Jacob Champion <jacob.champ...@enterprisedb.com> writes:
> On Wed, Jul 9, 2025 at 8:55 PM Michael Paquier <mich...@paquier.xyz> wrote:
>> On Wed, Jul 09, 2025 at 11:49:55AM -0400, Tom Lane wrote:
>>> Not sure. Yesterday I saw such warnings from arowana,
>>> boa, dhole, rhinoceros, and shelduck, eg
>> They are all using some gcc 4.X flavor, most with -O2 but not all.
> I think I remember that GCC has had historical problems with tuning
> the false-positive:false-negative rates for `-Wmaybe-uninitialized`.
> It's not super surprising to me that later versions aren't always
> better at seeing specific problems, especially if users were
> complaining that an earlier version was too sensitive...
Yeah. Worth noting also is that even the machines that were
complaining were warning about just a subset of the xpath.c functions
that had this problem :-(. So there's definitely some heuristics
involved, which seems odd for what feels like it ought to be a
pretty black-and-white condition.
regards, tom lane
