Hello,
kernel test robot noticed a 78.3% improvement of vm-scalability.throughput on:
commit: 44818d6e3eb5b6fdb4960e1b53a98b0b74fdb85a ("hugetlb: prioritize surplus allocation from current node")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
testcase: vm-scalability
config: x86_64-rhel-9.4
compiler: gcc-12
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz (Ice Lake) with 256G memory
parameters:
runtime: 300s
size: 8T
test: anon-w-seq-hugetlb
cpufreq_governor: performance
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20241227/202412271037.59a4097d-lkp@xxxxxxxxx
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/runtime/size/tbox_group/test/testcase:
gcc-12/performance/x86_64-rhel-9.4/debian-12-x86_64-20240206.cgz/300s/8T/lkp-icl-2sp2/anon-w-seq-hugetlb/vm-scalability
commit:
a297fa1dd6 ("readahead: properly shorten readahead when falling back to do_page_cache_ra()")
44818d6e3e ("hugetlb: prioritize surplus allocation from current node")
a297fa1dd6b37376 44818d6e3eb5b6fdb4960e1b53a
---------------- ---------------------------
%stddev %change %stddev
\ | \
1868 ± 34% -45.4% 1019 ± 66% perf-c2c.HITM.remote
8733 ± 6% +15.5% 10087 ± 6% uptime.idle
2.836e+09 ± 18% +35.1% 3.831e+09 ± 12% cpuidle..time
1267776 ± 4% +21.6% 1541787 cpuidle..usage
7.13 ± 18% +2.5 9.67 ± 11% mpstat.cpu.all.idle%
0.09 ± 4% -0.0 0.07 ± 8% mpstat.cpu.all.soft%
5109 ± 6% +51.3% 7729 ± 12% vmstat.system.cs
151097 -2.5% 147260 vmstat.system.in
29547 ± 2% -13.5% 25558 ± 3% meminfo.HugePages_Free
29548 ± 2% -13.5% 25559 ± 3% meminfo.HugePages_Rsvd
86746 ± 61% -100.0% 0.00 meminfo.Inactive(anon)
137371 ± 28% -95.4% 6295 ± 82% numa-numastat.node0.numa_foreign
1577394 ± 42% -95.5% 71023 ± 59% numa-numastat.node0.other_node
751460 ± 6% +334.8% 3267469 ± 41% numa-numastat.node1.local_node
746936 ± 7% +347.8% 3344651 ± 40% numa-numastat.node1.numa_hit
137371 ± 28% -95.4% 6295 ± 82% numa-numastat.node1.numa_miss
193678 ± 2% +78.1% 345017 ± 10% vm-scalability.median
5.65 ± 93% +24.6 30.21 ± 9% vm-scalability.median_stddev%
9.15 ± 88% +19.8 28.96 ± 10% vm-scalability.stddev%
25455097 ± 4% +78.3% 45377627 ± 8% vm-scalability.throughput
3515955 ± 2% +59.9% 5621813 ± 9% vm-scalability.time.minor_page_faults
11676 -2.7% 11364 vm-scalability.time.percent_of_cpu_this_job_got
18157 -8.3% 16643 vm-scalability.time.system_time
17234 +4.4% 17986 vm-scalability.time.user_time
31462 ± 5% +38.4% 43539 ± 4% vm-scalability.time.voluntary_context_switches
7.245e+09 ± 2% +60.2% 1.161e+10 ± 9% vm-scalability.workload
2040555 ± 27% +687.1% 16062067 ± 47% numa-vmstat.node0.nr_free_pages
14747440 ± 3% -38.7% 9040252 ± 34% numa-vmstat.node0.nr_hugetlb
21511 ± 60% -100.0% 0.00 numa-vmstat.node0.nr_inactive_anon
21511 ± 60% -100.0% 0.00 numa-vmstat.node0.nr_zone_inactive_anon
137371 ± 28% -95.4% 6295 ± 82% numa-vmstat.node0.numa_foreign
1577394 ± 42% -95.5% 71023 ± 59% numa-vmstat.node0.numa_other
31231173 -44.3% 17391522 ± 45% numa-vmstat.node1.nr_free_pages
1023247 ± 33% +705.1% 8238183 ± 45% numa-vmstat.node1.nr_hugetlb
746539 ± 7% +347.9% 3343775 ± 40% numa-vmstat.node1.numa_hit
751062 ± 6% +334.9% 3266583 ± 41% numa-vmstat.node1.numa_local
137371 ± 28% -95.4% 6295 ± 82% numa-vmstat.node1.numa_miss
8058778 ± 37% -34.8% 5256544 ± 27% sched_debug.cfs_rq:/.avg_vruntime.stddev
8058779 ± 37% -34.8% 5256544 ± 27% sched_debug.cfs_rq:/.min_vruntime.stddev
452243 ± 13% -30.8% 312801 ± 32% sched_debug.cpu.avg_idle.min
179738 ± 22% -19.6% 144435 ± 2% sched_debug.cpu.avg_idle.stddev
10523 ± 5% +20.3% 12654 ± 4% sched_debug.cpu.curr->pid.max
1700 ± 34% +73.5% 2951 ± 28% sched_debug.cpu.curr->pid.stddev
69760 ± 48% -40.4% 41570 ± 11% sched_debug.cpu.max_idle_balance_cost.stddev
6803 ± 6% +38.7% 9434 ± 9% sched_debug.cpu.nr_switches.avg
30627 ± 12% +30.6% 40002 ± 11% sched_debug.cpu.nr_switches.max
2809 ± 9% +26.7% 3560 ± 11% sched_debug.cpu.nr_switches.min
4583 ± 9% +42.3% 6520 ± 4% sched_debug.cpu.nr_switches.stddev
28729 ± 3% -53.2% 13433 ± 70% numa-meminfo.node0.HugePages_Free
58184 ± 2% -46.1% 31385 ± 50% numa-meminfo.node0.HugePages_Surp
58184 ± 2% -46.1% 31385 ± 50% numa-meminfo.node0.HugePages_Total
86568 ± 60% -99.5% 443.64 ±115% numa-meminfo.node0.Inactive
86480 ± 60% -100.0% 0.00 numa-meminfo.node0.Inactive(anon)
8479775 ± 25% +656.9% 64186465 ± 48% numa-meminfo.node0.MemFree
1.232e+08 -45.2% 67498215 ± 46% numa-meminfo.node0.MemUsed
17.66 ±113% +67092.2% 11869 ± 71% numa-meminfo.node1.HugePages_Free
2016 ± 34% +1286.9% 27962 ± 56% numa-meminfo.node1.HugePages_Surp
2016 ± 34% +1286.9% 27962 ± 56% numa-meminfo.node1.HugePages_Total
1.249e+08 -44.1% 69824972 ± 44% numa-meminfo.node1.MemFree
7114401 ± 2% +774.7% 62230355 ± 49% numa-meminfo.node1.MemUsed
6.716e+08 ± 30% -95.2% 32119866 ± 99% proc-vmstat.compact_daemon_free_scanned
6.716e+08 ± 30% -95.2% 32119866 ± 99% proc-vmstat.compact_free_scanned
83155 ± 29% -52.9% 39134 ± 30% proc-vmstat.compact_isolated
3150336 ± 2% +60.2% 5048064 ± 9% proc-vmstat.htlb_buddy_alloc_success
15894009 +7.3% 17057392 ± 3% proc-vmstat.nr_hugetlb
21591 ± 61% -100.0% 0.00 proc-vmstat.nr_inactive_anon
25925 -1.2% 25622 proc-vmstat.nr_kernel_stack
27603 ± 2% +5.2% 29044 proc-vmstat.nr_slab_reclaimable
68217 +2.3% 69790 proc-vmstat.nr_slab_unreclaimable
21591 ± 61% -100.0% 0.00 proc-vmstat.nr_zone_inactive_anon
137371 ± 28% -84.7% 21019 ± 51% proc-vmstat.numa_foreign
4426766 +49.3% 6609025 ± 8% proc-vmstat.numa_hit
2853943 ± 24% +126.9% 6475543 ± 8% proc-vmstat.numa_local
137371 ± 28% -84.7% 21019 ± 51% proc-vmstat.numa_miss
1710242 ± 39% -91.0% 154545 ± 6% proc-vmstat.numa_other
317740 ± 26% +40.3% 445933 ± 17% proc-vmstat.numa_pte_updates
111196 ± 9% -83.9% 17920 ± 96% proc-vmstat.pgalloc_dma
18541178 ± 2% -83.2% 3111103 ± 97% proc-vmstat.pgalloc_dma32
1.596e+09 ± 2% +61.9% 2.583e+09 ± 10% proc-vmstat.pgalloc_normal
4517187 +46.7% 6627031 ± 8% proc-vmstat.pgfault
1.614e+09 ± 2% +60.2% 2.586e+09 ± 9% proc-vmstat.pgfree
64134 ± 2% +23.9% 79452 ± 5% proc-vmstat.pgreuse
568.17 ± 62% -100.0% 0.00 proc-vmstat.pgscan_file
568.17 ± 62% -100.0% 0.00 proc-vmstat.pgscan_kswapd
27985 ± 44% -100.0% 0.00 proc-vmstat.slabs_scanned
5033 +48.2% 7459 ± 5% proc-vmstat.unevictable_pgs_culled
1.81 ± 57% -80.2% 0.36 ±173% perf-sched.sch_delay.avg.ms.__cond_resched.__kmalloc_cache_noprof.perf_event_mmap_event.perf_event_mmap.__mmap_region
3.05 ± 68% -73.9% 0.80 ±111% perf-sched.sch_delay.avg.ms.__cond_resched.kmem_cache_alloc_noprof.vm_area_alloc.__mmap_new_vma.__mmap_region
0.05 ± 20% -57.0% 0.02 ± 62% perf-sched.sch_delay.avg.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
0.37 ± 49% -48.5% 0.19 ± 25% perf-sched.sch_delay.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
3.06 ± 29% -85.1% 0.46 ±173% perf-sched.sch_delay.max.ms.__cond_resched.__kmalloc_cache_noprof.perf_event_mmap_event.perf_event_mmap.__mmap_region
0.11 ± 10% -61.9% 0.04 ± 74% perf-sched.sch_delay.max.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
27.66 ±181% -95.7% 1.20 ±136% perf-sched.sch_delay.max.ms.__cond_resched.stop_one_cpu.migrate_task_to.task_numa_migrate.isra
14.17 ± 38% +477.1% 81.78 ±110% perf-sched.sch_delay.max.ms.schedule_preempt_disabled.__mutex_lock.constprop.0.hugetlb_fault
0.33 ±110% +76908.2% 252.59 ±172% perf-sched.sch_delay.max.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
180.99 ± 70% -86.4% 24.68 ± 70% perf-sched.sch_delay.max.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
23645 ± 25% +32.3% 31287 ± 11% perf-sched.total_wait_and_delay.count.ms
301.09 ± 63% +115.8% 649.76 ± 33% perf-sched.wait_and_delay.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
4.03 ± 53% +338.6% 17.65 ± 26% perf-sched.wait_and_delay.avg.ms.do_wait.kernel_wait4.do_syscall_64.entry_SYSCALL_64_after_hwframe
235.84 ± 5% +32.3% 311.97 ± 13% perf-sched.wait_and_delay.avg.ms.irq_thread.kthread.ret_from_fork.ret_from_fork_asm
11.17 ± 23% +79.1% 20.00 ± 3% perf-sched.wait_and_delay.count.schedule_timeout.kcompactd.kthread.ret_from_fork
182.41 ± 89% +1102.2% 2192 ± 29% perf-sched.wait_and_delay.max.ms.do_wait.kernel_wait4.do_syscall_64.entry_SYSCALL_64_after_hwframe
29.90 ± 30% +446.9% 163.55 ±110% perf-sched.wait_and_delay.max.ms.schedule_preempt_disabled.__mutex_lock.constprop.0.hugetlb_fault
1.69 ± 78% +156.2% 4.32 ± 34% perf-sched.wait_time.avg.ms.__cond_resched.__kmalloc_cache_noprof.allocate_file_region_entries.region_chg.__vma_reservation_common
1.81 ± 57% -80.2% 0.36 ±173% perf-sched.wait_time.avg.ms.__cond_resched.__kmalloc_cache_noprof.perf_event_mmap_event.perf_event_mmap.__mmap_region
4.92 ± 16% +28.7% 6.32 ± 7% perf-sched.wait_time.avg.ms.__cond_resched.gather_surplus_pages.hugetlb_acct_memory.part.0
3.04 ± 68% -73.8% 0.80 ±111% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_noprof.vm_area_alloc.__mmap_new_vma.__mmap_region
299.81 ± 63% +95.6% 586.43 ± 21% perf-sched.wait_time.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
4.10 ± 31% +301.8% 16.49 ± 20% perf-sched.wait_time.avg.ms.do_wait.kernel_wait4.do_syscall_64.entry_SYSCALL_64_after_hwframe
235.76 ± 5% +32.3% 311.80 ± 13% perf-sched.wait_time.avg.ms.irq_thread.kthread.ret_from_fork.ret_from_fork_asm
3.06 ± 29% -85.1% 0.46 ±173% perf-sched.wait_time.max.ms.__cond_resched.__kmalloc_cache_noprof.perf_event_mmap_event.perf_event_mmap.__mmap_region
182.48 ± 87% +1101.3% 2192 ± 29% perf-sched.wait_time.max.ms.do_wait.kernel_wait4.do_syscall_64.entry_SYSCALL_64_after_hwframe
1256 ± 18% +84.7% 2321 ± 35% perf-sched.wait_time.max.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
2.639e+10 ± 2% +62.5% 4.288e+10 ± 11% perf-stat.i.branch-instructions
0.05 ± 7% -0.0 0.04 ± 5% perf-stat.i.branch-miss-rate%
9062629 ± 2% +5.6% 9569988 ± 2% perf-stat.i.branch-misses
5.914e+08 ± 2% +63.5% 9.672e+08 ± 12% perf-stat.i.cache-misses
6.515e+08 ± 2% +63.5% 1.065e+09 ± 11% perf-stat.i.cache-references
5231 ± 7% +53.1% 8010 ± 13% perf-stat.i.context-switches
3.97 -27.4% 2.88 ± 8% perf-stat.i.cpi
562.71 -21.8% 440.10 ± 14% perf-stat.i.cycles-between-cache-misses
8.316e+10 ± 2% +61.9% 1.347e+11 ± 11% perf-stat.i.instructions
0.26 ± 2% +61.8% 0.43 ± 9% perf-stat.i.ipc
0.36 ± 27% +42.1% 0.51 ± 5% perf-stat.i.major-faults
15175 ± 2% +50.7% 22862 ± 10% perf-stat.i.minor-faults
15175 ± 2% +50.7% 22863 ± 10% perf-stat.i.page-faults
0.03 ± 2% -0.0 0.02 ± 7% perf-stat.overall.branch-miss-rate%
3.88 ± 2% -37.3% 2.43 ± 9% perf-stat.overall.cpi
546.77 ± 2% -37.7% 340.65 ± 10% perf-stat.overall.cycles-between-cache-misses
0.26 ± 2% +60.7% 0.41 ± 9% perf-stat.overall.ipc
3336 -1.4% 3289 perf-stat.overall.path-length
2.521e+10 ± 2% +57.4% 3.967e+10 ± 10% perf-stat.ps.branch-instructions
5.635e+08 ± 2% +58.4% 8.926e+08 ± 11% perf-stat.ps.cache-misses
6.223e+08 ± 2% +58.4% 9.855e+08 ± 10% perf-stat.ps.cache-references
5044 ± 7% +52.1% 7674 ± 12% perf-stat.ps.context-switches
7.941e+10 ± 2% +56.9% 1.246e+11 ± 10% perf-stat.ps.instructions
0.34 ± 28% +41.8% 0.49 ± 3% perf-stat.ps.major-faults
14448 +47.0% 21235 ± 8% perf-stat.ps.minor-faults
14448 +47.0% 21236 ± 8% perf-stat.ps.page-faults
2.417e+13 ± 2% +57.9% 3.817e+13 ± 9% perf-stat.total.instructions
47.00 -4.2 42.80 ± 6% perf-profile.calltrace.cycles-pp.folio_zero_user.hugetlb_no_page.hugetlb_fault.handle_mm_fault.do_user_addr_fault
48.14 -4.1 44.00 ± 6% perf-profile.calltrace.cycles-pp.hugetlb_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
48.18 -4.1 44.04 ± 6% perf-profile.calltrace.cycles-pp.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
48.31 -4.1 44.16 ± 6% perf-profile.calltrace.cycles-pp.asm_exc_page_fault.do_access
48.24 -4.1 44.11 ± 6% perf-profile.calltrace.cycles-pp.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
48.24 -4.1 44.11 ± 6% perf-profile.calltrace.cycles-pp.exc_page_fault.asm_exc_page_fault.do_access
46.69 -4.0 42.71 ± 6% perf-profile.calltrace.cycles-pp.hugetlb_no_page.hugetlb_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault
41.81 -2.9 38.88 ± 5% perf-profile.calltrace.cycles-pp.clear_page_erms.folio_zero_user.hugetlb_no_page.hugetlb_fault.handle_mm_fault
2.43 ± 2% -0.7 1.76 ± 19% perf-profile.calltrace.cycles-pp.__cond_resched.folio_zero_user.hugetlb_no_page.hugetlb_fault.handle_mm_fault
1.42 -0.7 0.75 ± 11% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.clear_page_erms.folio_zero_user.hugetlb_no_page.hugetlb_fault
1.42 -0.2 1.24 ± 8% perf-profile.calltrace.cycles-pp.__mutex_lock.hugetlb_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault
1.38 -0.2 1.21 ± 8% perf-profile.calltrace.cycles-pp.mutex_spin_on_owner.__mutex_lock.hugetlb_fault.handle_mm_fault.do_user_addr_fault
0.20 ±144% +0.5 0.75 ± 30% perf-profile.calltrace.cycles-pp.folios_put_refs.free_pages_and_swap_cache.__tlb_batch_free_encoded_pages.tlb_finish_mmu.exit_mmap
0.20 ±144% +0.6 0.76 ± 30% perf-profile.calltrace.cycles-pp.__tlb_batch_free_encoded_pages.tlb_finish_mmu.exit_mmap.__mmput.exit_mm
0.20 ±144% +0.6 0.76 ± 30% perf-profile.calltrace.cycles-pp.free_pages_and_swap_cache.__tlb_batch_free_encoded_pages.tlb_finish_mmu.exit_mmap.__mmput
0.20 ±144% +0.6 0.76 ± 30% perf-profile.calltrace.cycles-pp.tlb_finish_mmu.exit_mmap.__mmput.exit_mm.do_exit
0.21 ±143% +0.6 0.78 ± 30% perf-profile.calltrace.cycles-pp.__mmput.exit_mm.do_exit.do_group_exit.__x64_sys_exit_group
0.21 ±143% +0.6 0.78 ± 30% perf-profile.calltrace.cycles-pp.exit_mm.do_exit.do_group_exit.__x64_sys_exit_group.x64_sys_call
0.21 ±143% +0.6 0.78 ± 30% perf-profile.calltrace.cycles-pp.exit_mmap.__mmput.exit_mm.do_exit.do_group_exit
0.21 ±143% +0.6 0.80 ± 29% perf-profile.calltrace.cycles-pp.__x64_sys_exit_group.x64_sys_call.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.21 ±143% +0.6 0.80 ± 29% perf-profile.calltrace.cycles-pp.do_exit.do_group_exit.__x64_sys_exit_group.x64_sys_call.do_syscall_64
0.21 ±143% +0.6 0.80 ± 29% perf-profile.calltrace.cycles-pp.do_group_exit.__x64_sys_exit_group.x64_sys_call.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.21 ±143% +0.6 0.80 ± 29% perf-profile.calltrace.cycles-pp.x64_sys_call.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.22 ±143% +0.6 0.81 ± 29% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.22 ±143% +0.6 0.81 ± 29% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
86.37 +1.0 87.32 perf-profile.calltrace.cycles-pp.do_access
28.67 +1.8 30.52 ± 4% perf-profile.calltrace.cycles-pp.do_rw_once
48.22 -4.2 44.07 ± 6% perf-profile.children.cycles-pp.handle_mm_fault
48.14 -4.1 44.00 ± 6% perf-profile.children.cycles-pp.hugetlb_fault
48.35 -4.1 44.21 ± 6% perf-profile.children.cycles-pp.asm_exc_page_fault
48.28 -4.1 44.14 ± 6% perf-profile.children.cycles-pp.do_user_addr_fault
48.28 -4.1 44.14 ± 6% perf-profile.children.cycles-pp.exc_page_fault
46.39 -4.0 42.38 ± 6% perf-profile.children.cycles-pp.folio_zero_user
46.69 -4.0 42.71 ± 6% perf-profile.children.cycles-pp.hugetlb_no_page
43.18 -3.3 39.90 ± 5% perf-profile.children.cycles-pp.clear_page_erms
2.74 ± 2% -0.7 2.02 ± 18% perf-profile.children.cycles-pp.__cond_resched
0.34 ± 22% -0.2 0.16 ± 29% perf-profile.children.cycles-pp.get_page_from_freelist
0.34 ± 22% -0.2 0.16 ± 30% perf-profile.children.cycles-pp.__alloc_frozen_pages_noprof
0.33 ± 24% -0.2 0.15 ± 31% perf-profile.children.cycles-pp.__folio_alloc_noprof
0.33 ± 24% -0.2 0.15 ± 31% perf-profile.children.cycles-pp.alloc_buddy_hugetlb_folio
1.42 -0.2 1.24 ± 8% perf-profile.children.cycles-pp.__mutex_lock
1.38 -0.2 1.21 ± 8% perf-profile.children.cycles-pp.mutex_spin_on_owner
1.82 ± 2% -0.1 1.67 ± 5% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
0.48 -0.1 0.40 ± 11% perf-profile.children.cycles-pp.rcu_all_qs
0.14 ± 3% -0.0 0.10 ± 13% perf-profile.children.cycles-pp.__irq_exit_rcu
0.16 ± 3% -0.0 0.12 ± 16% perf-profile.children.cycles-pp.native_irq_return_iret
0.12 ± 3% -0.0 0.08 ± 13% perf-profile.children.cycles-pp.handle_softirqs
0.17 ± 12% +0.1 0.23 ± 11% perf-profile.children.cycles-pp.io_serial_in
0.05 ± 13% +0.1 0.12 ± 34% perf-profile.children.cycles-pp.ktime_get
0.00 +0.1 0.07 ± 19% perf-profile.children.cycles-pp.tmigr_requires_handle_remote
0.20 ± 11% +0.1 0.26 ± 11% perf-profile.children.cycles-pp.wait_for_lsr
0.02 ±141% +0.1 0.09 ± 7% perf-profile.children.cycles-pp.copy_page_from_iter_atomic
0.22 ± 12% +0.1 0.30 ± 11% perf-profile.children.cycles-pp.serial8250_console_write
0.84 ± 3% +0.1 0.94 ± 5% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
0.10 ± 11% +0.1 0.20 ± 7% perf-profile.children.cycles-pp.generic_perform_write
0.10 ± 13% +0.1 0.20 ± 8% perf-profile.children.cycles-pp.shmem_file_write_iter
0.11 ± 12% +0.1 0.22 ± 6% perf-profile.children.cycles-pp.record__pushfn
0.11 ± 12% +0.1 0.22 ± 6% perf-profile.children.cycles-pp.writen
0.17 ± 11% +0.1 0.28 ± 5% perf-profile.children.cycles-pp.__cmd_record
0.17 ± 11% +0.1 0.28 ± 5% perf-profile.children.cycles-pp.cmd_record
0.18 ± 9% +0.1 0.29 ± 5% perf-profile.children.cycles-pp.handle_internal_command
0.18 ± 9% +0.1 0.29 ± 5% perf-profile.children.cycles-pp.main
0.18 ± 9% +0.1 0.29 ± 5% perf-profile.children.cycles-pp.run_builtin
0.14 ± 11% +0.1 0.26 ± 6% perf-profile.children.cycles-pp.perf_mmap__push
0.14 ± 11% +0.1 0.27 ± 6% perf-profile.children.cycles-pp.record__mmap_read_evlist
0.53 ± 10% +0.2 0.70 ± 6% perf-profile.children.cycles-pp.vfs_write
0.53 ± 10% +0.2 0.70 ± 6% perf-profile.children.cycles-pp.ksys_write
0.54 ± 10% +0.2 0.72 ± 6% perf-profile.children.cycles-pp.write
0.42 ± 35% +0.3 0.75 ± 30% perf-profile.children.cycles-pp.folios_put_refs
0.43 ± 34% +0.3 0.76 ± 30% perf-profile.children.cycles-pp.__tlb_batch_free_encoded_pages
0.43 ± 34% +0.3 0.76 ± 30% perf-profile.children.cycles-pp.free_pages_and_swap_cache
0.43 ± 34% +0.3 0.76 ± 30% perf-profile.children.cycles-pp.tlb_finish_mmu
0.45 ± 34% +0.3 0.78 ± 30% perf-profile.children.cycles-pp.__mmput
0.45 ± 34% +0.3 0.78 ± 30% perf-profile.children.cycles-pp.exit_mmap
0.44 ± 33% +0.3 0.78 ± 30% perf-profile.children.cycles-pp.exit_mm
0.45 ± 32% +0.3 0.80 ± 29% perf-profile.children.cycles-pp.__x64_sys_exit_group
0.45 ± 32% +0.3 0.80 ± 29% perf-profile.children.cycles-pp.do_exit
0.45 ± 32% +0.3 0.80 ± 29% perf-profile.children.cycles-pp.do_group_exit
0.45 ± 32% +0.3 0.80 ± 29% perf-profile.children.cycles-pp.x64_sys_call
43.21 +3.8 46.97 ± 4% perf-profile.children.cycles-pp.do_rw_once
42.71 -3.3 39.45 ± 6% perf-profile.self.cycles-pp.clear_page_erms
2.31 ± 2% -0.7 1.66 ± 20% perf-profile.self.cycles-pp.__cond_resched
1.37 -0.2 1.20 ± 8% perf-profile.self.cycles-pp.mutex_spin_on_owner
0.20 ± 2% -0.1 0.14 ± 20% perf-profile.self.cycles-pp.rcu_all_qs
0.16 ± 3% -0.0 0.12 ± 16% perf-profile.self.cycles-pp.native_irq_return_iret
0.17 ± 12% +0.1 0.23 ± 11% perf-profile.self.cycles-pp.io_serial_in
0.04 ± 47% +0.1 0.12 ± 34% perf-profile.self.cycles-pp.ktime_get
0.02 ±141% +0.1 0.09 ± 7% perf-profile.self.cycles-pp.copy_page_from_iter_atomic
41.00 +2.9 43.86 ± 3% perf-profile.self.cycles-pp.do_rw_once
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/wiki
