On Mon, Nov 21, 2022 at 07:36:21PM -0700, Song Liu wrote: > On Mon, Nov 21, 2022 at 1:20 PM Luis Chamberlain <mcgrof@xxxxxxxxxx> wrote: > > > > On Mon, Nov 21, 2022 at 12:12:49PM -0800, Luis Chamberlain wrote: > > > On Thu, Nov 17, 2022 at 12:23:16PM -0800, Song Liu wrote: > > > > Based on our experiments [5], we measured ~0.6% performance improvement > > > > from bpf_prog_pack. This patchset further boosts the improvement to ~0.8%. > > > > > > I'd prefer we leave out arbitrary performance data, as it does not help much. > > > > I'd like to clarify what I mean by this, as Linus has suggested before, you are > > missing the opportunity to present "actual numbers on real loads. (not > > some artificial benchmark)" > > > > [0] https://lkml.kernel.org/r/CAHk-=wiF1KnM1_paB3jCONR9Mh1D_RCsnXKBau1K7XLG-mwwTQ@xxxxxxxxxxxxxx > > Unless I made some serious mistakes, Linus' concern with performance was > addressed by the exact performance results above. [5] > > [5] https://lore.kernel.org/bpf/20220707223546.4124919-1-song@xxxxxxxxxx/ AFAICT no, that still is all still artificial. Luis
