Greeting, FYI, we noticed a 17.0% improvement of will-it-scale.per_process_ops due to commit: commit: f0a3a24b532d9a7e56a33c5112b2a212ed6ec580 ("mm: memcg/slab: rework non-root kmem_cache lifecycle management") https://kernel.googlesource.com/pub/scm/linux/kernel/git/torvalds/linux.git master in testcase: will-it-scale on test machine: 96 threads Intel(R) Xeon(R) CPU @ 2.30GHz with 128G memory with following parameters: nr_task: 50% mode: process test: open1 ucode: 0x400001c cpufreq_governor: performance 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 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/mode/nr_task/rootfs/tbox_group/test/testcase/ucode: gcc-7/performance/x86_64-rhel-7.2-clear/process/50%/clear-ota-25590-x86_64-2018-10-18.cgz/lkp-csl-2sp4/open1/will-it-scale/0x400001c commit: 63b02ef7dc ("mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock") f0a3a24b53 ("mm: memcg/slab: rework non-root kmem_cache lifecycle management") 63b02ef7dc4ec239 f0a3a24b532d9a7e56a33c5112b ---------------- --------------------------- fail:runs %reproduction fail:runs | | | :4 25% 1:4 dmesg.WARNING:at#for_ip_interrupt_entry/0x :4 25% 1:4 dmesg.WARNING:at#for_ip_swapgs_restore_regs_and_return_to_usermode/0x :4 25% 1:4 dmesg.WARNING:at_ip__fsnotify_parent/0x :4 25% 1:4 dmesg.WARNING:at_ip__slab_free/0x :4 25% 1:4 dmesg.WARNING:at_ip_do_filp_open/0x :4 25% 1:4 dmesg.WARNING:stack_recursion %stddev %change %stddev \ | \ 555883 +17.0% 650457 will-it-scale.per_process_ops 26682437 +17.0% 31221973 will-it-scale.workload 65867 ± 5% -18.4% 53730 ± 11% meminfo.Shmem 2636 ± 23% -20.9% 2085 ± 16% numa-meminfo.node1.PageTables 660.25 ± 24% -21.1% 520.75 ± 16% numa-vmstat.node1.nr_page_table_pages 1918 +2.2% 1961 turbostat.Avg_MHz 13.37 +2.0 15.36 mpstat.cpu.all.soft% 2.12 +0.5 2.60 mpstat.cpu.all.usr% 37.75 -4.6% 36.00 vmstat.cpu.id 59.25 +3.0% 61.00 vmstat.cpu.sy 3063 +4.6% 3202 vmstat.system.cs 555.75 ± 7% +17.5% 653.25 ± 4% slabinfo.bdev_cache.active_objs 555.75 ± 7% +17.5% 653.25 ± 4% slabinfo.bdev_cache.num_objs 1386 ± 7% +20.1% 1665 ± 6% slabinfo.file_lock_cache.active_objs 1386 ± 7% +20.1% 1665 ± 6% slabinfo.file_lock_cache.num_objs 14162 ± 6% -11.2% 12572 slabinfo.vmap_area.active_objs 83520 -3.6% 80550 proc-vmstat.nr_active_anon 16477 ± 5% -18.5% 13434 ± 11% proc-vmstat.nr_shmem 385794 +4.7% 403820 proc-vmstat.nr_slab_unreclaimable 83520 -3.6% 80550 proc-vmstat.nr_zone_active_anon 2.254e+08 +5.3% 2.374e+08 proc-vmstat.numa_hit 2.254e+08 +5.3% 2.374e+08 proc-vmstat.numa_local 23072 ± 2% -18.2% 18870 ± 14% proc-vmstat.pgactivate 4.497e+08 +5.3% 4.737e+08 proc-vmstat.pgalloc_normal 4.496e+08 +5.3% 4.736e+08 proc-vmstat.pgfree 537647 ± 22% +28.9% 693154 ± 5% sched_debug.cfs_rq:/.load.max 149130 ± 24% +33.4% 198967 ± 9% sched_debug.cfs_rq:/.load.stddev 3.24 ± 7% +38.8% 4.50 ± 6% sched_debug.cfs_rq:/.nr_spread_over.avg 10.21 ± 4% +18.0% 12.04 ± 3% sched_debug.cfs_rq:/.nr_spread_over.max 2.26 ± 2% +15.4% 2.61 ± 2% sched_debug.cfs_rq:/.nr_spread_over.stddev 537441 ± 22% +28.6% 691022 ± 5% sched_debug.cfs_rq:/.runnable_weight.max 149158 ± 24% +33.4% 198952 ± 9% sched_debug.cfs_rq:/.runnable_weight.stddev 1076 ± 3% +9.3% 1177 ± 3% sched_debug.cfs_rq:/.util_avg.max 751.93 ± 5% -11.1% 668.73 ± 9% sched_debug.cpu.ttwu_count.stddev 1157 +10.3% 1276 ± 2% sched_debug.cpu.ttwu_local.min 9246 ± 19% +174.1% 25345 ± 80% softirqs.CPU1.RCU 8014 ± 4% +136.1% 18921 ± 84% softirqs.CPU15.RCU 8260 ± 3% +20.6% 9964 ± 3% softirqs.CPU16.RCU 8507 ± 5% +18.8% 10108 ± 5% softirqs.CPU17.RCU 8509 ± 5% +21.1% 10303 ± 13% softirqs.CPU21.RCU 16958 ± 3% -7.3% 15718 softirqs.CPU3.SCHED 106141 ± 16% -14.0% 91324 ± 5% softirqs.CPU3.TIMER 8210 ± 4% +28.8% 10576 ± 14% softirqs.CPU30.RCU 7600 +19.7% 9097 ± 8% softirqs.CPU32.RCU 7866 ± 4% +23.6% 9721 ± 4% softirqs.CPU4.RCU 7751 ± 4% +43.2% 11103 ± 35% softirqs.CPU40.RCU 8072 ± 7% +56.3% 12620 ± 42% softirqs.CPU49.RCU 8006 ± 2% +17.3% 9389 ± 6% softirqs.CPU5.RCU 7787 ± 2% +142.1% 18851 ± 89% softirqs.CPU52.RCU 7905 ± 7% +18.9% 9398 ± 8% softirqs.CPU6.RCU 97009 ± 3% -7.8% 89464 ± 5% softirqs.CPU7.TIMER 7873 ± 4% +19.0% 9369 ± 11% softirqs.CPU74.RCU 7841 ± 5% +33.4% 10462 ± 22% softirqs.CPU75.RCU 7729 ± 3% +23.1% 9514 ± 5% softirqs.CPU76.RCU 7335 ± 3% +24.4% 9125 ± 9% softirqs.CPU80.RCU 825547 ± 2% +12.9% 932108 softirqs.RCU 3.36 -15.5% 2.84 perf-stat.i.MPKI 3.351e+10 +16.4% 3.899e+10 perf-stat.i.branch-instructions 1.616e+08 +16.0% 1.873e+08 perf-stat.i.branch-misses 51.01 +1.3 52.31 perf-stat.i.cache-miss-rate% 5.765e+08 -1.5% 5.678e+08 perf-stat.i.cache-references 3005 +4.6% 3144 perf-stat.i.context-switches 1.07 -12.3% 0.94 perf-stat.i.cpi 1.833e+11 +2.2% 1.872e+11 perf-stat.i.cpu-cycles 263.66 +22.5% 322.95 perf-stat.i.cpu-migrations 623.39 +1.2% 630.80 perf-stat.i.cycles-between-cache-misses 5.193e+10 +16.4% 6.043e+10 perf-stat.i.dTLB-loads 3.131e+10 +16.5% 3.649e+10 perf-stat.i.dTLB-stores 1.539e+08 +26.1% 1.942e+08 perf-stat.i.iTLB-load-misses 1.716e+11 +16.5% 1.999e+11 perf-stat.i.instructions 1114 -7.6% 1029 perf-stat.i.instructions-per-iTLB-miss 0.94 +14.0% 1.07 perf-stat.i.ipc 48.56 -19.4 29.21 perf-stat.i.node-load-miss-rate% 12639131 -4.7% 12049082 ± 2% perf-stat.i.node-load-misses 13399339 ± 2% +118.1% 29226043 perf-stat.i.node-loads 28.53 -3.5 25.03 ± 2% perf-stat.i.node-store-miss-rate% 9930522 +6.5% 10574595 ± 2% perf-stat.i.node-store-misses 24890314 +27.4% 31710424 ± 2% perf-stat.i.node-stores 3.36 -15.5% 2.84 perf-stat.overall.MPKI 51.00 +1.3 52.30 perf-stat.overall.cache-miss-rate% 1.07 -12.3% 0.94 perf-stat.overall.cpi 623.29 +1.2% 630.62 perf-stat.overall.cycles-between-cache-misses 1114 -7.7% 1029 perf-stat.overall.instructions-per-iTLB-miss 0.94 +14.0% 1.07 perf-stat.overall.ipc 48.55 -19.4 29.19 perf-stat.overall.node-load-miss-rate% 28.52 -3.5 25.01 ± 2% perf-stat.overall.node-store-miss-rate% 3.339e+10 +16.4% 3.886e+10 perf-stat.ps.branch-instructions 1.61e+08 +16.0% 1.867e+08 perf-stat.ps.branch-misses 5.746e+08 -1.5% 5.659e+08 perf-stat.ps.cache-references 2995 +4.6% 3134 perf-stat.ps.context-switches 1.826e+11 +2.2% 1.866e+11 perf-stat.ps.cpu-cycles 262.75 +22.5% 321.83 perf-stat.ps.cpu-migrations 5.176e+10 +16.4% 6.023e+10 perf-stat.ps.dTLB-loads 3.12e+10 +16.5% 3.637e+10 perf-stat.ps.dTLB-stores 1.534e+08 +26.1% 1.935e+08 perf-stat.ps.iTLB-load-misses 1.71e+11 +16.5% 1.992e+11 perf-stat.ps.instructions 12596472 -4.7% 12008197 ± 2% perf-stat.ps.node-load-misses 13354419 ± 2% +118.1% 29127885 perf-stat.ps.node-loads 9896963 +6.5% 10538664 ± 2% perf-stat.ps.node-store-misses 24805568 +27.4% 31602392 ± 2% perf-stat.ps.node-stores 5.103e+13 +16.5% 5.947e+13 perf-stat.total.instructions 0.25 ±173% +1.3e+06% 3347 ±173% interrupts.107:PCI-MSI.31981640-edge.i40e-eth0-TxRx-71 0.25 ±173% +26300.0% 66.00 ±166% interrupts.97:PCI-MSI.31981630-edge.i40e-eth0-TxRx-61 209.75 ± 26% +40.6% 295.00 ± 16% interrupts.CPU10.RES:Rescheduling_interrupts 104.25 ± 13% -47.0% 55.25 ± 44% interrupts.CPU10.TLB:TLB_shootdowns 223.50 ± 23% +52.0% 339.75 ± 10% interrupts.CPU13.RES:Rescheduling_interrupts 188.75 ± 20% +46.4% 276.25 ± 14% interrupts.CPU20.RES:Rescheduling_interrupts 169.50 ± 10% +114.9% 364.25 ± 31% interrupts.CPU22.RES:Rescheduling_interrupts 178.50 ± 12% +47.3% 263.00 ± 15% interrupts.CPU23.RES:Rescheduling_interrupts 74.50 ± 30% -41.6% 43.50 ± 28% interrupts.CPU23.TLB:TLB_shootdowns 55.50 ± 33% +72.1% 95.50 ± 9% interrupts.CPU24.TLB:TLB_shootdowns 229.00 ± 16% +35.7% 310.75 ± 9% interrupts.CPU26.RES:Rescheduling_interrupts 49.75 ± 48% +128.1% 113.50 ± 15% interrupts.CPU26.TLB:TLB_shootdowns 221.50 ± 14% +70.4% 377.50 ± 19% interrupts.CPU27.RES:Rescheduling_interrupts 49.50 ± 35% +65.2% 81.75 ± 17% interrupts.CPU30.TLB:TLB_shootdowns 201.50 ± 28% +111.3% 425.75 ± 39% interrupts.CPU32.RES:Rescheduling_interrupts 186.50 ± 21% +99.2% 371.50 ± 37% interrupts.CPU34.RES:Rescheduling_interrupts 215.00 ± 14% +46.5% 315.00 ± 17% interrupts.CPU37.RES:Rescheduling_interrupts 7287 ± 5% -28.1% 5239 ± 29% interrupts.CPU38.NMI:Non-maskable_interrupts 7287 ± 5% -28.1% 5239 ± 29% interrupts.CPU38.PMI:Performance_monitoring_interrupts 7222 ± 6% -28.2% 5186 ± 30% interrupts.CPU39.NMI:Non-maskable_interrupts 7222 ± 6% -28.2% 5186 ± 30% interrupts.CPU39.PMI:Performance_monitoring_interrupts 7244 ± 5% -28.5% 5179 ± 30% interrupts.CPU41.NMI:Non-maskable_interrupts 7244 ± 5% -28.5% 5179 ± 30% interrupts.CPU41.PMI:Performance_monitoring_interrupts 7242 ± 5% -27.6% 5240 ± 29% interrupts.CPU43.NMI:Non-maskable_interrupts 7242 ± 5% -27.6% 5240 ± 29% interrupts.CPU43.PMI:Performance_monitoring_interrupts 7224 ± 5% -28.4% 5173 ± 29% interrupts.CPU44.NMI:Non-maskable_interrupts 7224 ± 5% -28.4% 5173 ± 29% interrupts.CPU44.PMI:Performance_monitoring_interrupts 7250 ± 5% -28.4% 5189 ± 29% interrupts.CPU45.NMI:Non-maskable_interrupts 7250 ± 5% -28.4% 5189 ± 29% interrupts.CPU45.PMI:Performance_monitoring_interrupts 206.25 ± 23% +89.8% 391.50 ± 23% interrupts.CPU45.RES:Rescheduling_interrupts 7226 ± 5% -27.8% 5220 ± 29% interrupts.CPU46.NMI:Non-maskable_interrupts 7226 ± 5% -27.8% 5220 ± 29% interrupts.CPU46.PMI:Performance_monitoring_interrupts 41.00 ± 34% +1946.3% 839.00 ±150% interrupts.CPU46.TLB:TLB_shootdowns 296.00 ± 37% +64.2% 486.00 ± 24% interrupts.CPU48.RES:Rescheduling_interrupts 193.00 ± 22% +77.7% 343.00 ± 10% interrupts.CPU49.RES:Rescheduling_interrupts 7094 ± 5% -27.8% 5123 ± 29% interrupts.CPU53.NMI:Non-maskable_interrupts 7094 ± 5% -27.8% 5123 ± 29% interrupts.CPU53.PMI:Performance_monitoring_interrupts 59.50 ± 20% +56.3% 93.00 ± 22% interrupts.CPU53.TLB:TLB_shootdowns 7123 ± 5% -28.5% 5090 ± 30% interrupts.CPU54.NMI:Non-maskable_interrupts 7123 ± 5% -28.5% 5090 ± 30% interrupts.CPU54.PMI:Performance_monitoring_interrupts 193.25 ± 18% +43.2% 276.75 ± 9% interrupts.CPU57.RES:Rescheduling_interrupts 200.25 ± 17% +57.1% 314.50 ± 13% interrupts.CPU58.RES:Rescheduling_interrupts 219.75 ± 12% +24.7% 274.00 ± 10% interrupts.CPU59.RES:Rescheduling_interrupts 171.00 ± 12% +49.3% 255.25 ± 28% interrupts.CPU64.RES:Rescheduling_interrupts 215.00 ± 25% +39.5% 300.00 ± 24% interrupts.CPU65.RES:Rescheduling_interrupts 175.25 ± 23% +86.6% 327.00 ± 30% interrupts.CPU68.RES:Rescheduling_interrupts 248.25 ± 14% +32.3% 328.50 ± 8% interrupts.CPU73.RES:Rescheduling_interrupts 233.75 ± 12% +59.8% 373.50 ± 30% interrupts.CPU75.RES:Rescheduling_interrupts 250.75 ± 10% +31.1% 328.75 ± 17% interrupts.CPU76.RES:Rescheduling_interrupts 242.75 ± 27% +93.4% 469.50 ± 40% interrupts.CPU78.RES:Rescheduling_interrupts 197.00 ± 18% +79.1% 352.75 ± 24% interrupts.CPU79.RES:Rescheduling_interrupts 188.75 ± 20% +59.7% 301.50 ± 18% interrupts.CPU8.RES:Rescheduling_interrupts 168.50 ± 25% +83.7% 309.50 ± 15% interrupts.CPU84.RES:Rescheduling_interrupts 213.50 ± 8% +66.0% 354.50 ± 19% interrupts.CPU85.RES:Rescheduling_interrupts 202.25 ± 25% +44.9% 293.00 ± 8% interrupts.CPU88.RES:Rescheduling_interrupts 194.75 ± 33% +66.6% 324.50 ± 12% interrupts.CPU89.RES:Rescheduling_interrupts 175.00 ± 7% +46.3% 256.00 ± 22% interrupts.CPU9.RES:Rescheduling_interrupts 229.50 ± 21% +28.6% 295.25 ± 8% interrupts.CPU90.RES:Rescheduling_interrupts 200.50 ± 34% +63.6% 328.00 ± 17% interrupts.CPU92.RES:Rescheduling_interrupts 207.25 ± 31% +76.5% 365.75 ± 11% interrupts.CPU93.RES:Rescheduling_interrupts 191.50 ± 26% +44.6% 277.00 ± 8% interrupts.CPU94.RES:Rescheduling_interrupts 676228 ± 6% -18.6% 550169 ± 11% interrupts.NMI:Non-maskable_interrupts 676228 ± 6% -18.6% 550169 ± 11% interrupts.PMI:Performance_monitoring_interrupts 23852 ± 5% +34.9% 32177 interrupts.RES:Rescheduling_interrupts 6714 ± 12% +29.7% 8709 ± 24% interrupts.TLB:TLB_shootdowns 21.39 ± 7% -14.3 7.08 ± 5% perf-profile.calltrace.cycles-pp.kmem_cache_alloc.__alloc_file.alloc_empty_file.path_openat.do_filp_open 24.33 ± 7% -11.6 12.76 ± 5% perf-profile.calltrace.cycles-pp.__alloc_file.alloc_empty_file.path_openat.do_filp_open.do_sys_open 24.55 ± 7% -11.5 13.05 ± 5% perf-profile.calltrace.cycles-pp.alloc_empty_file.path_openat.do_filp_open.do_sys_open.do_syscall_64 9.37 ± 9% -9.4 0.00 perf-profile.calltrace.cycles-pp.get_mem_cgroup_from_mm.memcg_kmem_get_cache.kmem_cache_alloc.__alloc_file.alloc_empty_file 9.83 ± 9% -8.7 1.10 ± 6% perf-profile.calltrace.cycles-pp.memcg_kmem_get_cache.kmem_cache_alloc.__alloc_file.alloc_empty_file.path_openat 6.66 ± 7% -6.7 0.00 perf-profile.calltrace.cycles-pp.memcg_kmem_put_cache.kmem_cache_alloc.__alloc_file.alloc_empty_file.path_openat 39.66 ± 6% -5.8 33.81 ± 5% perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 39.98 ± 6% -5.7 34.30 ± 5% perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 44.71 ± 6% -4.5 40.22 ± 5% perf-profile.calltrace.cycles-pp.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.79 ± 9% +0.1 0.92 ± 8% perf-profile.calltrace.cycles-pp.__legitimize_mnt.legitimize_path.unlazy_walk.complete_walk.path_openat 0.68 ± 6% +0.1 0.80 ± 5% perf-profile.calltrace.cycles-pp.kmem_cache_alloc.getname_flags.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.59 ± 7% +0.2 0.75 ± 8% perf-profile.calltrace.cycles-pp.lookup_fast.path_openat.do_filp_open.do_sys_open.do_syscall_64 0.59 ± 6% +0.2 0.77 ± 5% perf-profile.calltrace.cycles-pp.ima_file_check.path_openat.do_filp_open.do_sys_open.do_syscall_64 0.98 ± 6% +0.2 1.17 ± 4% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64 0.83 ± 5% +0.2 1.04 ± 4% perf-profile.calltrace.cycles-pp.avc_has_perm_noaudit.selinux_inode_permission.security_inode_permission.link_path_walk.path_openat 0.94 ± 7% +0.2 1.14 ± 5% perf-profile.calltrace.cycles-pp.strncpy_from_user.getname_flags.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.07 ± 8% +0.2 1.28 ± 7% perf-profile.calltrace.cycles-pp.page_counter_try_charge.__memcg_kmem_charge_memcg.new_slab.___slab_alloc.__slab_alloc 0.78 ± 6% +0.2 1.00 ± 6% perf-profile.calltrace.cycles-pp.syscall_trace_enter.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.99 ± 4% +0.2 1.22 ± 5% perf-profile.calltrace.cycles-pp.kmem_cache_alloc.security_file_alloc.__alloc_file.alloc_empty_file.path_openat 0.93 ± 5% +0.2 1.17 ± 5% perf-profile.calltrace.cycles-pp.__call_rcu.task_work_run.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.20 ± 7% +0.2 1.44 ± 7% perf-profile.calltrace.cycles-pp.__memcg_kmem_charge_memcg.new_slab.___slab_alloc.__slab_alloc.kmem_cache_alloc 0.64 ± 5% +0.3 0.89 ± 5% perf-profile.calltrace.cycles-pp.__close_fd.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.61 ± 9% +0.3 0.87 ± 8% perf-profile.calltrace.cycles-pp.path_init.path_openat.do_filp_open.do_sys_open.do_syscall_64 0.66 ± 3% +0.3 0.92 ± 4% perf-profile.calltrace.cycles-pp.dput.__fput.task_work_run.exit_to_usermode_loop.do_syscall_64 0.81 ± 5% +0.3 1.07 ± 4% perf-profile.calltrace.cycles-pp.__audit_syscall_exit.syscall_slow_exit_work.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.41 ± 58% +0.3 0.68 ± 4% perf-profile.calltrace.cycles-pp.syscall_return_via_sysret 1.00 ± 2% +0.3 1.31 ± 6% perf-profile.calltrace.cycles-pp.selinux_file_open.security_file_open.do_dentry_open.path_openat.do_filp_open 1.04 ± 5% +0.3 1.36 ± 5% perf-profile.calltrace.cycles-pp.syscall_slow_exit_work.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.58 ± 4% +0.3 1.90 ± 5% perf-profile.calltrace.cycles-pp.security_file_alloc.__alloc_file.alloc_empty_file.path_openat.do_filp_open 0.74 ± 5% +0.3 1.09 ± 6% perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.task_work_run.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.89 ± 5% +0.4 1.26 ± 4% perf-profile.calltrace.cycles-pp.__alloc_fd.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.79 ± 6% +0.4 1.16 ± 27% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_cancel.page_counter_uncharge.__memcg_kmem_uncharge.__free_slab 1.30 ± 6% +0.4 1.68 ± 5% perf-profile.calltrace.cycles-pp.selinux_inode_permission.security_inode_permission.may_open.path_openat.do_filp_open 0.82 ± 4% +0.4 1.21 ± 5% perf-profile.calltrace.cycles-pp.dput.terminate_walk.path_openat.do_filp_open.do_sys_open 1.38 ± 6% +0.4 1.76 ± 5% perf-profile.calltrace.cycles-pp.security_inode_permission.may_open.path_openat.do_filp_open.do_sys_open 1.31 ± 2% +0.4 1.70 ± 5% perf-profile.calltrace.cycles-pp.security_file_open.do_dentry_open.path_openat.do_filp_open.do_sys_open 2.49 ± 4% +0.4 2.88 ± 4% perf-profile.calltrace.cycles-pp.selinux_inode_permission.security_inode_permission.link_path_walk.path_openat.do_filp_open 0.54 ± 7% +0.4 0.95 ± 8% perf-profile.calltrace.cycles-pp.lockref_get_not_dead.legitimize_path.unlazy_walk.complete_walk.path_openat 1.96 ± 6% +0.4 2.37 ± 5% perf-profile.calltrace.cycles-pp.getname_flags.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.13 ± 9% +0.4 2.56 ± 5% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_cancel.page_counter_uncharge.__memcg_kmem_uncharge_memcg.__memcg_kmem_uncharge 2.63 ± 4% +0.4 3.07 ± 4% perf-profile.calltrace.cycles-pp.security_inode_permission.link_path_walk.path_openat.do_filp_open.do_sys_open 1.03 ± 4% +0.4 1.47 ± 5% perf-profile.calltrace.cycles-pp.terminate_walk.path_openat.do_filp_open.do_sys_open.do_syscall_64 0.27 ±100% +0.4 0.71 ± 5% perf-profile.calltrace.cycles-pp.rcu_cblist_dequeue.rcu_core.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt 0.13 ±173% +0.5 0.61 ± 4% perf-profile.calltrace.cycles-pp.inode_security_rcu.selinux_inode_permission.security_inode_permission.may_open.path_openat 0.88 ± 7% +0.5 1.39 ± 6% perf-profile.calltrace.cycles-pp.lookup_fast.walk_component.link_path_walk.path_openat.do_filp_open 0.86 ± 5% +0.5 1.38 ± 5% perf-profile.calltrace.cycles-pp.task_work_add.fput_many.filp_close.__x64_sys_close.do_syscall_64 1.74 ± 4% +0.5 2.27 ± 5% perf-profile.calltrace.cycles-pp.may_open.path_openat.do_filp_open.do_sys_open.do_syscall_64 1.40 ± 8% +0.6 1.95 ± 8% perf-profile.calltrace.cycles-pp.legitimize_path.unlazy_walk.complete_walk.path_openat.do_filp_open 0.00 +0.6 0.56 ± 6% perf-profile.calltrace.cycles-pp.lockref_get.do_dentry_open.path_openat.do_filp_open.do_sys_open 0.00 +0.6 0.57 ± 7% perf-profile.calltrace.cycles-pp.__slab_free.kmem_cache_free.rcu_core.__softirqentry_text_start.irq_exit 1.51 ± 7% +0.6 2.08 ± 8% perf-profile.calltrace.cycles-pp.unlazy_walk.complete_walk.path_openat.do_filp_open.do_sys_open 3.84 ± 6% +0.6 4.42 ± 5% perf-profile.calltrace.cycles-pp.___slab_alloc.__slab_alloc.kmem_cache_alloc.__alloc_file.alloc_empty_file 1.05 ± 7% +0.6 1.65 ± 5% perf-profile.calltrace.cycles-pp.walk_component.link_path_walk.path_openat.do_filp_open.do_sys_open 0.13 ±173% +0.6 0.74 ± 4% perf-profile.calltrace.cycles-pp.__follow_mount_rcu.lookup_fast.walk_component.link_path_walk.path_openat 3.89 ± 6% +0.6 4.50 ± 6% perf-profile.calltrace.cycles-pp.__slab_alloc.kmem_cache_alloc.__alloc_file.alloc_empty_file.path_openat 0.00 +0.7 0.67 ± 4% perf-profile.calltrace.cycles-pp._raw_spin_lock.__close_fd.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.59 ± 7% +0.7 2.27 ± 7% perf-profile.calltrace.cycles-pp.complete_walk.path_openat.do_filp_open.do_sys_open.do_syscall_64 2.89 ± 4% +0.7 3.56 ± 6% perf-profile.calltrace.cycles-pp.page_counter_cancel.page_counter_uncharge.__memcg_kmem_uncharge.__free_slab.unfreeze_partials 0.00 +0.7 0.68 ± 5% perf-profile.calltrace.cycles-pp.lockref_put_or_lock.dput.terminate_walk.path_openat.do_filp_open 0.00 +0.7 0.74 ± 5% perf-profile.calltrace.cycles-pp.file_free_rcu.rcu_core.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt 0.00 +0.8 0.77 ± 6% perf-profile.calltrace.cycles-pp.__mnt_want_write.do_dentry_open.path_openat.do_filp_open.do_sys_open 3.57 ± 3% +0.8 4.35 ± 7% perf-profile.calltrace.cycles-pp.page_counter_uncharge.__memcg_kmem_uncharge.__free_slab.unfreeze_partials.put_cpu_partial 1.39 ± 5% +0.8 2.18 ± 6% perf-profile.calltrace.cycles-pp.fput_many.filp_close.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.66 ± 4% +0.9 2.57 ± 5% perf-profile.calltrace.cycles-pp.filp_close.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.75 ± 5% +0.9 3.69 ± 4% perf-profile.calltrace.cycles-pp.__fput.task_work_run.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 8.53 ± 4% +1.0 9.57 ± 6% perf-profile.calltrace.cycles-pp.put_cpu_partial.kmem_cache_free.rcu_core.__softirqentry_text_start.irq_exit 9.09 ± 4% +1.2 10.32 ± 6% perf-profile.calltrace.cycles-pp.kmem_cache_free.rcu_core.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt 2.49 ± 5% +1.2 3.73 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 11.92 ± 6% +1.3 13.22 ± 5% perf-profile.calltrace.cycles-pp.__memcg_kmem_uncharge.__free_slab.unfreeze_partials.put_cpu_partial.kmem_cache_free 12.14 ± 6% +1.4 13.49 ± 5% perf-profile.calltrace.cycles-pp.__free_slab.unfreeze_partials.put_cpu_partial.kmem_cache_free.rcu_core 6.87 ± 8% +1.4 8.24 ± 7% perf-profile.calltrace.cycles-pp.__memcg_kmem_uncharge_memcg.__memcg_kmem_uncharge.__free_slab.unfreeze_partials.put_cpu_partial 6.86 ± 8% +1.4 8.24 ± 7% perf-profile.calltrace.cycles-pp.page_counter_uncharge.__memcg_kmem_uncharge_memcg.__memcg_kmem_uncharge.__free_slab.unfreeze_partials 6.66 ± 8% +1.4 8.04 ± 7% perf-profile.calltrace.cycles-pp.page_counter_cancel.page_counter_uncharge.__memcg_kmem_uncharge_memcg.__memcg_kmem_uncharge.__free_slab 4.82 ± 5% +1.4 6.21 ± 4% perf-profile.calltrace.cycles-pp.link_path_walk.path_openat.do_filp_open.do_sys_open.do_syscall_64 12.94 ± 6% +1.5 14.40 ± 5% perf-profile.calltrace.cycles-pp.unfreeze_partials.put_cpu_partial.kmem_cache_free.rcu_core.__softirqentry_text_start 10.12 ± 4% +1.7 11.84 ± 6% perf-profile.calltrace.cycles-pp.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter 10.11 ± 4% +1.7 11.83 ± 6% perf-profile.calltrace.cycles-pp.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 10.09 ± 4% +1.7 11.81 ± 6% perf-profile.calltrace.cycles-pp.rcu_core.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt 3.55 ± 4% +1.8 5.34 ± 5% perf-profile.calltrace.cycles-pp.do_dentry_open.path_openat.do_filp_open.do_sys_open.do_syscall_64 5.70 ± 5% +1.9 7.58 ± 4% perf-profile.calltrace.cycles-pp.task_work_run.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 10.17 ± 4% +2.0 12.16 ± 8% perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle 10.17 ± 4% +2.1 12.25 ± 9% perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 6.30 ± 5% +2.1 8.44 ± 4% perf-profile.calltrace.cycles-pp.exit_to_usermode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 23.20 ± 7% -13.9 9.26 ± 5% perf-profile.children.cycles-pp.kmem_cache_alloc 24.37 ± 7% -11.6 12.81 ± 5% perf-profile.children.cycles-pp.__alloc_file 24.57 ± 7% -11.5 13.08 ± 5% perf-profile.children.cycles-pp.alloc_empty_file 9.39 ± 9% -9.4 0.00 perf-profile.children.cycles-pp.get_mem_cgroup_from_mm 9.84 ± 9% -8.7 1.10 ± 7% perf-profile.children.cycles-pp.memcg_kmem_get_cache 6.77 ± 7% -6.5 0.27 ± 2% perf-profile.children.cycles-pp.memcg_kmem_put_cache 39.73 ± 6% -5.8 33.90 ± 5% perf-profile.children.cycles-pp.path_openat 39.98 ± 6% -5.7 34.31 ± 5% perf-profile.children.cycles-pp.do_filp_open 44.77 ± 6% -4.5 40.30 ± 5% perf-profile.children.cycles-pp.do_sys_open 0.13 ± 3% -0.1 0.07 perf-profile.children.cycles-pp.getname 0.06 +0.0 0.07 ± 5% perf-profile.children.cycles-pp.putname 0.06 ± 11% +0.0 0.08 ± 10% perf-profile.children.cycles-pp.vfs_open 0.05 +0.0 0.07 ± 6% perf-profile.children.cycles-pp.__mnt_drop_write 0.09 ± 9% +0.0 0.11 ± 4% perf-profile.children.cycles-pp.__list_del_entry_valid 0.14 ± 6% +0.0 0.16 ± 4% perf-profile.children.cycles-pp.locks_remove_posix 0.09 ± 9% +0.0 0.11 ± 9% perf-profile.children.cycles-pp.nd_jump_root 0.04 ± 57% +0.0 0.06 perf-profile.children.cycles-pp.security_file_free 0.07 ± 5% +0.0 0.10 ± 8% perf-profile.children.cycles-pp.restore_nameidata 0.06 +0.0 0.09 ± 5% perf-profile.children.cycles-pp.inode_has_perm 0.12 ± 7% +0.0 0.14 ± 5% perf-profile.children.cycles-pp.mntput 0.12 ± 3% +0.0 0.15 ± 7% perf-profile.children.cycles-pp.path_put 0.10 ± 4% +0.0 0.13 ± 3% perf-profile.children.cycles-pp.blkcg_maybe_throttle_current 0.14 ± 8% +0.0 0.18 ± 6% perf-profile.children.cycles-pp.discard_slab 0.13 ± 8% +0.0 0.16 ± 5% perf-profile.children.cycles-pp.try_charge 0.15 ± 7% +0.0 0.19 ± 7% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax 0.14 ± 3% +0.0 0.18 ± 4% perf-profile.children.cycles-pp.mntput_no_expire 0.07 ± 6% +0.0 0.11 ± 12% perf-profile.children.cycles-pp.path_get 0.14 ± 3% +0.0 0.18 ± 3% perf-profile.children.cycles-pp.find_next_zero_bit 0.12 ± 12% +0.0 0.16 ± 9% perf-profile.children.cycles-pp.ktime_get_coarse_real_ts64 0.13 ± 9% +0.0 0.18 ± 6% perf-profile.children.cycles-pp.fpregs_assert_state_consistent 0.08 ± 8% +0.0 0.13 ± 5% perf-profile.children.cycles-pp.file_ra_state_init 0.00 +0.1 0.05 ± 8% perf-profile.children.cycles-pp.setup_object_debug 0.15 ± 4% +0.1 0.21 ± 7% perf-profile.children.cycles-pp.__x64_sys_openat 0.00 +0.1 0.05 ± 9% perf-profile.children.cycles-pp.put_pid 0.00 +0.1 0.05 ± 9% perf-profile.children.cycles-pp.try_module_get 0.03 ±100% +0.1 0.08 ± 12% perf-profile.children.cycles-pp.mntget 0.00 +0.1 0.06 ± 14% perf-profile.children.cycles-pp.avc_policy_seqno 0.43 ± 5% +0.1 0.49 ± 6% perf-profile.children.cycles-pp.selinux_file_alloc_security 0.00 +0.1 0.06 ± 11% perf-profile.children.cycles-pp.mem_cgroup_handle_over_high 0.31 ± 6% +0.1 0.37 ± 6% perf-profile.children.cycles-pp.rcu_all_qs 0.20 ± 6% +0.1 0.26 ± 5% perf-profile.children.cycles-pp.percpu_counter_add_batch 0.11 ± 8% +0.1 0.17 ± 7% perf-profile.children.cycles-pp.kfree 0.00 +0.1 0.07 ± 7% perf-profile.children.cycles-pp.memset 0.20 ± 13% +0.1 0.27 ± 4% perf-profile.children.cycles-pp.__lookup_mnt 0.11 ± 6% +0.1 0.19 ± 7% perf-profile.children.cycles-pp.expand_files 0.23 ± 9% +0.1 0.32 ± 8% perf-profile.children.cycles-pp.__fd_install 0.12 ± 5% +0.1 0.20 ± 23% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.32 ± 9% +0.1 0.41 ± 11% perf-profile.children.cycles-pp.generic_permission 0.32 ± 4% +0.1 0.41 ± 6% perf-profile.children.cycles-pp.__audit_syscall_entry 0.35 ± 5% +0.1 0.46 ± 7% perf-profile.children.cycles-pp.get_page_from_freelist 0.32 ± 6% +0.1 0.43 ± 5% perf-profile.children.cycles-pp.avc_has_perm 0.38 ± 5% +0.1 0.49 ± 6% perf-profile.children.cycles-pp.__alloc_pages_nodemask 0.79 ± 9% +0.1 0.92 ± 8% perf-profile.children.cycles-pp.__legitimize_mnt 0.12 ± 5% +0.1 0.25 ± 5% perf-profile.children.cycles-pp.process_measurement 0.14 ± 8% +0.1 0.28 ± 9% perf-profile.children.cycles-pp.get_partial_node 0.62 ± 4% +0.1 0.76 ± 4% perf-profile.children.cycles-pp._cond_resched 0.37 ± 6% +0.1 0.52 ± 4% perf-profile.children.cycles-pp.rcu_segcblist_enqueue 0.27 ± 6% +0.2 0.42 ± 14% perf-profile.children.cycles-pp.set_root 0.47 ± 6% +0.2 0.62 ± 10% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 0.66 ± 4% +0.2 0.84 ± 5% perf-profile.children.cycles-pp.inode_permission 0.38 ± 4% +0.2 0.56 ± 6% perf-profile.children.cycles-pp.lockref_get 0.70 ± 3% +0.2 0.88 ± 6% perf-profile.children.cycles-pp.__might_sleep 0.77 ± 4% +0.2 0.95 ± 5% perf-profile.children.cycles-pp.fsnotify 0.59 ± 6% +0.2 0.78 ± 4% perf-profile.children.cycles-pp.ima_file_check 0.47 ± 5% +0.2 0.66 ± 4% perf-profile.children.cycles-pp.__fsnotify_parent 0.99 ± 6% +0.2 1.19 ± 4% perf-profile.children.cycles-pp.entry_SYSCALL_64 0.63 ± 4% +0.2 0.82 ± 4% perf-profile.children.cycles-pp.memset_erms 0.73 ± 4% +0.2 0.93 ± 4% perf-profile.children.cycles-pp.inode_security_rcu 0.94 ± 6% +0.2 1.14 ± 5% perf-profile.children.cycles-pp.strncpy_from_user 0.81 ± 6% +0.2 1.02 ± 5% perf-profile.children.cycles-pp.syscall_trace_enter 0.97 ± 3% +0.2 1.20 ± 5% perf-profile.children.cycles-pp.__inode_security_revalidate 1.16 ± 7% +0.2 1.40 ± 7% perf-profile.children.cycles-pp.page_counter_try_charge 0.97 ± 6% +0.2 1.21 ± 5% perf-profile.children.cycles-pp.__call_rcu 0.73 ± 6% +0.2 0.97 ± 6% perf-profile.children.cycles-pp.__slab_free 1.20 ± 7% +0.3 1.45 ± 7% perf-profile.children.cycles-pp.__memcg_kmem_charge_memcg 0.62 ± 9% +0.3 0.87 ± 8% perf-profile.children.cycles-pp.path_init 0.65 ± 6% +0.3 0.90 ± 5% perf-profile.children.cycles-pp.__close_fd 0.51 ± 8% +0.3 0.78 ± 7% perf-profile.children.cycles-pp.__d_lookup_rcu 0.85 ± 5% +0.3 1.13 ± 5% perf-profile.children.cycles-pp.__audit_syscall_exit 1.03 ± 2% +0.3 1.33 ± 6% perf-profile.children.cycles-pp.selinux_file_open 1.18 ± 9% +0.3 1.48 ± 6% perf-profile.children.cycles-pp.avc_has_perm_noaudit 0.58 ± 7% +0.3 0.89 ± 4% perf-profile.children.cycles-pp.__follow_mount_rcu 1.59 ± 4% +0.3 1.91 ± 5% perf-profile.children.cycles-pp.security_file_alloc 1.06 ± 5% +0.3 1.38 ± 5% perf-profile.children.cycles-pp.syscall_slow_exit_work 0.85 ± 8% +0.3 1.18 ± 5% perf-profile.children.cycles-pp.rcu_cblist_dequeue 1.32 ± 5% +0.3 1.66 ± 6% perf-profile.children.cycles-pp.___might_sleep 0.78 ± 5% +0.3 1.13 ± 6% perf-profile.children.cycles-pp._raw_spin_lock_irq 1.45 ± 5% +0.4 1.80 ± 5% perf-profile.children.cycles-pp.syscall_return_via_sysret 0.92 ± 5% +0.4 1.29 ± 4% perf-profile.children.cycles-pp.__alloc_fd 1.31 ± 2% +0.4 1.70 ± 5% perf-profile.children.cycles-pp.security_file_open 0.38 ± 6% +0.4 0.77 ± 6% perf-profile.children.cycles-pp.__mnt_want_write 3.55 ± 6% +0.4 3.96 ± 5% perf-profile.children.cycles-pp.new_slab 0.54 ± 7% +0.4 0.95 ± 8% perf-profile.children.cycles-pp.lockref_get_not_dead 1.97 ± 6% +0.4 2.39 ± 5% perf-profile.children.cycles-pp.getname_flags 0.78 ± 6% +0.4 1.22 ± 5% perf-profile.children.cycles-pp.file_free_rcu 1.04 ± 4% +0.4 1.49 ± 5% perf-profile.children.cycles-pp.terminate_walk 0.73 ± 3% +0.5 1.18 ± 4% perf-profile.children.cycles-pp.lockref_put_or_lock 1.77 ± 4% +0.5 2.29 ± 5% perf-profile.children.cycles-pp.may_open 0.89 ± 5% +0.5 1.41 ± 5% perf-profile.children.cycles-pp.task_work_add 1.29 ± 5% +0.5 1.81 ± 6% perf-profile.children.cycles-pp._raw_spin_lock 1.40 ± 8% +0.6 1.95 ± 8% perf-profile.children.cycles-pp.legitimize_path 1.51 ± 7% +0.6 2.09 ± 8% perf-profile.children.cycles-pp.unlazy_walk 3.84 ± 6% +0.6 4.42 ± 5% perf-profile.children.cycles-pp.___slab_alloc 1.06 ± 6% +0.6 1.67 ± 5% perf-profile.children.cycles-pp.walk_component 3.89 ± 6% +0.6 4.50 ± 5% perf-profile.children.cycles-pp.__slab_alloc 1.60 ± 4% +0.7 2.27 ± 4% perf-profile.children.cycles-pp.dput 1.50 ± 6% +0.7 2.17 ± 6% perf-profile.children.cycles-pp.lookup_fast 1.59 ± 7% +0.7 2.27 ± 7% perf-profile.children.cycles-pp.complete_walk 3.83 ± 5% +0.8 4.61 ± 3% perf-profile.children.cycles-pp.selinux_inode_permission 1.41 ± 5% +0.8 2.21 ± 6% perf-profile.children.cycles-pp.fput_many 3.96 ± 9% +0.8 4.78 ± 6% perf-profile.children.cycles-pp.propagate_protected_usage 4.04 ± 4% +0.8 4.87 ± 4% perf-profile.children.cycles-pp.security_inode_permission 1.68 ± 4% +0.9 2.60 ± 5% perf-profile.children.cycles-pp.filp_close 2.84 ± 5% +1.0 3.81 ± 4% perf-profile.children.cycles-pp.__fput 2.49 ± 5% +1.2 3.73 ± 5% perf-profile.children.cycles-pp.__x64_sys_close 13.22 ± 5% +1.3 14.56 ± 6% perf-profile.children.cycles-pp.__memcg_kmem_uncharge 4.85 ± 5% +1.4 6.24 ± 4% perf-profile.children.cycles-pp.link_path_walk 13.45 ± 5% +1.4 14.86 ± 6% perf-profile.children.cycles-pp.__free_slab 7.69 ± 7% +1.5 9.14 ± 7% perf-profile.children.cycles-pp.__memcg_kmem_uncharge_memcg 14.31 ± 5% +1.5 15.83 ± 6% perf-profile.children.cycles-pp.unfreeze_partials 14.35 ± 5% +1.5 15.89 ± 6% perf-profile.children.cycles-pp.put_cpu_partial 3.56 ± 4% +1.8 5.36 ± 5% perf-profile.children.cycles-pp.do_dentry_open 11.68 ± 3% +1.8 13.50 ± 6% perf-profile.children.cycles-pp.irq_exit 5.74 ± 5% +1.9 7.63 ± 4% perf-profile.children.cycles-pp.task_work_run 16.05 ± 5% +2.1 18.12 ± 5% perf-profile.children.cycles-pp.kmem_cache_free 11.99 ± 3% +2.1 14.13 ± 7% perf-profile.children.cycles-pp.smp_apic_timer_interrupt 6.33 ± 5% +2.1 8.48 ± 4% perf-profile.children.cycles-pp.exit_to_usermode_loop 10.60 ± 6% +2.2 12.77 ± 6% perf-profile.children.cycles-pp.page_counter_cancel 12.03 ± 3% +2.2 14.26 ± 8% perf-profile.children.cycles-pp.apic_timer_interrupt 11.58 ± 5% +2.3 13.86 ± 6% perf-profile.children.cycles-pp.page_counter_uncharge 17.04 ± 5% +2.6 19.64 ± 5% perf-profile.children.cycles-pp.__softirqentry_text_start 17.01 ± 5% +2.6 19.62 ± 5% perf-profile.children.cycles-pp.rcu_core 8.87 ± 10% -8.9 0.00 perf-profile.self.cycles-pp.get_mem_cgroup_from_mm 6.30 ± 7% -6.1 0.21 ± 4% perf-profile.self.cycles-pp.memcg_kmem_put_cache 1.64 ± 4% -0.9 0.70 ± 9% perf-profile.self.cycles-pp.__memcg_kmem_uncharge 0.06 ± 7% +0.0 0.07 ± 5% perf-profile.self.cycles-pp.path_put 0.11 ± 3% +0.0 0.13 ± 5% perf-profile.self.cycles-pp.security_file_alloc 0.09 ± 4% +0.0 0.11 ± 3% perf-profile.self.cycles-pp.mntput 0.08 ± 8% +0.0 0.10 ± 7% perf-profile.self.cycles-pp.unlazy_walk 0.06 ± 9% +0.0 0.08 ± 6% perf-profile.self.cycles-pp.legitimize_path 0.09 ± 9% +0.0 0.11 ± 4% perf-profile.self.cycles-pp.__list_del_entry_valid 0.08 ± 5% +0.0 0.11 ± 7% perf-profile.self.cycles-pp.nd_jump_root 0.07 ± 5% +0.0 0.10 ± 9% perf-profile.self.cycles-pp.restore_nameidata 0.04 ± 57% +0.0 0.06 ± 6% perf-profile.self.cycles-pp.vfs_open 0.12 ± 7% +0.0 0.14 ± 8% perf-profile.self.cycles-pp.__x86_indirect_thunk_rax 0.12 ± 3% +0.0 0.15 ± 10% perf-profile.self.cycles-pp.alloc_empty_file 0.11 ± 4% +0.0 0.13 ± 3% perf-profile.self.cycles-pp.may_open 0.14 ± 3% +0.0 0.17 ± 4% perf-profile.self.cycles-pp.mntput_no_expire 0.09 ± 9% +0.0 0.12 ± 5% perf-profile.self.cycles-pp.blkcg_maybe_throttle_current 0.20 ± 7% +0.0 0.23 ± 7% perf-profile.self.cycles-pp.syscall_slow_exit_work 0.14 ± 9% +0.0 0.17 ± 6% perf-profile.self.cycles-pp.discard_slab 0.12 ± 4% +0.0 0.16 ± 4% perf-profile.self.cycles-pp.find_next_zero_bit 0.11 ± 6% +0.0 0.15 ± 7% perf-profile.self.cycles-pp.ima_file_check 0.15 ± 8% +0.0 0.19 ± 8% perf-profile.self.cycles-pp.___slab_alloc 0.04 ± 57% +0.0 0.08 ± 6% perf-profile.self.cycles-pp.inode_has_perm 0.20 ± 5% +0.0 0.24 ± 6% perf-profile.self.cycles-pp.rcu_all_qs 0.12 ± 12% +0.0 0.16 ± 6% perf-profile.self.cycles-pp.ktime_get_coarse_real_ts64 0.14 ± 9% +0.0 0.18 ± 5% perf-profile.self.cycles-pp.inode_security_rcu 0.06 ± 6% +0.0 0.10 ± 8% perf-profile.self.cycles-pp.security_task_getsecid 0.11 ± 7% +0.0 0.15 ± 5% perf-profile.self.cycles-pp.fpregs_assert_state_consistent 0.08 ± 8% +0.0 0.12 ± 8% perf-profile.self.cycles-pp.file_ra_state_init 0.21 ± 2% +0.0 0.25 ± 5% perf-profile.self.cycles-pp.security_inode_permission 0.14 ± 3% +0.0 0.18 ± 8% perf-profile.self.cycles-pp.__x64_sys_openat 0.11 ± 8% +0.0 0.15 ± 8% perf-profile.self.cycles-pp.get_partial_node 0.15 ± 7% +0.1 0.21 ± 5% perf-profile.self.cycles-pp.__x64_sys_close 0.41 ± 4% +0.1 0.46 ± 6% perf-profile.self.cycles-pp.selinux_file_alloc_security 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.unfreeze_partials 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.__mnt_drop_write 0.01 ±173% +0.1 0.07 ± 6% perf-profile.self.cycles-pp.__free_slab 0.18 ± 15% +0.1 0.24 ± 3% perf-profile.self.cycles-pp.__lookup_mnt 0.10 ± 9% +0.1 0.16 ± 6% perf-profile.self.cycles-pp.kfree 0.18 ± 5% +0.1 0.25 ± 4% perf-profile.self.cycles-pp.percpu_counter_add_batch 0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.memset 0.00 +0.1 0.07 ± 17% perf-profile.self.cycles-pp.mntget 0.30 ± 4% +0.1 0.36 ± 3% perf-profile.self.cycles-pp._cond_resched 0.27 ± 4% +0.1 0.34 ± 5% perf-profile.self.cycles-pp.dput 0.23 ± 9% +0.1 0.30 ± 8% perf-profile.self.cycles-pp.__fd_install 0.10 ± 9% +0.1 0.17 ± 8% perf-profile.self.cycles-pp.expand_files 0.59 ± 6% +0.1 0.67 ± 5% perf-profile.self.cycles-pp.__call_rcu 0.38 ± 6% +0.1 0.45 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.36 ± 7% +0.1 0.44 ± 7% perf-profile.self.cycles-pp.syscall_trace_enter 0.32 ± 7% +0.1 0.40 ± 6% perf-profile.self.cycles-pp.getname_flags 0.29 ± 4% +0.1 0.37 ± 5% perf-profile.self.cycles-pp.__audit_syscall_entry 0.29 ± 8% +0.1 0.38 ± 11% perf-profile.self.cycles-pp.generic_permission 0.36 ± 3% +0.1 0.45 ± 5% perf-profile.self.cycles-pp.__inode_security_revalidate 0.33 ± 10% +0.1 0.42 ± 6% perf-profile.self.cycles-pp.inode_permission 0.41 ± 6% +0.1 0.50 ± 6% perf-profile.self.cycles-pp.lookup_fast 0.08 ± 5% +0.1 0.18 ± 6% perf-profile.self.cycles-pp.complete_walk 0.10 ± 4% +0.1 0.20 ± 4% perf-profile.self.cycles-pp.filp_close 0.16 ± 6% +0.1 0.26 ± 5% perf-profile.self.cycles-pp.walk_component 0.31 ± 5% +0.1 0.42 ± 5% perf-profile.self.cycles-pp.avc_has_perm 0.63 ± 5% +0.1 0.73 ± 4% perf-profile.self.cycles-pp.do_sys_open 0.79 ± 9% +0.1 0.90 ± 8% perf-profile.self.cycles-pp.__legitimize_mnt 0.18 ± 3% +0.1 0.30 ± 3% perf-profile.self.cycles-pp.do_filp_open 0.59 ± 5% +0.1 0.71 ± 4% perf-profile.self.cycles-pp.do_syscall_64 0.12 ± 7% +0.1 0.24 ± 5% perf-profile.self.cycles-pp.process_measurement 0.33 ± 6% +0.1 0.47 ± 4% perf-profile.self.cycles-pp.__alloc_fd 0.59 ± 4% +0.1 0.73 ± 3% perf-profile.self.cycles-pp.memset_erms 0.26 ± 7% +0.1 0.40 ± 14% perf-profile.self.cycles-pp.set_root 0.36 ± 5% +0.1 0.51 ± 5% perf-profile.self.cycles-pp.rcu_segcblist_enqueue 0.47 ± 6% +0.2 0.62 ± 4% perf-profile.self.cycles-pp.__audit_syscall_exit 0.64 ± 4% +0.2 0.79 ± 6% perf-profile.self.cycles-pp.__might_sleep 0.47 ± 6% +0.2 0.62 ± 10% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 0.75 ± 5% +0.2 0.92 ± 5% perf-profile.self.cycles-pp.fsnotify 0.44 ± 5% +0.2 0.61 ± 4% perf-profile.self.cycles-pp.__fsnotify_parent 0.38 ± 5% +0.2 0.55 ± 6% perf-profile.self.cycles-pp.lockref_get 0.92 ± 7% +0.2 1.10 ± 5% perf-profile.self.cycles-pp.strncpy_from_user 0.80 ± 7% +0.2 0.99 ± 6% perf-profile.self.cycles-pp.page_counter_try_charge 0.99 ± 6% +0.2 1.19 ± 4% perf-profile.self.cycles-pp.entry_SYSCALL_64 0.47 ± 4% +0.2 0.66 ± 4% perf-profile.self.cycles-pp.exit_to_usermode_loop 0.52 ± 4% +0.2 0.72 ± 6% perf-profile.self.cycles-pp.path_openat 0.76 ± 5% +0.2 1.00 ± 6% perf-profile.self.cycles-pp.link_path_walk 0.72 ± 6% +0.2 0.96 ± 6% perf-profile.self.cycles-pp.__slab_free 0.49 ± 8% +0.2 0.73 ± 7% perf-profile.self.cycles-pp.__d_lookup_rcu 0.36 ± 7% +0.2 0.61 ± 5% perf-profile.self.cycles-pp.__follow_mount_rcu 1.85 ± 2% +0.3 2.11 ± 3% perf-profile.self.cycles-pp.selinux_inode_permission 1.25 ± 5% +0.3 1.52 ± 7% perf-profile.self.cycles-pp.kmem_cache_alloc 0.89 ± 7% +0.3 1.16 ± 4% perf-profile.self.cycles-pp.task_work_run 1.15 ± 9% +0.3 1.43 ± 6% perf-profile.self.cycles-pp.avc_has_perm_noaudit 0.97 ± 6% +0.3 1.24 ± 2% perf-profile.self.cycles-pp.kmem_cache_free 0.52 ± 5% +0.3 0.79 ± 7% perf-profile.self.cycles-pp.fput_many 0.71 ± 4% +0.3 0.99 ± 4% perf-profile.self.cycles-pp.__fput 1.25 ± 5% +0.3 1.54 ± 6% perf-profile.self.cycles-pp.___might_sleep 0.84 ± 8% +0.3 1.16 ± 5% perf-profile.self.cycles-pp.rcu_cblist_dequeue 1.45 ± 5% +0.3 1.79 ± 5% perf-profile.self.cycles-pp.syscall_return_via_sysret 0.75 ± 5% +0.3 1.10 ± 6% perf-profile.self.cycles-pp._raw_spin_lock_irq 0.38 ± 7% +0.4 0.75 ± 6% perf-profile.self.cycles-pp.__mnt_want_write 0.54 ± 7% +0.4 0.94 ± 7% perf-profile.self.cycles-pp.lockref_get_not_dead 0.89 ± 5% +0.4 1.30 ± 5% perf-profile.self.cycles-pp._raw_spin_lock 0.77 ± 6% +0.4 1.19 ± 5% perf-profile.self.cycles-pp.file_free_rcu 0.70 ± 4% +0.4 1.14 ± 5% perf-profile.self.cycles-pp.lockref_put_or_lock 0.82 ± 5% +0.5 1.32 ± 5% perf-profile.self.cycles-pp.task_work_add 0.45 ± 4% +0.6 1.06 ± 7% perf-profile.self.cycles-pp.memcg_kmem_get_cache 1.02 ± 6% +0.6 1.67 ± 5% perf-profile.self.cycles-pp.do_dentry_open 3.95 ± 9% +0.8 4.76 ± 6% perf-profile.self.cycles-pp.propagate_protected_usage 6.99 ± 4% +1.3 8.34 ± 7% perf-profile.self.cycles-pp.page_counter_cancel 1.30 ± 5% +2.4 3.66 ± 5% perf-profile.self.cycles-pp.__alloc_file will-it-scale.per_process_ops 700000 +-+----------------------------------------------------------------+ O O O O O O O O O O O O O O O O O O O O O O O O O O O O O O O 600000 +-+ | | .+.+.+.+..+.+. .+.+.+..+.+.+.+..+.+.+.+..+ | 500000 +-+.+..+.+.+.+. +.+..+.+ | | : | 400000 +-+ | |: | 300000 +-+ | |: | 200000 +-+ | |: | 100000 +-+ | | | 0 +-+----------------------------------------------------------------+ will-it-scale.workload 3.5e+07 +-+---------------------------------------------------------------+ | O O O O O O O O O | 3e+07 O-+ O O O O O O O O O O O O O O O O O O O O O | .+. .+.+.+.+.+..+ | 2.5e+07 +-+.+..+.+. .+.+..+.+.+.+.+.. .+. +.+.+.+. | | : + +.+.+.+ | 2e+07 +-+ | |: | 1.5e+07 +-+ | |: | 1e+07 +-+ | |: | 5e+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