On 03/23/2018 02:53 PM, Mathias Kresin wrote: > As long as nobody proves that there is a real performance gain, I don't > see a reason to backport the datastruct debloat.
Agreed, it will also make it a tad harder to merge stable kernels with these changes applied. Rosen, if you are willing to start working on improving cache footprint, then really start using tools like perf, pahole and whatnot to select what the lowest hanging fruit is... -- Florian _______________________________________________ Lede-dev mailing list Lede-dev@lists.infradead.org http://lists.infradead.org/mailman/listinfo/lede-dev
