如何提高SQL脚本性能

Question

The following script is very slow when its run.

I have no idea how to improve the performance of the script. Even with a view takes more than quite a lot minutes. Any idea please share to me.

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

Answer 1

Wow, where to start...

--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

Answer 2

As stated in a comment optimize one at a time. See which one takes the longest and focus on that one.

union will remove duplicates so you don't need the distinct on the individual queries

On you first I would try this:

The left join is killed by the WHERE hnci.customer_id IN so you might as well have a join.

The sub-query is not efficient as cannot use an index on the IN.
The query optimizer does not know what in ( select .. ) will return so it cannot optimize use of indexes.

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'

On that second join the query optimizer has the opportunity of which condition to apply first. Let say [Customer].[dbo].[Customer_ids].[customer_id] and [Transactions].[dbo].[Transaction_Header] each have indexes. The query optimizer has the option to apply that before [Transactions].[dbo].[Transaction_Header].[actual_transaction_date]. If [actual_transaction_date] is not indexed then for sure it would do the other ID join first.

With your in ( select ... ) the query optimizer has no option but to apply the actual_transaction_date > '20120218' first. OK some times query optimizer is smart enough to use an index inside the in outside the in but why make it hard for the query optimizer. I have found the query optimizer make better decisions if you make the decisions easier.

A join on a sub-query has the same problem. You take options away from the query optimizer. Give the query optimizer room to breathe.

Answer 3

Where exists is generally faster than in as well.

Or conditions are generally slower as well, use more union statements instead. And learn to use left joins correctly. If you have a where condition (other than where id is null) on the table on teh right side of a left join, it will convert to an inner join. If this is not what you want, then your code is currently giving you an incorrect result set.

See http://wiki.lessthandot.com/index.php/WHERE_conditions_on_a_LEFT_JOIN for an explanation of how to fix.

Answer 4

try this, temptable should help you:

    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