name       old time/op    new time/op    delta
Iterate-4    17.4µs ± 0%    13.1µs ± 1%  -24.65%  (p=0.000 n=10+9)

name       old alloc/op   new alloc/op   delta
Iterate-4    17.2kB ± 0%    10.6kB ± 0%  -38.29%  (p=0.000 n=10+10)

name       old allocs/op  new allocs/op  delta
Iterate-4       164 ± 0%        24 ± 0%  -85.37%  (p=0.000 n=10+10)

only -9%

name       old time/op  new time/op  delta
Iterate-4  17.4µs ± 0%  17.5µs ± 0%    ~     (p=0.234 n=10+9)
FsTail-4    278µs ± 1%   252µs ± 0%  -9.12%  (p=0.000 n=10+10)

because there are many IO direction misses.