s.b*_*ody 4 t-sql sql-server stored-procedures
我编写了一个存储过程来生成随机SMS记录/事件.
插入120万行时,查询需要数百分钟
exec insert_random_sms 1200000
Run Code Online (Sandbox Code Playgroud)
我以"程序"的方式编写了存储过程.但是,从我看来,SQL在这方面效率不高.
create proc insert_random_sms
@number_of_records int
as
begin
declare @cnt int = 0; -- loop counter
declare @phone_id int;
declare @dest_id int;
while (@cnt < @number_of_records)
begin
declare @charge int = rand() * 100; -- will generate a random charge value between 0 and 100.
declare @tarrif_plan int = round(rand() * 5, 0);
select top 1 @phone_id = phone_no
from tbl_phone_agenda
order by newid();
select top 1 @dest_id = phone_no
from tbl_phone_agenda
order by newid();
insert into tbl_sms (phone_id, dest_id, charge, tarrif_plan)
values (@phone_id, @dest_id, @charge,
convert(nvarchar(50), @tarrif_plan));
set @cnt += 1;
end
end
go
Run Code Online (Sandbox Code Playgroud)
优化此存储过程的方法是什么?
我喜欢用于生成x个记录的方法是堆叠CTE方法(已经阅读了Aaron Bertrand的文章,他将Itzik Ben-Gan归功于堆叠CTE方法):
WITH N1 (N) AS
( SELECT 1
FROM (VALUES
(1), (1), (1), (1), (1),
(1), (1), (1), (1), (1)
) n (Number)
),
N2 (N) AS (SELECT 1 FROM N1 AS N1 CROSS JOIN N1 AS N2),
N3 (N) AS (SELECT 1 FROM N2 AS N1 CROSS JOIN N2 AS N2),
N4 (N) AS (SELECT 1 FROM N3 AS N1 CROSS JOIN N3 AS N2)
SELECT COUNT(*)
FROM N4
Run Code Online (Sandbox Code Playgroud)
这只是从10行开始,并保持交叉连接,直到在上面的情况下有100,000,000行.这将是我如何生成你的行,
当你使用一组为基础的方法,你可以不再使用RAND()它自己,因为它是一个运行时间常数,以获得每个你需要组合排一个新的评估RAND()与NEWID()这是每行都是唯一的,所以下面将产生0到100之间的随机数,每行不同:
SELECT CAST(ROUND(RAND(CHECKSUM(NEWID())) * 100, 0) AS INT)
Run Code Online (Sandbox Code Playgroud)
我要做的下一件事是将所有的phonenumbers放入临时表中,以便它们具有顺序ID(这将用于随机分配):
CREATE TABLE #Phone
(
ID INT IDENTITY NOT NULL PRIMARY KEY,
PhoneNo VARCHAR(50) NOT NULL
);
INSERT #Phone (PhoneNo)
SELECT PhoneNo
FROM tbl_phone_agenda;
Run Code Online (Sandbox Code Playgroud)
所以你的最终查询将是
CREATE PROC insert_random_sms @number_of_records IN
AS
BEGIN
CREATE TABLE #Phone
(
ID INT IDENTITY NOT NULL PRIMARY KEY,
PhoneNo VARCHAR(50) NOT NULL
);
INSERT #Phone (PhoneNo)
SELECT PhoneNo
FROM tbl_phone_agenda;
-- NEEDED SO WE KNOW WHAT NUMBER TO GENERATE A RANDOM
-- NUMBER IN THE RIGHT RANGE LATER
DECLARE @PhoneCount INT = (SELECT COUNT(*) FROM #Phone);
WITH N1 (N) AS
( SELECT 1
FROM (VALUES
(1), (1), (1), (1), (1),
(1), (1), (1), (1), (1)
) n (Number)
),
N2 (N) AS (SELECT 1 FROM N1 AS N1 CROSS JOIN N1 AS N2),
N3 (N) AS (SELECT 1 FROM N2 AS N1 CROSS JOIN N2 AS N2),
N4 (N) AS (SELECT 1 FROM N3 AS N1 CROSS JOIN N3 AS N2)
INSERT tbl_sms (phone_id, dest_id, charge, tarrif_plan)
SELECT TOP (@number_of_records)
p.PhoneNo,
d.PhoneNo,
Charge = CAST(ROUND(RAND(CHECKSUM(NEWID())) * 100, 0) AS INT),
tarrif_plan = CAST(ROUND(RAND(CHECKSUM(NEWID())) * 5, 0) AS INT)
FROM N4
INNER JOIN #Phone p
ON p.ID = CAST(CEILING(RAND(CHECKSUM(NEWID())) * @PhoneCount) AS INT)
INNER JOIN #Phone d
ON d.ID = CAST(CEILING(RAND(CHECKSUM(NEWID())) * @PhoneCount) AS INT)
END
Run Code Online (Sandbox Code Playgroud)
在我的测试中,大约需要20-30秒才能生成120万条记录,查看100,000个电话号码.