Re: [PATCH bpf-next] xsk: introduce padding between ring pointers

[Daniel Borkmann <daniel@xxxxxxxxxxxxx>]

On 10/12/20 1:13 PM, Magnus Karlsson wrote:
[...]
> Nope, that was a bad idea. After measuring, this one produces worse
> performance than the original suggestion with padding in between all
> members. Cannot explain why at the moment, but the numbers are
> convincing and above noise level for sure. So let us keep this one:
>
> u32 producer ____cacheline_aligned_in_smp;
> ____cacheline_padding_in_smp;
> u32 consumer ____cacheline_aligned_in_smp;
> ____cacheline_padding_in_smp;
> u32 flags ____cacheline_aligned_in_smp;
> ____cacheline_padding_in_smp;
>
> > > Do you want to submit a patch, or shall I do it? I like your
> > > ____cacheline_padding_in_smp better than my explicit "padN" member.

Ok, feel free to go for it.

Thanks,
Daniel