关于SQL查询效率,100w数据,查询只要1秒,与您分享:
机器情况
p4: 2.4
内存: 1 G
os: windows 2003
数据库: ms sql server 2000
目的: 查询性能测试,比较两种查询的性能
SQL查询效率 step by step
-- setp 1.
-- 建表
create table t_userinfo
(
userid int identity(1,1) primary key nonclustered,
nick varchar(50) not null default '',
classid int not null default 0,
writetime datetime not null default getdate()
)
go
-- 建索引
create clustered index ix_userinfo_classid on t_userinfo(classid)
go
-- step 2.
declare @i int
declare @k int
declare @nick varchar(10)
set @i = 1
while @i<1000000
begin
set @k = @i % 10
set @nick = convert(varchar,@i)
insert into t_userinfo(nick,classid,writetime) values(@nick,@k,getdate())
set @i = @i + 1
end
-- 耗时 08:27 ,需要耐心等待
-- step 3.
select top 20 userid,nick,classid,writetime from t_userinfo
where userid not in
(
select top 900000 userid from t_userinfo order by userid asc
)
-- 耗时 8 秒 ,够长的
-- step 4.
select a.userid,b.nick,b.classid,b.writetime from
(
select top 20 a.userid from
(
select top 900020 userid from t_userinfo order by userid asc
) a order by a.userid desc
) a inner join t_userinfo b on a.userid = b.userid
order by a.userid asc
-- 耗时 1 秒,太快了吧,不可以思议
-- step 5 where 查询
select top 20 userid,nick,classid,writetime from t_userinfo
where classid = 1 and userid not in
(
select top 90000 userid from t_userinfo
where classid = 1
order by userid asc
)
-- 耗时 2 秒
-- step 6 where 查询
select a.userid,b.nick,b.classid,b.writetime from
(
select top 20 a.userid from
(
select top 90000 userid from t_userinfo
where classid = 1
order by userid asc
) a order by a.userid desc
) a inner join t_userinfo b on a.userid = b.userid
order by a.userid asc
-- 查询分析器显示不到 1 秒.
查询效率分析:
子查询为确保消除重复值,必须为外部查询的每个结果都处理嵌套查询。在这种情况下可以考虑用联接查询来取代。
如果要用子查询,那就用EXISTS替代IN、用NOT EXISTS替代NOT IN。因为EXISTS引入的子查询只是测试是否存在符合子查询中指定条件的行,效率较高。无论在哪种情况下,NOT IN都是最低效的。因为它对子查询中的表执行了一个全表遍历。
建立合理的索引,避免扫描多余数据,避免表扫描!
几百万条数据,照样几十毫秒完成查询.
机器情况
p4: 2.4
内存: 1 G
os: windows 2003
数据库: ms sql server 2000
目的: 查询性能测试,比较两种查询的性能
SQL查询效率 step by step
-- setp 1.
-- 建表
create table t_userinfo
(
userid int identity(1,1) primary key nonclustered,
nick varchar(50) not null default '',
classid int not null default 0,
writetime datetime not null default getdate()
)
go
-- 建索引
create clustered index ix_userinfo_classid on t_userinfo(classid)
go
-- step 2.
declare @i int
declare @k int
declare @nick varchar(10)
set @i = 1
while @i<1000000
begin
set @k = @i % 10
set @nick = convert(varchar,@i)
insert into t_userinfo(nick,classid,writetime) values(@nick,@k,getdate())
set @i = @i + 1
end
-- 耗时 08:27 ,需要耐心等待
-- step 3.
select top 20 userid,nick,classid,writetime from t_userinfo
where userid not in
(
select top 900000 userid from t_userinfo order by userid asc
)
-- 耗时 8 秒 ,够长的
-- step 4.
select a.userid,b.nick,b.classid,b.writetime from
(
select top 20 a.userid from
(
select top 900020 userid from t_userinfo order by userid asc
) a order by a.userid desc
) a inner join t_userinfo b on a.userid = b.userid
order by a.userid asc
-- 耗时 1 秒,太快了吧,不可以思议
-- step 5 where 查询
select top 20 userid,nick,classid,writetime from t_userinfo
where classid = 1 and userid not in
(
select top 90000 userid from t_userinfo
where classid = 1
order by userid asc
)
-- 耗时 2 秒
-- step 6 where 查询
select a.userid,b.nick,b.classid,b.writetime from
(
select top 20 a.userid from
(
select top 90000 userid from t_userinfo
where classid = 1
order by userid asc
) a order by a.userid desc
) a inner join t_userinfo b on a.userid = b.userid
order by a.userid asc
-- 查询分析器显示不到 1 秒.
查询效率分析:
子查询为确保消除重复值,必须为外部查询的每个结果都处理嵌套查询。在这种情况下可以考虑用联接查询来取代。
如果要用子查询,那就用EXISTS替代IN、用NOT EXISTS替代NOT IN。因为EXISTS引入的子查询只是测试是否存在符合子查询中指定条件的行,效率较高。无论在哪种情况下,NOT IN都是最低效的。因为它对子查询中的表执行了一个全表遍历。
建立合理的索引,避免扫描多余数据,避免表扫描!
几百万条数据,照样几十毫秒完成查询.