SQL INSERT but avoid duplicates

Question

I want to do some quick inserts but avoid duplicates into a Table. For argument\'s sake lets call it MarketPrices, I\'ve been experimenting with two ways of doing it but not

Answer 1

EDIT: to prevent race conditions in concurrent environments, use WITH (UPDLOCK) in the correlated subquery or EXCEPT'd SELECT. The test script I wrote below doesn't require it, since it uses temporary tables that are only visible to the current connection, but in a real environment, operating against user tables, it would be necessary.

MERGE doesn't require UPDLOCK.

---

Inspired by mcl's answer re: unique index & let the database throw an error, I decided to benchmark conditional inserts vs. try/catch.

The results appear to support the conditional insert over try/catch, but YMMV. It's a very simple scenario (one column, small table, etc), executed on one machine, etc.

Here are the results (SQL Server 2008, build 10.0.1600.2):

duplicates (short table)    
  try/catch:                14440 milliseconds / 100000 inserts
  conditional insert:        2983 milliseconds / 100000 inserts
  except:                    2966 milliseconds / 100000 inserts
  merge:                     2983 milliseconds / 100000 inserts

uniques
  try/catch:                 3920 milliseconds / 100000 inserts
  conditional insert:        3860 milliseconds / 100000 inserts
  except:                    3873 milliseconds / 100000 inserts
  merge:                     3890 milliseconds / 100000 inserts

  straight insert:           3173 milliseconds / 100000 inserts

duplicates (tall table)
  try/catch:                14436 milliseconds / 100000 inserts
  conditional insert:        3063 milliseconds / 100000 inserts
  except:                    3063 milliseconds / 100000 inserts
  merge:                     3030 milliseconds / 100000 inserts

Notice, even on unique inserts, there's slightly more overhead to try/catch than a conditional insert. I wonder if this varies by version, CPU, number of cores, etc.

I did not benchmark the IF conditional inserts, just WHERE. I assume the IF variety would show more overhead, since a) would you have two statements, and b) you would need to wrap the two statements in a transaction and set the isolation level to serializable (!). If someone wanted to test this, you would need to change the temp table to a regular user table (serializable doesn't apply to local temp tables).

Here is the script:

-- tested on SQL 2008.
-- to run on SQL 2005, comment out the statements using MERGE
set nocount on

if object_id('tempdb..#temp') is not null drop table #temp
create table #temp (col1 int primary key)
go

-------------------------------------------------------

-- duplicate insert test against a table w/ 1 record

-------------------------------------------------------

insert #temp values (1)
go

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  begin try 
    insert #temp select @x
  end try
  begin catch end catch
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (short table), try/catch: %i milliseconds / %i inserts',-1,-1,@duration,@y) with nowait
go

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  insert #temp select @x where not exists (select * from #temp where col1 = @x)
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (short table), conditional insert: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  insert #temp select @x except select col1 from #temp
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (short table), except: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go

-- comment this batch out for SQL 2005
declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  merge #temp t using (select @x) s (col1) on t.col1 = s.col1 when not matched by target then insert values (col1);
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (short table), merge: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go

-------------------------------------------------------

-- unique insert test against an initially empty table

-------------------------------------------------------

truncate table #temp
declare @x int, @now datetime, @duration int
select @x = 0, @now = getdate()
while @x < 100000 begin
  set @x = @x+1
  insert #temp select @x
end
set @duration = datediff(ms,@now,getdate())
raiserror('uniques, straight insert: %i milliseconds / %i inserts',-1,-1,@duration, @x) with nowait
go

truncate table #temp
declare @x int, @now datetime, @duration int
select @x = 0, @now = getdate()
while @x < 100000 begin
  set @x = @x+1
  begin try 
    insert #temp select @x
  end try
  begin catch end catch
end
set @duration = datediff(ms,@now,getdate())
raiserror('uniques, try/catch: %i milliseconds / %i inserts',-1,-1,@duration, @x) with nowait
go

truncate table #temp
declare @x int, @now datetime, @duration int
select @x = 0, @now = getdate()
while @x < 100000 begin
  set @x = @x+1
  insert #temp select @x where not exists (select * from #temp where col1 = @x)
end
set @duration = datediff(ms,@now,getdate())
raiserror('uniques, conditional insert: %i milliseconds / %i inserts',-1,-1,@duration, @x) with nowait
go

truncate table #temp
declare @x int, @now datetime, @duration int
select @x = 0, @now = getdate()
while @x < 100000 begin
  set @x = @x+1
  insert #temp select @x except select col1 from #temp
end
set @duration = datediff(ms,@now,getdate())
raiserror('uniques, except: %i milliseconds / %i inserts',-1,-1,@duration, @x) with nowait
go

-- comment this batch out for SQL 2005
truncate table #temp
declare @x int, @now datetime, @duration int
select @x = 1, @now = getdate()
while @x < 100000 begin
  set @x = @x+1
  merge #temp t using (select @x) s (col1) on t.col1 = s.col1 when not matched by target then insert values (col1);
end
set @duration = datediff(ms,@now,getdate())
raiserror('uniques, merge: %i milliseconds / %i inserts',-1,-1,@duration, @x) with nowait
go

-------------------------------------------------------

-- duplicate insert test against a table w/ 100000 records

-------------------------------------------------------

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  begin try 
    insert #temp select @x
  end try
  begin catch end catch
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (tall table), try/catch: %i milliseconds / %i inserts',-1,-1,@duration,@y) with nowait
go

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  insert #temp select @x where not exists (select * from #temp where col1 = @x)
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (tall table), conditional insert: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go

declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  insert #temp select @x except select col1 from #temp
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (tall table), except: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go

-- comment this batch out for SQL 2005
declare @x int, @y int, @now datetime, @duration int
select @x = 1, @y = 0, @now = getdate()
while @y < 100000 begin
  set @y = @y+1
  merge #temp t using (select @x) s (col1) on t.col1 = s.col1 when not matched by target then insert values (col1);
end
set @duration = datediff(ms,@now,getdate())
raiserror('duplicates (tall table), merge: %i milliseconds / %i inserts',-1,-1,@duration, @y) with nowait
go