On Mon, Mar 16, 2026 at 9:00 AM Michael Paquier <michael@paquier.xyz> wrote:
>
> On Sun, Mar 15, 2026 at 11:47:06AM +0800, Xuneng Zhou wrote:
> > The updated script now reports speedup separately for the read and
> > write paths like this:
> >
> > hash_vacuum_medium base= 33747.2ms patch= 27379.7ms 1.23x ( 18.9%)
> > read: 4662→1612 ops 8238.72→1725.86ms
> > (4.77x) write: 12689→12651 ops 25146.51→25053.57ms (1.00x)
> >
> > I think it is useful to keep the write-delay option even with this
> > reporting. Separating the read and write delays also helps reduce the
> > overall runtime of the tests, especially for large data sizes: we only
> > slow down the read path while keeping the write path fast.
>
> These write numbers are more in line with what I was seeing in my last
> tests, and I am not going to ignore a 20% runtime reduction. The
> stats numbers are looking nice, as well.
>
> At the end, I have checked the logic of what you are introducing,
> where things come down to the point of making sure that the data
> pushed to the callback remains consistent with the paths where
> _hash_getcachedmetap() is called. I have also cross-checked the data
> reports by pgstattuple for the relation and the index, to see that
> these are consistent between HEAD and the patch, just in case. And
> applied it. That was the last piece.
> --
> Michael
Thanks for double-checking and pushing it.
--
Best,
Xuneng
