On 2021-Nov-05, Daniel Gustafsson wrote:
> 2716: fix spinlock contention in LogwrtResult
> =============================================
> This addresses a bottleneck which definitely seems like one we want to fix, I
> don't have a hard time imagining it impacting other production usecases then
> the reported one. The goalposts moved early in the thread, and while there has
> been work on it the patch has stalled on Andres' review which raised some
> concerns. Are you still pursuing this Alvaro?
I am, but not in the immediate future. I am very absorbed by trying to
make MERGE work again for resubmission, so I haven't had time to invest
in these other patches. I hope I'll be able to return with a new
version of this for the January commitfest.
--
Álvaro Herrera PostgreSQL Developer — https://www.EnterpriseDB.com/
"On the other flipper, one wrong move and we're Fatal Exceptions"
(T.U.X.: Term Unit X - http://www.thelinuxreview.com/TUX/)