Vertica performance

Hi

 

I'm testing a vertica query performance.

I loaded 900,000,000 data that each data length about 300 bytes.

 

[TABLE]

                                   List of Fields by Tables
  Schema   | Table | Column |   Type   | Size | Default | Not Null | Primary Key | Foreign Key
-----------+-------+--------+----------+------+---------+----------+-------------+-------------
 abcdefghi | t1    | major  | char(50) |   50 |         | f        | f           |
 abcdefghi | t1    | minor  | char(50) |   50 |         | f        | f           |
 abcdefghi | t1    | param  | char(50) |   50 |         | f        | f           |
 abcdefghi | t1    | node   | char(50) |   50 |         | f        | f           |
 abcdefghi | t1    | item   | char(50) |   50 |         | f        | f           |
 abcdefghi | t1    | timeAt | int      |    8 |         | f        | f           |
 abcdefghi | t1    | val    | float    |    8 |         | f        | f           |

 

 

then i check the time by linux time command.

 

> time vsql database -f query file > /dev/null

 

This query select 72,000 data.

 

[QUERY]

 

select node,item,timeAt,val from t1
where
major='MAJOR0002' and minor='MINOR0003' and param='PARAM0004'
and
node in (
'NODE0010'
,'NODE0011'
,'NODE0012'
,'NODE0013'
,'NODE0014'
,'NODE0015'
,'NODE0016'
,'NODE0017'
,'NODE0018'
,'NODE0019'
)
and
timeAt >= 1434942000 and timeAt < 1435028400
order by node,item,timeAt
;

 

 

The result is 12-6 sec.

 

At top command, while running query, the CPU run queue is 4-6.

No swap, a little io.

 

My test machine has 4 core and no hyper thread.

And I don't any configuration specially.

 

I think this is a CPU bottle neck.

 

How do i improve this performance.

 

* When i tested the same query on other database,

 that time is a 1-2 seconds.

 

 

Best Regards

 

Comments

Leave a Comment

BoldItalicStrikethroughOrdered listUnordered list
Emoji
Image
Align leftAlign centerAlign rightToggle HTML viewToggle full pageToggle lights
Drop image/file