I have created a query which performs with aprox 2 seconds with top 100. If i create a stored procedure of this exact query it takes 12-13 seconds to run.
Why would that be?
Elements table count = 2309015 (with userid specified = 326969)
Matches table count = 1290 (with userid specified = 498)
sites table count = 71 (with userid specified = 9)
code
with search (elementid, siteid, title, description, site, link, addeddate)
as
(
select top(#top)
elementid,
elements.siteid, title, elements.description,
site =
case sites.description
when '' then sites.name
when null then sites.name
else sites.name + ' (' + sites.description + ')'
end,
elements.link,
elements.addeddate
from elements
left join sites on elements.siteid = sites.siteid
where title like #search and sites.userid = #userid
order by addeddate desc
)
select search.*, isnull(matches.elementid,0) as ismatch
from search
left join matches on matches.elementid = search.elementid
When you create SP it is compiled and stored and when the SP has parameters, by which you filter your result, the optimizer don't know which value you will pass on execution, then he treat as 33% selection and by this creates plan. When you execute query, the values are provided and optimizer create the execution plan depended on this values. I sure, the the plans are different.
Without code, I can only guess. When writing a sample query, you first have a constant where clause and second a cache. The stored procedure has no chance of either caching or optimizing the query plan based on a constant in the where clause.
I can suggest two ways to try
First one, write your sp like this:
create procedure sp_search
(
#top int,
#search nvarchar(max),
#userid int
)
as
begin
declare #p_top int, #p_search nvarchar(max), #p_userid int
select #p_top = #top, #p_search = #search, #p_userid = #userid
with search (elementid, siteid, title, description, site, link, addeddate)
as
(
select top(#p_top)
elementid,
elements.siteid, title, elements.description,
site =
case sites.description
when '' then sites.name
when null then sites.name
else sites.name + ' (' + sites.description + ')'
end,
elements.link,
elements.addeddate
from elements
left join sites on elements.siteid = sites.siteid
where title like #p_search and sites.userid = #p_userid
order by addeddate desc
)
select search.*, isnull(matches.elementid,0) as ismatch
from search
left join matches on matches.elementid = search.elementid
end
Second one, use inline table function
create function sf_search
(
#top int,
#search nvarchar(max),
#userid int
)
returns table
as
return
(
with search (elementid, siteid, title, description, site, link, addeddate)
as
(
select top(#top)
elementid,
elements.siteid, title, elements.description,
site =
case sites.description
when '' then sites.name
when null then sites.name
else sites.name + ' (' + sites.description + ')'
end,
elements.link,
elements.addeddate
from elements
left join sites on elements.siteid = sites.siteid
where title like #search and sites.userid = #userid
order by addeddate desc
)
select search.*, isnull(matches.elementid,0) as ismatch
from search
left join matches on matches.elementid = search.elementid
)
There is a similar question here
The problem was the stored proc declaration SET ANSI_NULLS OFF
Related
The following query returns 4 columns, but if I attempt to return the same from a stored procedure I get
Only one expression can be specified in the select list when the subquery is not introduced with EXISTS
If I want to get the values returned in a comma delimited string how do I write it?
Working query
Declare #g geography = 'POINT(-1.2846387 52.686091)'
Select top 1
Round(Geocolumn.STDistance(#g)/1000, 2) as DistanceInKlms,
Registration, location, dateoffix
from
Positions
where
Geocolumn.STDistance(#g) is not null
and Registration = 'DX17AAF'
order by
Geocolumn.STDistance(#g);
Stored procedure breaks because of multiple columns:
select #return = (Select Top(1)
Round(GeographyPositon.STDistance(#g)/1000, 2) as DistanceInKlms,
Registration, [location], dateoffix
from Positions
WHERE Registration = #Registration
ORDER BY GeographyPositon.STDistance(#g))
do you need that?
select #return = (Select Top(1)
Round(GeographyPositon.STDistance(#g)/1000, 2)+' , '
Registration+' , '+ [location] +' , '+ dateoffix
from Positions
WHERE Registration = #Registration
ORDER BY GeographyPositon.STDistance(#g)
Try below to get all 4 column values in a single string.
select #return = ( Select Top(1)
CAST(Round(GeographyPositon.STDistance(#g)/1000, 2) AS VARCHAR)+', '
CAST(Registration AS VARCHAR)+', '+ CAST([location] AS VARCHAR) +', '+ CAST(dateoffix AS VARCHAR)
from Positions
WHERE Registration = #Registration
ORDER BY GeographyPositon.STDistance(#g) )
As Azure DW is not supporting FOR XML and SELECT variable assignment, is there any other way to convert multiple rows into single row except using CURSOR?
I didn't found any direct method however the below code is working for me.
DECLARE #intColumnCount INT,
#intProcessCount INT,
#varColList VARCHAR(max)
SET #varColList = ''
IF Object_id('tempdb.dbo.#tempColumnNames') IS NOT NULL
BEGIN
DROP TABLE #tempcolumnnames;
END
CREATE TABLE #tempcolumnnames
(
intid INT,
varcolumnnames VARCHAR(256)
)
INSERT INTO #tempcolumnnames
SELECT Row_number()
OVER (
ORDER BY NAME),
NAME
FROM sys.tables
SET #intProcessCount = 1
SET #intColumnCount = (SELECT Count(*)
FROM #tempcolumnnames)
WHILE ( #intProcessCount <= #intColumnCount )
BEGIN
SET #varColList = #varColList + ', '
+ (SELECT varcolumnnames
FROM #tempcolumnnames
WHERE intid = #intProcessCount)
SET #intProcessCount +=1
END
SELECT Stuff(#varColList, 1, 2, '')
Hope this helps someone.
I have a simple table tblAllUsers which stores simple values like Name,Date Of Birth etc of a UserId.
Another table tblInterest stores the interest(s) of a UserId.Here a user may have any number of Interest and are stored seperately in separate rows :
Create table tblInterest
(
Id int primary key identity,
UserId varchar(10),
InterestId int,
Interest varchar(20)
)
So when i want to display the set of Interest together of a particular user, I use the below query :
DECLARE #listStr VARCHAR(MAX)
SELECT #listStr = COALESCE(#listStr + ', ' ,'') + Interest FROM tblInterest where UserId=#UserId
SELECT #listStr
Now, want to display a users info from both these tables wherein the Interest(S) are displayed in ONE string.
I have tried the below ;
Create proc spPlayersGridview
#listStr VARCHAR(MAX)
as
begin
Select tblAllUsers.Category, tblAllUsers.DOB, tblAllUsers.FirstName, tblAllUsers.LastName, tblAllUsers.City, tblAllUsers.State,
#listStr = COALESCE(#listStr + ', ' ,'') + tblInterest.Interest
from tblAllUsers
INNER JOIN tblInterest
ON tblAllUsers.UserId=tblInterest.UserId
where Category='Player'
end
throws an exception "A SELECT statement that assigns a value to a variable must not be combined with data-retrieval operations."
I had a similar problem a while back, and a bit of SQL STUFF magic helps - Maybe it will work for you as well.
CREATE PROC spPlayersGridview
AS
BEGIN
SELECT
tblAllUsers.Category
, tblAllUsers.DOB
, tblAllUsers.FirstName
, tblAllUsers.LastName
, tblAllUsers.City
, tblAllUsers.State
, listStr = STUFF((
SELECT ',' + tblInterest.Interest
FROM tblInterest
WHERE tblAllUsers.UserId=tblInterest.UserId
ORDER BY tblInterest.Interest
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)'), 1, 1, '')
FROM tblAllUsers
WHERE Category='Player'
END
Hope it helps - For more reading look at: https://msdn.microsoft.com/en-us/library/ms188043.aspx
I am wanting to build a query that looks at an existing Models table.
Table Structure:
ModelID | ManufacturerID | CategoryID | ModelName
What I want to do is pass two things to the query, ModelID and ModelName, so that it returns the specific model and also similar models.
ModelName could be made up of several words e.g iPhone 5s 16GB, so what I would like my query to do is:
SELECT
M.*
FROM
Models AS M
WHERE
(M.ModelID = 1840 OR M.ModelName LIKE '%iPhone%'
OR M.ModelName LIKE '%5s%' OR M.ModelName LIKE '%16GB%')
Is there a way that I can pass the ModelName to the query as a string and then have the query split the string to generate the OR statements?
Do a web search for T-SQL split function. There are loads out there. They take a string (comma-delimited or space delimited or whatever) and return a table of values. Then just do a JOIN against that result set.
SELECT DISTINCT M.*
FROM Models AS M
JOIN dbo.fn_split(#model_name, ' ') AS model_names
ON M.ModelID = #model_id OR m.ModelName LIKE '%' + model_names.value + '%';
OK, so I managed to get this working, following the advice given by Kevin Suchlicki re. fn_Split.
I have made this function even more complex than i intended to, but in order to help others out in a similar situation, here is my final solution:
DECLARE #CategoryID int = 1
DECLARE #ManufacturerID int = 3
DECLARE #ModelName varchar(100) = 'iPhone 5s 16GB'
DECLARE #ModelID int = 1840
DECLARE #Carrier varchar(10) = NULL
DECLARE #Colour varchar(10) = NULL
SELECT
I.*
FROM
(
SELECT
DISTINCT M.*
FROM
Models AS M
JOIN
dbo.fn_Split(#ModelName,' ') AS N
ON M.ModelID = #ModelID OR lower(M.ModelName) LIKE '%'+ Lower(N.value) + '%'
WHERE
M.CategoryID = #CategoryID AND M.ManufacturerID = #ManufacturerID
) AS A
LEFT OUTER JOIN
Items AS I ON A.ModelID = I.ModelID
WHERE
I.Barred <> 1
AND I.Locked <> 1
AND I.Ber <> 1
AND I.Condition = 'Working'
AND (LOWER(I.Colour) = LOWER(ISNULL(#Colour, I.Colour)) OR I.Colour IS NULL)
AND (LOWER(I.Carrier) = LOWER(ISNULL(#Carrier, I.Carrier)) OR I.Carrier IS NULL)
I will now create this as a stored procedure to complete the job.
For reference, HERE is a link to the fn_Split function.
I was looking at different ways of writing a stored procedure to return a "page" of data. This was for use with the ASP ObjectDataSource, but it could be considered a more general problem.
The requirement is to return a subset of the data based on the usual paging parameters; startPageIndex and maximumRows, but also a sortBy parameter to allow the data to be sorted. Also there are some parameters passed in to filter the data on various conditions.
One common way to do this seems to be something like this:
[Method 1]
;WITH stuff AS (
SELECT
CASE
WHEN #SortBy = 'Name' THEN ROW_NUMBER() OVER (ORDER BY Name)
WHEN #SortBy = 'Name DESC' THEN ROW_NUMBER() OVER (ORDER BY Name DESC)
WHEN #SortBy = ...
ELSE ROW_NUMBER() OVER (ORDER BY whatever)
END AS Row,
.,
.,
.,
FROM Table1
INNER JOIN Table2 ...
LEFT JOIN Table3 ...
WHERE ... (lots of things to check)
)
SELECT *
FROM stuff
WHERE (Row > #startRowIndex)
AND (Row <= #startRowIndex + #maximumRows OR #maximumRows <= 0)
ORDER BY Row
One problem with this is that it doesn't give the total count and generally we need another stored procedure for that. This second stored procedure has to replicate the parameter list and the complex WHERE clause. Not nice.
One solution is to append an extra column to the final select list, (SELECT COUNT(*) FROM stuff) AS TotalRows. This gives us the total but repeats it for every row in the result set, which is not ideal.
[Method 2]
An interesting alternative is given here (https://web.archive.org/web/20211020111700/https://www.4guysfromrolla.com/articles/032206-1.aspx) using dynamic SQL. He reckons that the performance is better because the CASE statement in the first solution drags things down. Fair enough, and this solution makes it easy to get the totalRows and slap it into an output parameter. But I hate coding dynamic SQL. All that 'bit of SQL ' + STR(#parm1) +' bit more SQL' gubbins.
[Method 3]
The only way I can find to get what I want, without repeating code which would have to be synchronized, and keeping things reasonably readable is to go back to the "old way" of using a table variable:
DECLARE #stuff TABLE (Row INT, ...)
INSERT INTO #stuff
SELECT
CASE
WHEN #SortBy = 'Name' THEN ROW_NUMBER() OVER (ORDER BY Name)
WHEN #SortBy = 'Name DESC' THEN ROW_NUMBER() OVER (ORDER BY Name DESC)
WHEN #SortBy = ...
ELSE ROW_NUMBER() OVER (ORDER BY whatever)
END AS Row,
.,
.,
.,
FROM Table1
INNER JOIN Table2 ...
LEFT JOIN Table3 ...
WHERE ... (lots of things to check)
SELECT *
FROM stuff
WHERE (Row > #startRowIndex)
AND (Row <= #startRowIndex + #maximumRows OR #maximumRows <= 0)
ORDER BY Row
(Or a similar method using an IDENTITY column on the table variable).
Here I can just add a SELECT COUNT on the table variable to get the totalRows and put it into an output parameter.
I did some tests and with a fairly simple version of the query (no sortBy and no filter), method 1 seems to come up on top (almost twice as quick as the other 2). Then I decided to test probably I needed the complexity and I needed the SQL to be in stored procedures. With this I get method 1 taking nearly twice as long as the other 2 methods. Which seems strange.
Is there any good reason why I shouldn't spurn CTEs and stick with method 3?
UPDATE - 15 March 2012
I tried adapting Method 1 to dump the page from the CTE into a temporary table so that I could extract the TotalRows and then select just the relevant columns for the resultset. This seemed to add significantly to the time (more than I expected). I should add that I'm running this on a laptop with SQL Server Express 2008 (all that I have available) but still the comparison should be valid.
I looked again at the dynamic SQL method. It turns out I wasn't really doing it properly (just concatenating strings together). I set it up as in the documentation for sp_executesql (with a parameter description string and parameter list) and it's much more readable. Also this method runs fastest in my environment. Why that should be still baffles me, but I guess the answer is hinted at in Hogan's comment.
I would most likely split the #SortBy argument into two, #SortColumn and #SortDirection, and use them like this:
…
ROW_NUMBER() OVER (
ORDER BY CASE #SortColumn
WHEN 'Name' THEN Name
WHEN 'OtherName' THEN OtherName
…
END *
CASE #SortDirection
WHEN 'DESC' THEN -1
ELSE 1
END
) AS Row
…
And this is how the TotalRows column could be defined (in the main select):
…
COUNT(*) OVER () AS TotalRows
…
I would definitely want to do a combination of a temp table and NTILE for this sort of approach.
The temp table will allow you to do your complicated series of conditions just once. Because you're only storing the pieces you care about, it also means that when you start doing selects against it further in the procedure, it should have a smaller overall memory usage than if you ran the condition multiple times.
I like NTILE() for this better than ROW_NUMBER() because it's doing the work you're trying to accomplish for you, rather than having additional where conditions to worry about.
The example below is one based off a similar query I'm using as part of a research query; I have an ID I can use that I know will be unique in the results. Using an ID that was an identity column would also be appropriate here, though.
--DECLARES here would be stored procedure parameters
declare #pagesize int, #sortby varchar(25), #page int = 1;
--Create temp with all relevant columns; ID here could be an identity PK to help with paging query below
create table #temp (id int not null primary key clustered, status varchar(50), lastname varchar(100), startdate datetime);
--Insert into #temp based off of your complex conditions, but with no attempt at paging
insert into #temp
(id, status, lastname, startdate)
select id, status, lastname, startdate
from Table1 ...etc.
where ...complicated conditions
SET #pagesize = 50;
SET #page = 5;--OR CAST(#startRowIndex/#pagesize as int)+1
SET #sortby = 'name';
--Only use the id and count to use NTILE
;with paging(id, pagenum, totalrows) as
(
select id,
NTILE((SELECT COUNT(*) cnt FROM #temp)/#pagesize) OVER(ORDER BY CASE WHEN #sortby = 'NAME' THEN lastname ELSE convert(varchar(10), startdate, 112) END),
cnt
FROM #temp
cross apply (SELECT COUNT(*) cnt FROM #temp) total
)
--Use the id to join back to main select
SELECT *
FROM paging
JOIN #temp ON paging.id = #temp.id
WHERE paging.pagenum = #page
--Don't need the drop in the procedure, included here for rerunnability
drop table #temp;
I generally prefer temp tables over table variables in this scenario, largely so that there are definite statistics on the result set you have. (Search for temp table vs table variable and you'll find plenty of examples as to why)
Dynamic SQL would be most useful for handling the sorting method. Using my example, you could do the main query in dynamic SQL and only pull the sort method you want to pull into the OVER().
The example above also does the total in each row of the return set, which as you mentioned was not ideal. You could, instead, have a #totalrows output variable in your procedure and pull it as well as the result set. That would save you the CROSS APPLY that I'm doing above in the paging CTE.
I would create one procedure to stage, sort, and paginate (using NTILE()) a staging table; and a second procedure to retrieve by page. This way you don't have to run the entire main query for each page.
This example queries AdventureWorks.HumanResources.Employee:
--------------------------------------------------------------------------
create procedure dbo.EmployeesByMartialStatus
#MaritalStatus nchar(1)
, #sort varchar(20)
as
-- Init staging table
if exists(
select 1 from sys.objects o
inner join sys.schemas s on s.schema_id=o.schema_id
and s.name='Staging'
and o.name='EmployeesByMartialStatus'
where type='U'
)
drop table Staging.EmployeesByMartialStatus;
-- Populate staging table with sort value
with s as (
select *
, sr=ROW_NUMBER()over(order by case #sort
when 'NationalIDNumber' then NationalIDNumber
when 'ManagerID' then ManagerID
-- plus any other sort conditions
else EmployeeID end)
from AdventureWorks.HumanResources.Employee
where MaritalStatus=#MaritalStatus
)
select *
into #temp
from s;
-- And now pages
declare #RowCount int; select #rowCount=COUNT(*) from #temp;
declare #PageCount int=ceiling(#rowCount/20); --assuming 20 lines/page
select *
, Page=NTILE(#PageCount)over(order by sr)
into Staging.EmployeesByMartialStatus
from #temp;
go
--------------------------------------------------------------------------
-- procedure to retrieve selected pages
create procedure EmployeesByMartialStatus_GetPage
#page int
as
declare #MaxPage int;
select #MaxPage=MAX(Page) from Staging.EmployeesByMartialStatus;
set #page=case when #page not between 1 and #MaxPage then 1 else #page end;
select EmployeeID,NationalIDNumber,ContactID,LoginID,ManagerID
, Title,BirthDate,MaritalStatus,Gender,HireDate,SalariedFlag,VacationHours,SickLeaveHours
, CurrentFlag,rowguid,ModifiedDate
from Staging.EmployeesByMartialStatus
where Page=#page
GO
--------------------------------------------------------------------------
-- Usage
-- Load staging
exec dbo.EmployeesByMartialStatus 'M','NationalIDNumber';
-- Get pages 1 through n
exec dbo.EmployeesByMartialStatus_GetPage 1;
exec dbo.EmployeesByMartialStatus_GetPage 2;
-- ...etc (this would actually be a foreach loop, but that detail is omitted for brevity)
GO
I use this method of using EXEC():
-- SP parameters:
-- #query: Your query as an input parameter
-- #maximumRows: As number of rows per page
-- #startPageIndex: As number of page to filter
-- #sortBy: As a field name or field names with supporting DESC keyword
DECLARE #query nvarchar(max) = 'SELECT * FROM sys.Objects',
#maximumRows int = 8,
#startPageIndex int = 3,
#sortBy as nvarchar(100) = 'name Desc'
SET #query = ';WITH CTE AS (' + #query + ')' +
'SELECT *, (dt.pagingRowNo - 1) / ' + CAST(#maximumRows as nvarchar(10)) + ' + 1 As pagingPageNo' +
', pagingCountRow / ' + CAST(#maximumRows as nvarchar(10)) + ' As pagingCountPage ' +
', (dt.pagingRowNo - 1) % ' + CAST(#maximumRows as nvarchar(10)) + ' + 1 As pagingRowInPage ' +
'FROM ( SELECT *, ROW_NUMBER() OVER (ORDER BY ' + #sortBy + ') As pagingRowNo, COUNT(*) OVER () AS pagingCountRow ' +
'FROM CTE) dt ' +
'WHERE (dt.pagingRowNo - 1) / ' + CAST(#maximumRows as nvarchar(10)) + ' + 1 = ' + CAST(#startPageIndex as nvarchar(10))
EXEC(#query)
At result-set after query result columns:
Note:
I add some extra columns that you can remove them:
pagingRowNo : The row number
pagingCountRow : The total number of rows
pagingPageNo : The current page number
pagingCountPage : The total number of pages
pagingRowInPage : The row number that started with 1 in this page