Greeting, FYI, we noticed a -15.4% regression of will-it-scale.per_thread_ops due to commit: commit: fa4e6b1ad57df096ddcf091fece3d9babfe90048 ("[patch 100/212] memcg: enable accounting for pollfd and select bits arrays") url: https://github.com/0day-ci/linux/commits/Andrew-Morton/ia64-fix-typo-in-a-comment/20210903-065028 in testcase: will-it-scale on test machine: 144 threads 4 sockets Intel(R) Xeon(R) CPU E7-8890 v3 @ 2.50GHz with 512G memory with following parameters: nr_task: 50% mode: thread test: poll2 cpufreq_governor: performance ucode: 0x16 test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two. test-url: https://github.com/antonblanchard/will-it-scale If you fix the issue, kindly add following tag Reported-by: kernel test robot Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run bin/lkp run generated-yaml-file ========================================================================================= compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode: gcc-9/performance/x86_64-rhel-8.3/thread/50%/debian-10.4-x86_64-20200603.cgz/lkp-hsw-4ex1/poll2/will-it-scale/0x16 commit: ddae5955e0 ("memcg: enable accounting for mnt_cache entries") fa4e6b1ad5 ("memcg: enable accounting for pollfd and select bits arrays") ddae5955e09fc376 fa4e6b1ad57df096ddcf091fece ---------------- --------------------------- %stddev %change %stddev \ | \ 20037899 -15.4% 16955694 ± 3% will-it-scale.72.threads 278303 -15.4% 235495 ± 3% will-it-scale.per_thread_ops 20037899 -15.4% 16955694 ± 3% will-it-scale.workload 1583653 ± 2% +47.6% 2338047 ± 8% cpuidle..usage 0.01 ± 2% +0.0 0.02 ± 8% mpstat.cpu.all.soft% 2568 ±188% +336.5% 11212 ± 44% numa-vmstat.node0.numa_other 76315 +3.5% 78953 vmstat.system.in 2953 ± 15% +39.4% 4118 ± 6% slabinfo.kmalloc-cg-1k.active_objs 2953 ± 15% +39.4% 4118 ± 6% slabinfo.kmalloc-cg-1k.num_objs 50719 ± 3% -21.6% 39775 ± 10% turbostat.C1E 1403174 +55.9% 2187482 ± 8% turbostat.C6 645.68 -2.6% 628.84 turbostat.PkgWatt 61545 ±178% +175.6% 169623 ± 78% interrupts.CPU110.LOC:Local_timer_interrupts 8916 ±147% +1620.7% 153419 ± 96% interrupts.CPU134.LOC:Local_timer_interrupts 108655 ±124% +105.1% 222831 ± 49% interrupts.CPU23.LOC:Local_timer_interrupts 611.50 ± 62% +65.4% 1011 ± 63% interrupts.CPU25.CAL:Function_call_interrupts 56545 ±189% +205.4% 172674 ± 74% interrupts.CPU25.LOC:Local_timer_interrupts 1652 ± 13% -48.5% 850.67 ± 63% interrupts.CPU52.CAL:Function_call_interrupts 346.83 +72.7% 598.83 ± 57% interrupts.CPU94.CAL:Function_call_interrupts 1279 ± 8% +83.7% 2350 ± 31% interrupts.RES:Rescheduling_interrupts 10413 ± 9% -15.1% 8842 ± 11% softirqs.CPU0.RCU 10111 ± 18% -34.4% 6636 ± 19% softirqs.CPU10.RCU 9749 ± 8% -35.8% 6263 ± 32% softirqs.CPU22.RCU 10009 ± 7% -59.3% 4069 ± 69% softirqs.CPU30.RCU 61.83 ± 38% +3560.9% 2263 ±210% softirqs.CPU74.TIMER 754991 ± 2% -23.4% 578181 ± 5% softirqs.RCU 727783 +16.3% 846764 ± 3% softirqs.SCHED 40315 +29.1% 52046 ± 4% softirqs.TIMER 5492 +14.7% 6298 ± 4% syscalls.sys_mmap.med 1.083e+08 ± 6% +1.3e+08 2.414e+08 ± 12% syscalls.sys_mmap.noise.100% 1.806e+08 ± 3% +1.3e+08 3.115e+08 ± 9% syscalls.sys_mmap.noise.2% 1.715e+08 ± 3% +1.3e+08 2.981e+08 ± 10% syscalls.sys_mmap.noise.25% 1.801e+08 ± 3% +1.3e+08 3.111e+08 ± 9% syscalls.sys_mmap.noise.5% 1.4e+08 ± 4% +1.3e+08 2.737e+08 ± 11% syscalls.sys_mmap.noise.50% 1.181e+08 ± 6% +1.4e+08 2.571e+08 ± 12% syscalls.sys_mmap.noise.75% 5921 +11.7% 6612 ± 3% syscalls.sys_openat.med 5133257 ± 10% +4.5e+08 4.563e+08 ± 38% syscalls.sys_poll.noise.100% 7282972 ± 31% +4.5e+08 4.599e+08 ± 37% syscalls.sys_poll.noise.2% 6705445 ± 30% +4.5e+08 4.593e+08 ± 37% syscalls.sys_poll.noise.25% 6828883 ± 32% +4.5e+08 4.596e+08 ± 37% syscalls.sys_poll.noise.5% 6600419 ± 29% +4.5e+08 4.592e+08 ± 37% syscalls.sys_poll.noise.50% 5686935 ± 13% +4.5e+08 4.585e+08 ± 37% syscalls.sys_poll.noise.75% 36152 ± 26% +56.4% 56553 ± 12% syscalls.sys_write.max 85796438 ± 15% +5.5e+07 1.407e+08 ± 20% syscalls.sys_write.noise.100% 1.024e+08 ± 14% +4.3e+07 1.451e+08 ± 19% syscalls.sys_write.noise.75% will-it-scale.per_thread_ops 300000 +------------------------------------------------------------------+ | ++.+.+.+.++.+.+.+.+.++.+.+.+.++.+.+.+.++.+.+.+.+.++.+.+.+.++.+.| 250000 |-+ : O O O | | O : OO O O O O O OO O O O OO | | :O O O O O O O O O O O O | 200000 |:+: O O | |: : O | 150000 |:+: | |: : | 100000 |:+: | |: : | | : | 50000 |-: | | : | 0 +------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/lkp@lists.01.org Intel Corporation Thanks, Oliver Sang