Re: pgsql: Fix up misuse of "volatile" in contrib/xml2.

From: Michael Paquier <michael(at)paquier(dot)xyz>
To: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Cc: pgsql-committers(at)lists(dot)postgresql(dot)org
Subject: Re: pgsql: Fix up misuse of "volatile" in contrib/xml2.
Date: 2025-07-08 23:32:20
Message-ID: aG2qhGodemZfrxcn@paquier.xyz
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-committers

On Tue, Jul 08, 2025 at 09:00:39PM +0000, Tom Lane wrote:
> Fix up misuse of "volatile" in contrib/xml2.
>
> Also fix a number of places where variables that are assigned to
> within a PG_TRY and then used after it were not initialized or
> not marked as volatile. (A few buildfarm members were issuing
> "may be used uninitialized" warnings about some of these variables,
> which is what drew my attention to this area.) In most cases
> these variables were being set as the last step within the PG_TRY
> block, which might mean that we could get away without the "volatile"
> marking. But doing that seems unsafe and is definitely not per our
> coding conventions.
>
> These problems seem to have come in with 732061150, so no need
> for back-patch.

Oops, thanks. I was not aware of these reports, and the buildfarm was
not showing any red, the CI looked fine and my machine did not
complain with a rather new gcc. What were the buildfarm members
impacted? Did these use a switch and/or a specific compiler that
helped in detecting these problems?
--
Michael

In response to

Responses

Browse pgsql-committers by date

  From Date Subject
Next Message Michael Paquier 2025-07-09 03:46:45 pgsql: libpq: Remove PQservice()
Previous Message Tom Lane 2025-07-08 21:00:39 pgsql: Fix up misuse of "volatile" in contrib/xml2.