Sql-server – Need help in converting this cursor to a set based operation

sql servert-sql

I have a stored procedure which runs as part of a report database refresh nightly which takes about 2 hours complete. The object B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP_T2 has 8 million rows. Can you suggest how can I convert this cursor to a set based approach for better performance? Can a CTE be used?

ALTER PROCEDURE [dbo].[B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP2_SP] AS      
SET NOCOUNT ON        
DECLARE @SEQ SMALLINT,      
@CASEID DECIMAL,       
@ASSIGNED  NCHAR(30),      
@AUDITSTAMP DATETIME,      
@AUDITOPRID NCHAR(60),      
@STATUS NCHAR(10),      
@LASTCASEID DECIMAL,       
@PROVGRPID NCHAR(20)      
SET @SEQ = 1      
SET @LASTCASEID = @CASEID      

DROP TABLE B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP   

CREATE TABLE B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP (      
  SEQ_NUM SMALLINT,       
  CASE_ID DECIMAL,       
  ASSIGNED_TO NCHAR(30),       
  AUDIT_STAMP DATETIME,       
  AUDIT_OPRID NCHAR(60),      
  RC_STATUS NCHAR(10),      
  PROVIDER_GRP_ID NCHAR(20) )      
DECLARE AUDIT CURSOR FOR        
   SELECT CASE_ID, ASSIGNED_TO, AUDIT_STAMP, AUDIT_OPRID, RC_STATUS, PROVIDER_GRP_ID      
   FROM B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP_T2      

-- Open the cursor      
OPEN AUDIT      
FETCH NEXT      
   FROM AUDIT      
    INTO @CASEID, @ASSIGNED, @AUDITSTAMP, @AUDITOPRID, @STATUS, @PROVGRPID       
WHILE @@FETCH_STATUS = 0      

begin       
 INSERT INTO B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP       
 SELECT @SEQ, @CASEID, @ASSIGNED, @AUDITSTAMP, @AUDITOPRID, @STATUS, @PROVGRPID      

SET @LASTCASEID = @CASEID      
FETCH NEXT      
   FROM AUDIT      
    INTO @CASEID, @ASSIGNED, @AUDITSTAMP, @AUDITOPRID, @STATUS, @PROVGRPID      

SET @SEQ = CASE WHEN @CASEID <> @LASTCASEID THEN 1 WHEN @CASEID = @LASTCASEID THEN @SEQ + 1 END      
end      
-- Close and deallocate the cursor      
CLOSE AUDIT      
DEALLOCATE AUDIT

Best Answer

Why do you need to DROP and RECREATE the table each time? Since you're doing a DROP-CREATE, it must already exist. So, outside of the SP, recreate it as follows:

CREATE TABLE B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP (      
  SEQ_NUM SMALLINT,       
  CASE_ID DECIMAL,       
  ASSIGNED_TO NCHAR(30),       
  AUDIT_STAMP DATETIME,       
  AUDIT_OPRID NCHAR(60),      
  RC_STATUS NCHAR(10),      
  PROVIDER_GRP_ID NCHAR(20),
  PRIMARY KEY(CASE_ID, SEQ_NUM)
); -- don't leave an 8 million record table in a heap!

Since all you need is merely to number the records within a CASE from 1 to N, you can use ROW_NUMBER().

ALTER PROCEDURE [dbo].[B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP2_SP]
AS
  SET NOCOUNT ON;
  TRUNCATE TABLE B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP;

  INSERT INTO B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP       
  SELECT ROW_NUMBER() OVER (PARTITION BY CASE_ID ORDER BY AUDIT_STAMP),
         CASE_ID, ASSIGNED_TO, AUDIT_STAMP, AUDIT_OPRID, RC_STATUS, PROVIDER_GRP_ID      
    FROM B_RPT_RC_AUDIT_ASSIGNED_TO_TEMP_T2;
GO

Related Solutions

Sql-server – Replace cursor with set-based approach

I would probably just do this the brute force way, and add indexes to support these joins where they don't exist. Not much gain to treating new customers and old customers any different once you've inserted all the customers that don't already exist:

INSERT dbo.Customer(fname, lname, address, city, state, zip, email)
    SELECT fname, lname, address, city, state, zip, email
     FROM dbo.job AS j
     WHERE job_no = @job_no
     AND NOT EXISTS
     (
        SELECT 1 FROM dbo.Customer
        WHERE fname = j.fname
        AND lname = j.lname
        AND (address = j.address OR email = j.email)
     );

INSERT INTO dbo.personal_code (customer_id, mailing_id, personal_code, email)
SELECT c.customer_id, j.mailing_id, j.personal_code, c.email
  FROM dbo.Customer AS c
  INNER JOIN dbo.job AS j
  ON c.fname = j.fname AND c.lname = j.lname 
  AND (c.address = j.address OR c.email = j.email)
  WHERE j.job_no = @job_no;

INSERT dbo.personal_code_extra(personal_code_id, extra)
SELECT pc.personal_code_id, j.extra
  FROM dbo.personal_code AS pc
  INNER JOIN dbo.Customer AS c
  ON pc.customer_id = c.customer_id
  INNER JOIN dbo.job AS j
  ON c.fname = j.fname AND c.lname = j.lname 
  AND (c.address = j.address OR c.email = j.email)
  WHERE j.job_no = @job_no;

SQL Server – Converting Cursor Based Filtering Logic to CTE

If I understand correctly, and you want to insert 10 values of the 2nd table for every iteration of the cursor (or cte), you can use this:

; WITH myCTE (value) AS
    ( SELECT value FROM sometable )
INSERT INTO @TOP10      
    SELECT t.Value1, t.Value2, t.Value3, t.Value4
    FROM myCTE AS mc
      CROSS APPLY 
        ( SELECT TOP (10)
              bt.Value1, bt.Value2, bt.Value3, bt.Value4
          FROM BaseTable AS bt 
          WHERE bt.SomeVariable = mc.value
          ORDER BY <SomeColumns>                     -- needs something here
        ) AS t ;

You also need an ORDER BY in the subquery with TOP to be consistent. Without order by, the database engine is free to return any 10 rows that match the conditions.

It could also be done using ROW_NUMBER():

; WITH myCTE (Value1, Value2, Value3, Value4) AS
    ( SELECT bt.Value1, bt.Value2, bt.Value3, bt.Value4,
             Rn = ROW_NUMBER() OVER (PARTITION BY bt.SomeVariable
                                     ORDER BY <SomeColumns>)
      FROM sometable AS s
        JOIN BaseTable AS bt 
          ON bt.SomeVariable = s.value
    )
INSERT INTO @TOP10      
    SELECT Value1, Value2, Value3, Value4
    FROM myCTE 
    WHERE Rn <= 10 ;

Best Answer

Related Solutions

Sql-server – Replace cursor with set-based approach

SQL Server – Converting Cursor Based Filtering Logic to CTE

Related Question