Greeting, FYI, we noticed a 36.5% improvement of aim7.jobs-per-min due to commit: commit: 942491c9e6d631c012f3c4ea8e7777b0b02edeab ("xfs: fix AIM7 regression") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master in testcase: aim7 on test machine: 40 threads Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz with 384G memory with following parameters: disk: 4BRD_12G md: RAID0 fs: xfs test: disk_rd load: 9000 cpufreq_governor: performance test-description: AIM7 is a traditional UNIX system level benchmark suite which is used to test and measure the performance of multiuser system. test-url: https://sourceforge.net/projects/aimbench/files/aim-suite7/ 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 run job.yaml testcase/path_params/tbox_group/run: aim7/4BRD_12G-RAID0-xfs-disk_rd-9000-performance/lkp-ivb-ep01 785545c8982604fe 942491c9e6d631c012f3c4ea8e ---------------- -------------------------- %stddev change %stddev \ | \ 351806 36% 480185 aim7.jobs-per-min 435880 447433 aim7.time.minor_page_faults 89458 ± 6% -18% 73786 ± 8% aim7.time.voluntary_context_switches 154 -27% 113 aim7.time.elapsed_time 154 -27% 113 aim7.time.elapsed_time.max 5698 -29% 4063 aim7.time.system_time 1052496 -30% 732527 aim7.time.involuntary_context_switches 64043 -22% 50231 interrupts.CAL:Function_call_interrupts 36.33 5% 38.33 turbostat.RAMWatt 3007 2927 turbostat.Avg_MHz 0.08 42% 0.11 perf-stat.ipc 2.015e+10 7% 2.151e+10 perf-stat.cache-references 3.339e+11 3% 3.448e+11 perf-stat.dTLB-stores 4.975e+11 5.109e+11 perf-stat.dTLB-loads 2.869e+11 2.913e+11 perf-stat.branch-instructions 1.494e+12 1.514e+12 perf-stat.instructions 47.33 46.61 perf-stat.node-load-miss-rate% 47.89 47.12 perf-stat.node-store-miss-rate% 3.367e+09 -4% 3.238e+09 perf-stat.cache-misses 16.71 -10% 15.05 perf-stat.cache-miss-rate% 789036 -10% 710465 perf-stat.page-faults 789032 -10% 710460 perf-stat.minor-faults 8.143e+08 -13% 7.083e+08 perf-stat.node-stores 7.483e+08 -16% 6.311e+08 perf-stat.node-store-misses 1.877e+13 -29% 1.339e+13 perf-stat.cpu-cycles 1821150 -29% 1296473 perf-stat.context-switches 12.56 -30% 8.85 perf-stat.cpi 109638 ± 3% -30% 77108 perf-stat.cpu-migrations 2.377e+09 ± 3% -48% 1.23e+09 ± 6% perf-stat.branch-misses 0.83 ± 3% -49% 0.42 ± 6% perf-stat.branch-miss-rate% aim7.jobs-per-min 520000 +-+----------------------------------------------------------------+ | | 500000 +-+ O O O O | 480000 +-+ O O O O O O O O O | O O O O O | 460000 +-+ O | 440000 +-+ | | | 420000 +-+ | 400000 +-+ | | | 380000 +-+ + + + | 360000 +-+.. : +. + + + + : +.+.. .+.. | |.+ : .. +.+..+. .+. .+ + + + .+ : .. +.+ +.+..+.| 340000 +-+----------------------------------------------------------------+ interrupts.CAL:Function_call_interrupts 66000 +-+-----------------------------------------------------------------+ 64000 +-+ +.. + +..+. .+ +. .+.| |.+ + : + +..+.+ + +.+ + .+. : + +. | 62000 +-++ : + : + : : + + : + + : + | 60000 +-+ + : + : + : : + + : + + + | | + + + + + + | 58000 +-+ | 56000 +-+ | 54000 +-+ | | | 52000 +-+ O O O O O | 50000 O-+ O O O O O O O O | | O O O | 48000 +-O O | 46000 +-+-----------------------------------------------------------------+ perf-stat.cpu-cycles 2e+13 +-+---------------------------------------------------------------+ |. .+.+.. .+. +. | 1.9e+13 +-+.. +. .+.+..+ + +.. +. .. + +. .+.+.. .+..+.| 1.8e+13 +-+ + +. + + + .. +..+ +.+ | | + + + | 1.7e+13 +-+ | | | 1.6e+13 +-+ | | | 1.5e+13 +-+ | 1.4e+13 +-+ O | O O O O O O O | 1.3e+13 +-+ O O O O O O O O O O | | O | 1.2e+13 +-+---------------------------------------------------------------+ perf-stat.context-switches 1.9e+06 +-+---------------------------------------------------------------+ | + .+.+.. .+ + + + +.+.. .| 1.8e+06 +-+ : : .+ + + : : + + + : +.+.+.. : + | | +.. : : .+. +.. : : + +. + : .. : | 1.7e+06 +-+ + +..+ + + + + + | 1.6e+06 +-+ | | | 1.5e+06 +-+ | | | 1.4e+06 +-+ | 1.3e+06 +-+ O O O O O O | O O O O O O O | 1.2e+06 +-O O O O | | | 1.1e+06 +-+--O---------------O--------------------------------------------+ perf-stat.cpu-migrations 120000 +-+----------------------------------------------------------------+ 115000 +-+ + + | | +.. +.. :: : : | 110000 +-+ +..+. + + : : : : .| 105000 +-+.. +..+. + +..+.+ + +.+ + +..+.+.. : :: +..+ | | + + + .. + + + + | 100000 +-+ + + + | 95000 +-+ | 90000 +-+ | | | 85000 +-+ O | 80000 +-+ O | O O O O O O O O O O O O O | 75000 +-+ O O O | 70000 +-+-------------------O--------------------------------------------+ perf-stat.node-load-miss-rate_ 47.6 +-+------------------------------------------------------------------+ | + | 47.4 +-+ .+ .+.. .+ .+ : + | |. .+ + .+..+ .+.. .+. : +.. .+. : .+.. : +.. .| 47.2 +-+. + .+..+ + + : + + : .+ +. : + | | + + +. + | 47 +-+ | | | 46.8 +-+ | | O O O O | 46.6 +-+ O O O O O O O | | O O O O O O | 46.4 +-+ O | O | 46.2 +-+------------------------------------------------------------------+ perf-stat.ipc 0.12 +-+--O--------------------------------------------------------------+ | O O O | 0.115 +-+ O O O O O O O | 0.11 +-O O O O O O | O O | 0.105 +-+ | 0.1 +-+ | | | 0.095 +-+ | 0.09 +-+ | | | 0.085 +-+ + + + | 0.08 +-+.. + .+. .+. .. + .+.. .. + .+.+.+..+.+..+. | |.+ +. +. +.+..+.+..+.+ + +.+ +. +..+.| 0.075 +-+-----------------------------------------------------------------+ perf-stat.cpi 13.5 +-+------------------------------------------------------------------+ 13 +-+ .+. .+.. +.. | | +.. +.. +.. .+. +..+ + + : + + .+.. .+..+.| 12.5 +-+ + + + + .. + : + .. + .+ +. .+ | 12 +-+ + + + + + +. +. | 11.5 +-+ | 11 +-+ | | | 10.5 +-+ | 10 +-+ | 9.5 +-+ | 9 O-+ O O O O O O | | O O O O O O O O O O | 8.5 +-+ O O | 8 +-+------------------------------------------------------------------+ aim7.time.system_time 6000 +-+------------------------------------------------------------------+ |.+ +.. .+.+.. .+..+ + +..+ + .+.| | + : .+..+.+. + : + + + : + + .+..+. .+.+. | 5500 +-+ + : + : + + : + +..+ +. | | + + + | | | 5000 +-+ | | | 4500 +-+ | | | O O O O O | 4000 +-O O O O O O O O O O O O | | O O | | | 3500 +-+------------------------------------------------------------------+ aim7.time.elapsed_time 160 +-+-------------------------------------------------------------------+ | + + +.+..+ +. +.. +.. : + + .+..+ +.+..+.| 150 +-+ + .. + .. + : + .. + .+ + .. | | + + + + + +. + | | | 140 +-+ | | | 130 +-+ | | | 120 +-+ | O O O O O | | O O O O O O O O O O O O | 110 +-+ O O | | | 100 +-+-------------------------------------------------------------------+ aim7.time.elapsed_time.max 160 +-+-------------------------------------------------------------------+ | + + +.+..+ +. +.. +.. : + + .+..+ +.+..+.| 150 +-+ + .. + .. + : + .. + .+ + .. | | + + + + + +. + | | | 140 +-+ | | | 130 +-+ | | | 120 +-+ | O O O O O | | O O O O O O O O O O O O | 110 +-+ O O | | | 100 +-+-------------------------------------------------------------------+ aim7.time.involuntary_context_switches 1.15e+06 +-+--------------------------------------------------------------+ 1.1e+06 +-+ + + + | |+ + .+ + + .. + + : + + .+.+ | 1.05e+06 +-+.. : + .+ + .+ + + + + : +.. : + .+ + +.+..+.| 1e+06 +-+ : +. +. + + + : +. + + | | + + + + | 950000 +-+ | 900000 +-+ | 850000 +-+ | | | 800000 +-+ O | 750000 O-+ O | | O O O O O O O O O O O O O | 700000 +-+ O O O | 650000 +-+--------------------------------------------------------------+ [*] 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. Thanks, Xiaolong