Re: odd variances in count(*) times

On Mon, Oct 09, 2006 at 02:41:07PM -0400, Merlin Moncure wrote:
> On 10/9/06, Stephen Frost <sfrost@snowman.net> wrote:
> >* Merlin Moncure (mmoncure@gmail.com) wrote:
> >> explain analyze select 5000!;
> >> A: 2.4 seconds
> >> B: 1.8 seconds
> >>
> >> explain analyze select count(*) from generate_series(1,500000);
> >> A: 0.85 seconds
> >> B: 4.94 seconds
> >
> >Try w/o the explain analyze.  It adds quite a bit of overhead and that
> >might be inconsistant between the systems (mainly it may have to do with
> >the gettimeofday() calls being implemented differently between Windows
> >and Linux..).
>
> that was it. amd system now drop to .3 seconds, windows .6. (doing
> time foo > psql -c bar > file). thanks...

You can also turn timing on in psql.

And FWIW, RAID5 generally isn't a good idea for databases.
--
Jim Nasby                                            jim@nasby.net
EnterpriseDB      http://enterprisedb.com      512.569.9461 (cell)