Hi, On 2022-10-11 10:21:17 +0700, John Naylor wrote: > On Tue, Oct 11, 2022 at 5:31 AM David Rowley <dgrowle...@gmail.com> wrote: > > > > The proposed patches in [1] do aim to make additional usages of the > > slab allocator, and I have a feeling that we'll want to fix the > > performance of slab.c before those. Perhaps the Asserts are a better > > option if we're to get the proposed radix tree implementation. > > Going by [1], that use case is not actually a natural fit for slab because > of memory fragmentation. > > [1] > https://www.postgresql.org/message-id/20220704220038.at2ane5xkymzzssb%40awork3.anarazel.de
Not so sure about that - IIRC I made one slab for each different size class, which seemed to work well and suit slab well? Greetings, Andres Freund