On 2016-10-01 20:04:18 +0100, Greg Stark wrote:
> On Sat, Oct 1, 2016 at 1:44 AM, Andres Freund <andres@anarazel.de> wrote:
> >
> > Unfortunately I'm running out battery right now, so I don't want to
> > re-run the benchmarks posted upthread (loading takes a while). But the
> > last time I ran them all the results after the patches were better than
> > before.
> I have a machine sitting idle now too if you have specific ideas of
> what to benchmark.
Last time I just extracted interesting parts of queries from tpc-h (to
be able to look at bitmapscans/hash-aggs in isolation) and ran tpc-h as
a whole. During development I also tried to come up with adverse cases
(e.g. huge bitmapscans, with very low work_mem). I don't really have a
lot better ideas than that.
Andres