FileTable分隔字符串拆分

时间:2017-07-04 15:12:12

标签: sql-server tsql user-defined-functions filetable

  

编辑 - 要明确我将把目标句放在最顶层。考试   我的问题是,是否有办法获得相同的表现   作为不使用临时表的临时表。

我觉得这应该是一个简单的问题,但我被困住了。我正在SQL2014中尝试使用FileTables。我知道一些可行的方法,但目标是建立从文件表中提取文本子串的可行性。

此测试包含35,000个文本文件,其中一行文本如下,每个文件平均有100个字节的非unicode文本。

Aaa|Bbb|Ccc|Ddd|Eee|Fff|Ggg

每个文件的所需输出为一行,分隔为七列的分隔字符串。

我找到了一个快速的字符串解析器函数,但与varchar列相比,在文件流上运行会产生显着的性能影响。

此查询需要18秒才能运行。我试图从filestream转换到varchar只执行一次,但我认为调用UDF可能导致它发生在每一行(文件)。

Create View vAddresses As
Select file_type, Convert(Varchar(8000),file_stream) TextData /* Into #Temp */ From InputFiles Where file_type = 'adr'
Go
Select  --TextData,
        dbo.udf_StringSplit(TextData, 1, '|'), dbo.udf_StringSplit(TextData, 2, '|'), dbo.udf_StringSplit(TextData, 3, '|'),
        dbo.udf_StringSplit(TextData, 4, '|'), dbo.udf_StringSplit(TextData, 5, '|'), dbo.udf_StringSplit(TextData, 6, '|'),
        dbo.udf_StringSplit(TextData, 7, '|')--, TextData
    From vAddresses

我已经尝试过它作为一个视图,一个cte和一个子查询。唯一似乎有帮助的是创建临时表。创建临时表需要1秒钟,查询需要一秒钟。因此对于35k行2秒总查询时间与18秒。

Drop Table #Temp
(Select file_type, Convert(Varchar(8000),file_stream) TextData Into #Temp From HumanaInputFiles Where file_type = 'adr')
Select  --TextData,
        dbo.udf_StringSplit(TextData, 1, '|'), dbo.udf_StringSplit(TextData, 2, '|'), dbo.udf_StringSplit(TextData, 3, '|'),
        dbo.udf_StringSplit(TextData, 4, '|'), dbo.udf_StringSplit(TextData, 5, '|'), dbo.udf_StringSplit(TextData, 6, '|'),
        dbo.udf_StringSplit(TextData, 7, '|')--, TextData
    From #Temp

我已经阅读了很多关于文件表和临时表与单一查询性能主题的帖子和博客,但我似乎无法弄明白。它可能与sargable或统计数据有关?任何建议都非常感谢。

这是UDF,我在MSDN博客/论坛上发现它,是迄今为止我发现的最佳表现者。

ALTER FUNCTION [dbo].[udf_StringSplit](
 @TEXT      varchar(8000)
,@COLUMN    tinyint
,@SEPARATOR char(1)
)RETURNS varchar(8000)
AS
  BEGIN
       DECLARE @POS_START  int = 1
       DECLARE @POS_END    int = CHARINDEX(@SEPARATOR, @TEXT, @POS_START)

       WHILE (@COLUMN >1 AND @POS_END> 0)
         BEGIN
             SET @POS_START = @POS_END + 1
             SET @POS_END = CHARINDEX(@SEPARATOR, @TEXT, @POS_START)
             SET @COLUMN = @COLUMN - 1
         END 

       IF @COLUMN > 1  SET @POS_START = LEN(@TEXT) + 1
       IF @POS_END = 0 SET @POS_END = LEN(@TEXT) + 1 

       RETURN SUBSTRING (@TEXT, @POS_START, @POS_END - @POS_START)
  END

这是临时表的执行计划。

<?xml version="1.0" encoding="utf-16"?>
<ShowPlanXML xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" Version="1.2" Build="12.0.4100.1" xmlns="http://schemas.microsoft.com/sqlserver/2004/07/showplan">
  <BatchSequence>
    <Batch>
      <Statements>
        <StmtSimple StatementCompId="1" StatementEstRows="17486" StatementId="1" StatementOptmLevel="TRIVIAL" CardinalityEstimationModelVersion="120" StatementSubTreeCost="0.166487" StatementText="Select --TextData,&#xD;&#xA;       dbo.udf_StringSplit(TextData, 1, '|'), dbo.udf_StringSplit(TextData, 2, '|'), dbo.udf_StringSplit(TextData, 3, '|'),&#xD;&#xA;      dbo.udf_StringSplit(TextData, 4, '|'), dbo.udf_StringSplit(TextData, 5, '|'), dbo.udf_StringSplit(TextData, 6, '|'),&#xD;&#xA;      dbo.udf_StringSplit(TextData, 7, '|')--, TextData&#xD;&#xA; From #Temp" StatementType="SELECT" QueryHash="0xC4D6F0215D332F3D" QueryPlanHash="0xC50CFAF9494B5DBE" RetrievedFromCache="true">
          <StatementSetOptions ANSI_NULLS="true" ANSI_PADDING="true" ANSI_WARNINGS="true" ARITHABORT="true" CONCAT_NULL_YIELDS_NULL="true" NUMERIC_ROUNDABORT="false" QUOTED_IDENTIFIER="true" />
          <QueryPlan DegreeOfParallelism="0" NonParallelPlanReason="CouldNotGenerateValidParallelPlan" CachedPlanSize="24" CompileTime="1" CompileCPU="1" CompileMemory="168">
            <MemoryGrantInfo SerialRequiredMemory="0" SerialDesiredMemory="0" />
            <OptimizerHardwareDependentProperties EstimatedAvailableMemoryGrant="838735" EstimatedPagesCached="419367" EstimatedAvailableDegreeOfParallelism="4" />
            <RelOp AvgRowSize="28023" EstimateCPU="0.0017486" EstimateIO="0" EstimateRebinds="0" EstimateRewinds="0" EstimatedExecutionMode="Row" EstimateRows="17486" LogicalOp="Compute Scalar" NodeId="0" Parallel="false" PhysicalOp="Compute Scalar" EstimatedTotalSubtreeCost="0.166487">
              <OutputList>
                <ColumnReference Column="Expr1003" />
                <ColumnReference Column="Expr1004" />
                <ColumnReference Column="Expr1005" />
                <ColumnReference Column="Expr1006" />
                <ColumnReference Column="Expr1007" />
                <ColumnReference Column="Expr1008" />
                <ColumnReference Column="Expr1009" />
              </OutputList>
              <RunTimeInformation>
                <RunTimeCountersPerThread Thread="0" ActualRows="17486" ActualEndOfScans="1" ActualExecutions="1" />
              </RunTimeInformation>
              <ComputeScalar>
                <DefinedValues>
                  <DefinedValue>
                    <ColumnReference Column="Expr1003" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(1),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(1)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1004" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(2),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(2)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1005" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(3),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(3)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1006" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(4),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(4)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1007" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(5),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(5)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1008" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(6),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(6)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1009" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([tempdb].[dbo].[#Temp].[TextData],(7),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(7)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                </DefinedValues>
                <RelOp AvgRowSize="4011" EstimateCPU="0.0193131" EstimateIO="0.145426" EstimateRebinds="0" EstimateRewinds="0" EstimatedExecutionMode="Row" EstimateRows="17486" LogicalOp="Table Scan" NodeId="1" Parallel="false" PhysicalOp="Table Scan" EstimatedTotalSubtreeCost="0.164739" TableCardinality="17486">
                  <OutputList>
                    <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                  </OutputList>
                  <RunTimeInformation>
                    <RunTimeCountersPerThread Thread="0" ActualRows="17486" ActualEndOfScans="1" ActualExecutions="1" />
                  </RunTimeInformation>
                  <TableScan Ordered="false" ForcedIndex="false" ForceScan="false" NoExpandHint="false" Storage="RowStore">
                    <DefinedValues>
                      <DefinedValue>
                        <ColumnReference Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" Column="TextData" />
                      </DefinedValue>
                    </DefinedValues>
                    <Object Database="[tempdb]" Schema="[dbo]" Table="[#Temp]" IndexKind="Heap" Storage="RowStore" />
                  </TableScan>
                </RelOp>
              </ComputeScalar>
            </RelOp>
          </QueryPlan>
        </StmtSimple>
      </Statements>
    </Batch>
  </BatchSequence>
</ShowPlanXML>

这是视图的计划。

<?xml version="1.0" encoding="utf-16"?>
<ShowPlanXML xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" Version="1.2" Build="12.0.4100.1" xmlns="http://schemas.microsoft.com/sqlserver/2004/07/showplan">
  <BatchSequence>
    <Batch>
      <Statements>
        <StmtSimple StatementCompId="1" StatementEstRows="17486" StatementId="1" StatementOptmLevel="FULL" StatementOptmEarlyAbortReason="GoodEnoughPlanFound" CardinalityEstimationModelVersion="120" StatementSubTreeCost="0.905265" StatementText="Select    --TextData,&#xD;&#xA;       dbo.udf_StringSplit(TextData, 1, '|'), dbo.udf_StringSplit(TextData, 2, '|'), dbo.udf_StringSplit(TextData, 3, '|'),&#xD;&#xA;      dbo.udf_StringSplit(TextData, 4, '|'), dbo.udf_StringSplit(TextData, 5, '|'), dbo.udf_StringSplit(TextData, 6, '|'),&#xD;&#xA;      dbo.udf_StringSplit(TextData, 7, '|')--, TextData&#xD;&#xA; From vAddresses" StatementType="SELECT" QueryHash="0xB4F8A0B288802C4E" QueryPlanHash="0x28DA02D774B1AF53" RetrievedFromCache="true">
          <StatementSetOptions ANSI_NULLS="true" ANSI_PADDING="true" ANSI_WARNINGS="true" ARITHABORT="true" CONCAT_NULL_YIELDS_NULL="true" NUMERIC_ROUNDABORT="false" QUOTED_IDENTIFIER="true" />
          <QueryPlan DegreeOfParallelism="0" NonParallelPlanReason="CouldNotGenerateValidParallelPlan" CachedPlanSize="32" CompileTime="3" CompileCPU="3" CompileMemory="520">
            <Warnings>
              <PlanAffectingConvert ConvertIssue="Cardinality Estimate" Expression="CONVERT(varchar(8000),[DmProd01].[dbo].[HumanaInputFiles].[file_stream],0)" />
            </Warnings>
            <MemoryGrantInfo SerialRequiredMemory="0" SerialDesiredMemory="0" />
            <OptimizerHardwareDependentProperties EstimatedAvailableMemoryGrant="838735" EstimatedPagesCached="419367" EstimatedAvailableDegreeOfParallelism="4" />
            <RelOp AvgRowSize="28023" EstimateCPU="0.0017486" EstimateIO="0" EstimateRebinds="0" EstimateRewinds="0" EstimatedExecutionMode="Row" EstimateRows="17486" LogicalOp="Compute Scalar" NodeId="0" Parallel="false" PhysicalOp="Compute Scalar" EstimatedTotalSubtreeCost="0.905265">
              <OutputList>
                <ColumnReference Column="Expr1004" />
                <ColumnReference Column="Expr1005" />
                <ColumnReference Column="Expr1006" />
                <ColumnReference Column="Expr1007" />
                <ColumnReference Column="Expr1008" />
                <ColumnReference Column="Expr1009" />
                <ColumnReference Column="Expr1010" />
              </OutputList>
              <RunTimeInformation>
                <RunTimeCountersPerThread Thread="0" ActualRows="17486" ActualEndOfScans="1" ActualExecutions="1" />
              </RunTimeInformation>
              <ComputeScalar>
                <DefinedValues>
                  <DefinedValue>
                    <ColumnReference Column="Expr1004" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(1),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(1)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1005" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(2),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(2)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1006" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(3),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(3)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1007" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(4),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(4)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1008" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(5),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(5)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1009" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(6),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(6)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                  <DefinedValue>
                    <ColumnReference Column="Expr1010" />
                    <ScalarOperator ScalarString="[DmProd01].[dbo].[udf_StringSplit]([Expr1011],(7),'|')">
                      <UserDefinedFunction FunctionName="[DmProd01].[dbo].[udf_StringSplit]">
                        <ScalarOperator>
                          <Identifier>
                            <ColumnReference Column="Expr1011" />
                          </Identifier>
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="(7)" />
                        </ScalarOperator>
                        <ScalarOperator>
                          <Const ConstValue="'|'" />
                        </ScalarOperator>
                      </UserDefinedFunction>
                    </ScalarOperator>
                  </DefinedValue>
                </DefinedValues>
                <RelOp AvgRowSize="4019" EstimateCPU="0.0034972" EstimateIO="0" EstimateRebinds="0" EstimateRewinds="0" EstimatedExecutionMode="Row" EstimateRows="17486" LogicalOp="Compute Scalar" NodeId="1" Parallel="false" PhysicalOp="Compute Scalar" EstimatedTotalSubtreeCost="0.88673">
                  <OutputList>
                    <ColumnReference Column="Expr1011" />
                  </OutputList>
                  <ComputeScalar>
                    <DefinedValues>
                      <DefinedValue>
                        <ColumnReference Column="Expr1011" />
                        <ScalarOperator ScalarString="CONVERT(varchar(8000),[DmProd01].[dbo].[HumanaInputFiles].[file_stream],0)">
                          <Convert DataType="varchar" Length="8000" Style="0" Implicit="false">
                            <ScalarOperator>
                              <Identifier>
                                <ColumnReference Database="[DmProd01]" Schema="[dbo]" Table="[HumanaInputFiles]" Column="file_stream" />
                              </Identifier>
                            </ScalarOperator>
                          </Convert>
                        </ScalarOperator>
                      </DefinedValue>
                    </DefinedValues>
                    <RelOp AvgRowSize="4043" EstimateCPU="0.0386262" EstimateIO="0.844606" EstimateRebinds="0" EstimateRewinds="0" EstimatedExecutionMode="Row" EstimateRows="17486" LogicalOp="Table Scan" NodeId="2" Parallel="false" PhysicalOp="Table Scan" EstimatedTotalSubtreeCost="0.883233" TableCardinality="34972">
                      <OutputList>
                        <ColumnReference Database="[DmProd01]" Schema="[dbo]" Table="[HumanaInputFiles]" Column="file_stream" />
                      </OutputList>
                      <RunTimeInformation>
                        <RunTimeCountersPerThread Thread="0" ActualRows="17486" ActualEndOfScans="1" ActualExecutions="1" />
                      </RunTimeInformation>
                      <TableScan Ordered="false" ForcedIndex="false" ForceScan="false" NoExpandHint="false" Storage="RowStore">
                        <DefinedValues>
                          <DefinedValue>
                            <ColumnReference Database="[DmProd01]" Schema="[dbo]" Table="[HumanaInputFiles]" Column="file_stream" />
                          </DefinedValue>
                        </DefinedValues>
                        <Object Database="[DmProd01]" Schema="[dbo]" Table="[HumanaInputFiles]" IndexKind="Heap" Storage="RowStore" />
                        <Predicate>
                          <ScalarOperator ScalarString="[DmProd01].[dbo].[HumanaInputFiles].[file_type]=N'adr'">
                            <Compare CompareOp="EQ">
                              <ScalarOperator>
                                <Identifier>
                                  <ColumnReference Database="[DmProd01]" Schema="[dbo]" Table="[HumanaInputFiles]" Column="file_type" ComputedColumn="true" />
                                </Identifier>
                              </ScalarOperator>
                              <ScalarOperator>
                                <Const ConstValue="N'adr'" />
                              </ScalarOperator>
                            </Compare>
                          </ScalarOperator>
                        </Predicate>
                      </TableScan>
                    </RelOp>
                  </ComputeScalar>
                </RelOp>
              </ComputeScalar>
            </RelOp>
          </QueryPlan>
        </StmtSimple>
      </Statements>
    </Batch>
  </BatchSequence>
</ShowPlanXML>

编辑:对此进行了不同的搜索,发现答案是使用top和order by。这让它降到了4秒。看起来有点笨拙,但仍然没有解释如何查看查询计划有助于解决这个问题,所以不要自己回答这个问题,而是将其打开。

5 个答案:

答案 0 :(得分:6)

MSDN中有一些建议不要在你的情况下使用FileTable:

  

FileTable功能构建于SQL Server FILESTREAM之上   技术

对于小对象,FileStream的性能不佳。 Filestream设计用于处理大约1MB或更多的文件,但您只有100个字节(https://docs.microsoft.com/en-us/sql/relational-databases/blob/filestream-sql-server):

  

何时使用FILESTREAM在SQL Server中,BLOB可以是标准的   varbinary(max)数据,用于将数据存储在表或FILESTREAM中   varbinary(max)对象,用于将数据存储在文件系统中。的的   数据的大小和使用决定了您是否应该使用数据库   存储或文件系统存储。如果满足以下条件,   你应该考虑使用FILESTREAM:

     
      
  • 平均存储的对象大于1 MB
  •   
  • 快速读取访问非常重要。
  •   
  • 您正在开发使用中间层进行应用程序逻辑的应用程序。
  •   
     

对于较小的对象,将varbinary(max)BLOB存储在   数据库通常提供更好的流媒体性能。

您可以模拟持久列 - 创建另一个表并使用触发器填充它。在这种情况下,您可以从两种情况中获得奖金

P.S。您可以使用内联TVF + union all来实现@TT的评论

答案 1 :(得分:3)

  

编辑 - 更快的方法

与其调用你的Parse / Split功能7次,也许这个TVF可能更有效率。以下内容将在 0.773秒中处理 35,000个唯一记录

示例

-- Create Some Sample/UNIQUE Data
Select N,TextData =concat(N,TextData )
Into #Temp
From  (values ('Aaa|Bbb|Ccc|Ddd|Eee|Fff|Ggg') ) A (TextData )
Cross Apply (Select Top 35000 N=Row_Number() Over (Order By (Select NULL)) From master..spt_values n1,master..spt_values n2) B

Select B.*
 From  #Temp A
 Cross Apply (
                Select Pos1=max(case when RetSeq=1 then RetVal end)
                      ,Pos2=max(case when RetSeq=2 then RetVal end)
                      ,Pos3=max(case when RetSeq=3 then RetVal end)
                      ,Pos4=max(case when RetSeq=4 then RetVal end)
                      ,Pos5=max(case when RetSeq=5 then RetVal end)
                      ,Pos6=max(case when RetSeq=6 then RetVal end)
                      ,Pos7=max(case when RetSeq=7 then RetVal end)
                 From [dbo].[udf-Str-Parse-8K](A.TextData,'|') B1
             ) B

感兴趣的UDF

CREATE FUNCTION [dbo].[udf-Str-Parse-8K] (@String varchar(max),@Delimiter varchar(25))
Returns Table 
As
Return (  
    with   cte1(N)   As (Select 1 From (Values(1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) N(N)),
           cte2(N)   As (Select Top (IsNull(DataLength(@String),0)) Row_Number() over (Order By (Select NULL)) From (Select N=1 From cte1 a,cte1 b,cte1 c,cte1 d) A ),
           cte3(N)   As (Select 1 Union All Select t.N+DataLength(@Delimiter) From cte2 t Where Substring(@String,t.N,DataLength(@Delimiter)) = @Delimiter),
           cte4(N,L) As (Select S.N,IsNull(NullIf(CharIndex(@Delimiter,@String,s.N),0)-S.N,8000) From cte3 S)

    Select RetSeq = Row_Number() over (Order By A.N)
          ,RetVal = LTrim(RTrim(Substring(@String, A.N, A.L)))
    From   cte4 A
);
--Orginal Source http://www.sqlservercentral.com/articles/Tally+Table/72993/
  

只是为了帮助可视化

作为独立的TVF包括可以应用于条件聚合的项目序列。

Select * from [dbo].[udf-Str-Parse-8K]('Aaa|Bbb|Ccc|Ddd|Eee|Fff|Ggg','|')

返回

RetSeq  RetVal
1       Aaa
2       Bbb
3       Ccc
4       Ddd
5       Eee
6       Fff
7       Ggg

答案 2 :(得分:0)

[1]我已经多次使用过解决方案(1.1)它将源字符串转换为XML然后(1.2)它每次都使用value方法从XMl中提取:

USE tempdb
GO
IF OBJECT_ID('dbo.SourceTable') IS NOT NULL
    DROP TABLE dbo.SourceTable
GO
CREATE TABLE dbo.SourceTable (
    ID      INT IDENTITY PRIMARY KEY,
    Col1    VARCHAR(100) NOT NULL
);
INSERT  dbo.SourceTable (Col1) VALUES ('Aaa|Bbb|Ccc|Ddd|Eee|Fff|Ggg')
INSERT  dbo.SourceTable (Col1) VALUES ('hhh|iii|JJJ|kkk')

SELECT  b.ID, c.XmlCol.value('.', 'VARCHAR(100)') AS ItemVal--, ROW_NUMBER() OVER(PARTITION BY b.ID ORDER BY c.XmlCol) AS RowNum
FROM (
    SELECT  a.ID, CONVERT(XML, '<root><i>' + REPLACE(a.Col1, '|', '</i><i>') + '</i></root>') AS Col1AsXML
    FROM    dbo.SourceTable a
) b OUTER APPLY b.Col1AsXML.nodes('root/i') c(XmlCol)
--OPTION(FORCE ORDER)

[2]如果你提供DDL&amp; DML声明。

[3]如果您能提供以下详细信息,可能会有所帮助

  1. 每个字符串都有最大数量的项目?
  2. 如果所有项目的长度相同(例如3个字符)?

答案 3 :(得分:0)

我已经玩过这一点,并且禁止编写CLR程序集(速度非常快)的最快解决方案似乎是以下某种类型的变体:

CREATE FUNCTION [UDF_Split] (
    @InputStr NVARCHAR(Max),
    @Delimiter NVARCHAR(255)
)
RETURNS TABLE
AS RETURN(

   WITH lv0 AS (SELECT 0 g UNION ALL SELECT 0)
    ,lv1 AS (SELECT 0 g FROM lv0 a CROSS JOIN lv0 b) -- 4
    ,lv2 AS (SELECT 0 g FROM lv1 a CROSS JOIN lv1 b) -- 16
    ,lv3 AS (SELECT 0 g FROM lv2 a CROSS JOIN lv2 b) -- 256
    ,lv4 AS (SELECT 0 g FROM lv3 a CROSS JOIN lv3 b) -- 65,536
    ,lv5 AS (SELECT 0 g FROM lv4 a CROSS JOIN lv4 b) -- 4,294,967,296
    ,Tally (n) AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM lv5)

 SELECT SUBSTRING(@InputStr, N, CHARINDEX(@Delimiter, @InputStr + @Delimiter, N) - N) AS TextLine
 FROM   Tally
 WHERE  N BETWEEN 1 AND LEN(@InputStr) + LEN(@InputStr)
        AND SUBSTRING(@Delimiter + @InputStr, N, LEN(@Delimiter)) = @Delimiter);

从MS SQL 2016开始,我们获得了自己的分割功能: Sql Server 2016 STRING_SPLIT ( string , separator )

答案 4 :(得分:0)

由于您要分割出固定/预定数量的列,因此您根本不需要使用字符串拆分功能。

以下能够在相当贫血的服务器上在~2秒内咀嚼100K行。

注意......此解决方案正在合并Adam Machanic's MakeParallel function以强制执行并行执行计划。

IF OBJECT_ID('tempdb..#TestData', 'U') IS NOT NULL 
DROP TABLE #TestData;

WITH 
    cte_n1 (n) AS (SELECT 1 FROM (VALUES (1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) n (n)), 
    cte_n2 (n) AS (SELECT 1 FROM cte_n1 a CROSS JOIN cte_n1 b),
    cte_n3 (n) AS (SELECT 1 FROM cte_n2 a CROSS JOIN cte_n2 b),
    cte_Tally (n) AS (
        SELECT TOP 100000
            ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
        FROM
            cte_n3 a CROSS JOIN cte_n3 b
        )
SELECT 
    ID = ISNULL(CAST(t.n AS INT), 0),
    FilePath = CAST(fp.FilePath AS VARCHAR(1000))
    INTO #TestData
FROM
    cte_Tally t
    CROSS APPLY ( VALUES (CONCAT(
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000, '|',
                                ABS(CHECKSUM(NEWID())) % 9999 + 1000
                                )
                            ) ) fp (FilePath);

ALTER TABLE #TestData ADD PRIMARY KEY CLUSTERED (ID);

--=============================================================================
DECLARE     -- Dump values into variables to eliminate display rendering from execution time.
    @id INT,
    @Col_1 VARCHAR(5),
    @Col_2 VARCHAR(5),
    @Col_3 VARCHAR(5),
    @Col_4 VARCHAR(5),
    @Col_5 VARCHAR(5),
    @Col_6 VARCHAR(5),
    @Col_7 VARCHAR(5);

SELECT 
    @ID = td.ID,
    @Col_1 = SUBSTRING(td.FilePath, 1, ABS(d1.DelimLocation - 1)),
    @Col_2 = SUBSTRING(td.FilePath, d1.DelimLocation + 1, ABS(d2.DelimLocation - d1.DelimLocation - 1)),
    @Col_3 = SUBSTRING(td.FilePath, d2.DelimLocation + 1, ABS(d3.DelimLocation - d2.DelimLocation - 1)),
    @Col_4 = SUBSTRING(td.FilePath, d3.DelimLocation + 1, ABS(d4.DelimLocation - d3.DelimLocation - 1)),
    @Col_5 = SUBSTRING(td.FilePath, d4.DelimLocation + 1, ABS(d5.DelimLocation - d4.DelimLocation - 1)),
    @Col_6 = SUBSTRING(td.FilePath, d5.DelimLocation + 1, ABS(d6.DelimLocation - d5.DelimLocation - 1)),
    @Col_7 = SUBSTRING(td.FilePath, d6.DelimLocation + 1, 1000)
FROM
    #TestData td
    CROSS APPLY ( VALUES (LEN(td.FilePath) - LEN(REPLACE(td.FilePath, '|', ''))) ) dc (DelimiterCount)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 1, 1000,  CHARINDEX('|', td.FilePath, 1))) ) d1 (DelimLocation)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 2, 1000,  CHARINDEX('|', td.FilePath, d1.DelimLocation + 1))) ) d2 (DelimLocation)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 3, 1000,  CHARINDEX('|', td.FilePath, d2.DelimLocation + 1))) ) d3 (DelimLocation)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 4, 1000,  CHARINDEX('|', td.FilePath, d3.DelimLocation + 1))) ) d4 (DelimLocation)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 5, 1000,  CHARINDEX('|', td.FilePath, d4.DelimLocation + 1))) ) d5 (DelimLocation)
    CROSS APPLY ( VALUES (IIF(dc.DelimiterCount < 6, 1000,  CHARINDEX('|', td.FilePath, d5.DelimLocation + 1))) ) d6 (DelimLocation)
    CROSS APPLY dbo.MakeParallel() mp;  -- Forces a parallel execution plan.
                                        -- http://dataeducation.com/next-level-parallel-plan-forcing-an-alternative-to-8649/

当然,MakeParallel函数也可以与Splitter函数结合使用。在这种情况下,请使用Jeff Moden's DelimitedSplit8K function

--=============================================================================
DECLARE     -- Dump values into variables to eliminate display rendering from execution time.
    @id INT,
    @Col_1 VARCHAR(5),
    @Col_2 VARCHAR(5),
    @Col_3 VARCHAR(5),
    @Col_4 VARCHAR(5),
    @Col_5 VARCHAR(5),
    @Col_6 VARCHAR(5),
    @Col_7 VARCHAR(5);

SELECT 
    @ID = td.ID,
    @Col_1 = MAX(CASE WHEN sc.ItemNumber = 1 THEN sc.Item END),
    @Col_2 = MAX(CASE WHEN sc.ItemNumber = 2 THEN sc.Item END),
    @Col_3 = MAX(CASE WHEN sc.ItemNumber = 3 THEN sc.Item END),
    @Col_4 = MAX(CASE WHEN sc.ItemNumber = 4 THEN sc.Item END),
    @Col_5 = MAX(CASE WHEN sc.ItemNumber = 5 THEN sc.Item END),
    @Col_6 = MAX(CASE WHEN sc.ItemNumber = 6 THEN sc.Item END),
    @Col_7 = MAX(CASE WHEN sc.ItemNumber = 7 THEN sc.Item END)
FROM
    #TestData td
    CROSS APPLY dbo.DelimitedSplit8K(td.FilePath, '|') sc
    CROSS APPLY dbo.MakeParallel() mp       -- Forces a parallel execution plan.
                                            -- http://dataeducation.com/next-level-parallel-plan-forcing-an-alternative-to-8649/
GROUP BY
    td.ID;

HTH, 杰森