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 > > > > 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-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. > > They are all using some gcc 4.X flavor, most with -O2 but not all. > > And -Wmaybe-uninitialized is included in my default switches with a > gcc 14, and there is nothing with several levels of optimizations > applied, up to -O3. :(
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... --Jacob
