UNION DISTINCT 和 UNION ALL

Question

这两种性能方面有什么区别吗？

-- eliminate duplicates using UNION
SELECT col1,col2,col3 FROM Table1 
UNION SELECT col1,col2,col3 FROM Table2 
UNION SELECT col1,col2,col3 FROM Table3 
UNION SELECT col1,col2,col3 FROM Table4 
UNION SELECT col1,col2,col3 FROM Table5       
UNION SELECT col1,col2,col3 FROM Table6       
UNION SELECT col1,col2,col3 FROM Table7       
UNION SELECT col1,col2,col3 FROM Table8       

-- eliminate duplicates using DISTINCT    
SELECT DISTINCT * FROM
(     
    SELECT col1,col2,col3 FROM Table1 
    UNION ALL SELECT col1,col2,col3 FROM Table2 
    UNION ALL SELECT col1,col2,col3 FROM Table3 
    UNION ALL SELECT col1,col2,col3 FROM Table4 
    UNION ALL SELECT col1,col2,col3 FROM Table5       
    UNION ALL SELECT col1,col2,col3 FROM Table6       
    UNION ALL SELECT col1,col2,col3 FROM Table7       
    UNION ALL SELECT col1,col2,col3 FROM Table8       
) x

Answer 1

联盟与全部联盟之间的区别在于 UNION ALL 不会消除重复的行，而只会从所有表中提取所有行拟合您的查询细节并将它们组合成一个表格。

UNION 语句有效地对结果集执行SELECT DISTINCT。

如果从Union All结果集中选择Distinct，那么输出将等于 Union结果集。

修改

CPU成本表现

让我用例子解释：

我有两个问题。一个是Union，另一个是Union All

SET STATISTICS TIME ON GO select distinct * from (select * from dbo.user_LogTime union all select * from dbo.user_LogTime) X GO SET STATISTICS TIME OFF SET STATISTICS TIME ON GO select * from dbo.user_LogTime union select * from dbo.user_LogTime GO SET STATISTICS TIME OFF

我确实在SMSS的同一查询窗口中运行了两者。让我们看一下SMSS中的执行计划：

发生的情况是，使用联盟所有和区别的查询将比使用联盟的查询花费更多的CPU费用。

按时效果

UNION ALL：

(1172 row(s) affected) SQL Server Execution Times: CPU time = 0 ms, elapsed time = 39 ms.

UNION：

(1172 row(s) affected) SQL Server Execution Times: CPU time = 10 ms, elapsed time = 25 ms.

所以联盟比表现明智
中的联盟更好

Answer 2

UNION DISTINCT 和 UNION ALL

之间的比较

此查询用于为扩展的雇员表创建下游系统的其他备用ID。此示例来自mySQL 8.0.20环境。

对于下面显示的数据和查询，测试产生了显着差异：

UNION ALL       8.983 sec  
UNION DISTINCT 15.344 sec

为显示此示例的规模和复杂性，下表显示了表大小和查询代码

hqsource 600K records
accountingemppos 180K 
accountingposld 200K
emp_no_accountingnumeric 20
First UNION block is approx 550K records, second approx 50K

               SELECT a.`emp_no_imported` AS `emp_no`,
              a.`supervisor_emp_no`,
              a.`first name`,
              a.`middle name`,
              a.`last name`,
              a.`jobtitle`,
              a.`status`,
              CASE WHEN rida.`accounting_emp_no` IS NOT NULL THEN
                    rida.`accounting_emp_no`
              ELSE 
                    a.`emp_no_imported`
              END AS `accounting_id`,
              CASE WHEN epfp.`emp_no` IS NOT NULL THEN
                        CASE WHEN `sridf`.`emp_no` IS NOT NULL THEN
                                `sridf`.`accounting_emp_no`
                            ELSE
                                epfp.`emp_no`
                            END
                    ELSE
                        CASE WHEN epp.`emp_no` IS NOT NULL THEN
                            CASE WHEN `srids`.`emp_no` IS NOT NULL THEN
                                `srids`.`accounting_emp_no`
                            ELSE                                        
                                epp.`emp_no`
                            END
                    ELSE
                        CASE WHEN `srida`.`emp_no` IS NOT NULL THEN
                            `srida`.`accounting_emp_no`
                        ELSE
                            a.`supervisor_emp_no`
                        END
                    END
                END AS `accounting_s_emp_no`,
                ep.`emp_no` AS `traas_emp_no`,
                epp.`emp_no` AS `traas_parent_emp_no`
       FROM `hqsource`.hq_people a
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `rida` ON `rida`.emp_no = a.`emp_no_imported`
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `srida` ON `srida`.emp_no = a.`supervisor_emp_no`

       LEFT OUTER JOIN `traas`.`accountingemppos_data_extract` ep  ON ep.`emp_no` = a.`emp_no_imported` AND ep.`End` = '2899-12-31' AND ep.`Primary` = 'Y'
       LEFT OUTER JOIN `epe`.`accountingposld_data_extract` p ON p.`RangeGID` = ep.`GID`
       LEFT OUTER JOIN `traas`.`accountingemppos_data_extract` epp  ON epp.`GID` = p.`ParentGID` AND epp.`End` = '2899-12-31' AND epp.`Primary` = 'Y'
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `rids` ON `rids`.emp_no = ep.`emp_no`
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `srids` ON `srids`.emp_no = epp.`emp_no` AND epp.`End` = '2899-12-31' AND epp.`Primary` = 'Y'

       LEFT OUTER JOIN `epe`.`accountingemppos_data_extract_filtered` epf  ON epf.`emp_no` = a.`emp_no_imported` AND epf.`End` = '2899-12-31' AND epf.`Primary` = 'Y'
       LEFT OUTER JOIN `epe`.`accountingposld_data_extract` pf ON pf.`RangeGID` = epf.`GID` 
       LEFT OUTER JOIN `epe`.`accountingemppos_data_extract_filtered` epfp  ON epfp.`GID` = pf.`ParentGID` AND epfp.`End` = '2899-12-31' AND epfp.`Primary` = 'Y'
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `ridf` ON `ridf`.emp_no = epf.`emp_no` AND epf.`End` = '2899-12-31' AND epf.`Primary` = 'Y'
       LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `sridf` ON `sridf`.emp_no = epfp.`emp_no` AND epfp.`End` = '2899-12-31' AND epfp.`Primary` = 'Y'
       WHERE a.`emp_no_imported` REGEXP ('^[a-z]{2}\\d{5}.$') 

UNION ALL
-- UNION DISTINCT

    SELECT a.`emp_no_imported` AS `emp_no`, a.`supervisor_emp_no` AS `s_emp_no`, u.`First_Name`, 'ƒ' AS `MI`, u.`Last_Name`, u.`Job_Title`, NULL AS `status`, 
          CASE WHEN rid.`accounting_emp_no` IS NULL THEN
            ep.`emp_no`
          ELSE 
            rid.`accounting_emp_no`
          END AS `accounting_emp_no`,
          CASE WHEN `srid`.`accounting_emp_no` IS NULL THEN
            epp.`emp_no`
          ELSE
            `srid`.`accounting_emp_no`
          END AS `accounting_s_emp_no`,
          ep.`emp_no` AS `traas_emp_no`,
          epp.`emp_no` AS `traas_parent_emp_no`
    FROM `epe`.`accountingemppos_data_extract_filtered`  ep

    LEFT OUTER JOIN  `hqsource`.`hq_people` a ON a.`emp_no_imported` = ep.`emp_no`
    LEFT OUTER JOIN `epe`.`accountingposld_data_extract` p ON p.`RangeGID` =  ep.`GID`
    LEFT OUTER JOIN `epe`.`accountingemppos_data_extract_filtered` epp ON epp.`GID` = p.`ParentGID`
    LEFT OUTER JOIN `siebel`.`users_all_output` u ON u.`LOGIN` = ep.`emp_no`
    LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `rid` ON `rid`.emp_no = ep.`emp_no`
    LEFT OUTER JOIN `hqsource`.`emp_no_accountingnumeric` `srid` ON `srid`.emp_no = epp.`emp_no`
    WHERE 
        ep.`End` = '2899-12-31' AND
        epp.`End` = '2899-12-31' AND
        p.`End` = '2899-12-31' AND
        ep.emp_no REGEXP ('^F\\d{8}$|^V[0-3]\\d{5}$')
        
ORDER BY LENGTH(accounting_emp_no) ASC, accounting_emp_no ASC

;

两个UNION块中的每个WHERE子句保证结果将是唯一的。（此查询已有几年历史，并且每天运行。我希望我能早点尝试此操作）。 字段名称已被混淆

Answer 3

另一个例子说明了四种可能的情况：

/* with each case we should expect a return set:
(1) DISTINCT UNION {1,2,3,4,5} - is redundant with case (2)
(2) UNION {1,2,3,4,5} - more efficient?
(3) DISTINCT UNION ALL {1,2,2,3,3,4,4,5} 
(4) UNION ALL {1,1,2,2,2,3,3,4,4,5} 
*/

declare @t1 table (c1 varchar(15));
declare @t2 table (c2 varchar(15));

insert into @t1 values ('1'),('1'),('2'),('3'),('4');

insert into @t2 values ('2'),('2'),('3'),('4'),('5');


select DISTINCT * from @t1 --case (1)
UNION
select DISTINCT * from @t2 order by c1

select * from @t1 --case (2)    
UNION
select * from @t2 order by c1

select DISTINCT * from @t1 --case (3)
UNION ALL
select DISTINCT * from @t2 order by c1

select * from @t1 --case (4)   
UNION ALL
select * from @t2 order by c1

UNION与SELECT DISTINCT和UNION ALL Performance

3 个答案:

UNION DISTINCT 和 UNION ALL