On Tue, Aug 11, 2026, 20:26 Alexandre Felipe <[email protected]>
wrote:

>
> On Tue, Aug 11, 2026 at 7:47 PM Andres Freund <[email protected]> wrote:
>
>> You absolutely, definitely, never, ever ever may hold a spinlock over
>> something even remotely as complicated like an lwlock or a hashtable
>> delete. NEVER.
>>
>
> So, the problem of spin locks there is that the contenders will spend
> CPU on this loop right?
> while (old_buf_state & BM_LOCKED)
> {
>   perform_spin_delay(&delayStatus);
>   old_buf_state = pg_atomic_read_u64(&desc->state);
> }
> And since there is a perform_spin_delay there I assume it is not 100%
> I imagined this was tuned to use maybe 1% CPU.
>
> If not, can't we simply use an exponentially increasing sleep until we get
> to say 1ms and that uses virtually 0 CPU while waiting.
>
>
>> And without that the patch is completely unsafe.
>>
>
> And with that is it safe? Pretending LockBufHdr not to be a spin-lock.
>
> Thank you for your quick response Andres
>
> Regards,
> Alexandre
>

Reply via email to