Out of curiosity, is the pg14 running with the default jit=on setting? This is obviously entirely due to the nature of the particular queries themselves, but we found that for our workloads that pg versions greater than 11 were exacting a huge cost due to the jit compiler. Once we explicitly turned jit=off we started to see improvements.
On Mon, 29 Jan 2024 at 07:55, Ron Johnson <ronljohnso...@gmail.com> wrote: > On Sun, Jan 28, 2024 at 10:44 PM David Rowley <dgrowle...@gmail.com> > wrote: > >> On Mon, 29 Jan 2024 at 07:37, Ron Johnson <ronljohnso...@gmail.com> >> wrote: >> >>> 08 9.6.24 1,142.164 1,160.801 1,103.716 1,249.852 1,191.081 >>> 14.10 159.354 155.111 155.111 162.797 158.157 86.72% >>> >> >> Your speedup per cent calculation undersells PG14 by quite a bit. I'd >> call that an increase of ~639% rather than 86.72%. >> >> I think you've done "1 - sum( <14.10 numbers> ) / sum( <9.6.24 numbers>)" >> whereas I think you should have done "sum( <9.6.24 numbers>) / sum( <14.10 >> numbers> ) - 1" >> >> Nonetheless, thanks for testing this out. I assume this is just a report >> giving good feedback about progress in this area...? >> > > The spreadsheet function, using the Median cells, is (PG9.6 - PG14) / > PG9.6). That's essentially the same as what you wrote. > > 158.157 / 1191.081 = 0.13278 > > 1191.081 / 158.157 = 7.53, so 9.6.24 on that query is 7.53x slower. > >