学步园

今天有一个表要做分区，写代码时，就想总结一下。

至于为什么要分区，分区的时机选择，分区的理论依据等就不赘述了，请参考MSDN。直接上代码。

这其实就是今天我对一个测试库的分区时的代码。环境是SQL Server 2008 R2，在2008里表分区其实是有可视化实现功能的。

USE MASTER
GO
--40万行分成5个文件组，PRIMARY加下面四个
--文件组命名:FG_数据库名_表名_字段名_流水号
ALTER DATABASE TEST ADD FILEGROUP FG_TEST_Product_ID_1;
ALTER DATABASE TEST ADD FILEGROUP FG_TEST_Product_ID_2;
ALTER DATABASE TEST ADD FILEGROUP FG_TEST_Product_ID_3;
ALTER DATABASE TEST ADD FILEGROUP FG_TEST_Product_ID_4;
GO

USE TEST
GO
--给每个文件组加个次数据文件
--文件命名:文件组名_data_流水号
ALTER DATABASE TEST
ADD FILE (
          NAME=N'FG_TEST_Product_ID_1_data_1',
          FILENAME=N'D:\Data\FG_TEST_Product_ID_1_data_1.ndf',
          SIZE=50MB,
          FILEGROWTH=10%
          )
TO FILEGROUP FG_TEST_Product_ID_1;

ALTER DATABASE TEST
ADD FILE (
          NAME=N'FG_TEST_Product_ID_2_data_1',
          FILENAME=N'D:\Data\FG_TEST_Product_ID_2_data_1.ndf',
          SIZE=50MB,
          FILEGROWTH=10%
          )
TO FILEGROUP FG_TEST_Product_ID_2;

ALTER DATABASE TEST
ADD FILE (
          NAME=N'FG_TEST_Product_ID_3_data_1',
          FILENAME=N'D:\Data\FG_TEST_Product_ID_3_data_1.ndf',
          SIZE=50MB,
          FILEGROWTH=10%
          )
TO FILEGROUP FG_TEST_Product_ID_3;

ALTER DATABASE TEST
ADD FILE (
          NAME=N'FG_TEST_Product_ID_4_data_1',
          FILENAME=N'D:\Data\FG_TEST_Product_ID_4_data_1.ndf',
          SIZE=50MB,
          FILEGROWTH=10%
          )
TO FILEGROUP FG_TEST_Product_ID_4;
GO

--创建分区函数
--分区函数命名：fn_Partition_表名_字段
CREATE PARTITION FUNCTION fn_Partition_Product_ID(INT)
AS 
RANGE RIGHT 
FOR VALUES(80000,160000,240000,320000);
GO

--创建分区架构
--分区架构命名：Sch_表名_字段名
CREATE PARTITION SCHEME Sch_Product_ID
AS PARTITION fn_Partition_Product_ID
TO 
([PRIMARY],[FG_TEST_Product_ID_1],[FG_TEST_Product_ID_2],[FG_TEST_Product_ID_3],[FG_TEST_Product_ID_4]);
GO

/**一切准备工作都已经完成，但是我用的是一个生产环境中的库的附本，
所以这个表上除了主键索引，还有一些其它的索引。
接下来的操作，主题就是在一个现有的表上如何进行分区。
**/
USE [TEST]
GO
BEGIN TRANSACTION
--移除聚集主键
ALTER TABLE [dbo].[Product] DROP CONSTRAINT [PK_Product]

--重新添加聚集主键，并指定分区架构
ALTER TABLE [dbo].[Product] ADD  CONSTRAINT [PK_Product] PRIMARY KEY CLUSTERED 
(
[ID] ASC
)WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, SORT_IN_TEMPDB = OFF, IGNORE_DUP_KEY = OFF, ONLINE = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON) 
ON [Sch_Product_ID]([ID])

/**
以下是对这个表上其它的非聚集索引的处理：重建时指定分区架构。
在WITH子句中加入DROP_EXISTING = ON选项，重建时如存在同名索引，先删除后新建。
**/
/**这样做目的其实就是实现存储位置对齐:不同索引会按照相同的分区架构将数据分布到文件组.
   但是个人认为,这样好处是在于多表的存储对齐而不是单表.
   详情可参考:http://msdn.microsoft.com/zh-cn/library/ms345146(SQL.90).aspx
**/
CREATE NONCLUSTERED INDEX [IX_Product_CategoryID_ID] ON [dbo].[Product] 
(
[CategoryID] ASC
)
INCLUDE ( [ID]) 
WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, SORT_IN_TEMPDB = OFF, IGNORE_DUP_KEY = OFF, 
      DROP_EXISTING = ON, ONLINE = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON)
ON [Sch_Product_ID]([ID])

CREATE NONCLUSTERED INDEX [IX_Product_ComID_IsAudit] ON [dbo].[Product] 
(
[ComID] ASC,
[IsAudit] ASC
)WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, SORT_IN_TEMPDB = OFF, IGNORE_DUP_KEY = OFF, 
       DROP_EXISTING = ON, ONLINE = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON) 
ON [Sch_Product_ID]([ID])

CREATE NONCLUSTERED INDEX [IX_Product_ComID_IsShelf_ShelfDate] ON [dbo].[Product] 
(
[ComID] ASC,
[IsShelf] ASC,
[ShelfDate] ASC
)
WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, SORT_IN_TEMPDB = OFF, IGNORE_DUP_KEY = OFF, 
       DROP_EXISTING = ON, ONLINE = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON) 
ON [Sch_Product_ID]([ID])

CREATE NONCLUSTERED INDEX [IX_Product_IA_IS_SD_ID_CID] ON [dbo].[Product] 
(
[IsAudit] ASC,
[IsShelf] ASC,
[ShelfDate] ASC
)
INCLUDE ( [ID],
[CategoryID]) 
WITH (PAD_INDEX  = OFF, STATISTICS_NORECOMPUTE  = OFF, SORT_IN_TEMPDB = OFF, IGNORE_DUP_KEY = OFF, 
      DROP_EXISTING = ON, ONLINE = OFF, ALLOW_ROW_LOCKS  = ON, ALLOW_PAGE_LOCKS  = ON) 
ON [Sch_Product_ID]([ID])

COMMIT TRANSACTION

分区表就就完成了，这些代码花了小部分时间，但是我想查看一下分区后数据在文件组中的分布

结果花了大部分时间在这个上面。

--创建这个函数的目的是传入分区边界值,就能得到这个分区对应的文件组.

-- =============================================
-- Author:        Joe.TJ
-- Create date: 20111130
-- Description:    获取各分区表中各分区对应的文件组
-- =============================================
CREATE FUNCTION dbo.fn_GetFileForPartition
(
@schemeName NVARCHAR(100),--分区架构名称
 @rangeValue int--分区的边界值
)
RETURNS TABLE
AS
RETURN
(
SELECT DDS.data_space_id AS [filegroup_id],DDS.destination_id AS [partition_number], DS.name as [filegroup_name] 
FROM sys.destination_data_spaces AS DDS
JOIN sys.data_spaces AS DS
ON DS.data_space_id=DDS.data_space_id
WHERE DDS.partition_scheme_id=(SELECT data_space_id FROM sys.partition_schemes
WHERE name=@schemeName)
AND DDS.destination_id=$PARTITION.fn_Partition_Product_ID(@rangeValue-1)
)
GO

--这个查询是要查询得我想要的信息,别名A表中得到分区段的基本信息,
--CROSS APPLY就是上面的函数,得到文件组的信息.
SELECT A.*,B.[filegroup_name]
FROM (
SELECT TOP 100 PERCENT $PARTITION.fn_Partition_Product_ID(ID) AS Partition_Num,
MIN(ID) AS MinValue,MAX(ID) AS MaxValue,COUNT(1) as Row_Num
FROM dbo.Product
GROUP BY $PARTITION.fn_Partition_Product_ID(ID)
ORDER BY $PARTITION.fn_Partition_Product_ID(ID)
     ) AS A
CROSS APPLY 
     dbo.fn_GetFileForPartition(N'Sch_Product_ID',A.MaxValue) AS B  --将分区最大值当边界值传入

参考：

   http://www.cnblogs.com/gaizai/archive/2011/07/01/2095539.html

   http://msdn.microsoft.com/zh-cn/library/ms345146(SQL.90).aspx