On Mon, Apr 26, 2021 at 10:31 PM Tomas Vondra <tomas.von...@enterprisedb.com> wrote: > > Hi, > > I took a look at this today, as I committed 39b66a91b back in January. I > can reproduce the issue, with just 1M rows the before/after timings are > roughly 480ms and 620ms on my hardware. > > Unfortunately, the v3 patch does not really fix the issue for me. The > timing with it applied is ~610ms so the improvement is only minimal.
Since the reading vmbuffer is likely to hit on the shared buffer during inserting frozen tuples, I think the improvement would not be visible with a few million tuples depending on hardware. But it might not be as fast as before commit 39b66a91b since we read vmbuffer at least per insertion. Regards, -- Masahiko Sawada EDB: https://www.enterprisedb.com/
