Re: Improving connection scalability: GetSnapshotData()

On Sun, Mar 1, 2020 at 12:36 AM Andres Freund <andres(at)anarazel(dot)de> wrote:
> The workload is a pgbench readonly, with pgbench -M prepared -c $conns
> -j $conns -S -n for each client count. This is on a machine with 2
> Intel(R) Xeon(R) Platinum 8168, but virtualized.
>
> conns tps master tps pgxact-split
>
> 1 26842.492845 26524.194821
> 10 246923.158682 249224.782661
> 50 695956.539704 709833.746374
> 100 1054727.043139 1903616.306028
> 200 964795.282957 1949200.338012
> 300 906029.377539 1927881.231478
> 400 845696.690912 1911065.369776
> 500 812295.222497 1926237.255856
> 600 888030.104213 1903047.236273
> 700 866896.532490 1886537.202142
> 800 863407.341506 1883768.592610
> 900 871386.608563 1874638.012128
> 1000 887668.277133 1876402.391502
> 1500 860051.361395 1815103.564241
> 2000 890900.098657 1775435.271018
> 3000 874184.980039 1653953.817997
> 4000 845023.080703 1582582.316043
> 5000 817100.195728 1512260.802371
>
> I think these are pretty nice results.

This scalability improvement is clearly very significant. There is
little question that this is a strategically important enhancement for
the Postgres project in general. I hope that you will ultimately be
able to commit the patchset before feature freeze.

I have heard quite a few complaints about the scalability of snapshot
acquisition in Postgres. Generally from very large users that are not
well represented on the mailing lists, for a variety of reasons. The
GetSnapshotData() bottleneck is a *huge* problem for us. (As problems
for Postgres users go, I would probably rank it second behind issues
with VACUUM.)

--
Peter Geoghegan