SQL字符串比较速度'喜欢'与'patindex'

Question

我有一个查询如下(简化)......

SELECT     *
FROM       table1 AS a
INNER JOIN table2 AS b ON (a.name LIKE '%' + b.name + '%')

对于我的数据集,这需要大约90秒才能执行,因此我一直在寻找加速它的方法.没有充分的理由,我以为我会尝试PATINDEX而不是LIKE ......

SELECT     *
FROM       table1 AS a
INNER JOIN table2 AS b ON (PATINDEX('%' + b.name + '%', a.name) > 0)

在相同的数据集上,它在眨眼间执行并返回相同的结果.

谁能解释为什么LIKE比PATINDEX慢得多？鉴于LIKE只是返回一个BOOLEAN,而PATINDEX正在返回实际位置,我预计后者会变慢,如果有的话,或者仅仅是两个函数编写效率的问题？

好的,这里是完整的每个查询,然后是执行计划."#StakeholderNames"只是我正在匹配的可能名称的临时表.

我已经撤回了实时数据并多次运行每个查询.第一个是花费大约17秒(比实际数据库中的原始90秒小一些),第二个小于1秒......

SELECT              sh.StakeholderID,
                    sh.HoldingID,
                    i.AgencyCommissionImportID,
                    1

    FROM            AgencyCommissionImport AS i
    INNER JOIN      #StakeholderNames AS sn ON REPLACE(REPLACE(i.ClientName,' ',''), ',','') LIKE '%' + sn.Name + '%'
    INNER JOIN      Holding AS h ON (h.ProviderName = i.Provider) AND (h.HoldingReference = i.PlanNumber)
    INNER JOIN      StakeholderHolding AS sh ON (sn.StakeholderID = sh.StakeholderID) AND (h.HoldingID = sh.HoldingID)
    WHERE           i.AgencyCommissionFileID = @AgencyCommissionFileID
                AND (i.MatchTypeID = 0)
                AND ((i.MatchedHoldingID IS NULL)
                    OR (i.MatchedStakeholderID IS NULL))

   |--Table Insert(OBJECT:([tempdb].[dbo].[#Results]), SET:([#Results].[StakeholderID] = [AttivoGroup_copy].[dbo].[StakeholderHolding].[StakeholderID] as [sh].[StakeholderID],[#Results].[HoldingID] = [AttivoGroup_copy].[dbo].[StakeholderHolding].[HoldingID] as [sh].[HoldingID],[#Results].[AgencyCommissionImportID] = [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[AgencyCommissionImportID] as [i].[AgencyCommissionImportID],[#Results].[MatchTypeID] = [Expr1014],[#Results].[indx] = [Expr1013]))
        |--Compute Scalar(DEFINE:([Expr1014]=(1)))
             |--Compute Scalar(DEFINE:([Expr1013]=getidentity((1835869607),(2),N'#Results')))
                  |--Top(ROWCOUNT est 0)
                       |--Hash Match(Inner Join, HASH:([h].[ProviderName], [h].[HoldingReference])=([i].[Provider], [i].[PlanNumber]), RESIDUAL:([AttivoGroup_copy].[dbo].[Holding].[ProviderName] as [h].[ProviderName]=[AttivoGroup_copy].[dbo].[AgencyCommissionImport].[Provider] as [i].[Provider] AND [AttivoGroup_copy].[dbo].[Holding].[HoldingReference] as [h].[HoldingReference]=[AttivoGroup_copy].[dbo].[AgencyCommissionImport].[PlanNumber] as [i].[PlanNumber] AND [Expr1015] like [Expr1016]))
                            |--Nested Loops(Inner Join, OUTER REFERENCES:([sh].[HoldingID]))
                            |    |--Nested Loops(Inner Join, OUTER REFERENCES:([sn].[StakeholderID]))
                            |    |    |--Compute Scalar(DEFINE:([Expr1016]=('%'+#StakeholderNames.[Name] as [sn].[Name])+'%', [Expr1017]=LikeRangeStart(('%'+#StakeholderNames.[Name] as [sn].[Name])+'%'), [Expr1018]=LikeRangeEnd(('%'+#StakeholderNames.[Name] as [sn].[Name])+'%'), [Expr1019]=LikeRangeInfo(('%'+#StakeholderNames.[Name] as [sn].[Name])+'%')))
                            |    |    |    |--Table Scan(OBJECT:([tempdb].[dbo].[#StakeholderNames] AS [sn]))
                            |    |    |--Clustered Index Seek(OBJECT:([AttivoGroup_copy].[dbo].[StakeholderHolding].[PK_StakeholderHolding] AS [sh]), SEEK:([sh].[StakeholderID]=#StakeholderNames.[StakeholderID] as [sn].[StakeholderID]) ORDERED FORWARD)
                            |    |--Clustered Index Seek(OBJECT:([AttivoGroup_copy].[dbo].[Holding].[PK_Holding] AS [h]), SEEK:([h].[HoldingID]=[AttivoGroup_copy].[dbo].[StakeholderHolding].[HoldingID] as [sh].[HoldingID]) ORDERED FORWARD)
                            |--Compute Scalar(DEFINE:([Expr1015]=replace(replace([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[ClientName] as [i].[ClientName],' ',''),',','')))
                                 |--Clustered Index Scan(OBJECT:([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[PK_AgencyCommissionImport] AS [i]), WHERE:([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[AgencyCommissionFileID] as [i].[AgencyCommissionFileID]=[@AgencyCommissionFileID] AND [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchTypeID] as [i].[MatchTypeID]=(0) AND ([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchedHoldingID] as [i].[MatchedHoldingID] IS NULL OR [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchedStakeholderID] as [i].[MatchedStakeholderID] IS NULL)))


SELECT              sh.StakeholderID,
                    sh.HoldingID,
                    i.AgencyCommissionImportID,
                    1

    FROM            AgencyCommissionImport AS i
    INNER JOIN      #StakeholderNames AS sn ON (PATINDEX('%' + sn.Name + '%', REPLACE(REPLACE(i.ClientName,' ',''), ',','')) > 0)
    INNER JOIN      Holding AS h ON (h.ProviderName = i.Provider) AND (h.HoldingReference = i.PlanNumber)
    INNER JOIN      StakeholderHolding AS sh ON (sn.StakeholderID = sh.StakeholderID) AND (h.HoldingID = sh.HoldingID)
    WHERE           i.AgencyCommissionFileID = @AgencyCommissionFileID
                AND (i.MatchTypeID = 0)
                AND ((i.MatchedHoldingID IS NULL)
                    OR (i.MatchedStakeholderID IS NULL))

   |--Table Insert(OBJECT:([tempdb].[dbo].[#Results]), SET:([#Results].[StakeholderID] = [AttivoGroup_copy].[dbo].[StakeholderHolding].[StakeholderID] as [sh].[StakeholderID],[#Results].[HoldingID] = [AttivoGroup_copy].[dbo].[StakeholderHolding].[HoldingID] as [sh].[HoldingID],[#Results].[AgencyCommissionImportID] = [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[AgencyCommissionImportID] as [i].[AgencyCommissionImportID],[#Results].[MatchTypeID] = [Expr1014],[#Results].[indx] = [Expr1013]))
        |--Compute Scalar(DEFINE:([Expr1014]=(1)))
             |--Compute Scalar(DEFINE:([Expr1013]=getidentity((1867869721),(2),N'#Results')))
                  |--Top(ROWCOUNT est 0)
                       |--Hash Match(Inner Join, HASH:([h].[ProviderName], [h].[HoldingReference])=([i].[Provider], [i].[PlanNumber]), RESIDUAL:([AttivoGroup_copy].[dbo].[Holding].[ProviderName] as [h].[ProviderName]=[AttivoGroup_copy].[dbo].[AgencyCommissionImport].[Provider] as [i].[Provider] AND [AttivoGroup_copy].[dbo].[Holding].[HoldingReference] as [h].[HoldingReference]=[AttivoGroup_copy].[dbo].[AgencyCommissionImport].[PlanNumber] as [i].[PlanNumber] AND patindex([Expr1015],[Expr1016])>(0)))
                            |--Nested Loops(Inner Join, OUTER REFERENCES:([sh].[HoldingID]))
                            |    |--Nested Loops(Inner Join, OUTER REFERENCES:([sn].[StakeholderID]))
                            |    |    |--Compute Scalar(DEFINE:([Expr1015]=('%'+#StakeholderNames.[Name] as [sn].[Name])+'%'))
                            |    |    |    |--Table Scan(OBJECT:([tempdb].[dbo].[#StakeholderNames] AS [sn]))
                            |    |    |--Clustered Index Seek(OBJECT:([AttivoGroup_copy].[dbo].[StakeholderHolding].[PK_StakeholderHolding] AS [sh]), SEEK:([sh].[StakeholderID]=#StakeholderNames.[StakeholderID] as [sn].[StakeholderID]) ORDERED FORWARD)
                            |    |--Clustered Index Seek(OBJECT:([AttivoGroup_copy].[dbo].[Holding].[PK_Holding] AS [h]), SEEK:([h].[HoldingID]=[AttivoGroup_copy].[dbo].[StakeholderHolding].[HoldingID] as [sh].[HoldingID]) ORDERED FORWARD)
                            |--Compute Scalar(DEFINE:([Expr1016]=replace(replace([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[ClientName] as [i].[ClientName],' ',''),',','')))
                                 |--Clustered Index Scan(OBJECT:([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[PK_AgencyCommissionImport] AS [i]), WHERE:([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[AgencyCommissionFileID] as [i].[AgencyCommissionFileID]=[@AgencyCommissionFileID] AND [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchTypeID] as [i].[MatchTypeID]=(0) AND ([AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchedHoldingID] as [i].[MatchedHoldingID] IS NULL OR [AttivoGroup_copy].[dbo].[AgencyCommissionImport].[MatchedStakeholderID] as [i].[MatchedStakeholderID] IS NULL)))

Answer 1

也许这是数据库缓存的问题......

在使用 DBCC 帮助程序运行每个查询之前尝试重置缓存：

• DBCC 删除清理缓冲区
• DBCC FREEPROCCache