【转】SQL百万数据分页研究
.net+mssql2000百万数据分页研究
公司一项目数据达到上百万，普通的分页方式满足不了要求，经常发生超时的错误，所以有必要对分页的方式来做下研究。
经过搜集和测试，当前网上的成熟的分页方式有以下几种方案：
分页存储过程1.
以下为引用的内容：
/*
说明：适合单表查询 cn-web.com提供
*/
CREATE PROCEDURE p_qcd_Pagination
@tblName varchar(255), -- 表名
@strGetFields varchar(1000) = '*', -- 需要返回的列
@fldName varchar(255)='', -- 排序的字段名
@PageSize int = 10, -- 页尺寸
@PageIndex int = 1, -- 页码
@doCount bit = 0, -- 返回记录总数, 非 0 值则返回
@OrderType bit = 0, -- 设置排序类型, 非 0 值则降序
@strWhere varchar(1500) = '' -- 查询条件 (注意: 不要加 where)
AS
declare @strSQL varchar(5000) -- 主语句
declare @strTmp varchar(110) -- 临时变量
declare @strOrder varchar(400) -- 排序类型
if @doCount != 0
begin
if @strWhere !=''
set @strSQL = 'select count(*) as Total from ['+ @tblName +'] where '+ @strWhere
else
set @strSQL = 'select count(*) as Total from ['+ @tblName +']'
end
--以上代码的意思是如果@doCount传递过来的不是0，就执行总数统计。以下的所有代码都
--是@doCount为0的情况
else
begin
if @OrderType != 0
begin
set @strTmp = '<(select min'
set @strOrder = ' order by ['+ @fldName +'] desc'
--如果@OrderType不是0，就执行降序，这句很重要！
end
else
begin
set @strTmp = '>(select max'
set @strOrder = ' order by ['+ @fldName +'] asc'
end
if @PageIndex = 1
begin
if @strWhere != ''
set @strSQL = 'select top ' + str(@PageSize) +' '+@strGetFields+ ' from ['+ @tblName +'] where ' + @strWhere + ' ' + @strOrder
else
set @strSQL = 'select top ' + str(@PageSize) +' '+@strGetFields+ ' from ['+ @tblName +'] '+ @strOrder
--如果是第一页就执行以上代码，这样会加快执行速度
end
else
begin
--以下代码赋予了@strSQL以真正执行的SQL代码
set @strSQL = 'select top ' + str(@PageSize) +' '+@strGetFields+ ' from [' + @tblName +'] where [' + @fldName + ']' + @strTmp + '(['+ @fldName + '])
from (select top ' + str((@PageIndex-1)*@PageSize) + ' ['+ @fldName + '] from ['+ @tblName +']' + @strOrder + ') as tblTmp)'+ @strOrder
if @strWhere != ''
set @strSQL = 'select top ' + str(@PageSize) +' '+@strGetFields+ ' from ['+ @tblName +'] where [' + @fldName + ']' + @strTmp + '(['+ @fldName + ']) from (select top ' + str((@PageIndex-1)*@PageSize) + ' ['+ @fldName + ']
from ['+ @tblName +'] where ' + @strWhere + ' ' + @strOrder + ') as tblTmp) and ' + @strWhere + ' ' + @strOrder
end
end
exec ( @strSQL)
GO
此方案只适合单表，中小数据查询，当条件出现in(1,2,3,4,5……)时，则速度明显下降。
分页存储过程2
以下为引用的内容：
create PROCEDURE p_qcd_PaginationDichotomy
(
@tblName nvarchar(200), ----要显示的表或多个表的连接
@fldName nvarchar(500) = '*', ----要显示的字段列表
@pageSize int = 10, ----每页显示的记录个数
@page int = 1, ----要显示那一页的记录
@fldSort nvarchar(200) = null, ----排序字段列表或条件
@Sort bit = 0, ----排序方法，0为升序，1为降序(如果是多字段排列Sort指代最后一个排序字段的排列顺序(最后一个排序字段不加排序标记)--程序传参如：' SortA Asc,SortB Desc,SortC ')
@strCondition nvarchar(1000) = null, ----查询条件,不需where
@ID nvarchar(150), ----主表的主键
@Dist bit = 0, ----是否添加查询字段的 DISTINCT 默认0不添加/1添加
@pageCount int = 1 output, ----查询结果分页后的总页数
@Counts int = 1 output ----查询到的记录数
)
AS
SET NOCOUNT ON
Declare @sqlTmp nvarchar(1000) ----存放动态生成的SQL语句
Declare @strTmp nvarchar(1000) ----存放取得查询结果总数的查询语句
Declare @strID nvarchar(1000) ----存放取得查询开头或结尾ID的查询语句
Declare @strSortType nvarchar(10) ----数据排序规则A
Declare @strFSortType nvarchar(10) ----数据排序规则B
Declare @SqlSelect nvarchar(50) ----对含有DISTINCT的查询进行SQL构造
Declare @SqlCounts nvarchar(50) ----对含有DISTINCT的总数查询进行SQL构造
declare @timediff datetime --耗时测试时间差
select @timediff=getdate()
if @Dist = 0
begin
set @SqlSelect = 'select '
set @SqlCounts = 'Count(*)'
end
else
begin
set @SqlSelect = 'select distinct '
set @SqlCounts = 'Count(DISTINCT '+@ID+')'
end
if @Sort=0
begin
set @strFSortType=' ASC '
set @strSortType=' DESC '
end
else
begin
set @strFSortType=' DESC '
set @strSortType=' ASC '
end
--------生成查询语句cn-web.com提供--------
--此处@strTmp为取得查询结果数量的语句
if @strCondition is null or @strCondition='' --没有设置显示条件
begin
set @sqlTmp = @fldName + ' From ' + @tblName
set @strTmp = @SqlSelect+' @Counts='+@SqlCounts+' FROM '+@tblName
set @strID = ' From ' + @tblName
end
else
begin
set @sqlTmp = + @fldName + 'From ' + @tblName + ' where (1>0) ' + @strCondition
set @strTmp = @SqlSelect+' @Counts='+@SqlCounts+' FROM '+@tblName + ' where (1>0) ' + @strCondition
set @strID = ' From ' + @tblName + ' where (1>0) ' + @strCondition
end
----取得查询结果总数量-----
exec sp_executesql @strTmp,N'@Counts int out ',@Counts out
declare @tmpCounts int
if @Counts = 0
set @tmpCounts = 1
else
set @tmpCounts = @Counts
--取得分页总数
set @pageCount=(@tmpCounts+@pageSize-1)/@pageSize
/**//**//**//**当前页大于总页数 取最后一页**/
if @page>@pageCount
set @page=@pageCount
--/*-----数据分页2分处理-------*/
declare @pageIndex int --总数/页大小
declare @lastcount int --总数%页大小
set @pageIndex = @tmpCounts/@pageSize
set @lastcount = @tmpCounts%@pageSize
if @lastcount > 0
set @pageIndex = @pageIndex + 1
else
set @lastcount = @pagesize
--//***显示分页
if @strCondition is null or @strCondition='' --没有设置显示条件
begin
if @pageIndex<2 or @page<=@pageIndex / 2 + @pageIndex % 2 --前半部分数据处理
begin
if @page=1
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' order by '+ @fldSort +' '+ @strFSortType
else
begin
if @Sort=1
begin
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' <(select min('+ @ID +') from ('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-1) as Varchar(20)) +' '+ @ID +' from '+@tblName
+' order by '+ @fldSort +' '+ @strFSortType+') AS TBMinID)'
+' order by '+ @fldSort +' '+ @strFSortType
end
else
begin
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' >(select max('+ @ID +') from ('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-1) as Varchar(20)) +' '+ @ID +' from '+@tblName
+' order by '+ @fldSort +' '+ @strFSortType+') AS TBMinID)'
+' order by '+ @fldSort +' '+ @strFSortType
end
end
end
else
begin
set @page = @pageIndex-@page+1 --后半部分数据处理
if @page <= 1 --最后一页数据显示
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@lastcount as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
else
if @Sort=1
begin
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' >(select max('+ @ID +') from('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-2)+@lastcount as Varchar(20)) +' '+ @ID +' from '+@tblName
+' order by '+ @fldSort +' '+ @strSortType+') AS TBMaxID)'
+' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
end
else
begin
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' <(select min('+ @ID +') from('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-2)+@lastcount as Varchar(20)) +' '+ @ID +' from '+@tblName
+' order by '+ @fldSort +' '+ @strSortType+') AS TBMaxID)'
+' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
end
end
end =@pageIndex / 2 + @pageIndex % 2 --前半部分数据处理
begin
if @page=1
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where 1=1 ' + @strCondition + ' order by '+ @fldSort +' '+ @strFSortType
else if(@Sort=1)
begin
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' <(select min('+ @ID +') from ('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-1) as Varchar(20)) +' '+ @ID +' from '+@tblName
+' where (1=1) ' + @strCondition +' order by '+ @fldSort +' '+ @strFSortType+') AS TBMinID)'
+' '+ @strCondition +' order by '+ @fldSort +' '+ @strFSortType
end
else
begin
set @strTmp=@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' >(select max('+ @ID +') from ('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-1) as Varchar(20)) +' '+ @ID +' from '+@tblName
+' where (1=1) ' + @strCondition +' order by '+ @fldSort +' '+ @strFSortType+') AS TBMinID)'
+' '+ @strCondition +' order by '+ @fldSort +' '+ @strFSortType
end
end
else
begin
set @page = @pageIndex-@page+1 --后半部分数据处理
if @page <= 1 --最后一页数据显示
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@lastcount as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where (1=1) '+ @strCondition +' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
else if(@Sort=1)
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' >(select max('+ @ID +') from('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-2)+@lastcount as Varchar(20)) +' '+ @ID +' from '+@tblName
+' where (1=1) '+ @strCondition +' order by '+ @fldSort +' '+ @strSortType+') AS TBMaxID)'
+' '+ @strCondition+' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
else
set @strTmp=@SqlSelect+' * from ('+@SqlSelect+' top '+ CAST(@pageSize as VARCHAR(4))+' '+ @fldName+' from '+@tblName
+' where '+@ID+' <(select min('+ @ID +') from('+ @SqlSelect+' top '+ CAST(@pageSize*(@page-2)+@lastcount as Varchar(20)) +' '+ @ID +' from '+@tblName
+' where (1=1) '+ @strCondition +' order by '+ @fldSort +' '+ @strSortType+') AS TBMaxID)'
+' '+ @strCondition+' order by '+ @fldSort +' '+ @strSortType+') AS TempTB'+' order by '+ @fldSort +' '+ @strFSortType
end
end
else --有查询条件
begin
if @pageIndex<2 or @page<
------返回查询结果-----
--select @pageCount ,@Counts
--select @pageCount
exec sp_executesql @strTmp
select datediff(ms,@timediff,getdate()) as 耗时
--print @strTmp
SET NOCOUNT OFF
GO
此分页俗称二分法，执行效率超快，数据量达到百万后效率也没有明显下降，缺点同上，当条件出现in(1,2,3,4,5……)时，则速度明显下降。
分页存储过程3
以下为引用的内容：
CREATE procedure p_qcd_Paginationcursor
@sql nvarchar(4000), --要执行的sql语句
@currentpage int=1, --要显示的页码
@pagesize int=10, --每页的大小
@pagecount int=0 out, --总页数
@recordCount int=0 out--总记录数
as
set nocount on
declare @cursor int --cursor 是游标的id
declare @timediff datetime --耗时测试时间差 cn-web.com提供
select @timediff=getdate()
exec sp_cursoropen @cursor output,@sql,@scrollopt=1,@ccopt=1,@rowcount=@pagecount output
select @recordCount=@pagecount
select @pagecount=ceiling(1.0*@pagecount/@pagesize) ,@currentpage=(@currentpage-1)*@pagesize+1
select @pagecount,@currentpage
exec sp_cursorfetch @cursor ,16,@currentpage,@pagesize
exec sp_cursorclose @cursor
select datediff(ms,@timediff,getdate()) as 耗时
GO
此方案所说是微软没有公开的游标分页，刚开始怀疑游标分页肯定浪费性能，不过经过详细测试后，发现微软就是微软，不管如何测试，不管条件如何复杂，数据量再大，性能一直保持最强劲。
总结：在没有in(1,2,3,4,5……)之类的条件的查询时，三种方案的性能：方案3=方案2>方案1。当存在复杂条件时，方案3>方案2=方案1。
