SQL 分页比获取所有数据花费的时间长 (x15~x20) 是否正常？
Is it normal for SQL Paging to take Longer (x15~x20) than Getting All Data?
我有大约 16k 行的视图，获取所有数据大约需要 5 秒。
我决定将 "loading" 实施到应用程序中，这样 GUI 就不会冻结，用户将能够 work/look with/at 在 DataGridView 中提供数据。
我注意到，如果我使用 SQL 分页获取所有数据，它需要大约 90 秒（1.5 分钟），所以会适得其反。
现在我想知道它是否正常，如果正常，为什么会有人使用它？
我试过3种SQL分页方式：
I'm using 160 for testing purposes!
DECLARE @int_percentage AS INT = 1
WHILE @int_percentage <= 100
BEGIN
SELECT O.*, P.Percentage
FROM vAppointmentDetailsWithComments O
LEFT JOIN (SELECT AppointmentID, NTILE(100) OVER(ORDER BY AppointmentID) Percentage
FROM vAppointmentDetailsWithoutComments) P ON P.AppointmentID = O.AppointmentID
WHERE P.Percentage = @int_percentage
SET @int_percentage = @int_percentage + 1
END
---------------------------------------------------------------------------------------------------
DECLARE @int_percentage AS INT = 1, @int_appointmentID AS INT = 0
WHILE @int_percentage <= 100
BEGIN
SELECT TOP 160 *
FROM vAppointmentDetailsWithComments
WHERE AppointmentID > @int_appointmentID
SET @int_percentage = @int_percentage + 1
SET @int_appointmentID = @int_appointmentID + 161
END
---------------------------------------------------------------------------------------------------
DECLARE @int_percentage AS INT = 1, @int_currentStartingRowIndex AS INT = 1
WHILE @int_percentage <= 100
BEGIN
EXEC spGetRows @int_startingRowIndex = @int_currentStartingRowIndex, @int_maxRows = 160
SET @int_percentage = @int_percentage + 1
SET @int_currentStartingRowIndex = @int_currentStartingRowIndex + 160
END
---------------------------------------------------------------------------------------------------
SELECT *
FROM vAppointmentDetailsWithComments
程序：
CREATE PROCEDURE [dbo].[spGetRows]
(
@int_startingRowIndex INT,
@int_maxRows INT
)
AS
DECLARE @int_firstID INT
-- Getting 1'st ID
SET ROWCOUNT @int_startingRowIndex
SELECT @int_firstID = AppointmentID FROM vAppointmentDetailsWithoutComments ORDER BY AppointmentID
-- Setting ROWCOUNT to MAX
SET ROWCOUNT @int_maxRows
-- Getting all data >= @int_firstID
SELECT *
FROM vAppointmentDetailsWithComments
WHERE AppointmentID >= @int_firstID
SET ROWCOUNT 0
GO
结果：
表和视图的创建和填充数据：
FOR XML PATH in "vAppointmentDetailsWithComments" is main performance
problem
CREATE TABLE [dbo].[Appointment](
[ID] [int] IDENTITY(1,1) NOT NULL,
[Number] [int] NOT NULL,
CONSTRAINT [PK_Appointment] PRIMARY KEY CLUSTERED
(
[ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO
ALTER TABLE [dbo].[Appointment] ADD CONSTRAINT [DF_Appointment_Number] DEFAULT ((0)) FOR [Number]
GO
---------------------------------------------------------------------------------------------------
CREATE TABLE [dbo].[Comment](
[ID] [int] IDENTITY(1,1) NOT NULL,
[Appointment_ID] [int] NOT NULL,
[Text] [nvarchar](max) NOT NULL,
[Time] [datetime] NOT NULL,
CONSTRAINT [PK_Comment] PRIMARY KEY CLUSTERED
(
[ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO
ALTER TABLE [dbo].[Comment] WITH CHECK ADD CONSTRAINT [FK_Comment_Appointment] FOREIGN KEY([Appointment_ID])
REFERENCES [dbo].[Appointment] ([ID])
GO
ALTER TABLE [dbo].[Comment] CHECK CONSTRAINT [FK_Comment_Appointment]
GO
ALTER TABLE [dbo].[Comment] ADD CONSTRAINT [DF_Comment_Text] DEFAULT (N'Some random Comment for Testing purposes') FOR [Text]
GO
ALTER TABLE [dbo].[Comment] ADD CONSTRAINT [DF_Comment_Time] DEFAULT (getdate()) FOR [Time]
GO
---------------------------------------------------------------------------------------------------
CREATE VIEW [dbo].[vAppointmentDetailsWithComments]
AS
SELECT A.ID AppointmentID, (K.Comments + CHAR(13) + CHAR(10)) Comment
FROM Appointment A LEFT JOIN
(SELECT A.ID,
(SELECT STUFF
((SELECT REPLACE(CHAR(13) + CHAR(10) + K.Text, CHAR(7), '')
FROM Comment K
WHERE K.Appointment_ID = A.ID
AND K.Text != ''
ORDER BY K.Time FOR XML PATH, TYPE ).value('.[1]', 'NVARCHAR(MAX)'), 1, 1, '')) Comments
FROM Appointment A) K ON K.ID = A.ID
GO
---------------------------------------------------------------------------------------------------
CREATE VIEW [dbo].[vAppointmentDetailsWithoutComments]
AS
SELECT A.ID AppointmentID
FROM Appointment A
GO
---------------------------------------------------------------------------------------------------
SET NOCOUNT ON
BEGIN TRAN
DECLARE @int_appointmentID AS INT = 1,
@int_tempComment AS INT
WHILE @int_appointmentID <= 16000
BEGIN
INSERT INTO Appointment VALUES (@int_appointmentID)
SET @int_tempComment = 1
WHILE @int_tempComment <= 5
BEGIN
INSERT INTO Comment (Appointment_ID) VALUES (@int_appointmentID)
SET @int_tempComment = @int_tempComment + 1
END
SET @int_appointmentID = @int_appointmentID + 1
END
COMMIT TRAN
GO
执行计划：
Fast(FetchAll)
Slow(Top)
部分性能问题是因为 Comment table Appointment_ID 列上没有索引。使用 Appointment_ID 上的聚簇索引并将主键索引更改为非聚簇索引，来自 vAppointmentDetailsWithComments 的 select 查询经过的时间从我的测试盒上的大约 5 秒减少到大约 3.5 秒。下面是创建聚簇索引并将主键重新创建为非聚簇索引的脚本。
ALTER TABLE dbo.Comment DROP CONSTRAINT FK_Comment_Appointment;
ALTER TABLE Appointment DROP CONSTRAINT PK_Appointment;
ALTER TABLE Appointment ADD CONSTRAINT PK_Appointment
PRIMARY KEY NONCLUSTERED(ID);
ALTER TABLE dbo.Comment
ADD CONSTRAINT FK_Comment_Appointment FOREIGN KEY(Appointment_ID)
REFERENCES dbo.Appointment (ID);
CREATE CLUSTERED INDEX cdx_Comment_Appointment_ID ON Comment(Appointment_ID);
GO
评论的字符串连接是在 T-SQL 中执行的昂贵操作。我建议您在应用程序端执行此操作，我预计这对于 16K 行将是亚秒级的。这将避免需要在 SQL 方面通过简单的加入评论来跳过箍：
CREATE VIEW dbo.vAppointmentDetailsWithIndividualComments
AS
SELECT A.ID AppointmentID, K.Text, K.Time
FROM dbo.Appointment A
LEFT JOIN dbo.Comment K
ON K.Appointment_ID = A.ID
AND K.Text <> '';
GO
SELECT AppointmentID, Text, Time
FROM dbo.vAppointmentDetailsWithIndividualComments
ORDER BY Time;
GO
关于您列出的分页技术，由于对约会的扫描，第一种技术在结果集中的表现会越来越差。
第二个查询缺少 ORDER BY Appointment_ID。 ORDER BY 需要 TOP 以获得确定性结果。但是，从分页性能的角度来看，此方法确实有优点，因为它将对约会执行索引查找 table，无论结果集中的位置如何，都提供一致的性能。
SET ROWCOUNT 已弃用，但最重要的是它将执行与第一个查询类似的操作（越来越差）。
我有大约 16k 行的视图，获取所有数据大约需要 5 秒。
我决定将 "loading" 实施到应用程序中，这样 GUI 就不会冻结，用户将能够 work/look with/at 在 DataGridView 中提供数据。
我注意到，如果我使用 SQL 分页获取所有数据，它需要大约 90 秒（1.5 分钟），所以会适得其反。
现在我想知道它是否正常，如果正常，为什么会有人使用它？
我试过3种SQL分页方式：
I'm using 160 for testing purposes!
DECLARE @int_percentage AS INT = 1
WHILE @int_percentage <= 100
BEGIN
SELECT O.*, P.Percentage
FROM vAppointmentDetailsWithComments O
LEFT JOIN (SELECT AppointmentID, NTILE(100) OVER(ORDER BY AppointmentID) Percentage
FROM vAppointmentDetailsWithoutComments) P ON P.AppointmentID = O.AppointmentID
WHERE P.Percentage = @int_percentage
SET @int_percentage = @int_percentage + 1
END
---------------------------------------------------------------------------------------------------
DECLARE @int_percentage AS INT = 1, @int_appointmentID AS INT = 0
WHILE @int_percentage <= 100
BEGIN
SELECT TOP 160 *
FROM vAppointmentDetailsWithComments
WHERE AppointmentID > @int_appointmentID
SET @int_percentage = @int_percentage + 1
SET @int_appointmentID = @int_appointmentID + 161
END
---------------------------------------------------------------------------------------------------
DECLARE @int_percentage AS INT = 1, @int_currentStartingRowIndex AS INT = 1
WHILE @int_percentage <= 100
BEGIN
EXEC spGetRows @int_startingRowIndex = @int_currentStartingRowIndex, @int_maxRows = 160
SET @int_percentage = @int_percentage + 1
SET @int_currentStartingRowIndex = @int_currentStartingRowIndex + 160
END
---------------------------------------------------------------------------------------------------
SELECT *
FROM vAppointmentDetailsWithComments
程序：
CREATE PROCEDURE [dbo].[spGetRows]
(
@int_startingRowIndex INT,
@int_maxRows INT
)
AS
DECLARE @int_firstID INT
-- Getting 1'st ID
SET ROWCOUNT @int_startingRowIndex
SELECT @int_firstID = AppointmentID FROM vAppointmentDetailsWithoutComments ORDER BY AppointmentID
-- Setting ROWCOUNT to MAX
SET ROWCOUNT @int_maxRows
-- Getting all data >= @int_firstID
SELECT *
FROM vAppointmentDetailsWithComments
WHERE AppointmentID >= @int_firstID
SET ROWCOUNT 0
GO
结果：
表和视图的创建和填充数据：
FOR XML PATHin "vAppointmentDetailsWithComments" is main performance problem
CREATE TABLE [dbo].[Appointment](
[ID] [int] IDENTITY(1,1) NOT NULL,
[Number] [int] NOT NULL,
CONSTRAINT [PK_Appointment] PRIMARY KEY CLUSTERED
(
[ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO
ALTER TABLE [dbo].[Appointment] ADD CONSTRAINT [DF_Appointment_Number] DEFAULT ((0)) FOR [Number]
GO
---------------------------------------------------------------------------------------------------
CREATE TABLE [dbo].[Comment](
[ID] [int] IDENTITY(1,1) NOT NULL,
[Appointment_ID] [int] NOT NULL,
[Text] [nvarchar](max) NOT NULL,
[Time] [datetime] NOT NULL,
CONSTRAINT [PK_Comment] PRIMARY KEY CLUSTERED
(
[ID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO
ALTER TABLE [dbo].[Comment] WITH CHECK ADD CONSTRAINT [FK_Comment_Appointment] FOREIGN KEY([Appointment_ID])
REFERENCES [dbo].[Appointment] ([ID])
GO
ALTER TABLE [dbo].[Comment] CHECK CONSTRAINT [FK_Comment_Appointment]
GO
ALTER TABLE [dbo].[Comment] ADD CONSTRAINT [DF_Comment_Text] DEFAULT (N'Some random Comment for Testing purposes') FOR [Text]
GO
ALTER TABLE [dbo].[Comment] ADD CONSTRAINT [DF_Comment_Time] DEFAULT (getdate()) FOR [Time]
GO
---------------------------------------------------------------------------------------------------
CREATE VIEW [dbo].[vAppointmentDetailsWithComments]
AS
SELECT A.ID AppointmentID, (K.Comments + CHAR(13) + CHAR(10)) Comment
FROM Appointment A LEFT JOIN
(SELECT A.ID,
(SELECT STUFF
((SELECT REPLACE(CHAR(13) + CHAR(10) + K.Text, CHAR(7), '')
FROM Comment K
WHERE K.Appointment_ID = A.ID
AND K.Text != ''
ORDER BY K.Time FOR XML PATH, TYPE ).value('.[1]', 'NVARCHAR(MAX)'), 1, 1, '')) Comments
FROM Appointment A) K ON K.ID = A.ID
GO
---------------------------------------------------------------------------------------------------
CREATE VIEW [dbo].[vAppointmentDetailsWithoutComments]
AS
SELECT A.ID AppointmentID
FROM Appointment A
GO
---------------------------------------------------------------------------------------------------
SET NOCOUNT ON
BEGIN TRAN
DECLARE @int_appointmentID AS INT = 1,
@int_tempComment AS INT
WHILE @int_appointmentID <= 16000
BEGIN
INSERT INTO Appointment VALUES (@int_appointmentID)
SET @int_tempComment = 1
WHILE @int_tempComment <= 5
BEGIN
INSERT INTO Comment (Appointment_ID) VALUES (@int_appointmentID)
SET @int_tempComment = @int_tempComment + 1
END
SET @int_appointmentID = @int_appointmentID + 1
END
COMMIT TRAN
GO
执行计划： Fast(FetchAll) Slow(Top)
部分性能问题是因为 Comment table Appointment_ID 列上没有索引。使用 Appointment_ID 上的聚簇索引并将主键索引更改为非聚簇索引，来自 vAppointmentDetailsWithComments 的 select 查询经过的时间从我的测试盒上的大约 5 秒减少到大约 3.5 秒。下面是创建聚簇索引并将主键重新创建为非聚簇索引的脚本。
ALTER TABLE dbo.Comment DROP CONSTRAINT FK_Comment_Appointment;
ALTER TABLE Appointment DROP CONSTRAINT PK_Appointment;
ALTER TABLE Appointment ADD CONSTRAINT PK_Appointment
PRIMARY KEY NONCLUSTERED(ID);
ALTER TABLE dbo.Comment
ADD CONSTRAINT FK_Comment_Appointment FOREIGN KEY(Appointment_ID)
REFERENCES dbo.Appointment (ID);
CREATE CLUSTERED INDEX cdx_Comment_Appointment_ID ON Comment(Appointment_ID);
GO
评论的字符串连接是在 T-SQL 中执行的昂贵操作。我建议您在应用程序端执行此操作，我预计这对于 16K 行将是亚秒级的。这将避免需要在 SQL 方面通过简单的加入评论来跳过箍：
CREATE VIEW dbo.vAppointmentDetailsWithIndividualComments
AS
SELECT A.ID AppointmentID, K.Text, K.Time
FROM dbo.Appointment A
LEFT JOIN dbo.Comment K
ON K.Appointment_ID = A.ID
AND K.Text <> '';
GO
SELECT AppointmentID, Text, Time
FROM dbo.vAppointmentDetailsWithIndividualComments
ORDER BY Time;
GO
关于您列出的分页技术，由于对约会的扫描，第一种技术在结果集中的表现会越来越差。
第二个查询缺少 ORDER BY Appointment_ID。 ORDER BY 需要 TOP 以获得确定性结果。但是，从分页性能的角度来看，此方法确实有优点，因为它将对约会执行索引查找 table，无论结果集中的位置如何，都提供一致的性能。
SET ROWCOUNT 已弃用，但最重要的是它将执行与第一个查询类似的操作（越来越差）。