On Tue, Sep 05, 2017 at 10:29:01AM -0700, Stephen Hemminger wrote:
> On Tue, 5 Sep 2017 16:18:51 +0530
> Pavan Nikhilesh <pbhagavat...@caviumnetworks.com> wrote:
>
> > +/**
> > + * Unsigned 32-bit divisor structure.
> > + */
> > +struct rte_reciprocal_u32 {
> > uint32_t m;
> > uint8_t sh1, sh2;
> > -};
> > +} __rte_cache_aligned;
> > +
> > +/**
> > + * Unsigned 64-bit divisor structure.
> > + */
> > +struct rte_reciprocal_u64 {
> > + uint64_t m;
> > + uint8_t sh1;
> > +} __rte_cache_aligned;
>
> I understand you want to squeeze every cycle out but it is not
> required that each of these structures always be cache aligned.
>
> They maybe embedded in other structures and having the structure
> padded so that these elements are cache aligned would take up
> more space and make cache performance worse.
>
> Better off to not put attributes on the structure definitions, and instead
> let usages of this feature align where appropriate.
>
Agreed, will remove cache alignment in the next version (v6).
Thanks,
Pavan.
