第二十一课 openGauss存储模型-行存和列存
学习目标
学习openGauss存储模型-行存和列存
行存储是指将表按行存储到硬盘分区上，列存储是指将表按列存储到硬盘分区上。默认情况下，创建的表为行存储。
行、列存储模型各有优劣，通常用于TP场景的数据库，默认使用行存储，仅对执行复杂查询且数据量大的AP场景时，才使用列存储
课程学习
连接数据库
#第一次进入等待15秒
#数据库启动中…
su - omm
gsql -r
学习内容如下
1.创建行存表
CREATE TABLE test_t1
(
col1 CHAR(2),
col2 VARCHAR2(40),
col3 NUMBER
);
–压缩属性为no
\d+ test_t1
insert into test_t1 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
2.创建列存表
CREATE TABLE test_t2
(
col1 CHAR(2),
col2 VARCHAR2(40),
col3 NUMBER
)
WITH (ORIENTATION = COLUMN);
–压缩属性为low
\d+ test_t2;
–插入和行存表相同的数据
insert into test_t2 select * from test_t1;
3.占用空间对比
\d+
4.对比读取一列的速度
analyze VERBOSE test_t1;
analyze VERBOSE test_t2;
–列存表时间少于行存表
explain analyze select distinct col1 from test_t1;
explain analyze select distinct col1 from test_t2;
5.对比插入一行的速度
–行存表时间少于列存表
explain analyze insert into test_t1 values(‘x’, ‘xxxx’, ‘123’);
explain analyze insert into test_t2 values(‘x’, ‘xxxx’, ‘123’);
6.清理数据
drop table test_t1;
drop table test_t2;
课程作业
1.创建行存表和列存表，并批量插入10万条数据(行存表和列存表数据相同)
需要自己建表！！
2.对比行存表和列存表空间大小
3.对比查询一列和插入一行的速度
4.清理数据
CREATE TABLE t1
(
col1 CHAR(2),
col2 VARCHAR2(40),
col3 NUMBER
);
CREATE TABLE t2
(
col1 CHAR(2),
col2 VARCHAR2(40),
col3 NUMBER
)
WITH (ORIENTATION = COLUMN);
insert into t1 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
insert into t2 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
\d+
analyze VERBOSE t1;
analyze VERBOSE t2;
explain analyze insert into t1 values('x', 'xxxx', '123');
explain analyze insert into t2 values('x', 'xxxx', '123');
drop table t1;
drop table t2;
课后作业记录
omm=#
omm=# CREATE TABLE test_t1
omm-# (
omm(# col1 CHAR(2),
omm(# col2 VARCHAR2(40),
omm(# col3 NUMBER
omm(# );
CREATE TABLE
omm=# omm=#
\d+ test_t1
Table "public.test_t1"
Column | Type | Modifiers | Storage | Stats target | Description
--------+-----------------------+-----------+----------+--------------+-------------
col1 | character(2) | | extended | |
col2 | character varying(40) | | extended | |
col3 | numeric | | main | |
Has OIDs: no
Options: orientation=row, compression=no
omm=# insert into test_t1 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
INSERT 0 100000
omm=#
omm=# CREATE TABLE test_t2
omm-# (
omm(# col1 CHAR(2),
omm(# col2 VARCHAR2(40),
omm(# col3 NUMBER
omm(# )
omm-# WITH (ORIENTATION = COLUMN);
CREATE TABLE
omm=#
omm=# \d+ test_t2;
Table "public.test_t2"
Column | Type | Modifiers | Storage | Stats target | Description
--------+-----------------------+-----------+----------+--------------+-------------
col1 | character(2) | | extended | |
col2 | character varying(40) | | extended | |
col3 | numeric | | main | |
Has OIDs: no
Options: orientation=column, compression=low
omm=#
omm=# insert into test_t2 select * from test_t1;
INSERT 0 100000
omm=#
omm=# \d+
List of relations
Schema | Name | Type | Owner | Size | Storage | Description
--------+----------------------+-------+-------+------------+--------------------------------------+-------------
public | test_t1 | table | omm | 6760 kB | {orientation=row,compression=no} |
public | test_t2 | table | omm | 1112 kB | {orientation=column,compression=low} |
public | test_trigger_des_tbl | table | omm | 8192 bytes | {orientation=row,compression=no} |
public | test_trigger_src_tbl | table | omm | 8192 bytes | {orientation=row,compression=no} |
public | tt1 | table | omm | 8192 bytes | {orientation=row,compression=no} |
public | tt2 | table | omm | 8192 bytes | {orientation=row,compression=no} |
(6 rows)
omm=#
omm=#
omm=# analyze VERBOSE test_t1;
INFO: analyzing "public.test_t1"(gaussdb pid=1)
INFO: ANALYZE INFO : "test_t1": scanned 841 of 841 pages, containing 100000 live rows and 0 dead rows; 30000 rows in sample, 100000 estimated total rows(gaussdb pid=1)
ANALYZE
omm=# analyze VERBOSE test_t2;
INFO: analyzing "public.test_t2"(gaussdb pid=1)
INFO: ANALYZE INFO : estimate total rows of "pg_delta_16446": scanned 0 pages of total 0 pages with 1 retry times, containing 0 live rows and 0 dead rows, estimated 0 total rows(gaussdb pid=1)
INFO: ANALYZE INFO : "test_t2": scanned 2 of 2 cus, sample 30000 rows, estimated total 100000 rows(gaussdb pid=1)
ANALYZE
omm=#
omm=# explain analyze select distinct col1 from test_t1;
omm=# QUERY PLAN
---------------------------------------------------------------------------------------------------------------------
HashAggregate (cost=2091.00..2091.27 rows=27 width=3) (actual time=52.141..52.147 rows=27 loops=1)
Group By Key: col1
-> Seq Scan on test_t1 (cost=0.00..1841.00 rows=100000 width=3) (actual time=0.013..25.189 rows=100000 loops=1)
Total runtime: 52.202 ms
(4 rows)
explain analyze select distinct col1 from test_t2;
QUERY PLAN
----------------------------------------------------------------------------------------------------------------------------
Row Adapter (cost=1008.27..1008.27 rows=27 width=3) (actual time=4.148..4.151 rows=27 loops=1)
-> Vector Sonic Hash Aggregate (cost=1008.00..1008.27 rows=27 width=3) (actual time=4.146..4.146 rows=27 loops=1)
Group By Key: col1
-> CStore Scan on test_t2 (cost=0.00..758.00 rows=100000 width=3) (actual time=0.028..0.254 rows=100000 loops=1)
Total runtime: 4.251 ms
(5 rows)
omm=#
omm=# explain analyze insert into test_t1 values('x', 'xxxx', '123');
QUERY PLAN
-----------------------------------------------------------------------------------------------
[Bypass]
Insert on test_t1 (cost=0.00..0.01 rows=1 width=0) (actual time=0.061..0.061 rows=1 loops=1)
-> Result (cost=0.00..0.01 rows=1 width=0) (actual time=0.002..0.002 rows=1 loops=1)
Total runtime: 0.156 ms
(4 rows)
omm=# explain analyze insert into test_t2 values('x', 'xxxx', '123');
QUERY PLAN
-----------------------------------------------------------------------------------------------
Insert on test_t2 (cost=0.00..0.01 rows=1 width=0) (actual time=3.232..3.233 rows=1 loops=1)
-> Result (cost=0.00..0.01 rows=1 width=0) (actual time=0.002..0.003 rows=1 loops=1)
Total runtime: 3.333 ms
(3 rows)
omm=#
omm=# drop table test_t1;
DROP TABLE
omm=# drop table test_t2;
DROP TABLE
omm=#
omm=# CREATE TABLE t1
omm-# (
omm(# col1 CHAR(2),
omm(# col2 VARCHAR2(40),
omm(# col3 NUMBER
omm(# );
CREATE TABLE
omm=# omm=#
omm-# CREATE TABLE t2
(
omm(# col1 CHAR(2),
omm(# col2 VARCHAR2(40),
omm(# col3 NUMBER
)
omm(# omm-# WITH (ORIENTATION = COLUMN);
CREATE TABLE
omm=#
omm=# \d+
List of relations
Schema | Name | Type | Owner | Size | Storage | Description
--------+------+-------+-------+------------+--------------------------------------+-------------
public | t1 | table | omm | 8192 bytes | {orientation=row,compression=no} |
public | t2 | table | omm | 24 kB | {orientation=column,compression=low} |
(2 rows)
omm=#
omm=#
omm=# insert into t1 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
INSERT 0 100000
omm=#
omm=# insert into t2 select col1, col2, col3 from (select generate_series(1, 100000) as key, repeat(chr(int4(random() * 26) + 65), 2) as col1, repeat(chr(int4(random() * 26) + 65), 30) as col2, (random() * (10^4))::integer as col3);
INSERT 0 100000
omm=#
omm=#
omm=# \d+
List of relations
Schema | Name | Type | Owner | Size | Storage | Description
--------+------+-------+-------+---------+--------------------------------------+-------------
public | t1 | table | omm | 6760 kB | {orientation=row,compression=no} |
public | t2 | table | omm | 1112 kB | {orientation=column,compression=low} |
(2 rows)
omm=#
omm=# \d+
List of relations
Schema | Name | Type | Owner | Size | Storage | Description
--------+------+-------+-------+---------+--------------------------------------+-------------
public | t1 | table | omm | 6760 kB | {orientation=row,compression=no} |
public | t2 | table | omm | 1112 kB | {orientation=column,compression=low} |
(2 rows)
omm=#
omm=#
omm=# analyze VERBOSE t1;
INFO: analyzing "public.t1"(gaussdb pid=1)
INFO: ANALYZE INFO : "t1": scanned 841 of 841 pages, containing 100000 live rows and 0 dead rows; 30000 rows in sample, 100000 estimated total rows(gaussdb pid=1)
ANALYZE
omm=# analyze VERBOSE t2;
INFO: analyzing "public.t2"(gaussdb pid=1)
INFO: ANALYZE INFO : estimate total rows of "pg_delta_16468": scanned 0 pages of total 0 pages with 1 retry times, containing 0 live rows and 0 dead rows, estimated 0 total rows(gaussdb pid=1)
INFO: ANALYZE INFO : "t2": scanned 2 of 2 cus, sample 30000 rows, estimated total 100000 rows(gaussdb pid=1)
omm=# ANALYZE
omm=#
omm=# \d+
omm=# List of relations
Schema | Name | Type | Owner | Size | Storage | Description
--------+------+-------+-------+---------+--------------------------------------+-------------
public | t1 | table | omm | 6760 kB | {orientation=row,compression=no} |
public | t2 | table | omm | 1112 kB | {orientation=column,compression=low} |
(2 rows)
omm=#
omm=# explain analyze insert into t1 values('x', 'xxxx', '123');
QUERY PLAN
------------------------------------------------------------------------------------------
[Bypass]
Insert on t1 (cost=0.00..0.01 rows=1 width=0) (actual time=0.074..0.075 rows=1 loops=1)
-> Result (cost=0.00..0.01 rows=1 width=0) (actual time=0.002..0.002 rows=1 loops=1)
Total runtime: 0.176 ms
(4 rows)
omm=# explain analyze insert into t2 values('x', 'xxxx', '123');
-> Result (cost=0.00..0.01 rows=1 width=0) (actual time=0.001..0.001 rows=1 loops=1)
Total runtime: 14.151 ms
(3 rows)
omm=# QUERY PLAN
--------------------------------------------------------------------------------------------
Insert on t2 (cost=0.00..0.01 rows=1 width=0) (actual time=14.059..14.061 rows=1 loops=1)
omm=#
omm=# drop table t1;
DROP TABLE
omm=# drop table t2;
DROP TABLE
omm=#
omm=#
「喜欢这篇文章，您的关注和赞赏是给作者最好的鼓励」
关注作者
【版权声明】本文为墨天轮用户原创内容，转载时必须标注文章的来源（墨天轮），文章链接，文章作者等基本信息，否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容，欢迎发送邮件至：contact@modb.pro进行举报，并提供相关证据，一经查实，墨天轮将立刻删除相关内容。
