Re: [PATCH bpf-next v4 0/6] execmem_alloc for BPF programs

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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



[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux