[linus:master] [sched] 89951fc1f8: stress-ng.enosys.ops_per_sec 4.7% improvement

[linus:master] [sched] 89951fc1f8: stress-ng.enosys.ops_per_sec 4.7% improvement

[kernel test robot]

Hello,

kernel test robot noticed a 4.7% improvement of stress-ng.enosys.ops_per_sec on:


commit: 89951fc1f8201df27366ac1eed1ddc9ee0f47729 ("sched: Reorder some fields in struct rq")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master


testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 256 threads 4 sockets INTEL(R) XEON(R) PLATINUM 8592+ (Emerald Rapids) with 256G memory
parameters:

	nr_threads: 100%
	testtime: 60s
	test: enosys
	cpufreq_governor: performance



Details are as below:
-------------------------------------------------------------------------------------------------->


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260226/202602261519.645f013d-lkp@intel.com

=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
  gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-emr-2sp1/enosys/stress-ng/60s

commit: 
  55b39b0cf1 ("sched/fair: Use cpumask_weight_and() in sched_balance_find_dst_group()")
  89951fc1f8 ("sched: Reorder some fields in struct rq")

55b39b0cf183b9c6 89951fc1f8201df27366ac1eed1 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
 8.757e+08            +4.7%  9.169e+08        stress-ng.enosys.ops
  14602390            +4.7%   15290136        stress-ng.enosys.ops_per_sec
    114078            +4.7%     119451        stress-ng.enosys.syscalls_per_second
   3314145            +4.6%    3466972        stress-ng.time.minor_page_faults
      8699            -1.4%       8575        stress-ng.time.system_time
      1649            +4.8%       1728        stress-ng.time.user_time
 1.661e+09            +5.0%  1.744e+09        stress-ng.time.voluntary_context_switches
 9.917e+08            +6.4%  1.055e+09        cpuidle..usage
  44556222            +3.9%   46298755        vmstat.system.cs
      1.05            -0.0        1.00        turbostat.C1E%
      0.56            +4.7%       0.58        turbostat.IPC
      2.20            +0.4        2.56 ±  2%  turbostat.POLL%
 7.024e+10            +4.2%   7.32e+10        perf-stat.i.branch-instructions
 5.411e+08            +3.7%  5.613e+08        perf-stat.i.branch-misses
     27.00            +3.6       30.63        perf-stat.i.cache-miss-rate%
 1.393e+09            +4.5%  1.456e+09        perf-stat.i.cache-misses
 5.185e+09            -8.1%  4.764e+09        perf-stat.i.cache-references
  46807212            +4.5%   48921785        perf-stat.i.context-switches
      1.92            -4.3%       1.83        perf-stat.i.cpi
  12283691            +5.4%   12944082        perf-stat.i.cpu-migrations
    466.69            -4.3%     446.75        perf-stat.i.cycles-between-cache-misses
 3.489e+11            +4.3%  3.639e+11        perf-stat.i.instructions
      0.54            +4.2%       0.57        perf-stat.i.ipc
    230.75            +4.7%     241.60        perf-stat.i.metric.K/sec
     26.88            +3.7       30.56        perf-stat.overall.cache-miss-rate%
      1.85            -4.2%       1.77        perf-stat.overall.cpi
    462.88            -4.3%     442.84        perf-stat.overall.cycles-between-cache-misses
      0.54            +4.3%       0.56        perf-stat.overall.ipc
  6.91e+10            +4.2%  7.201e+10        perf-stat.ps.branch-instructions
  5.32e+08            +3.7%  5.518e+08        perf-stat.ps.branch-misses
  1.37e+09            +4.5%  1.431e+09        perf-stat.ps.cache-misses
 5.098e+09            -8.1%  4.684e+09        perf-stat.ps.cache-references
  46015345            +4.5%   48090269        perf-stat.ps.context-switches
  12075501            +5.4%   12723669        perf-stat.ps.cpu-migrations
 3.432e+11            +4.3%  3.579e+11        perf-stat.ps.instructions
 2.085e+13            +4.7%  2.183e+13        perf-stat.total.instructions




Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.


-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki