On Fri, 25 Feb 2022 at 01:20, Kyotaro Horiguchi wrote:
> Yura Sokolov is proposing a patch to separte the two partition locks.
>
> https://www.postgresql.org/message-id/1edbb61981fe1d99c3f20e3d56d6c88999f4227c.camel%40postgrespro.ru
>
> And it seems to me viable for me and a benchmarking in the t
At Fri, 25 Feb 2022 10:20:25 +0900 (JST), Kyotaro Horiguchi
wrote in
> (I added Yura, as the author of a related patch)
>
> At Thu, 24 Feb 2022 12:58:23 +, Simon Riggs
> wrote in
> > Thinking about poor performance in the case where the data fits in
> > RAM, but the working set is too bi
(I added Yura, as the author of a related patch)
At Thu, 24 Feb 2022 12:58:23 +, Simon Riggs
wrote in
> Thinking about poor performance in the case where the data fits in
> RAM, but the working set is too big for shared_buffers, I notice a
> couple of things that seem bad in BufMgr, but don
Thinking about poor performance in the case where the data fits in
RAM, but the working set is too big for shared_buffers, I notice a
couple of things that seem bad in BufMgr, but don't understand why
they are like that.
1. If we need to allocate a buffer to a new block we do this in one
step, whi
