Re: insert performance riddle

On Friday August 12 2005 5:27 pm, Michael Fuhr wrote:
> On Fri, Aug 12, 2005 at 05:20:49PM -0600, Ed L. wrote:
> > Well, just as I thought I had this one pinned, my test
> > results have become wildly inconsistent, eroding all
> > confidence in my prior conclusions about DBI slowness, etc.
> > I've seen at least 1000+ QPS performance via DBI/DBD::Pg,
> > Pg, and C/libpq.  I'm now investigating the possibility of
> > simple old intermittent I/O congestion...
>
> How consistent were the results before?  I got the impression
> that you saw consistently bad performance with DBD::Pg when
> other methods performed well.

Results were very consistent until this morning.  Now dbi/dbd::pg
are intermittently showing performance 1-2 orders of magnitude
faster.   :/

Ed