Greeting, FYI, we noticed a -5.7% regression of reaim.jobs_per_min due to commit: commit: 46c7f523fc82c74a2d1f76f3baef4cb760449ed8 ("NFS: Add trace events to report non-zero NFS status codes") git://git.linux-nfs.org/projects/cel/cel-2.6.git nfs-for-5.1 in testcase: reaim on test machine: 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory with following parameters: runtime: 300s nr_task: 5000 test: shared_memory cpufreq_governor: performance ucode: 0x3d test-description: REAIM is an updated and improved version of AIM 7 benchmark. test-url: https://sourceforge.net/projects/re-aim-7/ 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 ========================================================================================= compiler/cpufreq_governor/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase/ucode: gcc-7/performance/x86_64-rhel-7.2/5000/debian-x86_64-2018-04-03.cgz/300s/lkp-hsw-ep5/shared_memory/reaim/0x3d commit: 4283ca7092 ("NFS: Remove print_overflow_msg()") 46c7f523fc ("NFS: Add trace events to report non-zero NFS status codes") 4283ca7092974c86 46c7f523fc82c74a2d1f76f3ba ---------------- -------------------------- %stddev %change %stddev \ | \ 101.08 +9.6% 110.83 reaim.child_systime 5554880 -5.7% 5238688 reaim.jobs_per_min 1110 -5.7% 1047 reaim.jobs_per_min_child 52.32 +1.1% 52.88 reaim.jti 5758796 -4.2% 5516843 reaim.max_jobs_per_min 5.40 +6.0% 5.73 reaim.parent_time 47.17 -1.1% 46.64 reaim.std_dev_percent 1.51 +6.2% 1.60 reaim.std_dev_time 779756 +8.2% 843333 reaim.time.involuntary_context_switches 29591228 -3.4% 28581342 reaim.time.minor_page_faults 1671 +3.0% 1721 reaim.time.percent_of_cpu_this_job_got 3834 +5.8% 4057 reaim.time.system_time 18625000 -3.4% 18000000 reaim.workload 4174 ± 56% -77.0% 961.75 ±163% numa-numastat.node1.other_node 38.50 ± 16% -23.4% 29.50 ± 17% vmstat.procs.r 65418 ± 5% -23.3% 50200 ± 7% slabinfo.kmalloc-8.active_objs 65422 ± 5% -23.3% 50203 ± 7% slabinfo.kmalloc-8.num_objs 35.87 ± 7% +9.7% 39.33 ± 4% boot-time.boot 28.41 ± 9% +11.5% 31.68 ± 4% boot-time.dhcp 806.28 ± 8% +12.4% 906.13 ± 4% boot-time.idle 10180409 ± 6% +100.4% 20400767 ± 56% cpuidle.C1.time 148525 ± 7% +160.6% 386998 ±101% cpuidle.C1.usage 2.073e+09 ± 41% -95.5% 94256485 ± 45% cpuidle.C3.time 5352746 ± 20% -94.5% 293404 ± 16% cpuidle.C3.usage 1.191e+09 ± 69% +143.2% 2.896e+09 ± 3% cpuidle.C6.time 206394 ± 3% +153.2% 522639 ± 73% cpuidle.POLL.time 110251 +1.4% 111796 proc-vmstat.nr_anon_pages 51632 +1.3% 52308 proc-vmstat.nr_kernel_stack 13512 -1.3% 13333 proc-vmstat.nr_slab_reclaimable 29364446 -3.2% 28416838 proc-vmstat.numa_hit 29358859 -3.2% 28411273 proc-vmstat.numa_local 30421242 -3.3% 29429146 proc-vmstat.pgalloc_normal 30400897 -3.3% 29398332 proc-vmstat.pgfault 30390028 -3.3% 29397805 proc-vmstat.pgfree 1293 +3.2% 1335 turbostat.Avg_MHz 143181 ± 7% +166.8% 382060 ±102% turbostat.C1 5352186 ± 20% -94.5% 292948 ± 16% turbostat.C3 24.23 ± 41% -23.1 1.10 ± 45% turbostat.C3% 14.03 ± 69% +19.7 33.74 ± 3% turbostat.C6% 19.22 ± 4% -38.3% 11.85 ± 10% turbostat.CPU%c1 8.84 ± 74% +171.4% 23.98 ± 4% turbostat.CPU%c6 3.66 ± 64% -98.9% 0.04 ± 86% turbostat.Pkg%pc3 1.89 ±168% +418.4% 9.80 ± 9% turbostat.Pkg%pc6 65556 ± 12% -37.2% 41158 ± 23% sched_debug.cfs_rq:/.load.avg 327.25 ± 29% +64.6% 538.50 ± 14% sched_debug.cfs_rq:/.load_avg.max 78.30 ± 19% +55.3% 121.63 ± 12% sched_debug.cfs_rq:/.load_avg.stddev 1081291 +11.7% 1207381 sched_debug.cfs_rq:/.min_vruntime.min 0.72 ± 2% -47.9% 0.37 ± 35% sched_debug.cfs_rq:/.nr_running.avg 23.92 ± 6% -30.2% 16.69 ± 16% sched_debug.cfs_rq:/.runnable_load_avg.avg 89.12 ± 40% +159.3% 231.08 ± 33% sched_debug.cfs_rq:/.runnable_load_avg.max 19.96 ± 33% +122.9% 44.50 ± 32% sched_debug.cfs_rq:/.runnable_load_avg.stddev 62697 ± 13% -39.9% 37698 ± 23% sched_debug.cfs_rq:/.runnable_weight.avg 127498 ± 42% -65.8% 43587 ±131% sched_debug.cfs_rq:/.spread0.avg 663531 ± 15% -23.8% 505383 ± 11% sched_debug.cfs_rq:/.spread0.max 697851 +18.7% 828205 ± 3% sched_debug.cpu.avg_idle.avg 236299 ± 13% +53.9% 363659 ± 11% sched_debug.cpu.avg_idle.min 215933 ± 4% -18.9% 175103 ± 7% sched_debug.cpu.avg_idle.stddev 24.15 ± 7% -36.0% 15.45 ± 20% sched_debug.cpu.cpu_load[0].avg 93.79 ± 40% +113.5% 200.29 ± 25% sched_debug.cpu.cpu_load[0].max 20.73 ± 33% +87.8% 38.92 ± 23% sched_debug.cpu.cpu_load[0].stddev 24.75 ± 8% -32.8% 16.62 ± 15% sched_debug.cpu.cpu_load[1].avg 90.88 ± 27% +129.3% 208.33 ± 23% sched_debug.cpu.cpu_load[1].max 3.71 ± 41% -86.5% 0.50 ± 62% sched_debug.cpu.cpu_load[1].min 18.93 ± 25% +112.9% 40.30 ± 23% sched_debug.cpu.cpu_load[1].stddev 24.95 ± 6% -30.0% 17.46 ± 11% sched_debug.cpu.cpu_load[2].avg 80.21 ± 16% +160.7% 209.08 ± 26% sched_debug.cpu.cpu_load[2].max 5.62 ± 26% -70.4% 1.67 ± 53% sched_debug.cpu.cpu_load[2].min 16.27 ± 17% +145.4% 39.92 ± 25% sched_debug.cpu.cpu_load[2].stddev 25.43 ± 4% -30.7% 17.63 ± 11% sched_debug.cpu.cpu_load[3].avg 69.54 ± 16% +173.1% 189.92 ± 33% sched_debug.cpu.cpu_load[3].max 8.17 ± 16% -64.3% 2.92 ± 49% sched_debug.cpu.cpu_load[3].min 13.42 ± 17% +169.8% 36.20 ± 32% sched_debug.cpu.cpu_load[3].stddev 26.50 ± 2% -34.7% 17.29 ± 14% sched_debug.cpu.cpu_load[4].avg 79.00 ± 11% +123.2% 176.33 ± 28% sched_debug.cpu.cpu_load[4].max 10.92 ± 7% -65.6% 3.75 ± 43% sched_debug.cpu.cpu_load[4].min 14.22 ± 15% +134.3% 33.30 ± 29% sched_debug.cpu.cpu_load[4].stddev 11486 ± 7% -46.9% 6099 ± 51% sched_debug.cpu.curr->pid.avg 18198 ± 2% -15.6% 15358 sched_debug.cpu.curr->pid.max 68227 ± 11% -44.3% 38029 ± 19% sched_debug.cpu.load.avg 72.99 ± 11% -43.0% 41.57 ± 57% sched_debug.cpu.nr_uninterruptible.avg 5.719e+09 -3.8% 5.501e+09 perf-stat.i.branch-instructions 1.019e+08 -2.9% 98985845 perf-stat.i.branch-misses 7901112 +12.2% 8864011 perf-stat.i.cache-misses 86276716 ± 2% +8.8% 93866788 perf-stat.i.cache-references 3.604e+10 +3.0% 3.712e+10 perf-stat.i.cpu-cycles 2289 -0.9% 2268 perf-stat.i.cpu-migrations 4550 ± 2% -10.4% 4077 perf-stat.i.cycles-between-cache-misses 32035320 ± 6% +11.2% 35631332 ± 6% perf-stat.i.dTLB-load-misses 8.759e+09 -3.8% 8.423e+09 perf-stat.i.dTLB-loads 0.03 ± 9% -0.0 0.03 ± 2% perf-stat.i.dTLB-store-miss-rate% 5.75e+09 -4.2% 5.51e+09 perf-stat.i.dTLB-stores 53194139 -3.6% 51270942 perf-stat.i.iTLB-load-misses 3.211e+10 -3.8% 3.088e+10 perf-stat.i.instructions 784.59 +2.9% 807.04 perf-stat.i.instructions-per-iTLB-miss 0.78 -4.8% 0.74 perf-stat.i.ipc 100147 -3.8% 96339 perf-stat.i.minor-faults 4342227 +8.3% 4700831 perf-stat.i.node-load-misses 51.69 -1.8 49.90 perf-stat.i.node-store-miss-rate% 1424485 +22.3% 1742541 perf-stat.i.node-store-misses 903382 +34.7% 1217029 perf-stat.i.node-stores 100147 -3.8% 96339 perf-stat.i.page-faults 2.69 ± 2% +13.2% 3.04 perf-stat.overall.MPKI 1.78 +0.0 1.80 perf-stat.overall.branch-miss-rate% 1.12 +7.1% 1.20 perf-stat.overall.cpi 4561 -8.2% 4187 perf-stat.overall.cycles-between-cache-misses 0.36 ± 6% +0.1 0.42 ± 6% perf-stat.overall.dTLB-load-miss-rate% 0.89 -6.6% 0.83 perf-stat.overall.ipc 78.12 +1.7 79.80 perf-stat.overall.node-load-miss-rate% 61.19 -2.3 58.88 perf-stat.overall.node-store-miss-rate% 5.697e+09 -3.8% 5.479e+09 perf-stat.ps.branch-instructions 1.015e+08 -2.9% 98587754 perf-stat.ps.branch-misses 7870822 +12.2% 8828904 perf-stat.ps.cache-misses 85959791 ± 2% +8.8% 93512981 perf-stat.ps.cache-references 3.59e+10 +3.0% 3.697e+10 perf-stat.ps.cpu-cycles 2281 -0.9% 2260 perf-stat.ps.cpu-migrations 31909883 ± 6% +11.2% 35486247 ± 6% perf-stat.ps.dTLB-load-misses 8.725e+09 -3.8% 8.389e+09 perf-stat.ps.dTLB-loads 5.728e+09 -4.2% 5.488e+09 perf-stat.ps.dTLB-stores 52984864 -3.6% 51061507 perf-stat.ps.iTLB-load-misses 3.199e+10 -3.9% 3.075e+10 perf-stat.ps.instructions 99784 -3.8% 95984 perf-stat.ps.minor-faults 4325419 +8.2% 4682086 perf-stat.ps.node-load-misses 1418927 +22.3% 1735479 perf-stat.ps.node-store-misses 900003 +34.7% 1212264 perf-stat.ps.node-stores 99784 -3.8% 95984 perf-stat.ps.page-faults 9.729e+12 -3.3% 9.403e+12 perf-stat.total.instructions 33.10 ± 15% -18.6 14.52 ± 16% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe 32.23 ± 15% -18.1 14.18 ± 16% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe 22.18 ± 14% -12.2 9.95 ± 17% perf-profile.calltrace.cycles-pp.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 10.52 ± 14% -6.4 4.10 ± 16% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64 9.65 ± 14% -6.0 3.69 ± 17% perf-profile.calltrace.cycles-pp.syscall_return_via_sysret 3.26 ± 23% -2.2 1.09 ± 19% perf-profile.calltrace.cycles-pp.security_ipc_permission.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.59 ± 18% -1.6 1.01 ± 25% perf-profile.calltrace.cycles-pp.security_sem_semop.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.44 ± 15% -1.1 0.30 ±100% perf-profile.calltrace.cycles-pp.__x64_sys_shmget.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.44 ± 15% -1.1 0.30 ±100% perf-profile.calltrace.cycles-pp.ipcget.__x64_sys_shmget.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.35 ± 18% -1.1 0.28 ±100% perf-profile.calltrace.cycles-pp.ksys_shmdt.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.39 ± 13% -1.1 0.33 ±101% perf-profile.calltrace.cycles-pp._copy_from_user.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.32 ± 17% -1.0 0.28 ±100% perf-profile.calltrace.cycles-pp.__do_munmap.ksys_shmdt.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.49 ± 15% -1.0 0.48 ± 60% perf-profile.calltrace.cycles-pp.do_smart_update.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 4.21 ± 12% -1.0 3.25 ± 16% perf-profile.calltrace.cycles-pp.ipc_obtain_object_check.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.42 ± 10% -0.6 1.77 ± 15% perf-profile.calltrace.cycles-pp.avc_has_perm.ipc_has_perm.security_sem_semop.do_semtimedop.do_syscall_64 1.34 ± 13% -0.5 0.85 ± 5% perf-profile.calltrace.cycles-pp.remove_vma.__do_munmap.ksys_shmdt.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.11 -0.1 1.02 perf-profile.calltrace.cycles-pp.page_fault 1.06 -0.1 0.98 perf-profile.calltrace.cycles-pp.__do_page_fault.do_page_fault.page_fault 1.09 ± 2% -0.1 1.01 perf-profile.calltrace.cycles-pp.do_page_fault.page_fault 0.90 ± 2% -0.1 0.82 perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault.page_fault 0.93 ± 2% -0.1 0.86 perf-profile.calltrace.cycles-pp.handle_mm_fault.__do_page_fault.do_page_fault.page_fault 0.58 ± 8% +0.1 0.67 ± 6% perf-profile.calltrace.cycles-pp.__might_fault._copy_from_user.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.14 ±173% +0.4 0.55 ± 4% perf-profile.calltrace.cycles-pp.dput.__fput.task_work_run.exit_to_usermode_loop.do_syscall_64 0.13 ±173% +0.4 0.56 ± 6% perf-profile.calltrace.cycles-pp.ipcperms.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 4.51 ± 2% +0.4 4.94 ± 3% perf-profile.calltrace.cycles-pp.__radix_tree_lookup.ipc_obtain_object_check.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.13 ±173% +0.4 0.57 ± 7% perf-profile.calltrace.cycles-pp.copy_user_generic_unrolled._copy_from_user.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.73 ± 19% +0.5 1.19 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_semop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 0.46 ± 59% +0.5 0.95 ± 6% perf-profile.calltrace.cycles-pp.shmctl_down.ksys_shmctl.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmctl 0.47 ± 59% +0.5 0.96 ± 6% perf-profile.calltrace.cycles-pp.ksys_shmctl.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmctl 0.69 ± 21% +0.5 1.21 ± 4% perf-profile.calltrace.cycles-pp._raw_spin_lock.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 0.91 ± 21% +0.5 1.44 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmat 0.90 ± 21% +0.5 1.43 ± 4% perf-profile.calltrace.cycles-pp.__do_munmap.ksys_shmdt.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmdt 0.89 ± 21% +0.5 1.43 ± 5% perf-profile.calltrace.cycles-pp.do_shmat.__x64_sys_shmat.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmat 0.90 ± 21% +0.5 1.44 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_shmat.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmat 0.91 ± 21% +0.5 1.45 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.shmat 0.91 ± 21% +0.5 1.46 ± 4% perf-profile.calltrace.cycles-pp.ksys_shmdt.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmdt 0.96 ± 21% +0.6 1.53 ± 5% perf-profile.calltrace.cycles-pp.shmat 0.30 ±101% +0.6 0.88 ± 4% perf-profile.calltrace.cycles-pp.perform_atomic_semop.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 0.00 +0.6 0.60 ± 6% perf-profile.calltrace.cycles-pp.task_work_run.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmctl 0.00 +0.6 0.63 ± 5% perf-profile.calltrace.cycles-pp.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmctl 1.03 ± 19% +0.6 1.67 ± 3% perf-profile.calltrace.cycles-pp.ipcget.__x64_sys_shmget.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmget 1.04 ± 19% +0.6 1.68 ± 3% perf-profile.calltrace.cycles-pp.__x64_sys_shmget.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmget 1.04 ± 20% +0.6 1.69 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.shmget 1.04 ± 20% +0.6 1.69 ± 3% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmget 1.02 ± 22% +0.6 1.67 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.shmdt 1.02 ± 22% +0.6 1.67 ± 3% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmdt 0.00 +0.6 0.65 ± 6% perf-profile.calltrace.cycles-pp.ksys_semctl.do_syscall_64.entry_SYSCALL_64_after_hwframe.semctl 0.95 ± 21% +0.7 1.60 ± 6% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.shmctl 0.95 ± 20% +0.7 1.60 ± 6% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.shmctl 0.00 +0.7 0.67 ± 7% perf-profile.calltrace.cycles-pp.ipcget.ksys_semget.do_syscall_64.entry_SYSCALL_64_after_hwframe.semget 0.00 +0.7 0.67 ± 6% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.semctl 1.12 ± 18% +0.7 1.80 ± 3% perf-profile.calltrace.cycles-pp.shmget 0.00 +0.7 0.68 ± 6% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.semctl 0.00 +0.7 0.69 ± 7% perf-profile.calltrace.cycles-pp.ksys_semget.do_syscall_64.entry_SYSCALL_64_after_hwframe.semget 1.00 ± 21% +0.7 1.68 ± 5% perf-profile.calltrace.cycles-pp.shmctl 1.07 ± 22% +0.7 1.76 ± 4% perf-profile.calltrace.cycles-pp.shmdt 0.00 +0.7 0.69 ± 7% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.semget 0.00 +0.7 0.70 ± 8% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.semget 1.05 ± 22% +0.7 1.77 ± 4% perf-profile.calltrace.cycles-pp.do_smart_update.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 0.97 ± 19% +0.7 1.71 ± 7% perf-profile.calltrace.cycles-pp._copy_from_user.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 0.00 +0.8 0.76 ± 7% perf-profile.calltrace.cycles-pp.semget 0.00 +0.8 0.82 ± 7% perf-profile.calltrace.cycles-pp.semctl 2.25 ± 18% +1.1 3.33 ± 9% perf-profile.calltrace.cycles-pp.security_ipc_permission.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 1.80 ± 20% +1.3 3.11 ± 13% perf-profile.calltrace.cycles-pp.security_sem_semop.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 6.48 ± 20% +4.6 11.10 ± 4% perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.semop 1.50 ± 13% +6.1 7.57 ± 2% perf-profile.calltrace.cycles-pp.idr_find.ipc_obtain_object_check.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe 9.22 ± 20% +6.4 15.61 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64.semop 2.93 ± 23% +7.4 10.34 ± 6% perf-profile.calltrace.cycles-pp.ipc_obtain_object_check.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 15.42 ± 20% +15.5 30.90 ± 5% perf-profile.calltrace.cycles-pp.do_semtimedop.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 17.24 ± 20% +16.8 34.03 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.semop 17.82 ± 19% +17.2 35.02 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.semop 33.80 ± 20% +28.4 62.22 ± 5% perf-profile.calltrace.cycles-pp.semop reaim.time.minor_page_faults 3.5e+07 +-+---------------------------------------------------------------+ | | 3e+07 +-++.++.++.++.++.++.++.+.+ ++.++.++.++.+ +.++.++.++.++.++.++.++.| O OO OO OO OO OO OO OO O OO OO OO OO OO O : | 2.5e+07 +-+: : : : : | |: : : : : : | 2e+07 +-+: : : : : | |: : : : : : | 1.5e+07 +-+: :: :: | |:: :: :: | 1e+07 +-+ :: :: | | : :: :: | 5e+06 +-+ : : | | : : : | 0 +-+---------------------------------------------------------------+ reaim.workload 2e+07 +-+---------------------------------------------------------------+ 1.8e+07 O-OO.OO.OO.OO.OO.OO.OO.+.OO OO.OO.OO.OO.O +.++.++.++.++.++.++.++.| | : O : : : : | 1.6e+07 +-+: : : : : | 1.4e+07 +-+: : : : : | |: : : : : : | 1.2e+07 +-+: : : : : | 1e+07 +-+: : : : : | 8e+06 +-+ :: :: | |:: :: :: | 6e+06 +-+ :: :: | 4e+06 +-+ : : | | : : : | 2e+06 +-+ : : | 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. Thanks, Rong Chen