On 28 November 2016 at 18:02, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Fri, 25 Nov, at 04:34:31PM, Vincent Guittot wrote: >> This patchset was originally 1 patch but a perf regression happened during >> the rebase. >> The patch 01 fixes the perf regression discovered in tip/sched/core during >> the >> rebase. >> The patch 02 is the rebase of the patch that fixes the regression raised by >> Matt Fleming . >> >>  https://lkml.org/lkml/2016/10/18/206 >> >> Vincent Guittot (2): >> sched: fix find_idlest_group for fork >> sched: use load_avg for selecting idlest group >> >> kernel/sched/fair.c | 54 >> +++++++++++++++++++++++++++++++++++++++++++---------- >> 1 file changed, 44 insertions(+), 10 deletions(-) > > FYI, I'm running both of these patches through the SUSE performance > testing grid right now. I'll let you know as soon as I have results > (should be in the next few days).