> not sure why it’s several multiples of a cache line - maybe to help the prefetcher or to minimize cache line bouncing?
The AMD64 cache line is only 64 bytes, that would make for very low branching factors given interior nodes need a pointer per child, plus key, plus record pointer if b-tree (as opposed to b+tree).
To be clear, I was examining only leaf nodes. I’m not sure if interior nodes use the same logic. Still, ABSEIL generally uses a larger branching factor than Rust for some undocumented reason.
The AMD64 cache line is only 64 bytes, that would make for very low branching factors given interior nodes need a pointer per child, plus key, plus record pointer if b-tree (as opposed to b+tree).