Linux環境下安裝TPC-H與資料匯入PostgreSQL
總共需要以下10個步驟,不包括QGEN部分(經過賦值的22個SQL語句參考附錄)。
1. 下載 TPC-H 官方工具包,地址:http://www.tpc.org/tpc_documents_current_versions/current_specifications.asp
2. 解壓工具包,開啟DBGEN資料夾
3. 編輯配置文件,修改其中的引數如下
vim makefile.suite
------------------------------------------------------
CC = gcc
DATABASE =SQLSERVER
VECTORWISE =LINUX
WORKLOAD =TPCH
4. 編譯工具
make -f makefile.suite
5. 生成1G大小的資料
./dbgen -s 1
6. 修改資料檔案,執行以下指令碼去掉資料行結尾的“|”符號,並將更改後的資料檔案儲存在新建的資料夾handle中
mkdir handle
------------------------------------------------------------
for i in `ls *.tbl`
do
name="handle/$i"
echo $name
`touch $name`
`chmod 777 $name`
sed 's/|$//' $i >> $name;
done
7. 開啟PostgreSQL控制檯
psql -h 127.0.0.1 -d postgres -U postgres
8. 執行下面的SQL,建立8張表結構
CREATE TABLE NATION ( N_NATIONKEY INTEGER NOT NULL,
N_NAME CHAR(25) NOT NULL,
N_REGIONKEY INTEGER NOT NULL,
N_COMMENT VARCHAR(152));
CREATE TABLE REGION ( R_REGIONKEY INTEGER NOT NULL,
R_NAME CHAR(25) NOT NULL,
R_COMMENT VARCHAR(152));
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 );
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);
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 );
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);
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);
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);
9. 輸入下面的PostgreSQL命令將步驟6中建立的資料匯入到表中,注意修改實際的檔案路徑
copy region from '/opt/tpc/2.17.3/dbgen/handle/region.tbl' with delimiter as '|' NULL '';
copy nation from '/opt/tpc/2.17.3/dbgen/handle/nation.tbl' with delimiter as '|' NULL '';
copy partsupp from '/opt/tpc/2.17.3/dbgen/handle/partsupp.tbl' with delimiter as '|' NULL '';
copy customer from '/opt/tpc/2.17.3/dbgen/handle/customer.tbl' with delimiter as '|' NULL '';
copy lineitem from '/opt/tpc/2.17.3/dbgen/handle/lineitem.tbl' with delimiter as '|' NULL '';
copy orders from '/opt/tpc/2.17.3/dbgen/handle/orders.tbl' with delimiter as '|' NULL '';
copy part from '/opt/tpc/2.17.3/dbgen/handle/part.tbl' with delimiter as '|' NULL '';
copy supplier from '/opt/tpc/2.17.3/dbgen/handle/supplier.tbl' with delimiter as '|' NULL '';
10. 執行下面的SQL建立主鍵等關係
-- For table REGION
ALTER TABLE REGION
ADD PRIMARY KEY (R_REGIONKEY);
-- For table NATION
ALTER TABLE NATION
ADD PRIMARY KEY (N_NATIONKEY);
ALTER TABLE NATION
ADD FOREIGN KEY (N_REGIONKEY) references REGION;
COMMIT WORK;
-- For table PART
ALTER TABLE PART
ADD PRIMARY KEY (P_PARTKEY);
COMMIT WORK;
-- For table SUPPLIER
ALTER TABLE SUPPLIER
ADD PRIMARY KEY (S_SUPPKEY);
ALTER TABLE SUPPLIER
ADD FOREIGN KEY (S_NATIONKEY) references NATION;
COMMIT WORK;
-- For table PARTSUPP
ALTER TABLE PARTSUPP
ADD PRIMARY KEY (PS_PARTKEY,PS_SUPPKEY);
COMMIT WORK;
-- For table CUSTOMER
ALTER TABLE CUSTOMER
ADD PRIMARY KEY (C_CUSTKEY);
ALTER TABLE CUSTOMER
ADD FOREIGN KEY (C_NATIONKEY) references NATION;
COMMIT WORK;
-- For table LINEITEM
ALTER TABLE LINEITEM
ADD PRIMARY KEY (L_ORDERKEY,L_LINENUMBER);
COMMIT WORK;
-- For table ORDERS
ALTER TABLE ORDERS
ADD PRIMARY KEY (O_ORDERKEY);
COMMIT WORK;
-- For table PARTSUPP
ALTER TABLE PARTSUPP
ADD FOREIGN KEY (PS_SUPPKEY) references SUPPLIER;
COMMIT WORK;
ALTER TABLE PARTSUPP
ADD FOREIGN KEY (PS_PARTKEY) references PART;
COMMIT WORK;
-- For table ORDERS
ALTER TABLE ORDERS
ADD FOREIGN KEY (O_CUSTKEY) references CUSTOMER;
COMMIT WORK;
-- For table LINEITEM
ALTER TABLE LINEITEM
ADD FOREIGN KEY (L_ORDERKEY) references ORDERS;
COMMIT WORK;
ALTER TABLE LINEITEM
ADD FOREIGN KEY (L_PARTKEY,L_SUPPKEY) references PARTSUPP;
COMMIT WORK;
附錄:
/* query 1 */
select
l_returnflag,
l_linestatus,
sum(l_quantity) as sum_qty,
sum(l_extendedprice) as sum_base_price,
sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
avg(l_quantity) as avg_qty,
avg(l_extendedprice) as avg_price,
avg(l_discount) as avg_disc,
count(*) as count_order
from
lineitem
where
l_shipdate <= date '1998-12-01' - interval '90' day
group by
l_returnflag,
l_linestatus
order by
l_returnflag,
l_linestatus;
/* query 2 */
select
s_acctbal,
s_name,
n_name,
p_partkey,
p_mfgr,
s_address,
s_phone,
s_comment
from
part,
supplier,
partsupp,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and p_size = 15
and p_type like '%BRASS'
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'EUROPE'
and ps_supplycost = (
select
min(ps_supplycost)
from
partsupp,
supplier,
nation,
region
where
p_partkey = ps_partkey
and s_suppkey = ps_suppkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'EUROPE'
)
order by
s_acctbal desc,
n_name,
s_name,
p_partkey;
/* query 3 */
select
l_orderkey,
sum(l_extendedprice * (1 - l_discount)) as revenue,
o_orderdate,
o_shippriority
from
customer,
orders,
lineitem
where
c_mktsegment = 'BUILDING'
and c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate < date '1995-03-15'
and l_shipdate > date '1995-03-15'
group by
l_orderkey,
o_orderdate,
o_shippriority
order by
revenue desc,
o_orderdate;
/* query 4 */
select
o_orderpriority,
count(*) as order_count
from
orders
where
o_orderdate >= date '1993-07-01'
and o_orderdate < date '1993-07-01' + interval '3' month
and exists (
select
*
from
lineitem
where
l_orderkey = o_orderkey
and l_commitdate < l_receiptdate
)
group by
o_orderpriority
order by
o_orderpriority;
/* query 5 */
select
n_name,
sum(l_extendedprice * (1 - l_discount)) as revenue
from
customer,
orders,
lineitem,
supplier,
nation,
region
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and l_suppkey = s_suppkey
and c_nationkey = s_nationkey
and s_nationkey = n_nationkey
and n_regionkey = r_regionkey
and r_name = 'ASIA'
and o_orderdate >= date '1994-01-01'
and o_orderdate < date '1994-01-01' + interval '1' year
group by
n_name
order by
revenue desc;
/* query 6 */
select
sum(l_extendedprice * l_discount) as revenue
from
lineitem
where
l_shipdate >= date '1994-01-01'
and l_shipdate < date '1994-01-01' + interval '1' year
and l_discount between .06 - 0.01 and .06 + 0.01
and l_quantity < 24;
/* query 7 */
select
supp_nation,
cust_nation,
l_year,
sum(volume) as revenue
from
(
select
n1.n_name as supp_nation,
n2.n_name as cust_nation,
extract(year from l_shipdate) as l_year,
l_extendedprice * (1 - l_discount) as volume
from
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2
where
s_suppkey = l_suppkey
and o_orderkey = l_orderkey
and c_custkey = o_custkey
and s_nationkey = n1.n_nationkey
and c_nationkey = n2.n_nationkey
and (
(n1.n_name = 'FRANCE' and n2.n_name = 'GERMANY')
or (n1.n_name = 'GERMANY' and n2.n_name = 'FRANCE')
)
and l_shipdate between date '1995-01-01' and date '1996-12-31'
) as shipping
group by
supp_nation,
cust_nation,
l_year
order by
supp_nation,
cust_nation,
l_year;
/* query 8 */
select
o_year,
sum(case
when nation = 'BRAZIL' then volume
else 0
end) / sum(volume) as mkt_share
from
(
select
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) as volume,
n2.n_name as nation
from
part,
supplier,
lineitem,
orders,
customer,
nation n1,
nation n2,
region
where
p_partkey = l_partkey
and s_suppkey = l_suppkey
and l_orderkey = o_orderkey
and o_custkey = c_custkey
and c_nationkey = n1.n_nationkey
and n1.n_regionkey = r_regionkey
and r_name = 'AMERICA'
and s_nationkey = n2.n_nationkey
and o_orderdate between date '1995-01-01' and date '1996-12-31'
and p_type = 'ECONOMY ANODIZED STEEL'
) as all_nations
group by
o_year
order by
o_year;
/* query 9 */
select
nation,
o_year,
sum(amount) as sum_profit
from
(
select
n_name as nation,
extract(year from o_orderdate) as o_year,
l_extendedprice * (1 - l_discount) - ps_supplycost * l_quantity as amount
from
part,
supplier,
lineitem,
partsupp,
orders,
nation
where
s_suppkey = l_suppkey
and ps_suppkey = l_suppkey
and ps_partkey = l_partkey
and p_partkey = l_partkey
and o_orderkey = l_orderkey
and s_nationkey = n_nationkey
and p_name like '%green%'
) as profit
group by
nation,
o_year
order by
nation,
o_year desc;
/* query 10 */
select
c_custkey,
c_name,
sum(l_extendedprice * (1 - l_discount)) as revenue,
c_acctbal,
n_name,
c_address,
c_phone,
c_comment
from
customer,
orders,
lineitem,
nation
where
c_custkey = o_custkey
and l_orderkey = o_orderkey
and o_orderdate >= date '1993-10-01'
and o_orderdate < date '1993-10-01' + interval '3' month
and l_returnflag = 'R'
and c_nationkey = n_nationkey
group by
c_custkey,
c_name,
c_acctbal,
c_phone,
n_name,
c_address,
c_comment
order by
revenue desc;
/* query 11 */
select
ps_partkey,
sum(ps_supplycost * ps_availqty) as value
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'GERMANY'
group by
ps_partkey having
sum(ps_supplycost * ps_availqty) > (
select
sum(ps_supplycost * ps_availqty) * 0.0001000000
from
partsupp,
supplier,
nation
where
ps_suppkey = s_suppkey
and s_nationkey = n_nationkey
and n_name = 'GERMANY'
)
order by
value desc;
/* query 12 */
select
l_shipmode,
sum(case
when o_orderpriority = '1-URGENT'
or o_orderpriority = '2-HIGH'
then 1
else 0
end) as high_line_count,
sum(case
when o_orderpriority <> '1-URGENT'
and o_orderpriority <> '2-HIGH'
then 1
else 0
end) as low_line_count
from
orders,
lineitem
where
o_orderkey = l_orderkey
and l_shipmode in ('MAIL', 'SHIP')
and l_commitdate < l_receiptdate
and l_shipdate < l_commitdate
and l_receiptdate >= date '1994-01-01'
and l_receiptdate < date '1994-01-01' + interval '1' year
group by
l_shipmode
order by
l_shipmode;
/* query 13 */
select
c_count,
count(*) as custdist
from
(
select
c_custkey,
count(o_orderkey)
from
customer left outer join orders on
c_custkey = o_custkey
and o_comment not like '%special%requests%'
group by
c_custkey
) as c_orders (c_custkey, c_count)
group by
c_count
order by
custdist desc,
c_count desc;
/* query 14 */
select
100.00 * sum(case
when p_type like 'PROMO%'
then l_extendedprice * (1 - l_discount)
else 0
end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
from
lineitem,
part
where
l_partkey = p_partkey
and l_shipdate >= date '1995-09-01'
and l_shipdate < date '1995-09-01' + interval '1' month;
/* query 15 */
create view revenue0 (supplier_no, total_revenue) as
select
l_suppkey,
sum(l_extendedprice * (1 - l_discount))
from
lineitem
where
l_shipdate >= date '1996-01-01'
and l_shipdate < date '1996-01-01' + interval '3' month
group by
l_suppkey;
select
s_suppkey,
s_name,
s_address,
s_phone,
total_revenue
from
supplier,
revenue0
where
s_suppkey = supplier_no
and total_revenue = (
select
max(total_revenue)
from
revenue0
)
order by
s_suppkey;
drop view revenue0;
/* query 16 */
select
p_brand,
p_type,
p_size,
count(distinct ps_suppkey) as supplier_cnt
from
partsupp,
part
where
p_partkey = ps_partkey
and p_brand <> 'Brand#45'
and p_type not like 'MEDIUM POLISHED%'
and p_size in (49, 14, 23, 45, 19, 3, 36, 9)
and ps_suppkey not in (
select
s_suppkey
from
supplier
where
s_comment like '%Customer%Complaints%'
)
group by
p_brand,
p_type,
p_size
order by
supplier_cnt desc,
p_brand,
p_type,
p_size;
/* query 17 */
select
sum(l_extendedprice) / 7.0 as avg_yearly
from
lineitem,
part
where
p_partkey = l_partkey
and p_brand = 'Brand#23'
and p_container = 'MED BOX'
and l_quantity < (
select
0.2 * avg(l_quantity)
from
lineitem
where
l_partkey = p_partkey
);
/* query 18 */
select
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice,
sum(l_quantity)
from
customer,
orders,
lineitem
where
o_orderkey in (
select
l_orderkey
from
lineitem
group by
l_orderkey having
sum(l_quantity) > 300
)
and c_custkey = o_custkey
and o_orderkey = l_orderkey
group by
c_name,
c_custkey,
o_orderkey,
o_orderdate,
o_totalprice
order by
o_totalprice desc,
o_orderdate;
/* query 19 */
select
sum(l_extendedprice* (1 - l_discount)) as revenue
from
lineitem,
part
where
(
p_partkey = l_partkey
and p_brand = 'Brand#12'
and p_container in ('SM CASE', 'SM BOX', 'SM PACK', 'SM PKG')
and l_quantity >= 1 and l_quantity <= 1 + 10
and p_size between 1 and 5
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_partkey = l_partkey
and p_brand = 'Brand#23'
and p_container in ('MED BAG', 'MED BOX', 'MED PKG', 'MED PACK')
and l_quantity >= 10 and l_quantity <= 10 + 10
and p_size between 1 and 10
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
)
or
(
p_partkey = l_partkey
and p_brand = 'Brand#34'
and p_container in ('LG CASE', 'LG BOX', 'LG PACK', 'LG PKG')
and l_quantity >= 20 and l_quantity <= 20 + 10
and p_size between 1 and 15
and l_shipmode in ('AIR', 'AIR REG')
and l_shipinstruct = 'DELIVER IN PERSON'
);
/* query 20 */
select
s_name,
s_address
from
supplier,
nation
where
s_suppkey in (
select
ps_suppkey
from
partsupp
where
ps_partkey in (
select
p_partkey
from
part
where
p_name like 'forest%'
)
and ps_availqty > (
select
0.5 * sum(l_quantity)
from
lineitem
where
l_partkey = ps_partkey
and l_suppkey = ps_suppkey
and l_shipdate >= date '1994-01-01'
and l_shipdate < date '1994-01-01' + interval '1' year
)
)
and s_nationkey = n_nationkey
and n_name = 'CANADA'
order by
s_name;
/* query 21 */
select
s_name,
count(*) as numwait
from
supplier,
lineitem l1,
orders,
nation
where
s_suppkey = l1.l_suppkey
and o_orderkey = l1.l_orderkey
and o_orderstatus = 'F'
and l1.l_receiptdate > l1.l_commitdate
and exists (
select
*
from
lineitem l2
where
l2.l_orderkey = l1.l_orderkey
and l2.l_suppkey <> l1.l_suppkey
)
and not exists (
select
*
from
lineitem l3
where
l3.l_orderkey = l1.l_orderkey
and l3.l_suppkey <> l1.l_suppkey
and l3.l_receiptdate > l3.l_commitdate
)
and s_nationkey = n_nationkey
and n_name = 'SAUDI ARABIA'
group by
s_name
order by
numwait desc,
s_name;
/* query 22 */
select
cntrycode,
count(*) as numcust,
sum(c_acctbal) as totacctbal
from
(
select
substring(c_phone from 1 for 2) as cntrycode,
c_acctbal
from
customer
where
substring(c_phone from 1 for 2) in
('13', '31', '23', '29', '30', '18', '17')
and c_acctbal > (
select
avg(c_acctbal)
from
customer
where
c_acctbal > 0.00
and substring(c_phone from 1 for 2) in
('13', '31', '23', '29', '30', '18', '17')
)
and not exists (
select
*
from
orders
where
o_custkey = c_custkey
)
) as custsale
group by
cntrycode
order by
cntrycode;