation = 'UNITED STATES'
    AND s_nation = 'UNITED STATES'
    AND d_year >= 1992
    AND d_year <= 1997
GROUP BY c_city, s_city, d_year
ORDER BY d_year ASC, REVENUE DESC;

--Q3.3
SELECT
    c_city,
    s_city,
    d_year,
    SUM(lo_revenue) AS REVENUE
FROM customer, lineorder, supplier, dates
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_orderdate = d_datekey
    AND (
        c_city = 'UNITED KI1'
        OR c_city = 'UNITED KI5'
    )
    AND (
        s_city = 'UNITED KI1'
        OR s_city = 'UNITED KI5'
    )
    AND d_year >= 1992
    AND d_year <= 1997
GROUP BY c_city, s_city, d_year
ORDER BY d_year ASC, REVENUE DESC;

--Q3.4
SELECT
    c_city,
    s_city,
    d_year,
    SUM(lo_revenue) AS REVENUE
FROM customer, lineorder, supplier, dates
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_orderdate = d_datekey
    AND (
        c_city = 'UNITED KI1'
        OR c_city = 'UNITED KI5'
    )
    AND (
        s_city = 'UNITED KI1'
        OR s_city = 'UNITED KI5'
    )
    AND d_yearmonth = 'Dec1997'
GROUP BY c_city, s_city, d_year
ORDER BY d_year ASC, REVENUE DESC;

--Q4.1
SELECT /*+SET_VAR(parallel_fragment_exec_instance_num=4, enable_vectorized_engine=true, batch_size=4096, enable_cost_based_join_reorder=true, enable_projection=true) */
    d_year,
    c_nation,
    SUM(lo_revenue - lo_supplycost) AS PROFIT
FROM dates, customer, supplier, part, lineorder
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_partkey = p_partkey
    AND lo_orderdate = d_datekey
    AND c_region = 'AMERICA'
    AND s_region = 'AMERICA'
    AND (
        p_mfgr = 'MFGR#1'
        OR p_mfgr = 'MFGR#2'
    )
GROUP BY d_year, c_nation
ORDER BY d_year, c_nation;

--Q4.2
SELECT /*+SET_VAR(parallel_fragment_exec_instance_num=2, enable_vectorized_engine=true, batch_size=4096, enable_cost_based_join_reorder=true, enable_projection=true) */  
    d_year,
    s_nation,
    p_category,
    SUM(lo_revenue - lo_supplycost) AS PROFIT
FROM dates, customer, supplier, part, lineorder
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_partkey = p_partkey
    AND lo_orderdate = d_datekey
    AND c_region = 'AMERICA'
    AND s_region = 'AMERICA'
    AND (
        d_year = 1997
        OR d_year = 1998
    )
    AND (
        p_mfgr = 'MFGR#1'
        OR p_mfgr = 'MFGR#2'
    )
GROUP BY d_year, s_nation, p_category
ORDER BY d_year, s_nation, p_category;

--Q4.3
SELECT /*+SET_VAR(parallel_fragment_exec_instance_num=2, enable_vectorized_engine=true, batch_size=4096, enable_cost_based_join_reorder=true, enable_projection=true) */
    d_year,
    s_city,
    p_brand,
    SUM(lo_revenue - lo_supplycost) AS PROFIT
FROM dates, customer, supplier, part, lineorder
WHERE
    lo_custkey = c_custkey
    AND lo_suppkey = s_suppkey
    AND lo_partkey = p_partkey
    AND lo_orderdate = d_datekey
    AND s_nation = 'UNITED STATES'
    AND (
        d_year = 1997
        OR d_year = 1998
    )
    AND p_category = 'MFGR#14'
GROUP BY d_year, s_city, p_brand
ORDER BY d_year, s_city, p_brand;