On Mon, Sep 2, 2024 at 4:58 PM Peter Geoghegan <pg@bowt.ie> wrote:
> On Mon, Sep 2, 2024 at 4:35 PM Pavel Luzanov <p.luzanov@postgrespro.ru> wrote:
> > If it helps, without creating index on id column, the numbers will be
> > much closer:
>
> Yes, avoiding all index vacuuming seems useful. It makes the test case
> cleaner, since we don't have to think about the variability from the
> TIDStore work (and from index vacuuming more generally).
It just occurred to me that earlier versions don't have the
HEAP_PAGE_PRUNE_MARK_UNUSED_NOW optimization added by commit
c120550edb. Postgres 17 does have that optimization, though, so it
should easily be able to write far fewer WAL records than earlier
versions. And yet your revised no-indexes test case seems to show that
Postgres 17 is doing slightly worse by that measure (and by others).
--
Peter Geoghegan
