On Fri, Jan 09, 2009 at 02:00:39PM -0800, Jeff Davis wrote:
> On Fri, 2009-01-09 at 14:29 -0600, Kenneth Marshall wrote:
> > Jeff,
> >
> > Thanks for the review. I would not really expect any differences in hash
> > index build times other than normal noise variances. The most definitive
> > benchmark that I have seen was done with my original patch submission
> > in March posted by Luke of Greenplum:
> >
> > "We just applied this and saw a 5 percent speedup on a hash aggregation
> > query with four columns in a 'group by' clause run against a single
> > TPC-H table."
> >
> > I wonder if they would be willing to re-run their test? Thanks again.
>
> Separating mix() and final() should have some performance benefit,
> right?
>
> Regards,
> Jeff Davis
>
>
Yes, it does but the results can be swamped by other latencies in the
code path. Tests such as Tom's benchmark of the underlying functions is
needed to isolate the timings effectively or a benchmark like Greenplum's
that will benefit from a more efficient function.
Ken
