MIME-Version: 1.0
References: <E1ty2Zm-001NPZ-2Z@gemulon.postgresql.org>
In-Reply-To: <E1ty2Zm-001NPZ-2Z@gemulon.postgresql.org>
From: Amit Kapila <amit.kapila16@gmail.com>
Date: Fri, 28 Mar 2025 17:20:53 +0530
Message-ID: 
 <CAA4eK1J0ZYk5500+pJs9MjhwEMphCrEXuhmgkitjn+bTN7vGZQ@mail.gmail.com>
Subject: Re: pgsql: Stablize tests added in 3abe9dc188.
To: Amit Kapila <akapila@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/CAA4eK1J0ZYk5500%2BpJs9MjhwEMphCrEXuhmgkitjn%2BbTN7vGZQ%40mail.gmail.com>
Precedence: bulk

On Fri, Mar 28, 2025 at 11:18=E2=80=AFAM Amit Kapila <akapila@postgresql.or=
g> wrote:
>
> Stablize tests added in 3abe9dc188.
>
> The problem is that after the ALTER SUBSCRIPTION tap_sub SET PUBLICATION
> command, we didn't wait for the new walsender to start on the publisher.
> Immediately after ALTER, we performed Insert and expected it to replicate=
.
> However, the replication could start from a point after the INSERT locati=
on,
> and as the subscription isn't copying initial data, we could miss such an
> Insert.
>
> The fix is to wait for connection to be established between publisher and
> subscriber before starting DML operations that are expected to replicate.
>
> As per CI.
>
> Reported-by: Andres Freund <andres@anarazel.de>
> Author: Hayato Kuroda <kuroda.hayato@fujitsu.com>
> Discussion: https://postgr.es/m/CALDaNm2ms1deM5EYNLFEfESv_Kw=3DY4AiTB0LP=
=3DqGS-UpFwGbPg@mail.gmail.com
>

By mistake, I added a wrong discussion link. The correct one is
https://postgr.es/m/ksxbayuk5hgqdsryjxqkbnjyvk6amd2jf5tui565ex6vazglls@jva4=
njirno4u

--=20
With Regards,
Amit Kapila.