Giters

chovy-3012 / doris-benchmark

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Doris Benchmark

一、测试

1.1 编译

make && make install

1.2 创建表

修改配置文件conf/doris.conf，指定脚本操作的Doris集群地址

# for mysql cmd
 mysql_host: 192.168.1.1
 mysql_port: 9030
 mysql_user: root
 mysql_password:
 doris_db: ssb
 
# cluster ports
  http_port: 8030
  be_heartbeat_port: 9050
  broker_port: 8000

# parallel_fragment_exec_instance_num
parallel_num: 8

# concurrency execute query num
# 设置并发测试线程
# 1,2,4,8
concurrency_num: 1

 ...

执行脚本创建表

bin/create_db_table.sh ddl_100

1.3 生成测试数据

用法：bin/gen-ssb.sh [数据文件数量] [文件目录]

1个文件有600万条记录

bin/gen-ssb.sh 10 data_dir

1.4 导入数据

bin/stream_load.sh data_dir

1.5 基准测试

执行基准测试

#星型聚合符合查询
bin/benchmark.sh -p -d ssb
#明细查询
bin/benchmark.sh -p -d ssb-index

二、 测试数据和过程

2.1 测试数据

表名 行数 解释
lineorder 文件数量*600万 商品订单表
customer 300万 客户表
part 140万 零部件表
supplier 20万 供应商表
dates 2556万 日期表
lineorder_flat 文件数量*600万 lineorder打平后的宽表

2.4 建表sql

CREATE TABLE IF NOT EXISTS `lineorder` (
  `lo_orderkey` int(11) NOT NULL COMMENT "",
  `lo_orderdate` int(11) NOT NULL COMMENT "",
  `lo_linenumber` int(11) 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(16) NOT NULL COMMENT "",
  `lo_shippriority` int(11) NOT NULL COMMENT "",
  `lo_quantity` int(11) NOT NULL COMMENT "",
  `lo_extendedprice` int(11) NOT NULL COMMENT "",
  `lo_ordtotalprice` int(11) NOT NULL COMMENT "",
  `lo_discount` int(11) NOT NULL COMMENT "",
  `lo_revenue` int(11) NOT NULL COMMENT "",
  `lo_supplycost` int(11) NOT NULL COMMENT "",
  `lo_tax` int(11) NOT NULL COMMENT "",
  `lo_commitdate` int(11) NOT NULL COMMENT "",
  `lo_shipmode` varchar(11) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`lo_orderkey`,`lo_orderdate`)
COMMENT "OLAP"
PARTITION BY RANGE(`lo_orderdate`)
(PARTITION p1 VALUES [("-2147483648"), ("19930101")),
PARTITION p2 VALUES [("19930101"), ("19940101")),
PARTITION p3 VALUES [("19940101"), ("19950101")),
PARTITION p4 VALUES [("19950101"), ("19960101")),
PARTITION p5 VALUES [("19960101"), ("19970101")),
PARTITION p6 VALUES [("19970101"), ("19980101")),
PARTITION p7 VALUES [("19980101"), ("19990101")))
DISTRIBUTED BY HASH(`lo_orderkey`) BUCKETS 48
PROPERTIES (
"replication_num" = "1",
"colocate_with" = "groupa1",
"in_memory" = "false"
);

CREATE TABLE IF NOT EXISTS `customer` (
  `c_custkey` int(11) NOT NULL COMMENT "",
  `c_name` varchar(26) NOT NULL COMMENT "",
  `c_address` varchar(41) NOT NULL COMMENT "",
  `c_city` varchar(11) NOT NULL COMMENT "",
  `c_nation` varchar(16) NOT NULL COMMENT "",
  `c_region` varchar(13) NOT NULL COMMENT "",
  `c_phone` varchar(16) NOT NULL COMMENT "",
  `c_mktsegment` varchar(11) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`c_custkey`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`c_custkey`) BUCKETS 12
PROPERTIES (
"replication_num" = "1",
"colocate_with" = "groupa2",
"in_memory" = "false"
);


CREATE TABLE IF NOT EXISTS `dates` (
  `d_datekey` int(11) NOT NULL COMMENT "",
  `d_date` varchar(20) NOT NULL COMMENT "",
  `d_dayofweek` varchar(10) NOT NULL COMMENT "",
  `d_month` varchar(11) NOT NULL COMMENT "",
  `d_year` int(11) NOT NULL COMMENT "",
  `d_yearmonthnum` int(11) NOT NULL COMMENT "",
  `d_yearmonth` varchar(9) NOT NULL COMMENT "",
  `d_daynuminweek` int(11) NOT NULL COMMENT "",
  `d_daynuminmonth` int(11) NOT NULL COMMENT "",
  `d_daynuminyear` int(11) NOT NULL COMMENT "",
  `d_monthnuminyear` int(11) NOT NULL COMMENT "",
  `d_weeknuminyear` int(11) NOT NULL COMMENT "",
  `d_sellingseason` varchar(14) NOT NULL COMMENT "",
  `d_lastdayinweekfl` int(11) NOT NULL COMMENT "",
  `d_lastdayinmonthfl` int(11) NOT NULL COMMENT "",
  `d_holidayfl` int(11) NOT NULL COMMENT "",
  `d_weekdayfl` int(11) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`d_datekey`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`d_datekey`) BUCKETS 1
PROPERTIES (
"replication_num" = "1",
"in_memory" = "false",
"colocate_with" = "groupa3"
);

 CREATE TABLE IF NOT EXISTS `supplier` (
  `s_suppkey` int(11) NOT NULL COMMENT "",
  `s_name` varchar(26) NOT NULL COMMENT "",
  `s_address` varchar(26) NOT NULL COMMENT "",
  `s_city` varchar(11) NOT NULL COMMENT "",
  `s_nation` varchar(16) NOT NULL COMMENT "",
  `s_region` varchar(13) NOT NULL COMMENT "",
  `s_phone` varchar(16) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`s_suppkey`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`s_suppkey`) BUCKETS 12
PROPERTIES (
"replication_num" = "1",
"colocate_with" = "groupa4",
"in_memory" = "false"
);

CREATE TABLE IF NOT EXISTS `part` (
  `p_partkey` int(11) NOT NULL COMMENT "",
  `p_name` varchar(23) NOT NULL COMMENT "",
  `p_mfgr` varchar(7) NOT NULL COMMENT "",
  `p_category` varchar(8) NOT NULL COMMENT "",
  `p_brand` varchar(10) NOT NULL COMMENT "",
  `p_color` varchar(12) NOT NULL COMMENT "",
  `p_type` varchar(26) NOT NULL COMMENT "",
  `p_size` int(11) NOT NULL COMMENT "",
  `p_container` varchar(11) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`p_partkey`)
COMMENT "OLAP"
DISTRIBUTED BY HASH(`p_partkey`) BUCKETS 12
PROPERTIES (
"replication_num" = "1",
"colocate_with" = "groupa5",
"in_memory" = "false"
);

2.3 测试sql

星型聚合复查查询

#lineorder、part表关联聚合，大表、小表关联聚合
--Q1.1
select sum(lo_revenue) as revenue
from lineorder join dates on lo_orderdate = d_datekey
where d_year = 1993 and lo_discount between 1 and 3 and lo_quantity < 25;
--Q1.2
select sum(lo_revenue) as revenue
from lineorder
join dates on lo_orderdate = d_datekey
where d_yearmonthnum = 199401
and lo_discount between 4 and 6
and lo_quantity between 26 and 35;
--Q1.3
select sum(lo_revenue) as revenue
from lineorder
join dates on lo_orderdate = d_datekey
where d_weeknuminyear = 6 and d_year = 1994
and lo_discount between 5 and 7
and lo_quantity between 26 and 35;

#lineorder、dates、part、supplier多表关联，大中小表多表关联聚合
--Q2.1
select sum(lo_revenue) as lo_revenue, d_year, p_brand
from lineorder
join dates on lo_orderdate = d_datekey
join part on lo_partkey = p_partkey
join supplier on lo_suppkey = s_suppkey
where p_category = 'MFGR#12' and s_region = 'AMERICA'
group by d_year, p_brand
order by d_year, p_brand;
--Q2.2
select sum(lo_revenue) as lo_revenue, d_year, p_brand
from lineorder
join dates on lo_orderdate = d_datekey
join part on lo_partkey = p_partkey
join supplier on lo_suppkey = s_suppkey
where 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) as lo_revenue, d_year, p_brand
from lineorder
join dates on lo_orderdate = d_datekey
join part on lo_partkey = p_partkey
join supplier on lo_suppkey = s_suppkey
where p_brand = 'MFGR#2239' and s_region = 'EUROPE'
group by d_year, p_brand
order by d_year, p_brand;

#lineorder、dates、part、supplier多表关联，大中小表多表关联聚合
--Q3.1
select c_nation, s_nation, d_year, sum(lo_revenue) as lo_revenue
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
where 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, lo_revenue desc;
--Q3.2
select c_city, s_city, d_year, sum(lo_revenue) as lo_revenue
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
where 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, lo_revenue desc;
--Q3.3
select c_city, s_city, d_year, sum(lo_revenue) as lo_revenue
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
where (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, lo_revenue desc;
--Q3.4
select c_city, s_city, d_year, sum(lo_revenue) as lo_revenue
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
where (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, lo_revenue desc;

#lineorder、dates、part、supplier多表关联，大中小表多表关联聚合
--Q4.1
select d_year, c_nation, sum(lo_revenue) - sum(lo_supplycost) as profit
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
join part on lo_partkey = p_partkey
where 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 d_year, s_nation, p_category, sum(lo_revenue) - sum(lo_supplycost) as profit
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
join part on lo_partkey = p_partkey
where 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 d_year, s_city, p_brand, sum(lo_revenue) - sum(lo_supplycost) as profit
from lineorder
join dates on lo_orderdate = d_datekey
join customer on lo_custkey = c_custkey
join supplier on lo_suppkey = s_suppkey
join part on lo_partkey = p_partkey
where c_region = 'AMERICA'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;

明细查询

#明细查询
--Q5.1
select *
from lineorder where lo_discount between 1 and 3 and lo_quantity < 25 limit 10;
--Q5.2
select *
from lineorder where lo_orderkey>=1000000 and  lo_discount between 5 and 7 and lo_quantity < 25 limit 10;
--Q5.3
select *
from lineorder where lo_orderkey=1000000 limit 10;

三、其他

# 删除表
drop table customer;
drop table dates;
drop table lineorder;
drop table lineorder_flat;
drop table part;
drop table supplier;

About

Languages

Language:Python 70.6%Language:Shell 27.9%Language:Makefile 1.6%