Re: pgsql: Move cancel key generation to after forking the backend

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(dot)linnakangas(at)iki(dot)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.

--
Heikki Linnakangas
Neon (https://neon.tech)