Hello, kernel test robot noticed a 47.4% improvement of hackbench.throughput due to commit: commit: a53ce18cacb477dd0513c607f187d16f0fa96f71 ("sched/fair: Sanitize vruntime of entity being migrated") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master in testcase: hackbench on test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480+ (Sapphire Rapids) with 256G memory with following parameters: nr_threads: 100% iterations: 4 mode: process ipc: socket cpufreq_governor: performance In addition to that, the commit also has performance change on the following tests: +------------------+------------------------------------------------------------------------------------------------+ | testcase: change | hackbench: hackbench.throughput 8.3% improvement | | test machine | 104 threads 2 sockets (Skylake) with 192G memory | | test parameters | cpufreq_governor=performance | | | ipc=socket | | | iterations=4 | | | mode=process | | | nr_threads=100% | +------------------+------------------------------------------------------------------------------------------------+ This means that the performance regression reported at the link below has been resolved: https://lore.kernel.org/oe-lkp/202303091155.672f546a-yujie.liu@intel.com/ Details are as below: ========================================================================================= compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase: gcc-11/performance/socket/4/x86_64-rhel-8.3/process/100%/debian-11.1-x86_64-20220510.cgz/lkp-spr-2sp1/hackbench commit: v6.3-rc3 a53ce18cac ("sched/fair: Sanitize vruntime of entity being migrated") v6.3-rc3 a53ce18cacb477dd0513c607f18 ---------------- --------------------------- %stddev %change %stddev \ | \ 424.18 ± 8% -28.9% 301.49 ± 4% uptime.boot 1.856e+09 ± 9% +34.5% 2.496e+09 ± 4% cpuidle..time 30711384 ± 38% +191.5% 89520869 ± 13% cpuidle..usage 2.23 ± 9% +2.2 4.45 ± 5% mpstat.cpu.all.idle% 4.63 ± 14% -1.4 3.28 ± 8% mpstat.cpu.all.irq% 0.03 ± 5% +0.0 0.05 ± 3% mpstat.cpu.all.soft% 1674225 ± 13% +81.9% 3045512 ± 26% numa-numastat.node0.local_node 1761309 ± 11% +80.9% 3187010 ± 25% numa-numastat.node0.numa_hit 1799559 ± 6% -23.5% 1377395 ± 13% numa-numastat.node1.numa_hit 3608584 ± 6% +88.5% 6802087 ± 32% vmstat.memory.cache 3439 ± 3% -31.6% 2354 ± 6% vmstat.procs.r 5879204 ± 11% -48.9% 3002210 ± 7% vmstat.system.cs 1029853 ± 14% -44.5% 571234 ± 7% vmstat.system.in 1873999 ± 69% +230.1% 6187004 ± 35% numa-meminfo.node0.FilePages 403862 ± 62% +858.3% 3870409 ± 59% numa-meminfo.node0.Inactive 403862 ± 62% +858.3% 3870302 ± 59% numa-meminfo.node0.Inactive(anon) 208254 ±104% +476.4% 1200340 ± 41% numa-meminfo.node0.Mapped 3743471 ± 37% +123.1% 8351788 ± 26% numa-meminfo.node0.MemUsed 139050 ±194% +2453.0% 3550021 ± 63% numa-meminfo.node0.Shmem 320664 ± 4% -23.7% 244546 ± 8% numa-meminfo.node1.Active 320608 ± 4% -23.7% 244527 ± 8% numa-meminfo.node1.Active(anon) 1561370 ± 77% -73.9% 406842 ± 10% numa-meminfo.node1.FilePages 585464 ± 12% -43.1% 332958 ± 21% numa-meminfo.node1.Shmem 453627 ± 15% +47.4% 668513 ± 10% hackbench.throughput 290970 ± 9% +49.8% 435960 ± 5% hackbench.throughput_avg 453627 ± 15% +47.4% 668513 ± 10% hackbench.throughput_best 227755 ± 15% +60.8% 366142 ± 3% hackbench.throughput_worst 368.43 ± 10% -33.4% 245.40 ± 5% hackbench.time.elapsed_time 368.43 ± 10% -33.4% 245.40 ± 5% hackbench.time.elapsed_time.max 6.778e+08 ± 23% -80.6% 1.313e+08 ± 17% hackbench.time.involuntary_context_switches 1134672 ± 2% -8.1% 1042275 hackbench.time.minor_page_faults 73764 ± 9% -34.2% 48540 ± 5% hackbench.time.system_time 3182 ± 14% -32.8% 2139 ± 5% hackbench.time.user_time 1.491e+09 ± 19% -64.8% 5.252e+08 ± 11% hackbench.time.voluntary_context_switches 335830 ± 2% -21.0% 265441 ± 7% meminfo.Active 335774 ± 2% -21.0% 265390 ± 7% meminfo.Active(anon) 484840 ± 8% +26.2% 611689 ± 7% meminfo.AnonPages 3440431 ± 7% +92.0% 6604853 ± 33% meminfo.Cached 3977740 ± 9% +87.3% 7449378 ± 29% meminfo.Committed_AS 878902 ± 33% +382.5% 4240713 ± 52% meminfo.Inactive 878746 ± 33% +382.6% 4240551 ± 52% meminfo.Inactive(anon) 432270 ± 64% +244.7% 1489964 ± 35% meminfo.Mapped 7065839 ± 5% +54.0% 10881593 ± 21% meminfo.Memused 729581 ± 34% +433.7% 3893991 ± 56% meminfo.Shmem 8813899 +32.3% 11664510 ± 16% meminfo.max_used_kB 10133249 ± 47% +173.5% 27716728 ± 22% turbostat.C1 0.08 ± 48% +0.3 0.42 ± 5% turbostat.C1% 19370237 ± 38% +207.9% 59632248 ± 9% turbostat.C1E 1.29 ± 11% +1.6 2.87 ± 4% turbostat.C1E% 0.84 ± 9% +0.3 1.13 ± 10% turbostat.C6% 2.19 ± 10% +96.9% 4.30 ± 5% turbostat.CPU%c1 0.30 ± 4% +26.6% 0.37 turbostat.IPC 3.866e+08 ± 24% -63.2% 1.421e+08 ± 13% turbostat.IRQ 83.42 ± 7% +19.6 102.99 ± 5% turbostat.PKG_% 445148 ± 44% +227.6% 1458182 ± 19% turbostat.POLL 0.00 ±223% +0.0 0.02 turbostat.POLL% 468176 ± 69% +231.8% 1553376 ± 35% numa-vmstat.node0.nr_file_pages 100706 ± 62% +867.6% 974455 ± 59% numa-vmstat.node0.nr_inactive_anon 51728 ±104% +486.5% 303394 ± 40% numa-vmstat.node0.nr_mapped 54.50 ± 72% -100.0% 0.00 numa-vmstat.node0.nr_mlock 34438 ±194% +2496.3% 894131 ± 63% numa-vmstat.node0.nr_shmem 100705 ± 62% +867.6% 974453 ± 59% numa-vmstat.node0.nr_zone_inactive_anon 1761001 ± 11% +81.0% 3186765 ± 25% numa-vmstat.node0.numa_hit 1673917 ± 13% +81.9% 3045267 ± 26% numa-vmstat.node0.numa_local 81949 ± 4% -24.2% 62153 ± 9% numa-vmstat.node1.nr_active_anon 392315 ± 77% -73.8% 102913 ± 10% numa-vmstat.node1.nr_file_pages 148338 ± 12% -43.1% 84442 ± 22% numa-vmstat.node1.nr_shmem 81949 ± 4% -24.2% 62153 ± 9% numa-vmstat.node1.nr_zone_active_anon 1799224 ± 6% -23.5% 1376976 ± 13% numa-vmstat.node1.numa_hit 82970 ± 3% -19.5% 66816 ± 7% proc-vmstat.nr_active_anon 121543 ± 8% +25.5% 152565 ± 7% proc-vmstat.nr_anon_pages 6381647 -1.5% 6286796 proc-vmstat.nr_dirty_background_threshold 12778899 -1.5% 12588965 proc-vmstat.nr_dirty_threshold 859674 ± 6% +92.1% 1651708 ± 33% proc-vmstat.nr_file_pages 64194818 -1.5% 63244918 proc-vmstat.nr_free_pages 220555 ± 31% +380.5% 1059808 ± 53% proc-vmstat.nr_inactive_anon 108806 ± 61% +242.0% 372136 ± 35% proc-vmstat.nr_mapped 77.67 ± 64% -100.0% 0.00 proc-vmstat.nr_mlock 51225 ± 3% +6.5% 54531 ± 3% proc-vmstat.nr_page_table_pages 181960 ± 32% +435.3% 973991 ± 56% proc-vmstat.nr_shmem 82970 ± 3% -19.5% 66816 ± 7% proc-vmstat.nr_zone_active_anon 220555 ± 31% +380.5% 1059808 ± 53% proc-vmstat.nr_zone_inactive_anon 124918 ± 29% +298.2% 497443 ± 42% proc-vmstat.numa_hint_faults_local 140811 ± 7% -30.3% 98111 ± 21% proc-vmstat.numa_pages_migrated 5979653 ± 12% -25.7% 4445814 ± 14% proc-vmstat.pgfree 140811 ± 7% -30.3% 98111 ± 21% proc-vmstat.pgmigrate_success 246196 ± 6% -16.3% 206181 ± 4% proc-vmstat.pgreuse 2815744 ± 10% -32.4% 1902336 ± 5% proc-vmstat.unevictable_pgs_scanned 0.59 ± 30% -54.4% 0.27 ± 58% sched_debug.cfs_rq:/.h_nr_running.min 39916437 ± 15% -50.7% 19661197 ± 13% sched_debug.cfs_rq:/.min_vruntime.avg 61775081 ± 22% -54.5% 28130592 ± 15% sched_debug.cfs_rq:/.min_vruntime.max 30282948 ± 11% -50.1% 15100710 ± 13% sched_debug.cfs_rq:/.min_vruntime.min 7448178 ± 33% -54.9% 3357079 ± 27% sched_debug.cfs_rq:/.min_vruntime.stddev 0.56 ± 26% -59.6% 0.22 ± 52% sched_debug.cfs_rq:/.nr_running.min 159.58 ± 10% +49.2% 238.14 ± 9% sched_debug.cfs_rq:/.removed.load_avg.max 81.37 ± 10% +52.2% 123.82 ± 9% sched_debug.cfs_rq:/.removed.runnable_avg.max 81.34 ± 10% +52.2% 123.79 ± 9% sched_debug.cfs_rq:/.removed.util_avg.max 12026 ± 10% -34.0% 7936 ± 26% sched_debug.cfs_rq:/.runnable_avg.avg 4004 ± 4% -30.3% 2791 ± 22% sched_debug.cfs_rq:/.runnable_avg.stddev -16690851 -57.9% -7025073 sched_debug.cfs_rq:/.spread0.avg -26445854 -55.8% -11696209 sched_debug.cfs_rq:/.spread0.min 7504656 ± 33% -54.8% 3394445 ± 26% sched_debug.cfs_rq:/.spread0.stddev 842.85 ± 6% -29.5% 593.87 ± 9% sched_debug.cfs_rq:/.util_avg.avg 278.11 ± 27% -60.8% 109.14 ± 40% sched_debug.cfs_rq:/.util_avg.min 186.96 ± 10% +51.5% 283.32 ± 8% sched_debug.cfs_rq:/.util_avg.stddev 492.57 ± 10% -40.4% 293.75 ± 18% sched_debug.cfs_rq:/.util_est_enqueued.avg 282.49 ± 9% -21.4% 222.01 ± 14% sched_debug.cfs_rq:/.util_est_enqueued.stddev 1244882 ± 7% -27.0% 909203 ± 11% sched_debug.cpu.avg_idle.max 237794 ± 8% -31.0% 164110 ± 19% sched_debug.cpu.avg_idle.stddev 231775 ± 10% -30.3% 161544 ± 8% sched_debug.cpu.clock.avg 232661 ± 10% -30.3% 162117 ± 8% sched_debug.cpu.clock.max 230602 ± 10% -30.2% 160904 ± 9% sched_debug.cpu.clock.min 224411 ± 9% -29.5% 158297 ± 8% sched_debug.cpu.clock_task.avg 228363 ± 10% -29.8% 160387 ± 8% sched_debug.cpu.clock_task.max 202929 ± 11% -32.3% 137479 ± 10% sched_debug.cpu.clock_task.min 4395639 ± 27% -66.1% 1490705 ± 15% sched_debug.cpu.nr_switches.avg 6927510 ± 26% -65.7% 2373854 ± 15% sched_debug.cpu.nr_switches.max 2411132 ± 20% -65.0% 843610 ± 4% sched_debug.cpu.nr_switches.min 1196317 ± 46% -59.2% 487745 ± 39% sched_debug.cpu.nr_switches.stddev 230571 ± 10% -30.2% 160893 ± 9% sched_debug.cpu_clk 225627 ± 10% -30.9% 155952 ± 9% sched_debug.ktime 231609 ± 10% -30.1% 161933 ± 9% sched_debug.sched_clk 0.58 ±113% +2.9 3.50 ± 65% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg 0.61 ±112% +3.0 3.57 ± 65% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg.sock_write_iter 0.48 ± 9% +0.1 0.62 ± 10% perf-profile.children.cycles-pp.task_tick_fair 0.17 ± 14% +0.1 0.31 ± 18% perf-profile.children.cycles-pp.__libc_start_main 0.17 ± 14% +0.1 0.31 ± 18% perf-profile.children.cycles-pp.main 0.17 ± 14% +0.1 0.31 ± 18% perf-profile.children.cycles-pp.run_builtin 0.16 ± 14% +0.1 0.31 ± 19% perf-profile.children.cycles-pp.cmd_record 0.58 ± 9% +0.1 0.72 ± 10% perf-profile.children.cycles-pp.tick_sched_timer 0.57 ± 9% +0.1 0.71 ± 10% perf-profile.children.cycles-pp.tick_sched_handle 0.69 ± 9% +0.1 0.84 ± 10% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt 0.68 ± 9% +0.1 0.82 ± 10% perf-profile.children.cycles-pp.hrtimer_interrupt 0.53 ± 10% +0.1 0.68 ± 10% perf-profile.children.cycles-pp.scheduler_tick 0.62 ± 9% +0.2 0.78 ± 10% perf-profile.children.cycles-pp.__hrtimer_run_queues 0.56 ± 10% +0.2 0.71 ± 10% perf-profile.children.cycles-pp.update_process_times 0.74 ± 10% +0.2 0.89 ± 10% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt 0.78 ± 9% +0.2 0.94 ± 10% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt 0.00 +0.2 0.16 ± 47% perf-profile.children.cycles-pp.perf_output_copy 0.00 +0.2 0.17 ± 37% perf-profile.children.cycles-pp.cmd_sched 0.06 ± 76% +0.2 0.24 ± 35% perf-profile.children.cycles-pp.select_idle_cpu 0.00 +0.2 0.21 ± 49% perf-profile.children.cycles-pp.__output_copy 0.16 ± 14% +0.2 0.41 ± 40% perf-profile.children.cycles-pp.record__mmap_read_evlist 0.15 ± 15% +0.2 0.40 ± 40% perf-profile.children.cycles-pp.perf_mmap__push 0.11 ± 20% +0.3 0.36 ± 44% perf-profile.children.cycles-pp.record__pushfn 0.11 ± 20% +0.3 0.36 ± 44% perf-profile.children.cycles-pp.writen 0.16 ± 14% +0.3 0.42 ± 40% perf-profile.children.cycles-pp.__cmd_record 0.07 ± 21% +0.3 0.33 ± 49% perf-profile.children.cycles-pp.__generic_file_write_iter 0.00 +0.3 0.26 ± 50% perf-profile.children.cycles-pp.perf_output_sample 0.07 ± 21% +0.3 0.33 ± 49% perf-profile.children.cycles-pp.generic_perform_write 0.08 ± 18% +0.3 0.34 ± 48% perf-profile.children.cycles-pp.generic_file_write_iter 0.15 ± 77% +0.3 0.41 ± 41% perf-profile.children.cycles-pp.select_idle_sibling 0.42 ± 58% +0.5 0.92 ± 38% perf-profile.children.cycles-pp.prepare_to_wait 0.84 ± 30% +0.8 1.65 ± 54% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 41.82 ± 3% +2.3 44.10 perf-profile.children.cycles-pp.ksys_write 41.40 ± 3% +2.3 43.74 ± 2% perf-profile.children.cycles-pp.vfs_write 0.02 ±141% +0.1 0.10 ± 15% perf-profile.self.cycles-pp.select_idle_cpu 7.36 ± 4% +20.0% 8.84 ± 2% perf-stat.i.MPKI 3.852e+10 ± 4% +31.1% 5.051e+10 ± 3% perf-stat.i.branch-instructions 0.69 ± 3% -0.2 0.48 perf-stat.i.branch-miss-rate% 23.53 ± 9% -11.5 12.05 ± 5% perf-stat.i.cache-miss-rate% 1.273e+09 ± 6% +74.9% 2.227e+09 ± 4% perf-stat.i.cache-references 7571717 ± 13% -58.7% 3125278 ± 7% perf-stat.i.context-switches 2.73 ± 6% -38.2% 1.69 perf-stat.i.cpi 237085 -4.5% 226321 perf-stat.i.cpu-clock 1403312 ± 8% -51.7% 677427 ± 10% perf-stat.i.cpu-migrations 2285 ± 11% -22.0% 1781 ± 5% perf-stat.i.cycles-between-cache-misses 0.15 ± 13% -0.1 0.07 ± 14% perf-stat.i.dTLB-load-miss-rate% 73162040 ± 14% -38.4% 45064668 ± 15% perf-stat.i.dTLB-load-misses 5.431e+10 ± 4% +37.3% 7.457e+10 ± 3% perf-stat.i.dTLB-loads 3.134e+10 ± 4% +40.4% 4.4e+10 ± 3% perf-stat.i.dTLB-stores 1.971e+11 ± 4% +34.6% 2.654e+11 ± 3% perf-stat.i.instructions 0.46 ± 5% +36.2% 0.63 perf-stat.i.ipc 550.07 ± 5% -16.6% 458.59 ± 3% perf-stat.i.metric.K/sec 534.60 ± 3% +42.4% 761.34 ± 3% perf-stat.i.metric.M/sec 11814 ± 7% +18.6% 14017 ± 7% perf-stat.i.minor-faults 70.52 ± 8% -11.0 59.48 ± 3% perf-stat.i.node-load-miss-rate% 78468492 ± 13% -37.6% 48927418 ± 5% perf-stat.i.node-load-misses 11951 ± 7% +18.5% 14158 ± 7% perf-stat.i.page-faults 237085 -4.5% 226321 perf-stat.i.task-clock 5.88 ± 5% +39.5% 8.21 ± 2% perf-stat.overall.MPKI 0.46 ± 4% -0.0 0.43 perf-stat.overall.branch-miss-rate% 17.23 ± 11% -6.0 11.21 ± 7% perf-stat.overall.cache-miss-rate% 2.02 ± 3% -20.8% 1.60 perf-stat.overall.cpi 2017 ± 9% -13.4% 1747 ± 4% perf-stat.overall.cycles-between-cache-misses 0.12 ± 11% -0.1 0.06 ± 13% perf-stat.overall.dTLB-load-miss-rate% 0.50 ± 3% +26.1% 0.62 perf-stat.overall.ipc 4.183e+10 ± 4% +17.7% 4.923e+10 ± 3% perf-stat.ps.branch-instructions 1.938e+08 ± 2% +8.6% 2.105e+08 ± 2% perf-stat.ps.branch-misses 2.161e+08 ± 8% +9.5% 2.367e+08 ± 2% perf-stat.ps.cache-misses 1.26e+09 ± 5% +68.2% 2.12e+09 ± 5% perf-stat.ps.cache-references 5887952 ± 10% -48.8% 3014282 ± 7% perf-stat.ps.context-switches 949854 ± 9% -33.3% 633638 ± 10% perf-stat.ps.cpu-migrations 70607155 ± 11% -36.8% 44647998 ± 16% perf-stat.ps.dTLB-load-misses 5.895e+10 ± 4% +22.8% 7.239e+10 ± 3% perf-stat.ps.dTLB-loads 3.38e+10 ± 4% +26.0% 4.258e+10 ± 3% perf-stat.ps.dTLB-stores 2.143e+11 ± 4% +20.5% 2.581e+11 ± 3% perf-stat.ps.instructions 49.89 ± 12% +55.0% 77.32 ± 10% perf-stat.ps.major-faults 7212 ± 6% +57.8% 11382 ± 10% perf-stat.ps.minor-faults 7262 ± 6% +57.8% 11459 ± 10% perf-stat.ps.page-faults 7.903e+13 ± 8% -19.6% 6.354e+13 perf-stat.total.instructions *************************************************************************************************** lkp-skl-fpga01: 104 threads 2 sockets (Skylake) with 192G memory ========================================================================================= compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase: gcc-11/performance/socket/4/x86_64-rhel-8.3/process/100%/debian-11.1-x86_64-20220510.cgz/lkp-skl-fpga01/hackbench commit: v6.3-rc3 a53ce18cac ("sched/fair: Sanitize vruntime of entity being migrated") v6.3-rc3 a53ce18cacb477dd0513c607f18 ---------------- --------------------------- %stddev %change %stddev \ | \ 2372517 ± 6% -15.3% 2009977 ± 3% cpuidle..usage 386.65 -15.1% 328.12 uptime.boot 202008 ± 65% +235.3% 677252 ± 50% numa-vmstat.node1.nr_file_pages 80400 ± 87% +121.6% 178136 ± 24% numa-vmstat.node1.nr_mapped 1.10 ± 7% +0.1 1.25 mpstat.cpu.all.idle% 0.03 +0.0 0.03 mpstat.cpu.all.soft% 19.97 +2.9 22.83 mpstat.cpu.all.usr% 814458 ± 64% +233.6% 2717000 ± 50% numa-meminfo.node1.FilePages 323256 ± 86% +122.7% 719869 ± 24% numa-meminfo.node1.Mapped 1850342 ± 41% +111.8% 3919066 ± 36% numa-meminfo.node1.MemUsed 2273 -24.1% 1725 vmstat.procs.r 5659154 ± 2% -71.9% 1591096 vmstat.system.cs 498688 -36.1% 318814 vmstat.system.in 1373950 ± 9% -27.0% 1003101 ± 4% turbostat.C1 336758 ± 7% -29.9% 236152 ± 9% turbostat.C1E 1.02 ± 6% +0.1 1.15 turbostat.C6% 1.691e+08 -47.0% 89681944 turbostat.IRQ 301212 ± 4% +47.0% 442678 ± 6% turbostat.POLL 32.72 +6.4% 34.82 turbostat.RAMWatt 81482 +2.6% 83563 proc-vmstat.nr_kernel_stack 111505 +7.6% 119994 proc-vmstat.nr_slab_unreclaimable 119548 ± 14% +72.4% 206115 ± 18% proc-vmstat.numa_hint_faults 56965 ± 30% +156.2% 145972 ± 25% proc-vmstat.numa_hint_faults_local 413798 ± 9% +31.6% 544570 ± 11% proc-vmstat.numa_pte_updates 3403745 ± 5% -23.1% 2617705 ± 3% proc-vmstat.pgalloc_normal 1498057 +7.1% 1604481 ± 2% proc-vmstat.pgfault 3087578 ± 7% -22.1% 2405993 ± 11% proc-vmstat.pgfree 119101 -5.3% 112827 ± 2% proc-vmstat.pgreuse 2587904 -16.5% 2159616 proc-vmstat.unevictable_pgs_scanned 165103 +8.3% 178791 hackbench.throughput 145699 +21.0% 176324 hackbench.throughput_avg 165103 +8.3% 178791 hackbench.throughput_best 109401 ± 3% +56.4% 171113 hackbench.throughput_worst 336.59 -17.3% 278.45 hackbench.time.elapsed_time 336.59 -17.3% 278.45 hackbench.time.elapsed_time.max 7.113e+08 ± 5% -85.6% 1.023e+08 hackbench.time.involuntary_context_switches 523124 -1.9% 513262 hackbench.time.minor_page_faults 27290 -20.3% 21749 hackbench.time.system_time 7022 -6.1% 6594 hackbench.time.user_time 1.206e+09 ± 2% -71.6% 3.428e+08 hackbench.time.voluntary_context_switches 17.78 ± 6% -22.3% 13.81 ± 2% sched_debug.cfs_rq:/.h_nr_running.avg 1.97 ± 18% -61.1% 0.77 ± 9% sched_debug.cfs_rq:/.h_nr_running.min 7.82 ± 9% +13.5% 8.87 sched_debug.cfs_rq:/.h_nr_running.stddev 22482 ± 14% +176.4% 62133 ±121% sched_debug.cfs_rq:/.load.max 3989 ± 10% +109.2% 8346 ± 85% sched_debug.cfs_rq:/.load.stddev 16432813 -28.2% 11806347 sched_debug.cfs_rq:/.min_vruntime.avg 27697257 ± 6% -49.2% 14056988 ± 4% sched_debug.cfs_rq:/.min_vruntime.max 14630804 -22.0% 11418377 sched_debug.cfs_rq:/.min_vruntime.min 1611161 ± 7% -80.4% 315248 ± 17% sched_debug.cfs_rq:/.min_vruntime.stddev 0.05 ± 6% +28.7% 0.07 ± 10% sched_debug.cfs_rq:/.nr_running.stddev 141.19 ± 44% +44.4% 203.87 sched_debug.cfs_rq:/.removed.load_avg.max 72.22 ± 44% +44.7% 104.53 sched_debug.cfs_rq:/.removed.runnable_avg.max 72.22 ± 44% +44.7% 104.53 sched_debug.cfs_rq:/.removed.util_avg.max 18306 ± 6% -23.7% 13975 ± 2% sched_debug.cfs_rq:/.runnable_avg.avg 28663 ± 12% -17.7% 23592 ± 3% sched_debug.cfs_rq:/.runnable_avg.max 4463 ± 10% -18.8% 3623 ± 4% sched_debug.cfs_rq:/.runnable_avg.stddev -3646660 -70.7% -1069365 sched_debug.cfs_rq:/.spread0.avg 7598731 ± 30% -84.5% 1180377 ± 66% sched_debug.cfs_rq:/.spread0.max -5400368 -72.9% -1460935 sched_debug.cfs_rq:/.spread0.min 1597450 ± 7% -80.2% 315751 ± 17% sched_debug.cfs_rq:/.spread0.stddev 166.55 ± 6% +39.0% 231.53 ± 2% sched_debug.cfs_rq:/.util_avg.stddev 683.78 ± 4% -29.5% 482.40 ± 3% sched_debug.cfs_rq:/.util_est_enqueued.avg 69.06 ± 20% -80.6% 13.37 ± 70% sched_debug.cfs_rq:/.util_est_enqueued.min 297890 ± 3% +13.2% 337258 sched_debug.cpu.avg_idle.avg 208323 -17.2% 172593 sched_debug.cpu.clock.avg 209312 -17.4% 172901 sched_debug.cpu.clock.max 207275 -16.9% 172268 sched_debug.cpu.clock.min 598.49 ± 23% -68.8% 186.64 ± 18% sched_debug.cpu.clock.stddev 206181 -17.1% 170875 sched_debug.cpu.clock_task.avg 207543 -17.4% 171519 sched_debug.cpu.clock_task.max 189665 -18.2% 155215 sched_debug.cpu.clock_task.min 1847 ± 4% -14.4% 1580 sched_debug.cpu.clock_task.stddev 0.00 ± 23% -68.1% 0.00 ± 18% sched_debug.cpu.next_balance.stddev 17.76 ± 6% -22.1% 13.84 ± 2% sched_debug.cpu.nr_running.avg 1.78 ± 20% -51.2% 0.87 ± 17% sched_debug.cpu.nr_running.min 8951364 ± 2% -80.1% 1785353 sched_debug.cpu.nr_switches.avg 13121147 ± 6% -83.0% 2229280 ± 6% sched_debug.cpu.nr_switches.max 6675136 ± 5% -77.1% 1528788 sched_debug.cpu.nr_switches.min 1223176 ± 12% -88.8% 136498 ± 18% sched_debug.cpu.nr_switches.stddev 207253 -16.9% 172251 sched_debug.cpu_clk 204122 -17.1% 169119 sched_debug.ktime 208018 -16.8% 173016 sched_debug.sched_clk 8.95 -18.4% 7.30 perf-stat.i.MPKI 2.198e+10 -11.5% 1.944e+10 perf-stat.i.branch-instructions 2.08 +0.1 2.15 perf-stat.i.branch-miss-rate% 4.454e+08 -6.3% 4.174e+08 perf-stat.i.branch-misses 14.80 ± 3% +8.3 23.06 perf-stat.i.cache-miss-rate% 1.17e+08 ± 3% +47.6% 1.727e+08 perf-stat.i.cache-misses 1.011e+09 ± 2% -25.2% 7.557e+08 perf-stat.i.cache-references 7375449 ± 4% -78.4% 1596261 perf-stat.i.context-switches 2.54 +6.7% 2.71 perf-stat.i.cpi 105262 -1.0% 104246 perf-stat.i.cpu-clock 454058 ± 9% -72.1% 126812 perf-stat.i.cpu-migrations 3793 ± 9% -56.3% 1658 perf-stat.i.cycles-between-cache-misses 1.11 ± 2% -0.6 0.48 perf-stat.i.dTLB-load-miss-rate% 3.656e+08 ± 2% -61.2% 1.42e+08 perf-stat.i.dTLB-load-misses 3.186e+10 -7.6% 2.944e+10 perf-stat.i.dTLB-loads 0.21 ± 3% -0.1 0.12 ± 4% perf-stat.i.dTLB-store-miss-rate% 40561226 ± 3% -46.2% 21804659 ± 4% perf-stat.i.dTLB-store-misses 1.909e+10 -7.3% 1.77e+10 perf-stat.i.dTLB-stores 44.18 +13.8 57.95 perf-stat.i.iTLB-load-miss-rate% 82455140 ± 2% -28.0% 59395280 ± 2% perf-stat.i.iTLB-load-misses 1.084e+08 ± 3% -59.8% 43544511 perf-stat.i.iTLB-loads 1.143e+11 -8.8% 1.042e+11 perf-stat.i.instructions 1584 ± 2% +11.9% 1773 ± 2% perf-stat.i.instructions-per-iTLB-miss 0.41 -8.9% 0.37 perf-stat.i.ipc 1441 +4.7% 1509 perf-stat.i.metric.K/sec 706.65 -8.5% 646.73 perf-stat.i.metric.M/sec 4941 +6.8% 5276 ± 3% perf-stat.i.minor-faults 41.57 -18.4 23.19 perf-stat.i.node-load-miss-rate% 24494497 ± 2% +66.8% 40863737 perf-stat.i.node-loads 33.06 ± 3% -24.8 8.27 ± 2% perf-stat.i.node-store-miss-rate% 4827109 ± 11% -40.4% 2878491 ± 2% perf-stat.i.node-store-misses 18618707 ± 2% +87.4% 34896795 perf-stat.i.node-stores 4971 +6.7% 5305 ± 3% perf-stat.i.page-faults 105262 -1.0% 104246 perf-stat.i.task-clock 8.08 -10.7% 7.22 perf-stat.overall.MPKI 2.06 +0.1 2.14 perf-stat.overall.branch-miss-rate% 14.44 ± 3% +8.5 22.91 perf-stat.overall.cache-miss-rate% 2.56 +5.5% 2.70 perf-stat.overall.cpi 2194 -25.6% 1632 perf-stat.overall.cycles-between-cache-misses 0.96 ± 2% -0.5 0.48 perf-stat.overall.dTLB-load-miss-rate% 0.19 ± 4% -0.1 0.12 ± 4% perf-stat.overall.dTLB-store-miss-rate% 43.98 +13.8 57.75 perf-stat.overall.iTLB-load-miss-rate% 1485 ± 2% +18.6% 1762 ± 2% perf-stat.overall.instructions-per-iTLB-miss 0.39 -5.2% 0.37 perf-stat.overall.ipc 28.27 ± 4% -5.7 22.53 perf-stat.overall.node-load-miss-rate% 14.63 ± 7% -7.2 7.40 ± 2% perf-stat.overall.node-store-miss-rate% 2.087e+10 -7.0% 1.94e+10 perf-stat.ps.branch-instructions 4.305e+08 -3.4% 4.158e+08 perf-stat.ps.branch-misses 1.276e+08 +34.7% 1.718e+08 perf-stat.ps.cache-misses 8.838e+08 -15.1% 7.501e+08 perf-stat.ps.cache-references 5683501 ± 2% -72.2% 1577596 perf-stat.ps.context-switches 318284 ± 8% -61.2% 123552 perf-stat.ps.cpu-migrations 2.975e+08 ± 2% -52.6% 1.411e+08 perf-stat.ps.dTLB-load-misses 3.063e+10 -4.2% 2.935e+10 perf-stat.ps.dTLB-loads 34785985 ± 4% -37.8% 21643894 ± 4% perf-stat.ps.dTLB-store-misses 1.837e+10 -4.0% 1.764e+10 perf-stat.ps.dTLB-stores 73690177 ± 2% -19.9% 59021610 ± 2% perf-stat.ps.iTLB-load-misses 93898143 ± 3% -54.0% 43180114 perf-stat.ps.iTLB-loads 1.094e+11 -5.0% 1.039e+11 perf-stat.ps.instructions 18.79 ± 9% +19.9% 22.54 ± 3% perf-stat.ps.major-faults 3833 +29.5% 4963 ± 2% perf-stat.ps.minor-faults 29621399 ± 2% +37.6% 40757022 perf-stat.ps.node-loads 3907385 ± 9% -28.9% 2776748 ± 2% perf-stat.ps.node-store-misses 22752383 +52.6% 34730720 perf-stat.ps.node-stores 3852 +29.4% 4985 ± 2% perf-stat.ps.page-faults 3.69e+13 -21.4% 2.899e+13 perf-stat.total.instructions 16.80 ± 3% -14.7 2.11 ± 5% perf-profile.calltrace.cycles-pp.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 15.81 ± 5% -14.0 1.84 ± 4% perf-profile.calltrace.cycles-pp.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg.sock_write_iter.vfs_write 16.18 ± 4% -13.7 2.46 ± 2% perf-profile.calltrace.cycles-pp.sock_def_readable.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write 15.12 ± 5% -13.5 1.63 ± 6% perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg.sock_write_iter 14.68 ± 4% -13.1 1.57 ± 6% perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg 14.40 ± 5% -12.9 1.54 ± 6% perf-profile.calltrace.cycles-pp.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sock_def_readable 14.47 ± 3% -12.7 1.81 ± 5% perf-profile.calltrace.cycles-pp.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg 14.25 ± 3% -12.5 1.78 ± 5% perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg 14.04 ± 3% -12.3 1.74 ± 5% perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic 6.92 ± 9% -6.9 0.00 perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 7.37 ± 4% -6.6 0.73 ± 5% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock 41.52 -6.2 35.38 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 6.10 ± 9% -6.1 0.00 perf-profile.calltrace.cycles-pp.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe 5.92 ± 9% -5.9 0.00 perf-profile.calltrace.cycles-pp.schedule.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64 5.78 ± 9% -5.8 0.00 perf-profile.calltrace.cycles-pp.__schedule.schedule.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode 6.18 ± 4% -5.6 0.62 ± 5% perf-profile.calltrace.cycles-pp.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common 5.84 ± 4% -5.2 0.62 ± 6% perf-profile.calltrace.cycles-pp.dequeue_task_fair.__schedule.schedule.schedule_timeout.unix_stream_data_wait 43.62 -5.0 38.58 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__libc_write 9.66 ± 5% -4.8 4.84 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 27.44 ± 2% -2.8 24.63 perf-profile.calltrace.cycles-pp.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write.do_syscall_64 50.46 -2.7 47.80 perf-profile.calltrace.cycles-pp.__libc_write 29.19 ± 2% -2.4 26.81 perf-profile.calltrace.cycles-pp.sock_write_iter.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 30.62 ± 2% -1.7 28.90 perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 28.56 -1.6 26.94 perf-profile.calltrace.cycles-pp.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter.vfs_read 28.92 -1.6 27.34 perf-profile.calltrace.cycles-pp.unix_stream_recvmsg.sock_recvmsg.sock_read_iter.vfs_read.ksys_read 30.08 -1.4 28.64 perf-profile.calltrace.cycles-pp.sock_recvmsg.sock_read_iter.vfs_read.ksys_read.do_syscall_64 31.28 -1.4 29.87 perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 32.85 -1.3 31.55 perf-profile.calltrace.cycles-pp.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 30.65 -1.2 29.46 perf-profile.calltrace.cycles-pp.sock_read_iter.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe 33.59 -1.2 32.44 perf-profile.calltrace.cycles-pp.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.90 ± 2% -0.3 0.60 perf-profile.calltrace.cycles-pp.mutex_lock.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 0.90 ± 3% -0.0 0.87 perf-profile.calltrace.cycles-pp.aa_sk_perm.security_socket_sendmsg.sock_write_iter.vfs_write.ksys_write 0.72 ± 3% +0.1 0.79 ± 2% perf-profile.calltrace.cycles-pp.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.sock_read_iter.vfs_read 1.07 ± 3% +0.1 1.15 ± 2% perf-profile.calltrace.cycles-pp.security_socket_sendmsg.sock_write_iter.vfs_write.ksys_write.do_syscall_64 0.55 ± 4% +0.1 0.64 ± 2% perf-profile.calltrace.cycles-pp.__fdget_pos.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.93 ± 3% +0.2 1.09 perf-profile.calltrace.cycles-pp.security_socket_recvmsg.sock_recvmsg.sock_read_iter.vfs_read.ksys_read 0.76 ± 5% +0.2 0.98 perf-profile.calltrace.cycles-pp.security_file_permission.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.60 ± 7% +0.2 0.84 perf-profile.calltrace.cycles-pp.apparmor_file_permission.security_file_permission.vfs_write.ksys_write.do_syscall_64 0.67 ± 4% +0.2 0.92 ± 3% perf-profile.calltrace.cycles-pp.get_obj_cgroup_from_current.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb 0.79 ± 3% +0.4 1.16 perf-profile.calltrace.cycles-pp.memcg_slab_post_alloc_hook.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb 0.34 ± 70% +0.4 0.72 ± 2% perf-profile.calltrace.cycles-pp.__fdget_pos.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 0.65 ± 3% +0.4 1.03 perf-profile.calltrace.cycles-pp.memcg_slab_post_alloc_hook.__kmem_cache_alloc_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb 0.76 ± 2% +0.4 1.21 perf-profile.calltrace.cycles-pp.__check_object_size.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_write_iter.vfs_write 0.56 ± 5% +0.5 1.02 ± 10% perf-profile.calltrace.cycles-pp.copyin._copy_from_iter.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_write_iter 0.00 +0.5 0.53 ± 4% perf-profile.calltrace.cycles-pp.get_obj_cgroup_from_current.__kmem_cache_alloc_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb 0.00 +0.6 0.55 ± 3% perf-profile.calltrace.cycles-pp.skb_unlink.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 0.00 +0.6 0.56 ± 4% perf-profile.calltrace.cycles-pp.unix_write_space.sock_wfree.unix_destruct_scm.skb_release_head_state.consume_skb 0.00 +0.6 0.56 ± 3% perf-profile.calltrace.cycles-pp.__get_obj_cgroup_from_memcg.get_obj_cgroup_from_current.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags 0.00 +0.6 0.61 ± 2% perf-profile.calltrace.cycles-pp.__fget_light.__fdget_pos.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.00 +0.6 0.63 ± 9% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.skb_queue_tail.unix_stream_sendmsg.sock_write_iter.vfs_write 0.86 ± 4% +0.6 1.49 ± 7% perf-profile.calltrace.cycles-pp._copy_from_iter.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_write_iter.vfs_write 1.66 ± 5% +0.7 2.33 ± 2% perf-profile.calltrace.cycles-pp.__kmem_cache_free.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg 4.27 +0.7 4.95 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.08 ±223% +0.7 0.78 ± 6% perf-profile.calltrace.cycles-pp.skb_set_owner_w.sock_alloc_send_pskb.unix_stream_sendmsg.sock_write_iter.vfs_write 0.00 +0.7 0.70 ± 9% perf-profile.calltrace.cycles-pp.skb_queue_tail.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write 0.00 +0.7 0.75 perf-profile.calltrace.cycles-pp.__build_skb_around.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg 1.47 ± 3% +0.8 2.24 perf-profile.calltrace.cycles-pp.__entry_text_start.__libc_read 0.09 ±223% +0.8 0.87 ± 13% perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyin._copy_from_iter.skb_copy_datagram_from_iter.unix_stream_sendmsg 0.46 ± 46% +0.8 1.27 ± 4% perf-profile.calltrace.cycles-pp._raw_spin_lock.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write 40.49 +0.8 41.33 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__libc_read 1.58 ± 3% +0.9 2.48 perf-profile.calltrace.cycles-pp.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic 1.27 ± 3% +0.9 2.18 ± 2% perf-profile.calltrace.cycles-pp.__entry_text_start.__libc_write 1.44 ± 3% +0.9 2.37 perf-profile.calltrace.cycles-pp.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor 0.00 +1.1 1.08 ± 23% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.__kmem_cache_alloc_node 0.00 +1.1 1.09 ± 22% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__unfreeze_partials.skb_release_data.consume_skb 0.92 ± 6% +1.1 2.01 ± 2% perf-profile.calltrace.cycles-pp.sock_wfree.unix_destruct_scm.skb_release_head_state.consume_skb.unix_stream_read_generic 1.10 ± 5% +1.1 2.23 perf-profile.calltrace.cycles-pp.unix_destruct_scm.skb_release_head_state.consume_skb.unix_stream_read_generic.unix_stream_recvmsg 0.00 +1.1 1.13 ± 22% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.__kmem_cache_alloc_node.__kmalloc_node_track_caller 0.00 +1.1 1.14 ± 21% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__unfreeze_partials.skb_release_data.consume_skb.unix_stream_read_generic 1.15 ± 5% +1.1 2.30 perf-profile.calltrace.cycles-pp.skb_release_head_state.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg 1.83 ± 3% +1.2 3.00 ± 3% perf-profile.calltrace.cycles-pp.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write 0.00 +1.2 1.20 ± 26% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.kmem_cache_alloc_node 0.00 +1.2 1.24 ± 26% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__unfreeze_partials.unix_stream_read_generic.unix_stream_recvmsg 0.00 +1.3 1.25 ± 25% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.kmem_cache_alloc_node.__alloc_skb 0.00 +1.3 1.29 ± 25% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__unfreeze_partials.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg 0.00 +1.3 1.30 ± 19% perf-profile.calltrace.cycles-pp.__unfreeze_partials.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg 1.38 ± 7% +1.4 2.80 perf-profile.calltrace.cycles-pp.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 0.00 +1.4 1.42 ± 19% perf-profile.calltrace.cycles-pp.get_partial_node.___slab_alloc.__kmem_cache_alloc_node.__kmalloc_node_track_caller.kmalloc_reserve 0.00 +1.4 1.44 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_safe_stack.__libc_read 0.00 +1.4 1.44 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_safe_stack.__libc_write 0.00 +1.5 1.46 ± 23% perf-profile.calltrace.cycles-pp.__unfreeze_partials.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 0.08 ±223% +1.5 1.55 ± 2% perf-profile.calltrace.cycles-pp.__slab_free.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 0.00 +1.5 1.54 ± 22% perf-profile.calltrace.cycles-pp.get_partial_node.___slab_alloc.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags 1.08 ± 7% +1.6 2.67 ± 2% perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter 1.16 ± 7% +1.6 2.78 ± 2% perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor 0.00 +1.7 1.68 perf-profile.calltrace.cycles-pp.__slab_free.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg 1.42 ± 6% +1.8 3.18 ± 2% perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic 0.00 +1.8 1.85 ± 15% perf-profile.calltrace.cycles-pp.___slab_alloc.__kmem_cache_alloc_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb 0.00 +2.0 1.98 ± 18% perf-profile.calltrace.cycles-pp.___slab_alloc.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb 3.28 ± 4% +2.3 5.56 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.__libc_write 3.36 ± 3% +2.4 5.74 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.__libc_read 48.59 +2.5 51.12 perf-profile.calltrace.cycles-pp.__libc_read 3.09 ± 4% +2.7 5.80 perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg 3.12 ± 4% +2.7 5.86 ± 2% perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg 3.15 ± 4% +2.8 5.91 ± 2% perf-profile.calltrace.cycles-pp.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 2.29 ± 6% +2.9 5.19 ± 6% perf-profile.calltrace.cycles-pp.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg 2.06 ± 7% +2.9 4.98 ± 5% perf-profile.calltrace.cycles-pp.__kmem_cache_alloc_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags 2.30 ± 7% +3.1 5.41 ± 4% perf-profile.calltrace.cycles-pp.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb 2.68 ± 6% +3.3 6.02 ± 4% perf-profile.calltrace.cycles-pp.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg 2.29 ± 9% +4.2 6.47 ± 2% perf-profile.calltrace.cycles-pp.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg 3.65 ± 7% +5.4 9.06 perf-profile.calltrace.cycles-pp.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter 5.79 ± 6% +7.2 12.99 ± 4% perf-profile.calltrace.cycles-pp.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg.sock_write_iter 5.91 ± 6% +7.3 13.18 ± 4% perf-profile.calltrace.cycles-pp.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg.sock_write_iter.vfs_write 6.55 ± 6% +8.1 14.68 ± 3% perf-profile.calltrace.cycles-pp.sock_alloc_send_pskb.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write 20.60 ± 5% -18.1 2.47 ± 4% perf-profile.children.cycles-pp.__schedule 20.44 ± 5% -18.0 2.43 ± 4% perf-profile.children.cycles-pp.schedule 16.85 ± 3% -14.7 2.11 ± 5% perf-profile.children.cycles-pp.unix_stream_data_wait 16.19 ± 4% -13.7 2.47 perf-profile.children.cycles-pp.sock_def_readable 15.84 ± 4% -13.7 2.12 ± 3% perf-profile.children.cycles-pp.__wake_up_common_lock 15.13 ± 5% -13.2 1.90 ± 4% perf-profile.children.cycles-pp.__wake_up_common 14.70 ± 4% -12.9 1.84 ± 4% perf-profile.children.cycles-pp.autoremove_wake_function 14.43 ± 4% -12.6 1.80 ± 4% perf-profile.children.cycles-pp.try_to_wake_up 14.49 ± 3% -12.3 2.21 ± 3% perf-profile.children.cycles-pp.schedule_timeout 8.67 ± 8% -7.9 0.77 ± 4% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 7.40 ± 4% -6.5 0.86 ± 4% perf-profile.children.cycles-pp.ttwu_do_activate 79.94 -6.4 73.55 perf-profile.children.cycles-pp.do_syscall_64 6.35 ± 8% -6.1 0.28 ± 10% perf-profile.children.cycles-pp.exit_to_user_mode_loop 6.20 ± 4% -5.5 0.74 ± 3% perf-profile.children.cycles-pp.enqueue_task_fair 5.86 ± 4% -5.1 0.75 ± 5% perf-profile.children.cycles-pp.dequeue_task_fair 13.96 ± 4% -4.1 9.85 perf-profile.children.cycles-pp.syscall_exit_to_user_mode 84.26 -4.1 80.14 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 4.41 ± 6% -3.9 0.52 ± 3% perf-profile.children.cycles-pp.pick_next_task_fair 4.28 ± 4% -3.8 0.50 ± 5% perf-profile.children.cycles-pp.update_curr 3.95 ± 6% -3.5 0.47 ± 4% perf-profile.children.cycles-pp.switch_mm_irqs_off 3.65 ± 4% -3.2 0.43 ± 2% perf-profile.children.cycles-pp.enqueue_entity 3.64 ± 6% -3.2 0.48 ± 2% perf-profile.children.cycles-pp.update_load_avg 27.48 ± 2% -2.8 24.70 perf-profile.children.cycles-pp.unix_stream_sendmsg 3.11 ± 4% -2.7 0.39 ± 4% perf-profile.children.cycles-pp.dequeue_entity 50.81 -2.6 48.19 perf-profile.children.cycles-pp.__libc_write 4.67 ± 5% -2.5 2.16 perf-profile.children.cycles-pp._raw_spin_lock 29.21 ± 2% -2.4 26.82 perf-profile.children.cycles-pp.sock_write_iter 2.32 ± 11% -2.0 0.29 ± 4% perf-profile.children.cycles-pp.select_task_rq 2.12 ± 5% -1.8 0.27 ± 7% perf-profile.children.cycles-pp.prepare_task_switch 2.10 ± 6% -1.8 0.28 ± 2% perf-profile.children.cycles-pp.switch_fpu_return 1.97 ± 13% -1.7 0.25 ± 4% perf-profile.children.cycles-pp.select_task_rq_fair 30.65 ± 2% -1.7 28.94 perf-profile.children.cycles-pp.vfs_write 28.60 -1.6 26.99 perf-profile.children.cycles-pp.unix_stream_read_generic 28.93 -1.6 27.35 perf-profile.children.cycles-pp.unix_stream_recvmsg 1.65 ± 6% -1.5 0.19 ± 3% perf-profile.children.cycles-pp.set_next_entity 30.10 -1.4 28.67 perf-profile.children.cycles-pp.sock_recvmsg 1.61 ± 4% -1.4 0.19 ± 6% perf-profile.children.cycles-pp.reweight_entity 1.63 ± 7% -1.4 0.22 ± 3% perf-profile.children.cycles-pp.restore_fpregs_from_fpstate 31.30 -1.4 29.90 perf-profile.children.cycles-pp.ksys_write 1.53 ± 6% -1.3 0.20 ± 7% perf-profile.children.cycles-pp.__switch_to_asm 32.87 -1.3 31.59 perf-profile.children.cycles-pp.vfs_read 30.66 -1.2 29.47 perf-profile.children.cycles-pp.sock_read_iter 33.60 -1.1 32.46 perf-profile.children.cycles-pp.ksys_read 1.01 ± 8% -0.9 0.06 ± 7% perf-profile.children.cycles-pp.put_prev_entity 1.04 ± 5% -0.9 0.13 ± 5% perf-profile.children.cycles-pp.__switch_to 0.97 ± 6% -0.9 0.09 ± 7% perf-profile.children.cycles-pp.check_preempt_curr 1.08 ± 5% -0.9 0.22 ± 3% perf-profile.children.cycles-pp.prepare_to_wait 0.92 ± 27% -0.9 0.07 ± 8% perf-profile.children.cycles-pp.select_idle_sibling 0.92 ± 7% -0.8 0.09 ± 9% perf-profile.children.cycles-pp.___perf_sw_event 0.94 ± 3% -0.8 0.12 ± 4% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq 0.94 ± 5% -0.8 0.13 ± 3% perf-profile.children.cycles-pp.update_rq_clock 0.92 ± 5% -0.8 0.16 ± 4% perf-profile.children.cycles-pp.perf_trace_sched_wakeup_template 0.83 ± 6% -0.8 0.08 ± 6% perf-profile.children.cycles-pp.check_preempt_wakeup 0.88 ± 4% -0.7 0.14 ± 5% perf-profile.children.cycles-pp.__update_load_avg_se 0.95 ± 2% -0.7 0.27 ± 5% perf-profile.children.cycles-pp.update_cfs_group 0.70 ± 5% -0.6 0.08 ± 7% perf-profile.children.cycles-pp.update_min_vruntime 0.68 ± 6% -0.6 0.08 ± 6% perf-profile.children.cycles-pp.os_xsave 0.61 ± 6% -0.5 0.08 ± 6% perf-profile.children.cycles-pp.perf_trace_sched_stat_runtime 0.52 ± 6% -0.5 0.02 ± 99% perf-profile.children.cycles-pp.pick_next_entity 0.48 ± 3% -0.4 0.07 ± 9% perf-profile.children.cycles-pp.__calc_delta 0.46 ± 3% -0.4 0.08 ± 6% perf-profile.children.cycles-pp.perf_tp_event 0.49 ± 15% -0.4 0.12 ± 4% perf-profile.children.cycles-pp.wake_affine 0.49 ± 5% -0.4 0.12 ± 3% perf-profile.children.cycles-pp.asm_sysvec_reschedule_ipi 0.38 ± 5% -0.3 0.05 ± 8% perf-profile.children.cycles-pp.finish_task_switch 1.08 ± 2% -0.3 0.76 perf-profile.children.cycles-pp.__cond_resched 0.36 ± 5% -0.3 0.05 ± 8% perf-profile.children.cycles-pp.sched_clock_cpu 0.93 ± 2% -0.3 0.62 perf-profile.children.cycles-pp.mutex_lock 0.34 ± 9% -0.3 0.03 ± 70% perf-profile.children.cycles-pp.cpuacct_charge 0.48 ± 4% -0.3 0.19 ± 3% perf-profile.children.cycles-pp.__list_del_entry_valid 0.32 ± 6% -0.3 0.04 ± 44% perf-profile.children.cycles-pp.native_sched_clock 0.44 ± 2% -0.2 0.19 ± 3% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 0.28 ± 5% -0.2 0.03 ± 70% perf-profile.children.cycles-pp.rb_erase 0.32 ± 15% -0.2 0.08 ± 7% perf-profile.children.cycles-pp.task_h_load 0.18 ± 5% -0.1 0.07 ± 7% perf-profile.children.cycles-pp.__list_add_valid 0.13 ± 9% -0.1 0.04 ± 44% perf-profile.children.cycles-pp.irqentry_exit_to_user_mode 0.23 ± 2% +0.0 0.25 ± 2% perf-profile.children.cycles-pp.mutex_unlock 0.06 +0.0 0.08 ± 4% perf-profile.children.cycles-pp.put_pid 0.16 ± 4% +0.0 0.18 ± 2% perf-profile.children.cycles-pp.__x64_sys_write 0.11 ± 6% +0.0 0.14 ± 5% perf-profile.children.cycles-pp.check_stack_object 0.09 ± 10% +0.0 0.12 ± 7% perf-profile.children.cycles-pp.__mod_memcg_state 0.05 ± 7% +0.0 0.09 ± 7% perf-profile.children.cycles-pp.unix_scm_to_skb 0.11 ± 6% +0.0 0.15 ± 6% perf-profile.children.cycles-pp.should_failslab 0.06 ± 6% +0.0 0.10 ± 4% perf-profile.children.cycles-pp.scm_recv 0.13 ± 5% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.__x64_sys_read 0.11 ± 16% +0.0 0.16 ± 15% perf-profile.children.cycles-pp.__mod_memcg_lruvec_state 0.00 +0.1 0.05 perf-profile.children.cycles-pp.skb_put 0.02 ± 99% +0.1 0.08 ± 4% perf-profile.children.cycles-pp.try_charge_memcg 0.12 +0.1 0.18 ± 2% perf-profile.children.cycles-pp.apparmor_socket_getpeersec_dgram 0.08 ± 8% +0.1 0.14 ± 4% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare 0.12 ± 3% +0.1 0.18 ± 3% perf-profile.children.cycles-pp.apparmor_socket_recvmsg 0.18 ± 5% +0.1 0.24 ± 4% perf-profile.children.cycles-pp.kmalloc_size_roundup 0.13 ± 8% +0.1 0.20 ± 3% perf-profile.children.cycles-pp.memcg_account_kmem 0.27 ± 2% +0.1 0.34 ± 2% perf-profile.children.cycles-pp.security_socket_getpeersec_dgram 0.00 +0.1 0.07 ± 10% perf-profile.children.cycles-pp.rw_verify_area 0.00 +0.1 0.07 ± 18% perf-profile.children.cycles-pp.newidle_balance 0.24 ± 5% +0.1 0.31 ± 2% perf-profile.children.cycles-pp.obj_cgroup_uncharge_pages 0.14 ± 7% +0.1 0.21 ± 5% perf-profile.children.cycles-pp.aa_file_perm 0.00 +0.1 0.08 ± 16% perf-profile.children.cycles-pp.load_balance 0.11 ± 8% +0.1 0.18 ± 4% perf-profile.children.cycles-pp.apparmor_socket_sendmsg 0.43 ± 5% +0.1 0.50 ± 3% perf-profile.children.cycles-pp.syscall_enter_from_user_mode 1.07 ± 3% +0.1 1.16 ± 2% perf-profile.children.cycles-pp.security_socket_sendmsg 0.02 ±141% +0.1 0.11 ± 7% perf-profile.children.cycles-pp.refill_stock 0.36 ± 3% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt 0.30 ± 5% +0.1 0.40 ± 2% perf-profile.children.cycles-pp.__hrtimer_run_queues 0.14 ± 10% +0.1 0.25 ± 3% perf-profile.children.cycles-pp.scheduler_tick 0.35 ± 3% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.hrtimer_interrupt 0.10 ± 12% +0.1 0.20 ± 3% perf-profile.children.cycles-pp.task_tick_fair 0.35 ± 2% +0.1 0.46 ± 2% perf-profile.children.cycles-pp.wait_for_unix_gc 0.20 ± 7% +0.1 0.31 ± 3% perf-profile.children.cycles-pp.update_process_times 0.24 ± 6% +0.1 0.35 ± 3% perf-profile.children.cycles-pp.tick_sched_timer 0.40 ± 4% +0.1 0.51 ± 2% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt 0.21 ± 7% +0.1 0.32 ± 3% perf-profile.children.cycles-pp.tick_sched_handle 0.00 +0.1 0.12 ± 11% perf-profile.children.cycles-pp.ordered_events__queue 0.00 +0.1 0.12 ± 11% perf-profile.children.cycles-pp.queue_event 0.04 ± 73% +0.1 0.16 ± 9% perf-profile.children.cycles-pp.__cmd_record 0.00 +0.1 0.12 ± 8% perf-profile.children.cycles-pp.process_simple 0.44 ± 4% +0.1 0.56 ± 2% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt 0.00 +0.1 0.13 ± 8% perf-profile.children.cycles-pp.record__finish_output 0.00 +0.1 0.13 ± 8% perf-profile.children.cycles-pp.perf_session__process_events 0.00 +0.1 0.13 ± 8% perf-profile.children.cycles-pp.reader__read_event 0.40 ± 3% +0.1 0.53 ± 2% perf-profile.children.cycles-pp.__might_sleep 0.00 +0.1 0.14 ± 4% perf-profile.children.cycles-pp.put_cpu_partial 0.83 ± 4% +0.1 0.97 perf-profile.children.cycles-pp.__virt_addr_valid 0.17 ± 7% +0.2 0.32 ± 2% perf-profile.children.cycles-pp.refill_obj_stock 0.24 ± 6% +0.2 0.40 ± 3% perf-profile.children.cycles-pp.kmalloc_slab 0.94 ± 2% +0.2 1.10 perf-profile.children.cycles-pp.security_socket_recvmsg 0.05 ± 48% +0.2 0.24 ± 5% perf-profile.children.cycles-pp.fsnotify_perm 0.28 ± 5% +0.2 0.48 ± 2% perf-profile.children.cycles-pp.__might_fault 1.81 ± 4% +0.2 2.05 perf-profile.children.cycles-pp.security_file_permission 0.46 ± 6% +0.3 0.71 ± 9% perf-profile.children.cycles-pp.skb_queue_tail 1.00 ± 4% +0.3 1.27 ± 2% perf-profile.children.cycles-pp.__fget_light 0.62 ± 5% +0.3 0.89 perf-profile.children.cycles-pp.__check_heap_object 0.41 ± 4% +0.3 0.69 perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack 0.41 ± 6% +0.3 0.70 ± 2% perf-profile.children.cycles-pp.obj_cgroup_charge 1.41 ± 5% +0.3 1.71 ± 2% perf-profile.children.cycles-pp.apparmor_file_permission 0.49 ± 4% +0.3 0.79 ± 2% perf-profile.children.cycles-pp.__get_obj_cgroup_from_memcg 0.26 ± 4% +0.3 0.56 ± 4% perf-profile.children.cycles-pp.unix_write_space 0.25 ± 9% +0.3 0.56 ± 3% perf-profile.children.cycles-pp.skb_unlink 0.46 ± 6% +0.3 0.78 ± 6% perf-profile.children.cycles-pp.skb_set_owner_w 1.06 ± 4% +0.3 1.39 ± 2% perf-profile.children.cycles-pp.__fdget_pos 0.70 ± 3% +0.3 1.03 ± 2% perf-profile.children.cycles-pp.__might_resched 0.58 ± 4% +0.5 1.04 ± 10% perf-profile.children.cycles-pp.copyin 0.26 ± 22% +0.5 0.75 perf-profile.children.cycles-pp.__build_skb_around 0.99 ± 3% +0.5 1.49 ± 3% perf-profile.children.cycles-pp.get_obj_cgroup_from_current 0.88 ± 4% +0.6 1.46 ± 2% perf-profile.children.cycles-pp.mod_objcg_state 0.88 ± 4% +0.6 1.52 ± 7% perf-profile.children.cycles-pp._copy_from_iter 1.66 ± 4% +0.7 2.34 perf-profile.children.cycles-pp.__kmem_cache_free 1.45 ± 3% +0.8 2.21 perf-profile.children.cycles-pp.memcg_slab_post_alloc_hook 0.72 ± 6% +0.9 1.62 perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack 1.58 ± 3% +0.9 2.48 perf-profile.children.cycles-pp.simple_copy_to_iter 0.92 ± 6% +1.1 2.02 perf-profile.children.cycles-pp.sock_wfree 1.13 ± 5% +1.1 2.26 perf-profile.children.cycles-pp.unix_destruct_scm 1.16 ± 5% +1.1 2.31 perf-profile.children.cycles-pp.skb_release_head_state 1.84 ± 3% +1.2 3.02 ± 3% perf-profile.children.cycles-pp.skb_copy_datagram_from_iter 2.41 ± 2% +1.4 3.77 perf-profile.children.cycles-pp.__check_object_size 1.39 ± 7% +1.4 2.82 perf-profile.children.cycles-pp.kmem_cache_free 1.16 ± 7% +1.6 2.79 ± 2% perf-profile.children.cycles-pp.copyout 1.43 ± 6% +1.8 3.20 ± 2% perf-profile.children.cycles-pp._copy_to_iter 1.66 ± 6% +2.0 3.71 ± 4% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 3.24 ± 4% +2.4 5.69 perf-profile.children.cycles-pp.__entry_text_start 49.06 +2.5 51.55 perf-profile.children.cycles-pp.__libc_read 0.62 ± 23% +2.6 3.24 perf-profile.children.cycles-pp.__slab_free 3.09 ± 4% +2.7 5.80 perf-profile.children.cycles-pp.__skb_datagram_iter 0.04 ±223% +2.7 2.77 ± 21% perf-profile.children.cycles-pp.__unfreeze_partials 3.12 ± 4% +2.7 5.86 ± 2% perf-profile.children.cycles-pp.skb_copy_datagram_iter 3.16 ± 4% +2.8 5.92 perf-profile.children.cycles-pp.unix_stream_read_actor 2.36 ± 5% +2.9 5.29 ± 6% perf-profile.children.cycles-pp.kmem_cache_alloc_node 0.04 ±223% +3.0 3.00 ± 20% perf-profile.children.cycles-pp.get_partial_node 2.14 ± 7% +3.0 5.10 ± 5% perf-profile.children.cycles-pp.__kmem_cache_alloc_node 2.12 ± 10% +3.0 5.12 ± 21% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 2.38 ± 7% +3.2 5.56 ± 4% perf-profile.children.cycles-pp.__kmalloc_node_track_caller 2.70 ± 6% +3.3 6.04 ± 4% perf-profile.children.cycles-pp.kmalloc_reserve 0.18 ±102% +3.7 3.83 ± 17% perf-profile.children.cycles-pp.___slab_alloc 2.24 ± 6% +4.0 6.25 ± 17% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 2.30 ± 9% +4.2 6.49 ± 2% perf-profile.children.cycles-pp.skb_release_data 6.70 ± 3% +4.7 11.39 perf-profile.children.cycles-pp.syscall_return_via_sysret 3.66 ± 7% +5.4 9.08 perf-profile.children.cycles-pp.consume_skb 5.82 ± 7% +7.2 13.04 ± 4% perf-profile.children.cycles-pp.__alloc_skb 5.92 ± 6% +7.3 13.19 ± 4% perf-profile.children.cycles-pp.alloc_skb_with_frags 6.56 ± 6% +8.1 14.70 ± 3% perf-profile.children.cycles-pp.sock_alloc_send_pskb 3.84 ± 6% -3.4 0.46 ± 4% perf-profile.self.cycles-pp.switch_mm_irqs_off 1.99 ± 5% -1.8 0.21 ± 6% perf-profile.self.cycles-pp.update_curr 1.78 ± 8% -1.6 0.22 ± 3% perf-profile.self.cycles-pp.update_load_avg 1.70 ± 5% -1.5 0.22 ± 6% perf-profile.self.cycles-pp.__schedule 1.63 ± 7% -1.4 0.22 ± 3% perf-profile.self.cycles-pp.restore_fpregs_from_fpstate 1.52 ± 6% -1.3 0.20 ± 7% perf-profile.self.cycles-pp.__switch_to_asm 1.39 ± 3% -1.2 0.16 ± 3% perf-profile.self.cycles-pp.enqueue_entity 0.98 ± 5% -0.9 0.12 ± 5% perf-profile.self.cycles-pp.__switch_to 0.92 ± 5% -0.8 0.12 ± 8% perf-profile.self.cycles-pp.pick_next_task_fair 0.90 ± 3% -0.8 0.11 perf-profile.self.cycles-pp.__update_load_avg_cfs_rq 0.84 ± 7% -0.8 0.08 ± 10% perf-profile.self.cycles-pp.___perf_sw_event 2.58 ± 3% -0.7 1.85 ± 2% perf-profile.self.cycles-pp._raw_spin_lock 0.85 ± 4% -0.7 0.13 ± 5% perf-profile.self.cycles-pp.__update_load_avg_se 2.12 ± 5% -0.7 1.40 ± 3% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.93 ± 2% -0.7 0.27 ± 5% perf-profile.self.cycles-pp.update_cfs_group 0.72 ± 6% -0.6 0.07 ± 7% perf-profile.self.cycles-pp.enqueue_task_fair 0.67 ± 5% -0.6 0.08 ± 6% perf-profile.self.cycles-pp.update_min_vruntime 0.67 ± 6% -0.6 0.07 ± 6% perf-profile.self.cycles-pp.os_xsave 0.70 ± 7% -0.6 0.12 ± 6% perf-profile.self.cycles-pp.prepare_task_switch 0.61 ± 5% -0.5 0.08 ± 6% perf-profile.self.cycles-pp.perf_trace_sched_stat_runtime 0.60 ± 5% -0.5 0.08 ± 6% perf-profile.self.cycles-pp.dequeue_task_fair 0.60 ± 4% -0.5 0.09 ± 9% perf-profile.self.cycles-pp.reweight_entity 0.57 ± 9% -0.5 0.07 perf-profile.self.cycles-pp.update_rq_clock 0.55 ± 3% -0.5 0.07 ± 5% perf-profile.self.cycles-pp.select_task_rq_fair 0.55 ± 4% -0.5 0.08 ± 9% perf-profile.self.cycles-pp.try_to_wake_up 0.49 ± 6% -0.4 0.06 ± 11% perf-profile.self.cycles-pp.unix_stream_data_wait 0.48 ± 4% -0.4 0.07 ± 8% perf-profile.self.cycles-pp.__calc_delta 0.46 ± 8% -0.4 0.05 ± 7% perf-profile.self.cycles-pp.switch_fpu_return 0.43 ± 6% -0.4 0.02 ± 99% perf-profile.self.cycles-pp.check_preempt_wakeup 0.43 ± 7% -0.4 0.06 ± 11% perf-profile.self.cycles-pp.__wake_up_common 0.44 ± 4% -0.4 0.08 perf-profile.self.cycles-pp.prepare_to_wait 1.21 ± 5% -0.4 0.86 ± 2% perf-profile.self.cycles-pp.__libc_read 0.35 ± 6% -0.3 0.03 ± 70% perf-profile.self.cycles-pp.select_task_rq 0.32 ± 10% -0.3 0.03 ± 70% perf-profile.self.cycles-pp.cpuacct_charge 0.32 ± 5% -0.3 0.04 ± 44% perf-profile.self.cycles-pp.native_sched_clock 0.95 ± 6% -0.3 0.69 perf-profile.self.cycles-pp.vfs_read 0.31 ± 3% -0.3 0.05 ± 7% perf-profile.self.cycles-pp.dequeue_entity 0.30 ± 4% -0.3 0.05 ± 7% perf-profile.self.cycles-pp.perf_tp_event 0.27 ± 5% -0.2 0.02 ± 99% perf-profile.self.cycles-pp.rb_erase 0.32 ± 14% -0.2 0.08 ± 4% perf-profile.self.cycles-pp.task_h_load 0.42 ± 4% -0.2 0.19 ± 3% perf-profile.self.cycles-pp.__list_del_entry_valid 0.29 ± 12% -0.2 0.06 ± 7% perf-profile.self.cycles-pp.perf_trace_sched_wakeup_template 0.47 ± 2% -0.2 0.28 ± 4% perf-profile.self.cycles-pp.mutex_lock 0.22 ± 4% -0.2 0.05 perf-profile.self.cycles-pp.schedule_timeout 0.27 ± 4% -0.1 0.14 ± 2% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore 0.17 ± 6% -0.1 0.07 ± 7% perf-profile.self.cycles-pp.__list_add_valid 0.39 ± 6% -0.1 0.34 ± 5% perf-profile.self.cycles-pp.security_file_permission 0.24 ± 7% -0.0 0.20 ± 3% perf-profile.self.cycles-pp.exit_to_user_mode_prepare 0.17 ± 7% -0.0 0.14 perf-profile.self.cycles-pp.is_vmalloc_addr 0.06 ± 8% +0.0 0.07 ± 5% perf-profile.self.cycles-pp.should_failslab 0.15 ± 4% +0.0 0.17 ± 4% perf-profile.self.cycles-pp.obj_cgroup_uncharge_pages 0.22 ± 2% +0.0 0.25 ± 3% perf-profile.self.cycles-pp.mutex_unlock 0.20 ± 3% +0.0 0.22 ± 5% perf-profile.self.cycles-pp.unix_destruct_scm 0.15 ± 6% +0.0 0.18 ± 2% perf-profile.self.cycles-pp.__x64_sys_write 0.07 ± 5% +0.0 0.10 ± 3% perf-profile.self.cycles-pp.__might_fault 0.12 ± 4% +0.0 0.14 ± 4% perf-profile.self.cycles-pp.wait_for_unix_gc 0.09 ± 7% +0.0 0.12 ± 5% perf-profile.self.cycles-pp.check_stack_object 0.32 ± 3% +0.0 0.36 ± 2% perf-profile.self.cycles-pp.unix_stream_recvmsg 0.05 ± 7% +0.0 0.08 ± 5% perf-profile.self.cycles-pp.scm_recv 0.25 ± 4% +0.0 0.28 perf-profile.self.cycles-pp.unix_write_space 0.07 ± 5% +0.0 0.10 ± 3% perf-profile.self.cycles-pp.security_socket_recvmsg 0.12 ± 7% +0.0 0.16 ± 3% perf-profile.self.cycles-pp.__x64_sys_read 0.03 ± 70% +0.0 0.08 ± 6% perf-profile.self.cycles-pp.security_socket_sendmsg 0.07 ± 5% +0.0 0.11 ± 4% perf-profile.self.cycles-pp.__skb_datagram_iter 0.15 ± 3% +0.0 0.20 ± 3% perf-profile.self.cycles-pp._copy_to_iter 0.42 ± 2% +0.0 0.46 perf-profile.self.cycles-pp.__cond_resched 0.16 ± 3% +0.0 0.21 ± 4% perf-profile.self.cycles-pp.ksys_read 0.00 +0.1 0.05 perf-profile.self.cycles-pp.copyout 0.08 ± 10% +0.1 0.13 ± 3% perf-profile.self.cycles-pp.syscall_exit_to_user_mode_prepare 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.skb_release_head_state 0.12 ± 4% +0.1 0.17 ± 4% perf-profile.self.cycles-pp.apparmor_socket_recvmsg 0.11 ± 3% +0.1 0.17 ± 2% perf-profile.self.cycles-pp.apparmor_socket_getpeersec_dgram 0.00 +0.1 0.06 ± 9% perf-profile.self.cycles-pp.rw_verify_area 0.02 ± 99% +0.1 0.08 ± 8% perf-profile.self.cycles-pp.unix_scm_to_skb 0.00 +0.1 0.06 ± 8% perf-profile.self.cycles-pp.refill_stock 0.10 ± 9% +0.1 0.16 ± 3% perf-profile.self.cycles-pp.alloc_skb_with_frags 0.00 +0.1 0.06 ± 6% perf-profile.self.cycles-pp.put_pid 0.07 ± 5% +0.1 0.13 ± 5% perf-profile.self.cycles-pp.__fdget_pos 0.00 +0.1 0.06 perf-profile.self.cycles-pp.try_charge_memcg 0.35 ± 5% +0.1 0.41 ± 3% perf-profile.self.cycles-pp.syscall_enter_from_user_mode 0.29 ± 2% +0.1 0.35 perf-profile.self.cycles-pp.do_syscall_64 0.13 ± 7% +0.1 0.19 ± 2% perf-profile.self.cycles-pp.skb_copy_datagram_from_iter 0.00 +0.1 0.06 ± 7% perf-profile.self.cycles-pp.skb_copy_datagram_iter 0.13 ± 6% +0.1 0.20 ± 6% perf-profile.self.cycles-pp.aa_file_perm 0.01 ±223% +0.1 0.08 ± 9% perf-profile.self.cycles-pp.copyin 0.00 +0.1 0.07 ± 5% perf-profile.self.cycles-pp.memcg_account_kmem 0.16 ± 7% +0.1 0.23 ± 2% perf-profile.self.cycles-pp._copy_from_iter 0.15 ± 8% +0.1 0.22 ± 5% perf-profile.self.cycles-pp.ksys_write 0.10 ± 5% +0.1 0.18 ± 5% perf-profile.self.cycles-pp.apparmor_socket_sendmsg 0.62 +0.1 0.70 ± 3% perf-profile.self.cycles-pp.__libc_write 0.17 ± 4% +0.1 0.26 ± 2% perf-profile.self.cycles-pp.sock_alloc_send_pskb 0.20 ± 2% +0.1 0.29 ± 3% perf-profile.self.cycles-pp.consume_skb 0.00 +0.1 0.09 ± 7% perf-profile.self.cycles-pp.skb_queue_tail 0.17 ± 5% +0.1 0.27 ± 5% perf-profile.self.cycles-pp.kmalloc_slab 0.14 ± 7% +0.1 0.24 ± 3% perf-profile.self.cycles-pp.kmalloc_reserve 0.00 +0.1 0.11 ± 12% perf-profile.self.cycles-pp.queue_event 0.80 ± 4% +0.1 0.91 ± 2% perf-profile.self.cycles-pp.__virt_addr_valid 0.35 ± 3% +0.1 0.47 ± 2% perf-profile.self.cycles-pp.__might_sleep 0.22 ± 5% +0.1 0.35 perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack 0.00 +0.1 0.14 ± 2% perf-profile.self.cycles-pp.put_cpu_partial 0.17 ± 7% +0.2 0.32 ± 2% perf-profile.self.cycles-pp.refill_obj_stock 0.95 ± 4% +0.2 1.10 perf-profile.self.cycles-pp.aa_sk_perm 0.15 ± 13% +0.2 0.31 perf-profile.self.cycles-pp.__kmalloc_node_track_caller 0.01 ±223% +0.2 0.18 ± 8% perf-profile.self.cycles-pp.skb_unlink 0.26 ± 7% +0.2 0.44 ± 2% perf-profile.self.cycles-pp.obj_cgroup_charge 0.04 ± 72% +0.2 0.24 ± 4% perf-profile.self.cycles-pp.fsnotify_perm 0.47 ± 4% +0.2 0.67 ± 7% perf-profile.self.cycles-pp.get_obj_cgroup_from_current 1.26 ± 6% +0.2 1.49 ± 2% perf-profile.self.cycles-pp.apparmor_file_permission 0.57 ± 3% +0.2 0.80 perf-profile.self.cycles-pp.sock_read_iter 0.36 ± 4% +0.2 0.60 perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack 0.99 ± 4% +0.3 1.25 ± 2% perf-profile.self.cycles-pp.__fget_light 0.35 ± 4% +0.3 0.61 ± 7% perf-profile.self.cycles-pp.sock_def_readable 0.60 ± 5% +0.3 0.86 perf-profile.self.cycles-pp.__check_heap_object 0.01 ±223% +0.3 0.28 ± 9% perf-profile.self.cycles-pp.__unfreeze_partials 0.47 ± 4% +0.3 0.74 ± 2% perf-profile.self.cycles-pp.__get_obj_cgroup_from_memcg 0.44 ± 6% +0.3 0.73 ± 3% perf-profile.self.cycles-pp.kmem_cache_alloc_node 0.45 ± 7% +0.3 0.77 ± 6% perf-profile.self.cycles-pp.skb_set_owner_w 0.68 ± 3% +0.3 1.00 ± 2% perf-profile.self.cycles-pp.__might_resched 0.64 ± 4% +0.3 0.98 perf-profile.self.cycles-pp.sock_write_iter 0.51 ± 5% +0.3 0.86 perf-profile.self.cycles-pp.__kmem_cache_alloc_node 1.12 ± 2% +0.4 1.48 ± 4% perf-profile.self.cycles-pp.unix_stream_sendmsg 1.09 ± 5% +0.4 1.50 ± 2% perf-profile.self.cycles-pp.__kmem_cache_free 0.54 ± 4% +0.4 0.95 perf-profile.self.cycles-pp.vfs_write 0.02 ±223% +0.4 0.43 ± 8% perf-profile.self.cycles-pp.get_partial_node 0.52 ± 6% +0.5 0.98 ± 2% perf-profile.self.cycles-pp.__alloc_skb 0.24 ± 21% +0.5 0.73 perf-profile.self.cycles-pp.__build_skb_around 1.12 ± 3% +0.5 1.62 perf-profile.self.cycles-pp.memcg_slab_post_alloc_hook 0.75 ± 4% +0.5 1.28 perf-profile.self.cycles-pp.mod_objcg_state 1.32 ± 3% +0.6 1.95 perf-profile.self.cycles-pp.unix_stream_read_generic 0.11 ± 78% +0.7 0.82 ± 5% perf-profile.self.cycles-pp.___slab_alloc 0.20 ± 17% +0.8 0.96 perf-profile.self.cycles-pp.skb_release_data 0.64 ± 8% +0.8 1.43 perf-profile.self.cycles-pp.sock_wfree 0.71 ± 7% +1.0 1.69 perf-profile.self.cycles-pp.__check_object_size 0.99 ± 9% +1.1 2.12 perf-profile.self.cycles-pp.kmem_cache_free 1.64 ± 6% +2.0 3.66 ± 4% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 2.89 ± 3% +2.2 5.10 perf-profile.self.cycles-pp.__entry_text_start 4.39 ± 3% +2.4 6.75 perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.61 ± 24% +2.6 3.22 perf-profile.self.cycles-pp.__slab_free 2.11 ± 10% +3.0 5.12 ± 21% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 5.32 ± 4% +3.7 8.98 perf-profile.self.cycles-pp.syscall_exit_to_user_mode 6.69 ± 3% +4.7 11.38 perf-profile.self.cycles-pp.syscall_return_via_sysret 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