From: Tom Lane <tgl@sss.pgh.pa.us>
To: Michael Paquier <michael@paquier.xyz>
cc: pgsql-committers@lists.postgresql.org
Subject: Re: pgsql: Fix up misuse of "volatile" in contrib/xml2.
In-reply-to: <aG2qhGodemZfrxcn@paquier.xyz>
References: <E1uZFQd-005Je7-1t@gemulon.postgresql.org>
 <aG2qhGodemZfrxcn@paquier.xyz>
Comments: In-reply-to Michael Paquier <michael@paquier.xyz>
	message dated "Wed, 09 Jul 2025 08:32:20 +0900"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <1141877.1752076195.1@sss.pgh.pa.us>
Content-Transfer-Encoding: quoted-printable
Date: Wed, 09 Jul 2025 11:49:55 -0400
Message-ID: <1141878.1752076195@sss.pgh.pa.us>
Archived-At: 
 <https://www.postgresql.org/message-id/1141878.1752076195%40sss.pgh.pa.us>
Precedence: bulk

Michael Paquier <michael@paquier.xyz> writes:
> On Tue, Jul 08, 2025 at 09:00:39PM +0000, Tom Lane wrote:
>> 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.)

> 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?

Not sure.  Yesterday I saw such warnings from arowana,
boa, dhole, rhinoceros, and shelduck, eg

 arowana       | 2025-07-08 04:54:18 | xpath.c:274:6: warning: 'workspace'=
 may be used uninitialized in this function [-Wmaybe-uninitialized]
 arowana       | 2025-07-08 04:54:18 | xpath.c:319:6: warning: 'workspace'=
 may be used uninitialized in this function [-Wmaybe-uninitialized]
 arowana       | 2025-07-08 04:54:18 | xpath.c:374:6: warning: 'workspace'=
 may be used uninitialized in this function [-Wmaybe-uninitialized]
 arowana       | 2025-07-08 04:54:18 | ../../src/include/postgres.h:329:2:=
 warning: 'result' may be used uninitialized in this function [-Wmaybe-uni=
nitialized]

Didn't look to try to figure out what the common factor
among these machines is, but I think all of them are somewhat
dated, which is depressing.  You'd hope that newer compilers
are more likely to find such issues, not less likely.

			regards, tom lane