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
inthis function [-Wmaybe-uninitialized]
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
