能否将这个 SQL 提高效率并组合成一个选择？

Question

我有下面的 4 个 SQL 查询，最后我将它们组合成一个结果集。

我猜是因为我在每个 SQL 部分都对相同的表进行操作，所以有一种很酷的方法可以从一个统一的 SQL 查询中获取我的结果。

目前我是这样做的：

select 
[date] = CONVERT(DATE, M.crdate), 
[tally sent to smc w/ attachment] = count(*) ,
[total MB size] =  sum(cast(AD.Size as decimal (10,2)) )/1024/1024 
into #tmp_Attachments_Sent_To_smc
from AttachmentDetail AD
inner join MessageAttachment MA on AD.AttachmentId = MA.AttachmentId
inner join MessageRecipient MR on MA.MessageId = MR.MessageId 
inner join Message M on MR.MessageId = M.id
where AD.isinline <>1 and MR.RecipientTypeId =2 and left(mr.EmailAddress,4)='smc+' 
GROUP BY  CONVERT(DATE, M.crdate)
ORDER BY [date] DESC;
--select * from #tmp_Attachments_Sent_To_smc

select 
[date] = CONVERT(DATE, M.crdate), 
[tally sent from smc w/ attachment] = count(*) ,
[total MB size] =  sum(cast(AD.Size as decimal (10,2)) )/1024/1024 
into #tmp_Attachments_Sent_from_smc
from AttachmentDetail AD
inner join MessageAttachment MA on AD.AttachmentId = MA.AttachmentId
inner join MessageRecipient MR on MA.MessageId = MR.MessageId 
inner join Message M on MR.MessageId = M.id
where AD.isinline <>1 and MR.RecipientTypeId =1 and left(mr.EmailAddress,4)='smc+' 
GROUP BY  CONVERT(DATE, M.crdate)
ORDER BY [date] DESC;


select 
[date] = CONVERT(DATE, M.crdate), 
[grand total sent to smc] = count(*) ,
[total MB size sent to smc] =  sum(cast(Size as decimal ) )/1024/1024 
into #tmp_Sent_to_smc
from Message M
where MessageSourceId=2
GROUP BY  CONVERT(DATE, crdate)
ORDER BY [date] DESC;


select 
[date] = CONVERT(DATE, M.crdate), 
[grand total sent from smc] = count(*) ,
[total MB size sent from smc] =  sum(cast(Size as decimal ) )/1024/1024 
into #tmp_Sent_from_smc
from Message M
where MessageSourceId=1
GROUP BY  CONVERT(DATE, crdate)
ORDER BY [date] DESC;


select   A.* ,
         B.[tally sent from smc w/ attachment] ,
         B.[total MB size],
         C.[grand total sent from smc] ,
         C.[total MB size sent from smc],
         D.[grand total sent to smc] ,
         D.[total MB size sent to smc]
from #tmp_Attachments_Sent_To_smc A
join #tmp_Attachments_Sent_from_smc B on A.date = b.date
join #tmp_Sent_from_smc C on A.date = C.date
join #tmp_Sent_to_smc D on A.date = D.date


drop table #tmp_Attachments_Sent_To_smc
drop table #tmp_Attachments_Sent_from_smc
drop table #tmp_Sent_from_smc
drop table #tmp_Sent_to_smc

Answer 1

首先，我会看看您是否可以消除临时表。我喜欢CTE，但它们并不总是提供更好的性能。

;WITH tmp_Attachments_Sent_To_smc AS
(
    -- Find all the emails to smc+
    -- that had attachments 
    -- and something else
    SELECT
        [date] = CONVERT(date, M.crdate)
    ,   [tally sent to smc w/ attachment] = COUNT(*)
    ,   [total MB size] = SUM(CAST(AD.Size AS decimal(10, 2))) / 1024 / 1024
    FROM
        AttachmentDetail AD
        INNER JOIN 
            MessageAttachment MA
            ON AD.AttachmentId = MA.AttachmentId
        INNER JOIN 
            MessageRecipient MR
            ON MA.MessageId = MR.MessageId
        INNER JOIN 
            [Message] M
            ON MR.MessageId = M.id
    WHERE
        AD.isinline <> 1
        AND MR.RecipientTypeId = 2
        AND LEFT(mr.EmailAddress, 4) = 'smc+'
    GROUP BY
        CONVERT(date, M.crdate)
)
, tmp_Attachments_Sent_from_smc AS
(
    SELECT
        [date] = CONVERT(date, M.crdate)
    ,   [tally sent from smc w/ attachment] = COUNT(*)
    ,   [total MB size] = SUM(CAST(AD.Size AS decimal(10, 2))) / 1024 / 1024
    FROM
        AttachmentDetail AD
        INNER JOIN 
            MessageAttachment MA
            ON AD.AttachmentId = MA.AttachmentId
        INNER JOIN 
            MessageRecipient MR
            ON MA.MessageId = MR.MessageId
        INNER JOIN 
            [Message] M
            ON MR.MessageId = M.id
    WHERE
        AD.isinline <> 1
        AND MR.RecipientTypeId = 1
        AND LEFT(mr.EmailAddress, 4) = 'smc+'
    GROUP BY
        CONVERT(date, M.crdate)
)
, tmp_Sent_to_smc AS
(
    SELECT
        [date] = CONVERT(date, M.crdate)
    ,   [grand total sent to smc] = COUNT(*)
    ,   [total MB size sent to smc] = SUM(CAST(Size AS decimal)) / 1024 / 1024
    FROM
        [Message] M
    WHERE
        MessageSourceId = 2
    GROUP BY
        CONVERT(date, crdate)
)
, tmp_Sent_from_smc AS
(
    SELECT
        [date] = CONVERT(date, M.crdate)
    ,   [grand total sent from smc] = COUNT(*)
    ,   [total MB size sent from smc] = SUM(CAST(Size AS decimal)) / 1024 / 1024
    FROM
        [Message] M
    WHERE
        MessageSourceId = 1
    GROUP BY
        CONVERT(date, crdate)
)
SELECT
    A.*
,   B.[tally sent from smc w/ attachment]
,   B.[total MB size]
,   C.[grand total sent from smc]
,   C.[total MB size sent from smc]
,   D.[grand total sent to smc]
,   D.[total MB size sent to smc]
FROM
    tmp_Attachments_Sent_To_smc A
    INNER JOIN 
        tmp_Attachments_Sent_from_smc B
        ON A.date = b.date
    INNER JOIN 
        tmp_Sent_from_smc C
        ON A.date = C.date
    INNER JOIN 
        tmp_Sent_to_smc D
        ON A.date = D.date;

否则，可能会损害您的性能的是 WHEREs 和 GROUP BY ( 中的转换CONVERT(date, M.crdate) CAST(AD.Size AS decimal(10, 2)。这些可能会导致表扫描对您造成伤害。如果您无法将现有数据类型修改为意味着存储这些计算项。

我盯着LEFT(mr.EmailAddress, 4)并且我认为这也会强制进行表扫描，但我认为它可以通过mr.EmailAddress LIKE 'smc+%'至少应该是 SARGAable 来修复。

此时，您应该能够查看查询计划并确定索引是否有帮助。

此外，使用适当的架构为您的表添加前缀。我认为它是 dbo，但据我所知，这将有助于计划缓存重用。

Answer 2

笔记

1. 因为您在最终选择中是 INNER JOIN-ing A 和 B，所以我在源中预过滤了数据以尽早消除不匹配（删除日期没有两个 RecipientTypeIds 的地方）。这使用了两次。
2. billinkc是对的。在 varchar 列上使用 LEFT 函数不是SARGable，因此请改用 LIKE 。支持 SARG 意味着可以在搜索 ARGument 到索引中使用条件
3. 使用 PIVOTing 模式，可以在一次通过数据时解析 from/to。这种技术被使用了两次。
4. DATE如果您正在处理 1000 个唯一日期（3 年的数据），则在临时表上创建索引将有助于查询
5. 在CAST(.. to decimal)需要说明符。否则，它相当于十进制（18,0）。（这对于避免整数除法仍然很有用）

单个查询

select   A.*,
         C.[grand total sent from smc] ,
         C.[total MB size sent from smc],
         C.[grand total sent to smc] ,
         C.[total MB size sent to smc]
from (
    select 
    [date] = CONVERT(DATE, M.crdate), 
    [tally sent to smc w/ attachment] = SUM(case MR.RecipientTypeId when 2 then 1 else 0 end),
    [tally sent from smc w/ attachment] = SUM(case MR.RecipientTypeId when 1 then 1 else 0 end),
    [total MB size to] =  sum(cast(case MR.RecipientTypeId when 2 then AD.Size else 0 end as decimal (10,2)) )/1024/1024,
    [total MB size from] =  sum(cast(case MR.RecipientTypeId when 1 then AD.Size else 0 end as decimal (10,2)) )/1024/1024
    from AttachmentDetail AD
    inner join MessageAttachment MA on AD.AttachmentId = MA.AttachmentId
    inner join MessageRecipient MR on MA.MessageId = MR.MessageId 
    inner join Message M on MR.MessageId = M.id
    where AD.isinline <>1
        and MR.RecipientTypeId in(1,2)
        and mr.EmailAddress LIKE 'smc+%'
    GROUP BY  CONVERT(DATE, M.crdate)
    HAVING COUNT(DISTINCT MR.RecipientTypeId) = 2
    ) A
join (
    select 
    [date] = CONVERT(DATE, M.crdate), 
    [grand total sent to smc] = SUM(case MessageSourceId when 2 then 1 else 0 end),
    [grand total sent from smc] = SUM(case MessageSourceId when 1 then 1 else 0 end),
    [total MB size sent to smc] =  sum(cast(case MessageSourceId when 2 then Size else 0 end as decimal(10,2) ) )/1024/1024 ,
    [total MB size sent from smc] =  sum(cast(case MessageSourceId when 1 then Size else 0 end as decimal(10,2) ) )/1024/1024 
    from Message M
    where MessageSourceId in (1,2)
    GROUP BY  CONVERT(DATE, crdate)
    HAVING COUNT(DISTINCT MessageSourceId) = 2 -- note #1
    ) C on A.[date] = C.[date]
GO

原始查询批处理：

create table #tmp_Attachments_Sent_smc
(
    [date] DATE primary key clustered, -- indexed as well for final query
    [tally sent to smc w/ attachment] bigint,
    [tally sent from smc w/ attachment] bigint,
    [total MB size to] decimal(10,2),
    [total MB size from] decimal(10,2)
)
GO
insert #tmp_Attachments_Sent_smc
select 
    [date] = CONVERT(DATE, M.crdate), 
    [tally sent to smc w/ attachment] = count(case MR.RecipientTypeId when 2 then 0 end),
    [tally sent from smc w/ attachment] = count(case MR.RecipientTypeId when 1 then 0 end),
    [total MB size to] =  sum(cast(case MR.RecipientTypeId when 2 then AD.Size end as decimal (10,2)) )/1024/1024,
    [total MB size from] =  sum(cast(case MR.RecipientTypeId when 1 then AD.Size end as decimal (10,2)) )/1024/1024 
  from AttachmentDetail AD
  join MessageAttachment MA on AD.AttachmentId = MA.AttachmentId
  join MessageRecipient MR on MA.MessageId = MR.MessageId 
  join Message M on MR.MessageId = M.id
 where AD.isinline <>1
   and MR.RecipientTypeId in(1,2)
   and mr.EmailAddress LIKE 'smc+%' -- note #2
 GROUP BY CONVERT(DATE, M.crdate)
HAVING COUNT(DISTINCT MR.RecipientTypeId) = 2 -- note #1
-- ORDER BY [date] DESC; -- no point to ordering in an insert statement
GO

create table #tmp_Sent_smc
(
    [date] DATE primary key clustered, -- indexed as well for final query
    [grand total sent to smc] bigint,
    [grand total sent from smc] bigint,
    [total MB size sent to smc] decimal(10,2),
    [total MB size sent from smc] decimal(10,2)
)
GO
insert #tmp_Sent_smc
select 
    [date] = CONVERT(DATE, M.crdate), 
    [grand total sent to smc] = count(case MessageSourceId when 2 then 1 end),
    [grand total sent from smc] = count(case MessageSourceId when 1 then 1 end),
    [total MB size sent to smc] =  sum(cast(case MessageSourceId when 2 then Size end as decimal(10,2) ) )/1024/1024 ,
    [total MB size sent from smc] =  sum(cast(case MessageSourceId when 1 then Size end as decimal(10,2) ) )/1024/1024 
  from Message M
 where MessageSourceId in (1,2)
 GROUP BY  CONVERT(DATE, crdate)
HAVING COUNT(DISTINCT MessageSourceId) = 2 -- note #1
--ORDER BY [date] DESC;

select A.*,
       C.[grand total sent from smc] ,
       C.[total MB size sent from smc],
       C.[grand total sent to smc] ,
       C.[total MB size sent to smc]
  from #tmp_Attachments_Sent_smc A
  join #tmp_Sent_smc C on A.date = C.date

我使用这个 DDL 和 DML 进行测试：

USE TEMPDB;
if object_id('dbo.VNewID') is not null drop view dbo.VNewID;
if object_id('dbo.Rnd') is not null drop function dbo.Rnd;
if object_id('AttachmentDetail') is not null drop table AttachmentDetail;
if object_id('MessageAttachment') is not null drop table MessageAttachment;
if object_id('Message') is not null drop table Message;
if object_id('MessageRecipient') is not null drop table MessageRecipient;
GO
-- this view supports the next function
create view VNewID as select NewID() N
GO
-- this function generates a random number within a range, for the random data in the insert statements below
create function dbo.Rnd(@max int) returns int as begin return (SELECT ABS(CAST(CAST(N AS VARBINARY) AS INT)) from VNewID) % (@max+1) end
GO
-- create tables with some sample date
create table AttachmentDetail (AttachmentId int primary key clustered, isinline bit, size int);
insert AttachmentDetail select number, dbo.Rnd(2), number from master..spt_values where type='p' and number % 3 = 1;
insert AttachmentDetail select AttachmentId+10000, isinline, size from AttachmentDetail;
insert AttachmentDetail select AttachmentId+20000, isinline, size from AttachmentDetail;
create table MessageAttachment (AttachmentId int, MessageId int, primary key clustered (AttachmentId, MessageId));
insert MessageAttachment select number, number from master..spt_values where type='p' and number % 3 = 1;
insert MessageAttachment select AttachmentId+10000, MessageId +10000 from MessageAttachment;
insert MessageAttachment select AttachmentId+20000, MessageId +20000 from MessageAttachment;
create table Message (Id int primary key clustered, crdate datetime, size int, MessageSourceId tinyint);
insert Message select number, dateadd(hh, -number, getdate()), number, dbo.Rnd(4) from master..spt_values where type='p';
insert Message select Id+10000, dateadd(d,-365,crdate), size, MessageSourceId from Message;
insert Message select Id+20000, dateadd(d,-730,crdate), size, MessageSourceId from Message;
create index ix_message_1 on Message(MessageSourceId) include(id, crdate);
create table MessageRecipient (MessageId int, RecipientTypeId tinyint, EmailAddress varchar(100));
insert MessageRecipient select number, dbo.Rnd(2) + 1, case dbo.Rnd(2) when 0 then 'smc+' else 'other' end + right(number,10) 
    from master..spt_values where type='p';
insert MessageRecipient select MessageId+10000, RecipientTypeId, EmailAddress from MessageRecipient;
insert MessageRecipient select MessageId+20000, RecipientTypeId, EmailAddress from MessageRecipient;
create index ix_MessageRecipient_1 on MessageRecipient(EmailAddress);
GO