lkml.org 
[lkml]   [2020]   [Dec]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    Date
    SubjectRe: [iov_iter] 9bd0e337c6: will-it-scale.per_process_ops -4.8% regression
    On Wed, Dec 2, 2020 at 10:31 PM kernel test robot <oliver.sang@intel.com> wrote:
    >
    > FYI, we noticed a -4.8% regression of will-it-scale.per_process_ops due to commit:

    Ok, I guess that's bigger than expected, but the profile data does
    show how bad the indirect branches are.

    There's both a "direct" cost of them:

    > 0.55 ą 14% +0.3 0.87 ą 15% perf-profile.children.cycles-pp.__x86_retpoline_rax
    > 0.12 ą 14% +0.1 0.19 ą 14% perf-profile.self.cycles-pp.__x86_indirect_thunk_rax
    > 0.43 ą 14% +0.3 0.68 ą 15% perf-profile.self.cycles-pp.__x86_retpoline_rax

    The actual retpoline profile costs themselves do not add up to 4%, but
    I think that's because the indirect costs are higher, because the
    branch mis-predicts will basically make everything run slower for a
    while as the OoO engine needs to restart.

    So the global cost then shows up in CPU and branch miss stats, where
    the IPC goes down (which is the same thing as saying that CPI goes
    up):

    > 1.741e+08 +42.3% 2.476e+08 perf-stat.i.branch-misses
    > 0.74 -3.9% 0.71 perf-stat.overall.ipc
    > 1.35 +4.1% 1.41 perf-stat.overall.cpi

    which is why it ends up being so costly even if the retpoline overhead
    itself is "only" just under 1%.

    Linus

    \
     
     \ /
      Last update: 2020-12-03 18:48    [W:8.853 / U:0.032 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site