On 29/07/2024 17:30, Heikki Linnakangas wrote:
On 29/07/2024 16:25, Heikki Linnakangas wrote:
On 29/07/2024 16:23, Daniel Gustafsson wrote:
On 29 Jul 2024, at 15:18, Heikki Linnakangas <heikki.linnakan...@iki.fi> wrote:
Move cancel key generation to after forking the backend
longfin seems a tad sad about this one:
procsignal.c:87:3: error: redefinition of typedef 'ProcSignalHeader' is a C11
feature [-Werror,-Wtypedef-redefinition]
} ProcSignalHeader;
^
../../../../src/include/storage/procsignal.h:77:33: note: previous definition
is here
typedef struct ProcSignalHeader ProcSignalHeader;
^
1 error generated.
make[4]: *** [procsignal.o] Error 1
Yep, thanks, just noticed and fixed it myself. I should add that to the
list of compiler options I use...
The --disable-spinlocks animals are still failing, however. Weird. I can
reproduce it locally, and started to debug but I have no clue what's
wrong. I'll keep debugging, but I'm all ears if anyone has ideas.
Found & fixed. I released the spinlock twice in EmitProcSignalBarrier. Oops.
I'm a little surprised there isn't an assertion for that. Would be
useful. This might have gone unnoticed for a long time if not for the
--disable-spinlocks implementation, and we've been talking about
removing that.
--
Heikki Linnakangas
Neon (https://neon.tech)
