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

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(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.

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)