postgresql分页数据重复问题的深入理解

abase=# create table t_sort(n_int int,c_id varchar(300));
CREATE TABLE
abase=# insert into t_sort(n_int,c_id) select 100,generate_series(1,9);
INSERT 0 9
abase=# insert into t_sort(n_int,c_id) select 200,generate_series(1,9);
INSERT 0 9
abase=# insert into t_sort(n_int,c_id) select 300,generate_series(1,9);
INSERT 0 9
abase=# insert into t_sort(n_int,c_id) select 400,generate_series(1,9);
INSERT 0 9
abase=# insert into t_sort(n_int,c_id) select 500,generate_series(1,9);
INSERT 0 9
abase=# insert into t_sort(n_int,c_id) select 600,generate_series(1,9);
INSERT 0 9

--快速排序 quicksort
abase=# explain analyze select ctid,n_int,c_id from t_sort order by n_int asc;
            QUERY PLAN            
------------------------------------------------------------
 Sort (cost=3.09..3.23 rows=54 width=12) (actual time=0.058..0.061 rows=54 loops=1)
 Sort Key: n_int
 Sort Method: quicksort Memory: 27kB
 -> Seq Scan on t_sort (cost=0.00..1.54 rows=54 width=12) (actual time=0.021..0.032 rows=54 loops=1)
 Planning time: 0.161 ms
 Execution time: 0.104 ms
(6 rows)
--堆排序 top-N heapsort
abase=# explain analyze select ctid,n_int,c_id from t_sort order by n_int asc limit 10;
             QUERY PLAN             
 
------------------------------------------------------------
 Limit (cost=2.71..2.73 rows=10 width=12) (actual time=0.066..0.068 rows=10 loops=1)
 -> Sort (cost=2.71..2.84 rows=54 width=12) (actual time=0.065..0.066 rows=10 loops=1)
   Sort Key: n_int
   Sort Method: top-N heapsort Memory: 25kB
   -> Seq Scan on t_sort (cost=0.00..1.54 rows=54 width=12) (actual time=0.022..0.031 rows=54 loops=1
)
 Planning time: 0.215 ms
 Execution time: 0.124 ms
(7 rows)
--归并排序 external sort Disk
--插入大量值为a的数据
abase=# insert into t_sort(n_int,c_id) select generate_series(1000,2000),'a';
INSERT 0 1001
abase=# set work_mem = '64kB';
SET
abase=# explain analyze select ctid,n_int,c_id from t_sort order by n_int asc;
             QUERY PLAN             
-------------------------------------------------------------
 Sort (cost=18.60..19.28 rows=270 width=12) (actual time=1.235..1.386 rows=1055 loops=1)
 Sort Key: n_int
 Sort Method: external sort Disk: 32kB
 -> Seq Scan on t_sort (cost=0.00..7.70 rows=270 width=12) (actual time=0.030..0.247 rows=1055 loops=1)
 Planning time: 0.198 ms
 Execution time: 1.663 ms
(6 rows)

--快速排序
abase=# explain analyze select ctid,n_int,c_id from t_sort order by n_int asc;
            QUERY PLAN            
------------------------------------------------------------
 Sort (cost=3.09..3.23 rows=54 width=12) (actual time=0.058..0.061 rows=54 loops=1)
 Sort Key: n_int
 Sort Method: quicksort Memory: 27kB
 -> Seq Scan on t_sort (cost=0.00..1.54 rows=54 width=12) (actual time=0.021..0.032 rows=54 loops=1)
 Planning time: 0.161 ms
 Execution time: 0.104 ms
(6 rows) 
"color: #ff0000">堆排序




abase=# select count(*) from t_sort;
 count 
-------
 1055
(1 row)
--设置work_mem 4MB
abase=# show work_mem ;
 work_mem 
----------
 4MB
(1 row)
"color: #ff0000">归并排序




--将work_mem设置为64kb让其走归并排序。
abase=# set work_mem ='64kB';
SET
abase=# show work_mem;
 work_mem 
----------
 64kB
(1 row)
"htmlcode">

--设置work_mem =64kb
abase=# show work_mem;
 work_mem 
----------
 64kB
(1 row)
--查询limit 10 offset 10
abase=# explain analyze select * from ( select ctid,n_int,c_id from test order by n_int asc limit 10 offset 10) td limit 10;
              QUERY PLAN               
---------------------------------------------------------------------------------------------------------------------------
 Limit (cost=1221.42..1221.54 rows=10 width=13) (actual time=12.881..12.884 rows=10 loops=1)
 -> Limit (cost=1221.42..1221.44 rows=10 width=13) (actual time=12.879..12.881 rows=10 loops=1)
   -> Sort (cost=1221.39..1295.79 rows=29757 width=13) (actual time=12.877..12.879 rows=20 loops=1)
    Sort Key: test.n_int
    Sort Method: top-N heapsort Memory: 25kB
    -> Seq Scan on test (cost=0.00..429.57 rows=29757 width=13) (actual time=0.058..6.363 rows=29757 loops=1)
 Planning time: 0.230 ms
 Execution time: 12.976 ms
(8 rows)
"external nofollow" target="_blank" href="https://stackoverflow.com/questions/13580826/postgresql-repeating-rows-from-limit-offset">PostgreSQL - repeating rows from LIMIT OFFSET

参考资料: LIMIT and OFFSET
结语


1.关于分页重复数据的问题主要是排序字段不唯一并且执行计划走了快速排序和堆排序导致。
2.当排序有重复字段，但是如果查询是归并排序，便不会存在有重复数据的问题。
3.当用重复字段排序，前面的页重复，随着offset的增大导致work_mem不足以后使用归并排序，就不存在重复的数据了。
4.排序和算法的稳定性有关，当执行计划选择不同的排序算法时，返回的结果不一样。
5.处理重复数据的常见手段就是，排序的时候可以在排序字段d_larq(立案日期)后面加上c_bh(唯一字段)来排序。
order by d_larq,c_bh;
总结
以上就是这篇文章的全部内容了，希望本文的内容对大家的学习或者工作具有一定的参考学习价值，谢谢大家对的支持。

                                
                                

                                    postgresql分页查询,postgresql分页,postgresql分页数据重复 
                                

                                    标签：
                                        
postgresql分页查询,postgresql分页,postgresql分页数据重复