On 25/02/2026 1:39, Jakub Kicinski wrote:

I'd simply change the defines based on PAGE_SIZE. The allocation batch
size has nothing to do with the ring size, it's just amortizing
allocations within a single NAPI cycle.

Thanks, that sounds good to me.
Do you think a formula like this would work?

#define PP_ALLOC_CACHE_REFILL ((64 * SZ_4K) / PAGE_SIZE)
#define PP_ALLOC_CACHE_SIZE   (PP_ALLOC_CACHE_REFILL * 2)

It keeps both values constant in bytes across page sizes, ensuring a
consistent memory footprint for pool alloc-caches regardless of a
system's page size.