惜分飞

需求：有两张很大的表，写了一个存储过程处理（加工数据然后插入到一张新表中），因为一次性处理数据量很大，会导致tempdb等资源被耗尽，为了解决这个问题，每次输入两个参数，每次根据两个id的范围处理程序
1、建一张日志表

CREATE TABLE [dbo].[data_log](
	[start_time] [datetime] NULL DEFAULT (getdate()),
	[min_id] [int] NULL,
	[max_id] [int] NULL,
	[end_time] [datetime] NULL DEFAULT (getdate()
) 

2、编写处理过程

CREATE PROCEDURE [dbo].[insert_more](@min_data int,@max_data int)
as
begin
--开始处理
insert into data_log values(getdate(),@min_data,@max_data,getdate())
--处理程序
INSERT INTO test_1 
 SELECT t1.name,
           t2.name,
           t1.id
    FROM   t_1 t1,
           t_2 t2
    WHERE  t1.id = t2.id
    AND t1.id<=@max_data
    AND t1.id>@min_data
--结束处理    
update data_log set end_time=getdate() where min_id=@min_data and max_id=@max_data
end

3、生成批量执行该存储过程语句

CREATE PROCEDURE [dbo].[get_list](@min_id int,@max_id int,@mode int)
AS
declare @i int
declare @max_m int
begin
set @i=0
while @i<=(@max_id-@min_id)/@mode
begin
set @max_m=@min_id+(@i+1)*@mode
if @max_m>@max_id  
  set	@max_m=@max_id
print 'EXEC [dbo].[insert_more] @min_data = '+CAST(@min_id+@i*@mode as VARCHAR(50))+',@max_data = '+CAST(@max_m as VARCHAR(50))+';'
set @i=@i+1
END
end

利用3的过程，输入最小id，最大id，取值间隔，生成需要执行2过程的sql语句，执行这些语句完成操作，通过日志监控操作情况

1、创建数据库

USE Master 
GO
CREATE DATABASE Test_Partitioning
ON PRIMARY
(NAME='Partitioning_1',
FILENAME=
'E:\database\partitions\Partitioning_1.mdf',
SIZE=4,
MAXSIZE=100,
FILEGROWTH=1 ),
FILEGROUP FG2
(NAME = 'Partitioning_2',
FILENAME =
'E:\database\partitions\Partitioning_2.mdf',
SIZE = 4,
MAXSIZE=100,
FILEGROWTH=1 ),
FILEGROUP FG3
(NAME = 'Partitioning_3',
FILENAME =
'E:\database\partitions\Partitioning_3.mdf',
SIZE = 4,
MAXSIZE=100,
FILEGROWTH=1 )
GO

2、创建分区函数

Use test_Partitioning 
GO
CREATE PARTITION FUNCTION salesYearPartitions (datetime)
AS RANGE RIGHT FOR VALUES ( '2009-01-01', '2010-01-01')
GO

说明：
RIGHT:表示”=”在右边
LEFT:表示”=”在左边

3、创建分区方案

Use test_Partitioning 
GO
CREATE PARTITION SCHEME Test_PartitionScheme
AS PARTITION salesYearPartitions
TO ([PRIMARY], FG2, FG3 )
GO

4、使用分区创建表

Use test_Partitioning 
GO
CREATE TABLE SalesArchival
(SaleTime datetime PRIMARY KEY,
ItemName varchar(50))
ON Test_PartitionScheme (SaleTime);
GO

5、验证SQL语句
5.1)确定文件组的数量和数据库数据文件的数量

Use test_Partitioning 
GO
-- Confirm Filegroups
SELECT name as [File Group Name]
FROM sys.filegroups
WHERE type = 'FG'
GO 
-- Confirm Datafiles
SELECT name as [DB File Name],physical_name as [DB File Path]
FROM sys.database_files
where type_desc = 'ROWS'
GO

5.2)验证分区表上的数据分布

Use test_Partitioning 
GO
select partition_id, index_id, partition_number, Rows
FROM sys.partitions
WHERE OBJECT_NAME(OBJECT_ID)='SalesArchival'
GO