[tip:core/rseq] [rseq] 9f6ffd4ceb: stress-ng.timer.ops_per_sec 5.5% improvement

[kernel test robot <oliver.sang@intel.com>]

Hello,

kernel test robot noticed a 5.5% improvement of stress-ng.timer.ops_per_sec on:


commit: 9f6ffd4cebda86841700775de3213f22bb0ea22d ("rseq: Separate the signal delivery path")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git core/rseq


testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 192 threads 2 sockets Intel(R) Xeon(R) 6740E  CPU @ 2.4GHz (Sierra Forest) with 256G memory
parameters:

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



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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20251111/202511111524.d2e6b63d-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-srf-2sp3/timer/stress-ng/60s

commit: 
  0f085b4188 ("rseq: Provide and use rseq_set_ids()")
  9f6ffd4ceb ("rseq: Separate the signal delivery path")

0f085b41880e3140 9f6ffd4cebda86841700775de32 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
    147208 ±  3%     +15.8%     170452 ±  4%  meminfo.Mapped
     50.63           +34.3       84.92        mpstat.cpu.all.sys%
     36.46           -34.8        1.67 ± 13%  mpstat.cpu.all.usr%
     14932 ± 35%     +67.9%      25072 ± 15%  numa-vmstat.node0.nr_slab_reclaimable
     22290 ± 24%     -45.5%      12149 ± 32%  numa-vmstat.node1.nr_slab_reclaimable
     10.17 ± 44%    +375.4%      48.33 ±  9%  perf-c2c.DRAM.local
    162.67 ± 31%    +558.7%       1071 ± 12%  perf-c2c.DRAM.remote
    141.00 ± 29%    +578.6%     956.83 ± 12%  perf-c2c.HITM.local
    154.50 ± 32%    +476.2%     890.17 ± 13%  perf-c2c.HITM.remote
     37215 ±  3%     +15.2%      42879 ±  5%  proc-vmstat.nr_mapped
     66948            +8.7%      72780        proc-vmstat.nr_shmem
    818668            +2.7%     840430        proc-vmstat.numa_hit
    620609            +3.5%     642526        proc-vmstat.numa_local
     59728 ± 35%     +67.9%     100287 ± 15%  numa-meminfo.node0.KReclaimable
     59728 ± 35%     +67.9%     100287 ± 15%  numa-meminfo.node0.SReclaimable
    304140 ±  8%     +16.4%     353946 ±  7%  numa-meminfo.node0.Slab
     89141 ± 24%     -45.5%      48551 ± 32%  numa-meminfo.node1.KReclaimable
     89141 ± 24%     -45.5%      48551 ± 32%  numa-meminfo.node1.SReclaimable
     47698 ±  2%     +16.6%      55634        stress-ng.time.involuntary_context_switches
      5931           +67.8%       9952        stress-ng.time.system_time
      4259           -95.8%     179.67 ± 14%  stress-ng.time.user_time
 5.054e+09            +5.5%  5.335e+09        stress-ng.timer.ops
  84269084            +5.5%   88943393        stress-ng.timer.ops_per_sec
      0.05 ±  4%     -14.9%       0.04 ±  2%  perf-sched.sch_delay.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
      0.05 ±  4%     -14.9%       0.04 ±  2%  perf-sched.total_sch_delay.average.ms
    159.90 ±  2%     -15.6%     135.02        perf-sched.total_wait_and_delay.average.ms
      7663 ±  2%     +18.3%       9069 ±  2%  perf-sched.total_wait_and_delay.count.ms
    159.86 ±  2%     -15.6%     134.98        perf-sched.total_wait_time.average.ms
    159.90 ±  2%     -15.6%     135.02        perf-sched.wait_and_delay.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
      7663 ±  2%     +18.3%       9069 ±  2%  perf-sched.wait_and_delay.count.[unknown].[unknown].[unknown].[unknown].[unknown]
    159.86 ±  2%     -15.6%     134.98        perf-sched.wait_time.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
  6.55e+10            +3.2%  6.757e+10        perf-stat.i.branch-instructions
  92397918            +6.4%   98318472 ±  2%  perf-stat.i.branch-misses
   6980157            +3.0%    7189854        perf-stat.i.cache-references
      1977 ±  2%     +12.2%       2219        perf-stat.i.context-switches
      1.76            -2.6%       1.71        perf-stat.i.cpi
    301.54            -2.7%     293.44        perf-stat.i.cpu-migrations
 3.435e+11            +2.6%  3.526e+11        perf-stat.i.instructions
      0.57            +2.7%       0.58        perf-stat.i.ipc
      1.76            -2.6%       1.71        perf-stat.overall.cpi
      0.57            +2.7%       0.58        perf-stat.overall.ipc
 6.443e+10            +3.2%  6.647e+10        perf-stat.ps.branch-instructions
  90890135            +6.4%   96717754 ±  2%  perf-stat.ps.branch-misses
   6864424            +3.0%    7069354        perf-stat.ps.cache-references
      1945 ±  2%     +12.2%       2183        perf-stat.ps.context-switches
    296.64            -2.7%     288.77        perf-stat.ps.cpu-migrations
 3.379e+11            +2.7%  3.469e+11        perf-stat.ps.instructions
 2.077e+13            +2.7%  2.133e+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