Fix order of -I switches for building pg_regress.o. We need the -I switch for libpq_srcdir to come before any -I switches injected by configure. Otherwise there is a risk of pulling in a mismatched version of libpq_fe.h from someplace like /usr/local/include, if the platform has another Postgres version installed there. This evidently accounts for today's buildfarm failures on "anaconda".
In principle the -I switch for src/port/ is at similar hazard, and has been for a very long time. But the only .h files we keep there are pg_config_paths.h and pthread-win32.h, neither of which get installed on Unix-ish systems, so the odds of picking up a conflicting header seem pretty small. That doubtless accounts for the lack of prior reports. Back-patch to v17 where pg_regress acquired a build dependency on libpq_fe.h. We could go back further to fix the hazard for src/port/ in older branches, but it seems unlikely to be worth troubling over. Reported-by: Nathan Bossart <nathandboss...@gmail.com> Author: Tom Lane <t...@sss.pgh.pa.us> Discussion: https://postgr.es/m/Z-MhRzoc7t-nPUQG@nathan Backpatch-through: 17 Branch ------ REL_17_STABLE Details ------- https://git.postgresql.org/pg/commitdiff/f186f90e55b7d984be572e3628e19e6d018c7199 Modified Files -------------- src/test/regress/GNUmakefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
