在某些情况下,为什么CTE(公用表表达式)与SQL Server中的临时表相比会减慢查询速度
Posted
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了在某些情况下,为什么CTE(公用表表达式)与SQL Server中的临时表相比会减慢查询速度相关的知识,希望对你有一定的参考价值。
我有几种情况,我的复杂CTE
(Common Table Expressions
)比使用SQL Server
中的临时表的相同查询慢十倍。
我的问题是关于SQL Server
如何处理CTE
查询,看起来它试图加入所有分离的查询而不是存储每个查询的结果,然后尝试运行以下查询。因此,这可能是使用临时表时速度更快的原因。
例如:
查询1:使用Common Table Expression
:
;WITH Orders AS
(
SELECT
ma.MasterAccountId,
IIF(r.FinalisedDate IS NULL, 1, 0)) [Status]
FROM
MasterAccount ma
INNER JOIN
task.tblAccounts a ON a.AccountNumber = ma.TaskAccountId
AND a.IsActive = 1
LEFT OUTER JOIN
task.tblRequisitions r ON r.AccountNumber = a.AccountNumber
WHERE
ma.IsActive = 1
AND CAST(r.BatchDateTime AS DATE) BETWEEN @fromDate AND @toDate
AND r.BatchNumber > 0
),
StockAvailability AS
(
SELECT sa.AccountNumber,
sa.RequisitionNumber,
sa.RequisitionDate,
sa.Lines,
sa.HasStock,
sa.NoStock,
CASE WHEN sa.Lines = 0 THEN 'Empty'
WHEN sa.HasStock = 0 THEN 'None'
WHEN (sa.Lines > 0 AND sa.Lines > sa.HasStock) THEN 'Partial'
WHEN (sa.Lines > 0 AND sa.Lines <= sa.HasStock) THEN 'Full'
END AS [Status]
FROM
(
SELECT
r.AccountNumber,
r.RequisitionNumber,
r.RequisitionDate,
COUNT(rl.ProductNumber) Lines,
SUM(IIF(ISNULL(psoh.AvailableStock, 0) >= ISNULL(rl.Quantity, 0), 1, 0)) AS HasStock,
SUM(IIF(ISNULL(psoh.AvailableStock, 0) < ISNULL(rl.Quantity, 0), 1, 0)) AS NoStock
FROM task.tblrequisitions r
INNER JOIN task.tblRequisitionLines rl ON rl.RequisitionNumber = r.RequisitionNumber
LEFT JOIN ProductStockOnHandSummary psoh ON psoh.ProductNumber = rl.ProductNumber
WHERE dbo.fn_RemoveUnitPrefix(r.BatchNumber) = 0
AND r.UnitId = 1
AND r.FinalisedDate IS NULL
AND r.RequisitionStatus = 1
AND r.TransactionTypeNumber = 301
GROUP BY r.AccountNumber, r.RequisitionNumber, r.RequisitionDate
) AS sa
),
Available AS
(
SELECT ma.MasterAccountId,
SUM(IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END)) AS AvailableStock,
SUM(IIF(sa.[Status] IN ('Full', 'Partial', 'None'), 1, 0)) AS OrdersAnyStock,
SUM(IIF(sa.RequisitionDate < dbo.TicksToTime(ma.DailyOrderCutOffTime, @toDate),
IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END), 0)) AS AvailableBeforeCutOff
FROM MasterAccount ma
INNER JOIN StockAvailability sa ON sa.AccountNumber = ma.TaskAccountId
GROUP BY ma.MasterAccountId, ma.IsPartialStock
),
Totals AS
(
SELECT
o.MasterAccountId,
COUNT(o.MasterAccountId) AS BatchedOrders
FROM Orders o
GROUP BY o.MasterAccountId
)
SELECT a.MasterAccountId,
ISNULL(t.BatchedOrders, 0) BatchedOrders,
ISNULL(t.PendingOrders, 0) PendingOrders,
ISNULL(av.AvailableStock, 0) AvailableOrders,
ISNULL(av.AvailableBeforeCutOff, 0) AvailableCutOff,
ISNULL(av.OrdersAnyStock, 0) AllOrders
FROM MasterAccount a
LEFT OUTER JOIN Available av ON av.MasterAccountId = a.MasterAccountId
LEFT OUTER JOIN Totals t ON t.MasterAccountId = a.MasterAccountId
WHERE a.IsActive = 1
查询2:使用临时表:
DROP TABLE IF EXISTS #Orders
CREATE TABLE #Orders (MasterAccountId int, [Status] int);
INSERT INTO #Orders
SELECT
ma.MasterAccountId,
dbo.fn_GetBatchPickingStatus(ma.BatchPickingOnHold,
iif(r.GroupNumber > 0, 1, 0),
iif(r.FinalisedDate is null, 1, 0)) [Status]
FROM MasterAccount ma (nolock)
INNER JOIN wh3.dbo.tblAccounts a (nolock) on a.AccountNumber = dbo.fn_RemoveUnitPrefix(ma.TaskAccountId) and a.IsActive = 1
LEFT OUTER JOIN wh3.dbo.tblRequisitions r (nolock) on r.AccountNumber = a.AccountNumber
WHERE cast(r.BatchDateTime as date) between @fromDate and @toDate
AND r.BatchNumber > 0
AND ma.IsActive = 1
DROP TABLE IF EXISTS #StockAvailability
Create Table #StockAvailability (AccountNumber int, RequisitionNumber int, RequisitionDate datetime, Lines int, HasStock int, NoStock int);
Insert Into #StockAvailability
SELECT
r.AccountNumber,
r.RequisitionNumber,
r.RequisitionDate,
COUNT(rl.ProductNumber) Lines,
SUM(IIF(ISNULL(psoh.AvailableStock, 0) >= ISNULL(rl.Quantity, 0), 1, 0)) AS HasStock,
SUM(IIF(ISNULL(psoh.AvailableStock, 0) < ISNULL(rl.Quantity, 0), 1, 0)) AS NoStock
FROM WH3.dbo.tblrequisitions r (nolock)
INNER JOIN WH3.dbo.tblRequisitionLines rl (nolock) ON rl.RequisitionNumber = r.RequisitionNumber
LEFT JOIN ProductStockOnHandSummary psoh (nolock) ON psoh.ProductNumber = rl.ProductNumber -- Joined with View
WHERE r.BatchNumber = 0
AND r.FinalisedDate is null
AND r.RequisitionStatus = 1
AND r.TransactionTypeNumber = 301
GROUP BY r.AccountNumber, r.RequisitionNumber, r.RequisitionDate
DROP TABLE IF EXISTS #StockAvailability2
Create Table #StockAvailability2 (AccountNumber int, RequisitionNumber int, RequisitionDate datetime, Lines int, HasStock int, NoStock int, [Status] nvarchar(7));
Insert Into #StockAvailability2
SELECT sa.AccountNumber,
sa.RequisitionNumber,
sa.RequisitionDate,
sa.Lines,
sa.HasStock,
sa.NoStock,
CASE WHEN sa.Lines = 0 THEN 'Empty'
WHEN sa.HasStock = 0 THEN 'None'
WHEN (sa.Lines > 0 AND sa.Lines > sa.HasStock) THEN 'Partial'
WHEN (sa.Lines > 0 AND sa.Lines <= sa.HasStock) THEN 'Full'
END AS [Status]
FROM #StockAvailability sa
DROP TABLE IF EXISTS #Available
Create Table #Available (MasterAccountId int, AvailableStock int, OrdersAnyStock int, AvailableBeforeCutOff int);
INSERT INTO #Available
SELECT ma.MasterAccountId,
SUM(IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END)) AS AvailableStock,
SUM(IIF(sa.[Status] IN ('Full', 'Partial', 'None'), 1, 0)) AS OrdersAnyStock,
SUM(IIF(sa.RequisitionDate < dbo.TicksToTime(ma.DailyOrderCutOffTime, @toDate),
IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END), 0)) AS AvailableBeforeCutOff
FROM MasterAccount ma (NOLOCK)
INNER JOIN #StockAvailability2 sa ON sa.AccountNumber = dbo.fn_RemoveUnitPrefix(ma.TaskAccountId)
GROUP BY ma.MasterAccountId, ma.IsPartialStock
;WITH Totals AS
(
SELECT
o.MasterAccountId,
COUNT(o.MasterAccountId) AS BatchedOrders,
SUM(IIF(o.[Status] IN (0,1,2), 1, 0)) PendingOrders
FROM #Orders o (NOLOCK)
GROUP BY o.MasterAccountId
)
SELECT a.MasterAccountId,
ISNULL(t.BatchedOrders, 0) BatchedOrders,
ISNULL(t.PendingOrders, 0) PendingOrders,
ISNULL(av.AvailableStock, 0) AvailableOrders,
ISNULL(av.AvailableBeforeCutOff, 0) AvailableCutOff,
ISNULL(av.OrdersAnyStock, 0) AllOrders
FROM MasterAccount a (NOLOCK)
LEFT OUTER JOIN #Available av (NOLOCK) ON av.MasterAccountId = a.MasterAccountId
LEFT OUTER JOIN Totals t (NOLOCK) ON t.MasterAccountId = a.MasterAccountId
WHERE a.IsActive = 1
答案很简单。
SQL Server不实现CTE。正如您可以从执行计划中看到的那样,它会内联它们。
其他DBMS可能会以不同的方式实现它,一个众所周知的例子是Postgres,它确实实现了CTE(它实际上为引擎盖后面的CTE创建了临时表)。
中间结构的显式实现是否更快,取决于查询。
在复杂查询中,写入和读取中间数据到临时表的开销可以通过优化器能够生成的更有效的更简单的执行计划来抵消。
另一方面,在Postgres中,CTE是一个“优化围栏”,引擎无法跨越CTE边界推送谓词。
有时一种方式更好,有时另一种方式。一旦查询复杂度超出某个阈值,优化器就无法分析处理数据的所有可能方法,并且必须解决某些问题。例如,加入表的顺序。排列的数量随着可供选择的表的数量呈指数增长。优化程序生成计划的时间有限,因此当所有CTE都内联时,它可能会做出糟糕的选择。当您手动将复杂查询分解为更简单的查询时,您需要了解自己在做什么,但优化者有更好的机会为每个简单查询生成一个好的计划。
两者有不同的用例,不同的优点/缺点。
公用表表达式
应将公用表表达式视为表达式,而不是表。作为表达式,CTE不需要实例化,因此查询优化器可以将其折叠到查询的其余部分,并优化CTE和查询其余部分的组合。
临时表
对于临时表,查询结果存储在临时数据库中的实时表中。然后,查询结果可以在多个查询中重复使用,与CTE不同,CTE如果在多个单独的查询中使用,则必须是每个单独查询中工作计划的一部分。
此外,临时表可以具有索引,键等。将这些添加到临时表可以在优化某些查询时提供很大帮助,并且在CTE中不可用,尽管CTE可以利用表中的索引和键CTE。
如果CTE的基础表不支持您需要的优化类型,则临时表可能更好。
根据具体的查询和要求,Temp table
表现优于CTE
可能有几个原因,反之亦然。
在你的情况下IMO都没有优化查询。
由于CTE在每次引用时都会被评估。所以在你的情况下
SELECT a.MasterAccountId,
ISNULL(t.BatchedOrders, 0) BatchedOrders,
ISNULL(t.PendingOrders, 0) PendingOrders,
ISNULL(av.AvailableStock, 0) AvailableOrders,
ISNULL(av.AvailableBeforeCutOff, 0) AvailableCutOff,
ISNULL(av.OrdersAnyStock, 0) AllOrders
FROM MasterAccount a
LEFT OUTER JOIN Available av ON av.MasterAccountId = a.MasterAccountId
LEFT OUTER JOIN Totals t ON t.MasterAccountId = a.MasterAccountId
WHERE a.IsActive = 1
此查询显示High Cardinality
估计.MasterAccount表被多次评估。由于这个原因,它很慢。
在Temp表的情况下,
SELECT a.MasterAccountId,
ISNULL(t.BatchedOrders, 0) BatchedOrders,
ISNULL(t.PendingOrders, 0) PendingOrders,
ISNULL(av.AvailableStock, 0) AvailableOrders,
ISNULL(av.AvailableBeforeCutOff, 0) AvailableCutOff,
ISNULL(av.OrdersAnyStock, 0) AllOrders
FROM MasterAccount a (NOLOCK)
LEFT OUTER JOIN #Available av (NOLOCK) ON av.MasterAccountId = a.MasterAccountId
LEFT OUTER JOIN Totals t (NOLOCK) ON t.MasterAccountId = a.MasterAccountId
WHERE a.IsActive = 1
这里#Available
已经被评估,结果存储在临时表中,因此MasterAccount
表与Less结果集连接,因此Cardinality Estimate更少。与#Orders
表类似。
CTE和Temp表查询都可以在您的情况下进行优化,从而提高性能。
所以#Orders
应该是你的基本临时表,你不应该在以后再次使用MasterAccount。你应该使用#Orders。
INSERT INTO #Available
SELECT ma.MasterAccountId,
SUM(IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END)) AS AvailableStock,
SUM(IIF(sa.[Status] IN ('Full', 'Partial', 'None'), 1, 0)) AS OrdersAnyStock,
SUM(IIF(sa.RequisitionDate < dbo.TicksToTime(ma.DailyOrderCutOffTime, @toDate),
IIF(ma.IsPartialStock = 1, CASE WHEN sa.[Status] IN ('Full', 'Partial') THEN 1 ELSE 0 END,
CASE WHEN sa.[Status] = 'Full' THEN 1 ELSE 0 END), 0)) AS AvailableBeforeCutOff
FROM #Orders ma (NOLOCK)
INNER JOIN #StockAvailability2 sa ON sa.AccountNumber = dbo.fn_RemoveUnitPrefix(ma.TaskAccountId)
GROUP BY ma.MasterAccountId, ma.IsPartialStock
这里需要来自MasterAcount表的列,如ma.IsPartialStock等,如果可能的话,应该在#order表中加入。希望我的想法很清楚。
在上次查询中不需要MasterAccount表
SELECT a.MasterAccountId,
ISNULL(t.BatchedOrders, 0) BatchedOrders,
ISNULL(t.PendingOrders, 0) PendingOrders,
ISNULL(av.AvailableStock, 0) AvailableOrders,
ISNULL(av.AvailableBeforeCutOff, 0) AvailableCutOff,
ISNULL(av.OrdersAnyStock, 0) AllOrders
FROM #Available av
LEFT OUTER JOIN Totals t ON t.MasterAccountId = av.MasterAccountId
--WHERE a.IsActive = 1
我认为在临时表中不需要Nolock hint
。
以上是关于在某些情况下,为什么CTE(公用表表达式)与SQL Server中的临时表相比会减慢查询速度的主要内容,如果未能解决你的问题,请参考以下文章