如何提高 sql 脚本性能
How to improve sql script performance
以下脚本在 运行 时非常慢。
我不知道如何提高脚本的性能。
即使有一个视图也需要花费很多分钟。
有什么想法请分享给我。
SELECT DISTINCT
( id )
FROM ( SELECT DISTINCT
ct.id AS id
FROM [Customer].[dbo].[Contact] ct
LEFT JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
WHERE hnci.customer_id IN (
SELECT DISTINCT
( [Customer_ID] )
FROM [Transactions].[dbo].[Transaction_Header]
WHERE actual_transaction_date > '20120218' )
UNION
SELECT DISTINCT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
UNION
SELECT DISTINCT
( ct.id )
FROM [Customer].[dbo].[Contact] ct
INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
AND startconnection > '2012-02-17'
UNION
SELECT DISTINCT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( opt_out_Mail <> 1
OR opt_out_email <> 1
OR opt_out_SMS <> 1
OR opt_out_Mail IS NULL
OR opt_out_email IS NULL
OR opt_out_SMS IS NULL
)
AND ( address_1 IS NOT NULL
OR email IS NOT NULL
OR mobile IS NOT NULL
)
UNION
SELECT DISTINCT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
) AS tbl
试试这个，temptable 应该能帮到你：
IF OBJECT_ID('Tempdb..#Temp1') IS NOT NULL
DROP TABLE #Temp1
--Low perfomance because of using "WHERE hnci.customer_id IN ( .... ) " - loop join must be
--and this "where" condition will apply to two tables after left join,
--so result will be same as with two inner joints but with bad perfomance
--SELECT DISTINCT
-- ct.id AS id
--INTO #temp1
--FROM [Customer].[dbo].[Contact] ct
-- LEFT JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
--WHERE hnci.customer_id IN (
-- SELECT DISTINCT
-- ( [Customer_ID] )
-- FROM [Transactions].[dbo].[Transaction_Header]
-- WHERE actual_transaction_date > '20120218' )
--------------------------------------------------------------------------------
--this will give the same result but with better perfomance then previouse one
--------------------------------------------------------------------------------
SELECT DISTINCT
ct.id AS id
INTO #temp1
FROM [Customer].[dbo].[Contact] ct
JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
JOIN ( SELECT DISTINCT
( [Customer_ID] )
FROM [Transactions].[dbo].[Transaction_Header]
WHERE actual_transaction_date > '20120218'
) T ON hnci.customer_id = T.[Customer_ID]
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
INSERT INTO #temp1
( id
)
SELECT DISTINCT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
INSERT INTO #temp1
( id
)
SELECT DISTINCT
( ct.id )
FROM [Customer].[dbo].[Contact] ct
INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
AND startconnection > '2012-02-17'
INSERT INTO #temp1
( id
)
SELECT DISTINCT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( opt_out_Mail <> 1
OR opt_out_email <> 1
OR opt_out_SMS <> 1
OR opt_out_Mail IS NULL
OR opt_out_email IS NULL
OR opt_out_SMS IS NULL
)
AND ( address_1 IS NOT NULL
OR email IS NOT NULL
OR mobile IS NOT NULL
)
INSERT INTO #temp1
( id
)
SELECT DISTINCT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
SELECT DISTINCT
id
FROM #temp1 AS T
如评论中所述，一次优化一个。看看哪个花费的时间最长，然后专注于那个。
union 将删除重复项，因此您不需要对单个查询使用 distinct
你先试试这个：
左联接被 WHERE hnci.customer_id IN 终止，因此您最好有一个联接。
子查询效率不高，因为不能在 IN 上使用索引。
查询优化器不知道 ( select .. ) 中的内容 return 因此它无法优化索引的使用。
SELECT ct.id AS id
FROM [Customer].[dbo].[Contact] ct
JOIN [Customer].[dbo].[Customer_ids] hnci
ON ct.id = hnci.contact_id
JOIN [Transactions].[dbo].[Transaction_Header] th
on hnci.customer_id = th.[Customer_ID]
and th.actual_transaction_date > '20120218'
在第二次连接中，查询优化器有机会首先应用哪个条件。假设 [Customer].[dbo].[Customer_ids].[customer_id] 和 [Transactions].[dbo].[Transaction_Header] 每个都有索引。查询优化器可以选择在 [Transactions].[dbo].[Transaction_Header].[actual_transaction_date] 之前应用它。
如果 [actual_transaction_date] 没有被索引，那么它肯定会首先执行另一个 ID 连接。
在 ( select ... ) 中，查询优化器别无选择，只能先应用 actual_transaction_date > '20120218'。好吧，有时查询优化器足够聪明，可以在内部外部使用索引，但为什么查询优化器很难做到这一点。我发现如果您使决策更容易，查询优化器会做出更好的决策。
子查询的连接也有同样的问题。您从查询优化器中获取选项。给查询优化器一个喘息的空间。
Where exists 通常也比 in 快。
或者条件通常也较慢，请改用更多联合语句。
并学会正确使用左连接。如果在左联接右侧的 table 上有 where 条件（除了 id 为 null 的地方），它将转换为内部联接。如果这不是您想要的，那么您的代码当前为您提供了不正确的结果集。
有关如何修复的说明，请参阅 http://wiki.lessthandot.com/index.php/WHERE_conditions_on_a_LEFT_JOIN。
哇，从哪里开始...
--this distinct does nothing. Union is already distinct
--SELECT DISTINCT
-- ( id )
--FROM (
SELECT DISTINCT [Customer_ID] as ID
FROM [Transactions].[dbo].[Transaction_Header]
where actual_transaction_date > '20120218' )
UNION
SELECT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
-- not sure that you are getting the date range you want. Should these be >=
-- if you want everything that occurred on the 18th or after you want >= '2012-02-18 00:00:00.000'
-- if you want everything that occurred on the 19th or after you want >= '2012-02-19 00:00:00.000'
-- the way you have it now, you will get everything on the 18th unless it happened exactly at midnight
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
-- all of this does nothing because we already have every id in the contact table from the first query
-- UNION
-- SELECT
-- ( ct.id )
-- FROM [Customer].[dbo].[Contact] ct
-- INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
-- AND startconnection > '2012-02-17'
UNION
-- cleaned this up with isnull function and coalesce
SELECT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( isnull(opt_out_Mail,0) <> 1
OR isnull(opt_out_email,0) <> 1
OR isnull(opt_out_SMS,0) <> 1
)
AND coalesce(address_1 , email, mobile) IS NOT NULL
UNION
SELECT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
-- ) AS tbl
以下脚本在 运行 时非常慢。
我不知道如何提高脚本的性能。 即使有一个视图也需要花费很多分钟。 有什么想法请分享给我。
SELECT DISTINCT
( id )
FROM ( SELECT DISTINCT
ct.id AS id
FROM [Customer].[dbo].[Contact] ct
LEFT JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
WHERE hnci.customer_id IN (
SELECT DISTINCT
( [Customer_ID] )
FROM [Transactions].[dbo].[Transaction_Header]
WHERE actual_transaction_date > '20120218' )
UNION
SELECT DISTINCT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
UNION
SELECT DISTINCT
( ct.id )
FROM [Customer].[dbo].[Contact] ct
INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
AND startconnection > '2012-02-17'
UNION
SELECT DISTINCT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( opt_out_Mail <> 1
OR opt_out_email <> 1
OR opt_out_SMS <> 1
OR opt_out_Mail IS NULL
OR opt_out_email IS NULL
OR opt_out_SMS IS NULL
)
AND ( address_1 IS NOT NULL
OR email IS NOT NULL
OR mobile IS NOT NULL
)
UNION
SELECT DISTINCT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
) AS tbl
试试这个，temptable 应该能帮到你：
IF OBJECT_ID('Tempdb..#Temp1') IS NOT NULL
DROP TABLE #Temp1
--Low perfomance because of using "WHERE hnci.customer_id IN ( .... ) " - loop join must be
--and this "where" condition will apply to two tables after left join,
--so result will be same as with two inner joints but with bad perfomance
--SELECT DISTINCT
-- ct.id AS id
--INTO #temp1
--FROM [Customer].[dbo].[Contact] ct
-- LEFT JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
--WHERE hnci.customer_id IN (
-- SELECT DISTINCT
-- ( [Customer_ID] )
-- FROM [Transactions].[dbo].[Transaction_Header]
-- WHERE actual_transaction_date > '20120218' )
--------------------------------------------------------------------------------
--this will give the same result but with better perfomance then previouse one
--------------------------------------------------------------------------------
SELECT DISTINCT
ct.id AS id
INTO #temp1
FROM [Customer].[dbo].[Contact] ct
JOIN [Customer].[dbo].[Customer_ids] hnci ON ct.id = hnci.contact_id
JOIN ( SELECT DISTINCT
( [Customer_ID] )
FROM [Transactions].[dbo].[Transaction_Header]
WHERE actual_transaction_date > '20120218'
) T ON hnci.customer_id = T.[Customer_ID]
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
INSERT INTO #temp1
( id
)
SELECT DISTINCT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
INSERT INTO #temp1
( id
)
SELECT DISTINCT
( ct.id )
FROM [Customer].[dbo].[Contact] ct
INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
AND startconnection > '2012-02-17'
INSERT INTO #temp1
( id
)
SELECT DISTINCT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( opt_out_Mail <> 1
OR opt_out_email <> 1
OR opt_out_SMS <> 1
OR opt_out_Mail IS NULL
OR opt_out_email IS NULL
OR opt_out_SMS IS NULL
)
AND ( address_1 IS NOT NULL
OR email IS NOT NULL
OR mobile IS NOT NULL
)
INSERT INTO #temp1
( id
)
SELECT DISTINCT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
SELECT DISTINCT
id
FROM #temp1 AS T
如评论中所述，一次优化一个。看看哪个花费的时间最长，然后专注于那个。
union 将删除重复项，因此您不需要对单个查询使用 distinct
你先试试这个：
左联接被 WHERE hnci.customer_id IN 终止，因此您最好有一个联接。
子查询效率不高，因为不能在 IN 上使用索引。
查询优化器不知道 ( select .. ) 中的内容 return 因此它无法优化索引的使用。
SELECT ct.id AS id
FROM [Customer].[dbo].[Contact] ct
JOIN [Customer].[dbo].[Customer_ids] hnci
ON ct.id = hnci.contact_id
JOIN [Transactions].[dbo].[Transaction_Header] th
on hnci.customer_id = th.[Customer_ID]
and th.actual_transaction_date > '20120218'
在第二次连接中，查询优化器有机会首先应用哪个条件。假设 [Customer].[dbo].[Customer_ids].[customer_id] 和 [Transactions].[dbo].[Transaction_Header] 每个都有索引。查询优化器可以选择在 [Transactions].[dbo].[Transaction_Header].[actual_transaction_date] 之前应用它。 如果 [actual_transaction_date] 没有被索引，那么它肯定会首先执行另一个 ID 连接。
在 ( select ... ) 中，查询优化器别无选择，只能先应用 actual_transaction_date > '20120218'。好吧，有时查询优化器足够聪明，可以在内部外部使用索引，但为什么查询优化器很难做到这一点。我发现如果您使决策更容易，查询优化器会做出更好的决策。
子查询的连接也有同样的问题。您从查询优化器中获取选项。给查询优化器一个喘息的空间。
Where exists 通常也比 in 快。
或者条件通常也较慢，请改用更多联合语句。 并学会正确使用左连接。如果在左联接右侧的 table 上有 where 条件（除了 id 为 null 的地方），它将转换为内部联接。如果这不是您想要的，那么您的代码当前为您提供了不正确的结果集。
有关如何修复的说明，请参阅 http://wiki.lessthandot.com/index.php/WHERE_conditions_on_a_LEFT_JOIN。
哇，从哪里开始...
--this distinct does nothing. Union is already distinct
--SELECT DISTINCT
-- ( id )
--FROM (
SELECT DISTINCT [Customer_ID] as ID
FROM [Transactions].[dbo].[Transaction_Header]
where actual_transaction_date > '20120218' )
UNION
SELECT
contact_id AS id
FROM [Customer].[dbo].[Restaurant_Attendance]
-- not sure that you are getting the date range you want. Should these be >=
-- if you want everything that occurred on the 18th or after you want >= '2012-02-18 00:00:00.000'
-- if you want everything that occurred on the 19th or after you want >= '2012-02-19 00:00:00.000'
-- the way you have it now, you will get everything on the 18th unless it happened exactly at midnight
WHERE ( created > '2012-02-18 00:00:00.000'
OR modified > '2012-02-18 00:00:00.000'
)
AND ( [Fifth_Floor_London] = 1
OR [Fourth_Floor_Leeds] = 1
OR [Second_Floor_Bristol] = 1
)
-- all of this does nothing because we already have every id in the contact table from the first query
-- UNION
-- SELECT
-- ( ct.id )
-- FROM [Customer].[dbo].[Contact] ct
-- INNER JOIN [Customer].[dbo].[Wifinity_Devices] wfd ON ct.wifinity_uniqueID = wfd.[CustomerUniqueID]
-- AND startconnection > '2012-02-17'
UNION
-- cleaned this up with isnull function and coalesce
SELECT
comdt.id AS id
FROM [Customer].[dbo].[Complete_dataset] comdt
LEFT JOIN [Customer].[dbo].[Aggregate_Spend_Counts] agsc ON comdt.id = agsc.contact_id
WHERE agsc.contact_id IS NULL
AND ( isnull(opt_out_Mail,0) <> 1
OR isnull(opt_out_email,0) <> 1
OR isnull(opt_out_SMS,0) <> 1
)
AND coalesce(address_1 , email, mobile) IS NOT NULL
UNION
SELECT
( contact_id ) AS id
FROM [Customer].[dbo].[VIP_Card_Holders]
WHERE VIP_Card_number IS NOT NULL
-- ) AS tbl