MIME-Version: 1.0
References: <E1tzmW2-002COZ-2W@gemulon.postgresql.org>
 <CA+HiwqFT0fPPoYBr0iUFWNB-Og7bEXB9hB=6ogk_qD9=OM8Vbw@mail.gmail.com>
 <CA+HiwqG=_5tSA-FWJ_Fzs2xWkxOUxFhzDs2KaDCUDHQOKe41ew@mail.gmail.com>
In-Reply-To: 
 <CA+HiwqG=_5tSA-FWJ_Fzs2xWkxOUxFhzDs2KaDCUDHQOKe41ew@mail.gmail.com>
From: Amit Langote <amitlangote09@gmail.com>
Date: Mon, 30 Mar 2026 10:32:57 +0900
Message-ID: 
 <CA+HiwqGtMJWAs398ahifM0LXAVrwxcx6UYSjeo-a9Pm0Lxh6Fg@mail.gmail.com>
Subject: Re: pgsql: Doc: add information about partition locking
To: David Rowley <drowley@postgresql.org>
Cc: pgsql-committers@lists.postgresql.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Archived-At: 
 <https://www.postgresql.org/message-id/CA%2BHiwqGtMJWAs398ahifM0LXAVrwxcx6UYSjeo-a9Pm0Lxh6Fg%40mail.gmail.com>
Precedence: bulk

On Fri, Mar 27, 2026 at 4:15=E2=80=AFPM Amit Langote <amitlangote09@gmail.c=
om> wrote:
> On Fri, Mar 27, 2026 at 4:09=E2=80=AFPM Amit Langote <amitlangote09@gmail=
.com> wrote:
> > Hi David,
> >
> > On Wed, Apr 2, 2025 at 10:03=E2=80=AFAM David Rowley <drowley@postgresq=
l.org> wrote:
> > >
> > > Doc: add information about partition locking
> > >
> > > The documentation around locking of partitions for the executor start=
up
> > > phase of run-time partition pruning wasn't clear about which partitio=
ns
> > > were being locked.  Fix that.
> > >
> > > Reviewed-by: Tender Wang <tndrwang@gmail.com>
> > > Discussion: https://postgr.es/m/CAApHDvp738G75HfkKcfXaf3a8s%3D6mmtOLh=
46tMD0D2hAo1UCzA%40mail.gmail.com
> > > Backpatch-through: 13
> > >
> > > Branch
> > > ------
> > > master
> > >
> > > Details
> > > -------
> > > https://git.postgresql.org/pg/commitdiff/121d774caea4c93c8b36fb20a17e=
f774e60894d6
> >
> > -       <command>EXPLAIN</command> output.
> > +       <command>EXPLAIN</command> output.  The query planner obtains l=
ocks for
> > +       all partitions which are part of the plan.  However, when the e=
xecutor
> > +       uses a cached plan, locks are only obtained on the partitions w=
hich
> > +       remain after partition pruning done during the initialization p=
hase of
> > +       execution, i.e., the ones shown in the <command>EXPLAIN</comman=
d>
> > +       output and not the ones referred to by the
> > +       <quote>Subplans Removed</quote> property.
> >        </para>
> >       </listitem>
> >
> > This text was correct when committed, but became incorrect after I
> > reverted 525392d57 in May 2025. Sorry for not catching it sooner.
> >
> > I think we should change the text in both master and REL_18_STABLE to
> > match what you added in the older branches.  I can change it back to
> > this when we get pruning-aware locking again.
>
> Will apply the attached.

Pushed.

--=20
Thanks, Amit Langote