1. 首先从TPC官网上下载TPC-H tools的压缩包,网址为:http://www.tpc.org/tpc_documents_current_versions/current_specifications.asp;
2. 解压;
3. 使用Visual Studio打开项目tpch.sln(dbgen目录下);
4. 右键dbgen项目,选择生成,然后将dbgen\Debug目录下的dbgen.exe拷贝到dbgen目录下;
5. 此时,通过cmd到dbgen目录下,便可根据命令“dbgen-vf -s 1”生成测试数据库实例(-s后面的是Scale Facter因子);
6. 后缀名为“.tbl”即为生成的数据。
7. 然后我在MySQL数据库上建立一个数据库,名为“tpch”;
8. 所有的建表语句在文件dss.ddl中,但是原始文件中没有主外键的约束,所以我自己添加了主外键的约束,注意LINEITEM与PARTSUPP之间存在混合引用的关系,具体建表语句如下:
DROP TABLE IF EXISTS LINEITEM;
DROP TABLE IF EXISTS ORDERS;
DROP TABLE IF EXISTS CUSTOMER;
DROP TABLE IF EXISTS PARTSUPP;
DROP TABLE IF EXISTS SUPPLIER;
DROP TABLE IF EXISTS PART;
DROP TABLE IF EXISTS NATION;
DROP TABLE IF EXISTS REGION;
CREATE TABLE REGION ( R_REGIONKEY INTEGER NOT NULL,
R_NAME CHAR(25) NOT NULL,
R_COMMENT VARCHAR(152),
PRIMARY KEY(R_REGIONKEY));
CREATE TABLE NATION ( N_NATIONKEY INTEGER NOT NULL,
N_NAME CHAR(25) NOT NULL,
N_REGIONKEY INTEGER NOT NULL,
N_COMMENT VARCHAR(152),
PRIMARY KEY(N_NATIONKEY),
FOREIGN KEY(N_REGIONKEY) REFERENCES REGION(R_REGIONKEY));
CREATE TABLE PART ( P_PARTKEY INTEGER NOT NULL,
P_NAME VARCHAR(55) NOT NULL,
P_MFGR CHAR(25) NOT NULL,
P_BRAND CHAR(10) NOT NULL,
P_TYPE VARCHAR(25) NOT NULL,
P_SIZE INTEGER NOT NULL,
P_CONTAINER CHAR(10) NOT NULL,
P_RETAILPRICE DECIMAL(15,2) NOT NULL,
P_COMMENT VARCHAR(23) NOT NULL,
PRIMARY KEY(P_PARTKEY));
CREATE TABLE SUPPLIER ( S_SUPPKEY INTEGER NOT NULL,
S_NAME CHAR(25) NOT NULL,
S_ADDRESS VARCHAR(40) NOT NULL,
S_NATIONKEY INTEGER NOT NULL,
S_PHONE CHAR(15) NOT NULL,
S_ACCTBAL DECIMAL(15,2) NOT NULL,
S_COMMENT VARCHAR(101) NOT NULL,
PRIMARY KEY(S_SUPPKEY),
FOREIGN KEY(S_NATIONKEY) REFERENCES NATION(N_NATIONKEY));
CREATE TABLE PARTSUPP ( PS_PARTKEY INTEGER NOT NULL,
PS_SUPPKEY INTEGER NOT NULL,
PS_AVAILQTY INTEGER NOT NULL,
PS_SUPPLYCOST DECIMAL(15,2) NOT NULL,
PS_COMMENT VARCHAR(199) NOT NULL,
PRIMARY KEY(PS_PARTKEY, PS_SUPPKEY),
FOREIGN KEY(PS_PARTKEY) REFERENCES PART(P_PARTKEY),
FOREIGN KEY(PS_SUPPKEY) REFERENCES SUPPLIER(S_SUPPKEY));
CREATE TABLE CUSTOMER ( C_CUSTKEY INTEGER NOT NULL,
C_NAME VARCHAR(25) NOT NULL,
C_ADDRESS VARCHAR(40) NOT NULL,
C_NATIONKEY INTEGER NOT NULL,
C_PHONE CHAR(15) NOT NULL,
C_ACCTBAL DECIMAL(15,2) NOT NULL,
C_MKTSEGMENT CHAR(10) NOT NULL,
C_COMMENT VARCHAR(117) NOT NULL,
PRIMARY KEY(C_CUSTKEY),
FOREIGN KEY(C_NATIONKEY) REFERENCES NATION(N_NATIONKEY));
CREATE TABLE ORDERS ( O_ORDERKEY INTEGER NOT NULL,
O_CUSTKEY INTEGER NOT NULL,
O_ORDERSTATUS CHAR(1) NOT NULL,
O_TOTALPRICE DECIMAL(15,2) NOT NULL,
O_ORDERDATE DATE NOT NULL,
O_ORDERPRIORITY CHAR(15) NOT NULL,
O_CLERK CHAR(15) NOT NULL,
O_SHIPPRIORITY INTEGER NOT NULL,
O_COMMENT VARCHAR(79) NOT NULL,
PRIMARY KEY(O_ORDERKEY),
FOREIGN KEY(O_CUSTKEY) REFERENCES CUSTOMER(C_CUSTKEY));
CREATE TABLE LINEITEM ( L_ORDERKEY INTEGER NOT NULL,
L_PARTKEY INTEGER NOT NULL,
L_SUPPKEY INTEGER NOT NULL,
L_LINENUMBER INTEGER NOT NULL,
L_QUANTITY DECIMAL(15,2) NOT NULL,
L_EXTENDEDPRICE DECIMAL(15,2) NOT NULL,
L_DISCOUNT DECIMAL(15,2) NOT NULL,
L_TAX DECIMAL(15,2) NOT NULL,
L_RETURNFLAG CHAR(1) NOT NULL,
L_LINESTATUS CHAR(1) NOT NULL,
L_SHIPDATE DATE NOT NULL,
L_COMMITDATE DATE NOT NULL,
L_RECEIPTDATE DATE NOT NULL,
L_SHIPINSTRUCT CHAR(25) NOT NULL,
L_SHIPMODE CHAR(10) NOT NULL,
L_COMMENT VARCHAR(44) NOT NULL,
PRIMARY KEY(L_ORDERKEY, L_LINENUMBER),
FOREIGN KEY(L_PARTKEY, L_SUPPKEY) REFERENCES PARTSUPP(PS_PARTKEY, PS_SUPPKEY));
9. 然后开始数据导入,具体导入命令如下(下述命令不能正常运行的话,则在登录MySQL客户端时加“--local-infile”):
LOAD DATA LOCAL INFILE '~/tpchdata/region.tbl' INTO TABLE REGION FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/nation.tbl' INTO TABLE NATION FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/part.tbl' INTO TABLE PART FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/supplier.tbl' INTO TABLE SUPPLIER FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/partsupp.tbl' INTO TABLE PARTSUPP FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/customer.tbl' INTO TABLE CUSTOMER FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/orders.tbl' INTO TABLE ORDERS FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
LOAD DATA LOCAL INFILE '~/tpchdata/lineitem.tbl' INTO TABLE LINEITEM FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
10. 右键项目qgen,选择生成,然后 将dbgen\Debug目录下的qgen.exe拷贝到dbgen目录下,并把dbgen\queries文件夹中的sql文件拷出来到目录dbgen\下;
11. 利用命令“qgen-d 1 > _1.sql”生成实例化的SQL,一直运行22次便可得到实例化的22个query(每次需指定query的序号)。
12. 然后就可以利用实例化的query进行测试啦。