[linux-next:master] [vmsplice] e2c0b23680: stress-ng.vm-splice.vm-splice_calls_per_sec 10.2% regression

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

Hello,

kernel test robot noticed a 10.2% regression of stress-ng.vm-splice.vm-splice_calls_per_sec on:


commit: e2c0b2368081bef7d1f6758cc9e7edde8521237c ("vmsplice: make vmsplice a trivial wrapper for preadv2/pwritev2")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master

[still regression on linux-next/master 6e845bcb78c95af935094040bd4edc3c2b6dd784]

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: vm-splice
	cpufreq_governor: performance



If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202606111018.cc992614-lkp@intel.com


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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260611/202606111018.cc992614-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/vm-splice/stress-ng/60s

commit: 
  a9f7db50ed ("tee: fs/splice.c: remove unused parameter "flags" from "link_pipe"")
  e2c0b23680 ("vmsplice: make vmsplice a trivial wrapper for preadv2/pwritev2")

a9f7db50ed2fff96 e2c0b2368081bef7d1f6758cc9e 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      2122            -2.7%       2064        stress-ng.time.user_time
  13281641           -10.2%   11928183        stress-ng.vm-splice.MB_per_sec_vm-splice_rate
 1.183e+10            -4.8%  1.126e+10        stress-ng.vm-splice.ops
 1.972e+08            -4.8%  1.878e+08        stress-ng.vm-splice.ops_per_sec
   3.4e+09           -10.2%  3.054e+09        stress-ng.vm-splice.vm-splice_calls_per_sec
      1397 ±  7%     -21.1%       1103 ± 10%  sched_debug.cfs_rq:/.runnable_avg.max
      1.28           -22.1%       1.00 ± 44%  turbostat.IPC
     74419            +3.9%      77317        proc-vmstat.nr_shmem
    633806            +1.1%     640727        proc-vmstat.numa_local
    331878 ± 13%     -30.3%     231247 ± 18%  numa-numastat.node0.local_node
     37379 ± 76%    +241.6%     127705 ± 50%  numa-numastat.node0.other_node
    298829 ± 14%     +36.1%     406730 ± 10%  numa-numastat.node1.local_node
    162072 ± 17%     -55.7%      71783 ± 89%  numa-numastat.node1.other_node
    332129 ± 13%     -30.4%     231269 ± 18%  numa-vmstat.node0.numa_local
     37379 ± 76%    +241.6%     127705 ± 50%  numa-vmstat.node0.numa_other
    298881 ± 14%     +36.1%     406833 ± 10%  numa-vmstat.node1.numa_local
    162072 ± 17%     -55.7%      71783 ± 89%  numa-vmstat.node1.numa_other




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