From: kernel test robot <oliver.sang@intel.com>
To: Matthew Wilcox <willy@infradead.org>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>, <oliver.sang@intel.com>
Subject: [willy-pagecache:vma-lock] [mm] 06d7da17eb: vm-scalability.throughput 226.9% improvement
Date: Fri, 26 Apr 2024 10:47:04 +0800 [thread overview]
Message-ID: <202404261055.c5e24608-oliver.sang@intel.com> (raw)
Hello,
kernel test robot noticed a 226.9% improvement of vm-scalability.throughput on:
commit: 06d7da17eb40ba4d1b68f894ee16a8df78a4442f ("mm: Delay the check for a NULL anon_vma")
git://git.infradead.org/users/willy/pagecache vma-lock
testcase: vm-scalability
test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 512G memory
parameters:
runtime: 300s
test: small-allocs-mt
cpufreq_governor: performance
In addition to that, the commit also has significant impact on the following tests:
+------------------+-------------------------------------------------------------------------------------------+
| testcase: change | vm-scalability: vm-scalability.throughput 208.9% improvement |
| test machine | 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory |
| test parameters | cpufreq_governor=performance |
| | runtime=300s |
| | test=small-allocs-mt |
+------------------+-------------------------------------------------------------------------------------------+
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240426/202404261055.c5e24608-oliver.sang@intel.com
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/runtime/tbox_group/test/testcase:
gcc-13/performance/x86_64-rhel-8.3/debian-12-x86_64-20240206.cgz/300s/lkp-spr-2sp4/small-allocs-mt/vm-scalability
commit:
b6adf494d7 ("mm: Assert the mmap_lock is held in __anon_vma_prepare()")
06d7da17eb ("mm: Delay the check for a NULL anon_vma")
b6adf494d78314b6 06d7da17eb40ba4d1b68f894ee1
---------------- ---------------------------
%stddev %change %stddev
\ | \
74523 -67.2% 24454 uptime.idle
6.34e+10 -78.8% 1.342e+10 cpuidle..time
1.701e+08 -89.6% 17747986 ± 2% cpuidle..usage
906035 ± 5% +90.8% 1728983 ± 7% numa-numastat.node0.local_node
1046067 ± 4% +77.3% 1854474 ± 3% numa-numastat.node0.numa_hit
1311558 ± 3% +59.1% 2086157 ± 6% numa-numastat.node1.local_node
1410254 ± 2% +55.5% 2192628 ± 2% numa-numastat.node1.numa_hit
6425 ± 4% -16.7% 5355 ± 3% perf-c2c.DRAM.remote
7051 ± 3% -25.8% 5231 ± 3% perf-c2c.HITM.local
4511 ± 4% -34.8% 2940 ± 2% perf-c2c.HITM.remote
11563 ± 3% -29.3% 8172 ± 3% perf-c2c.HITM.total
90.71 -80.4% 17.78 vmstat.cpu.id
8.99 ± 3% +805.0% 81.38 vmstat.cpu.sy
19.84 ± 10% +824.7% 183.50 vmstat.procs.r
698619 -87.6% 86741 ± 2% vmstat.system.cs
227194 +6.3% 241573 vmstat.system.in
90.65 -73.4 17.27 mpstat.cpu.all.idle%
0.20 ± 5% +0.3 0.50 ± 2% mpstat.cpu.all.irq%
0.08 -0.0 0.07 mpstat.cpu.all.soft%
8.77 ± 3% +72.6 81.33 mpstat.cpu.all.sys%
0.31 +0.5 0.83 mpstat.cpu.all.usr%
215.33 ± 12% -38.0% 133.50 ± 34% mpstat.max_utilization.seconds
11.08 ± 2% +772.7% 96.67 mpstat.max_utilization_pct
907614 -12.3% 795617 meminfo.Active
907482 -12.3% 795486 meminfo.Active(anon)
130738 ± 4% +12.4% 147011 ± 5% meminfo.Mapped
9309220 +55.5% 14472405 meminfo.Memused
498476 +223.2% 1611222 meminfo.PageTables
2111517 +192.8% 6182069 meminfo.SUnreclaim
2263824 +179.8% 6333898 meminfo.Slab
9568677 +57.6% 15076828 meminfo.max_used_kB
248208 +225.0% 806656 numa-meminfo.node0.PageTables
1034116 +199.6% 3098428 numa-meminfo.node0.SUnreclaim
1125682 +183.8% 3194597 numa-meminfo.node0.Slab
863270 ± 8% -18.1% 706715 ± 3% numa-meminfo.node1.Active
863210 ± 8% -18.1% 706649 ± 3% numa-meminfo.node1.Active(anon)
249620 +222.9% 805984 numa-meminfo.node1.PageTables
1076184 +186.6% 3084567 numa-meminfo.node1.SUnreclaim
1136926 +176.2% 3140231 numa-meminfo.node1.Slab
62102 +224.4% 201448 numa-vmstat.node0.nr_page_table_pages
258627 +199.5% 774500 numa-vmstat.node0.nr_slab_unreclaimable
1045168 ± 4% +77.4% 1854224 ± 3% numa-vmstat.node0.numa_hit
905137 ± 5% +91.0% 1728733 ± 7% numa-vmstat.node0.numa_local
215659 ± 8% -17.9% 176972 ± 3% numa-vmstat.node1.nr_active_anon
62453 +222.3% 201271 numa-vmstat.node1.nr_page_table_pages
269139 +186.5% 771014 numa-vmstat.node1.nr_slab_unreclaimable
215659 ± 8% -17.9% 176972 ± 3% numa-vmstat.node1.nr_zone_active_anon
1409093 ± 2% +55.5% 2191166 ± 2% numa-vmstat.node1.numa_hit
1310396 ± 3% +59.1% 2084707 ± 6% numa-vmstat.node1.numa_local
8530 +226.9% 27887 vm-scalability.median
1910909 +226.9% 6246734 vm-scalability.throughput
314.36 +9.6% 344.62 vm-scalability.time.elapsed_time
314.36 +9.6% 344.62 vm-scalability.time.elapsed_time.max
663.67 ± 5% +7551.9% 50783 vm-scalability.time.involuntary_context_switches
1.276e+08 +226.9% 4.172e+08 vm-scalability.time.minor_page_faults
2140 ± 2% +761.1% 18433 vm-scalability.time.percent_of_cpu_this_job_got
6569 ± 2% +858.6% 62975 vm-scalability.time.system_time
161.49 +242.2% 552.58 vm-scalability.time.user_time
1.105e+08 -86.7% 14697764 ± 2% vm-scalability.time.voluntary_context_switches
5.743e+08 +226.9% 1.877e+09 vm-scalability.workload
226935 -12.3% 198989 proc-vmstat.nr_active_anon
12879162 -1.0% 12750211 proc-vmstat.nr_dirty_background_threshold
25789814 -1.0% 25531597 proc-vmstat.nr_dirty_threshold
1074059 -1.7% 1055610 proc-vmstat.nr_file_pages
1.295e+08 -1.0% 1.282e+08 proc-vmstat.nr_free_pages
243814 +4.6% 255031 proc-vmstat.nr_inactive_anon
33032 ± 4% +11.1% 36709 ± 5% proc-vmstat.nr_mapped
124572 +223.7% 403234 proc-vmstat.nr_page_table_pages
308933 -6.0% 290477 proc-vmstat.nr_shmem
527641 +192.9% 1545582 proc-vmstat.nr_slab_unreclaimable
226935 -12.3% 198989 proc-vmstat.nr_zone_active_anon
243814 +4.6% 255031 proc-vmstat.nr_zone_inactive_anon
82731 ± 16% -65.0% 28974 ± 47% proc-vmstat.numa_hint_faults
50675 ± 24% -59.5% 20504 ± 45% proc-vmstat.numa_hint_faults_local
2458414 +64.7% 4049539 proc-vmstat.numa_hit
2219686 +72.0% 3817577 proc-vmstat.numa_local
485406 ± 2% -49.9% 243333 ± 30% proc-vmstat.numa_pte_updates
290930 +3.3% 300617 proc-vmstat.pgactivate
3016705 +84.0% 5551173 proc-vmstat.pgalloc_normal
1.291e+08 +224.2% 4.186e+08 proc-vmstat.pgfault
2592277 ± 2% +95.8% 5075265 proc-vmstat.pgfree
1.07 -11.4% 0.95 perf-stat.i.MPKI
4.303e+09 +611.1% 3.06e+10 perf-stat.i.branch-instructions
0.43 -0.3 0.15 perf-stat.i.branch-miss-rate%
19064779 -29.7% 13393929 perf-stat.i.branch-misses
30.45 +7.7 38.18 perf-stat.i.cache-miss-rate%
15794717 +17.1% 18496465 perf-stat.i.cache-misses
706504 -88.1% 84094 ± 2% perf-stat.i.context-switches
4.09 ± 2% -19.8% 3.28 perf-stat.i.cpi
6.907e+10 ± 2% +645.0% 5.145e+11 perf-stat.i.cpu-cycles
1955 -76.9% 451.18 perf-stat.i.cpu-migrations
4450 ± 2% +512.0% 27236 perf-stat.i.cycles-between-cache-misses
1.67e+10 +751.2% 1.422e+11 perf-stat.i.instructions
0.27 ± 2% +39.1% 0.37 perf-stat.i.ipc
0.03 ± 37% +142.9% 0.08 ± 31% perf-stat.i.major-faults
6.82 +51.2% 10.31 perf-stat.i.metric.K/sec
411063 +181.7% 1158109 perf-stat.i.minor-faults
411063 +181.7% 1158110 perf-stat.i.page-faults
0.95 -86.8% 0.12 perf-stat.overall.MPKI
0.44 -0.4 0.04 perf-stat.overall.branch-miss-rate%
29.03 +3.9 32.95 perf-stat.overall.cache-miss-rate%
4.13 ± 2% -12.3% 3.62 perf-stat.overall.cpi
4366 ± 2% +565.6% 29061 perf-stat.overall.cycles-between-cache-misses
0.24 ± 2% +14.0% 0.28 perf-stat.overall.ipc
9135 +199.3% 27347 perf-stat.overall.path-length
4.285e+09 +646.7% 3.199e+10 perf-stat.ps.branch-instructions
19006353 -29.6% 13372254 perf-stat.ps.branch-misses
15744973 +17.7% 18532137 perf-stat.ps.cache-misses
54240830 +3.7% 56254046 perf-stat.ps.cache-references
703147 -87.6% 87147 ± 2% perf-stat.ps.context-switches
6.875e+10 ± 2% +683.3% 5.385e+11 perf-stat.ps.cpu-cycles
1948 -76.5% 457.14 perf-stat.ps.cpu-migrations
1.663e+10 +793.4% 1.486e+11 perf-stat.ps.instructions
0.03 ± 37% +126.8% 0.08 ± 32% perf-stat.ps.major-faults
409108 +196.1% 1211563 perf-stat.ps.minor-faults
409108 +196.1% 1211564 perf-stat.ps.page-faults
5.247e+12 +878.5% 5.134e+13 perf-stat.total.instructions
335413 ± 5% +9958.6% 33737897 sched_debug.cfs_rq:/.avg_vruntime.avg
495046 ± 8% +6770.8% 34013537 sched_debug.cfs_rq:/.avg_vruntime.max
317459 ± 5% +9262.1% 29720916 sched_debug.cfs_rq:/.avg_vruntime.min
18070 ± 5% +1726.6% 330082 ± 7% sched_debug.cfs_rq:/.avg_vruntime.stddev
0.10 ± 11% +721.6% 0.79 ± 2% sched_debug.cfs_rq:/.h_nr_running.avg
1.00 +69.4% 1.69 ± 8% sched_debug.cfs_rq:/.h_nr_running.max
0.29 ± 4% -15.4% 0.25 ± 10% sched_debug.cfs_rq:/.h_nr_running.stddev
6.88 ± 15% +122.1% 15.28 ± 87% sched_debug.cfs_rq:/.load_avg.avg
335413 ± 5% +9958.6% 33737897 sched_debug.cfs_rq:/.min_vruntime.avg
495046 ± 8% +6770.8% 34013538 sched_debug.cfs_rq:/.min_vruntime.max
317459 ± 5% +9262.1% 29720916 sched_debug.cfs_rq:/.min_vruntime.min
18070 ± 5% +1726.6% 330082 ± 7% sched_debug.cfs_rq:/.min_vruntime.stddev
0.10 ± 11% +714.0% 0.79 sched_debug.cfs_rq:/.nr_running.avg
0.29 ± 4% -21.1% 0.23 ± 13% sched_debug.cfs_rq:/.nr_running.stddev
103.95 ± 3% +679.9% 810.70 sched_debug.cfs_rq:/.runnable_avg.avg
764.53 ± 5% +122.0% 1697 ± 3% sched_debug.cfs_rq:/.runnable_avg.max
7.25 ±147% +2188.5% 165.92 ± 29% sched_debug.cfs_rq:/.runnable_avg.min
73.92 ± 3% +104.3% 150.99 ± 6% sched_debug.cfs_rq:/.runnable_avg.stddev
103.68 ± 3% +676.5% 805.15 sched_debug.cfs_rq:/.util_avg.avg
764.39 ± 5% +106.4% 1577 ± 6% sched_debug.cfs_rq:/.util_avg.max
7.25 ±147% +1892.0% 144.42 ± 32% sched_debug.cfs_rq:/.util_avg.min
73.79 ± 3% +95.2% 144.07 ± 7% sched_debug.cfs_rq:/.util_avg.stddev
9.64 ± 11% +7825.0% 764.08 sched_debug.cfs_rq:/.util_est.avg
234.92 ± 7% +509.0% 1430 ± 10% sched_debug.cfs_rq:/.util_est.max
35.12 ± 4% +513.4% 215.42 ± 12% sched_debug.cfs_rq:/.util_est.stddev
594748 +41.9% 843772 sched_debug.cpu.avg_idle.avg
905212 ± 5% +18.9% 1075937 ± 7% sched_debug.cpu.avg_idle.max
118694 ± 12% -96.5% 4212 sched_debug.cpu.avg_idle.min
79158 ± 5% +284.1% 304031 ± 3% sched_debug.cpu.avg_idle.stddev
13.69 +19.0% 16.30 ± 8% sched_debug.cpu.clock.stddev
636.82 ± 8% +752.2% 5426 sched_debug.cpu.curr->pid.avg
10191 -10.4% 9134 ± 7% sched_debug.cpu.curr->pid.max
1943 ± 3% -23.1% 1493 ± 13% sched_debug.cpu.curr->pid.stddev
0.00 ± 6% +164.5% 0.00 ± 40% sched_debug.cpu.next_balance.stddev
0.09 ± 8% +749.5% 0.79 sched_debug.cpu.nr_running.avg
1.00 +69.4% 1.69 ± 8% sched_debug.cpu.nr_running.max
0.29 ± 3% -14.6% 0.24 ± 10% sched_debug.cpu.nr_running.stddev
488871 -86.4% 66243 ± 2% sched_debug.cpu.nr_switches.avg
508846 -59.9% 203810 ± 11% sched_debug.cpu.nr_switches.max
447153 -90.9% 40770 ± 5% sched_debug.cpu.nr_switches.min
6511 ± 12% +166.2% 17331 ± 4% sched_debug.cpu.nr_switches.stddev
0.75 -92.1% 0.06 ± 26% sched_debug.cpu.nr_uninterruptible.avg
40.86 ± 9% +370.0% 192.03 ± 22% sched_debug.cpu.nr_uninterruptible.max
-15.06 +324.4% -63.89 sched_debug.cpu.nr_uninterruptible.min
6.99 ± 7% +336.4% 30.50 ± 6% sched_debug.cpu.nr_uninterruptible.stddev
0.00 ±101% +2.8e+05% 0.36 ± 51% sched_debug.rt_rq:.rt_time.avg
0.03 ±101% +2.8e+05% 81.08 ± 51% sched_debug.rt_rq:.rt_time.max
0.00 ±101% +2.8e+05% 5.41 ± 51% sched_debug.rt_rq:.rt_time.stddev
74.54 -73.7 0.87 perf-profile.calltrace.cycles-pp.do_access
72.57 -72.6 0.00 perf-profile.calltrace.cycles-pp.exc_page_fault.asm_exc_page_fault.do_access
73.28 -72.6 0.70 perf-profile.calltrace.cycles-pp.asm_exc_page_fault.do_access
72.55 -72.5 0.00 perf-profile.calltrace.cycles-pp.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
69.93 -69.9 0.00 perf-profile.calltrace.cycles-pp.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
69.12 -69.1 0.00 perf-profile.calltrace.cycles-pp.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
68.78 -68.8 0.00 perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault
65.78 -65.8 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault
65.43 -65.4 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma
13.67 -13.7 0.00 perf-profile.calltrace.cycles-pp.__mmap
13.56 -13.6 0.00 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
13.56 -13.6 0.00 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__mmap
13.54 -13.5 0.00 perf-profile.calltrace.cycles-pp.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
13.50 -13.5 0.00 perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
10.72 ± 3% -10.7 0.00 perf-profile.calltrace.cycles-pp.common_startup_64
10.68 ± 3% -10.7 0.00 perf-profile.calltrace.cycles-pp.start_secondary.common_startup_64
10.67 ± 3% -10.7 0.00 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.common_startup_64
10.66 ± 3% -10.7 0.00 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.common_startup_64
7.96 ± 4% -8.0 0.00 perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.common_startup_64
7.38 ± 4% -7.4 0.00 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
7.20 ± 4% -7.2 0.00 perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
7.15 ± 3% -7.2 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff
7.05 ± 3% -7.0 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff
1.04 ± 3% -0.5 0.53 perf-profile.calltrace.cycles-pp.do_rw_once
0.00 +0.6 0.56 ± 5% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.osq_lock
0.00 +0.6 0.57 ± 5% perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.osq_lock.rwsem_optimistic_spin
0.00 +0.6 0.64 ± 4% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.osq_lock.rwsem_optimistic_spin.rwsem_down_write_slowpath
0.00 +0.7 0.66 ± 5% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.osq_lock.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable
11.22 +86.5 97.68 perf-profile.calltrace.cycles-pp.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
11.14 +86.5 97.66 perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64
3.17 ± 2% +94.0 97.12 perf-profile.calltrace.cycles-pp.osq_lock.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff
3.45 ± 2% +94.1 97.59 perf-profile.calltrace.cycles-pp.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff
0.00 +98.2 98.15 perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +98.2 98.16 perf-profile.calltrace.cycles-pp.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +98.2 98.17 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +98.2 98.17 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
74.52 -73.4 1.12 perf-profile.children.cycles-pp.do_access
72.96 -73.0 0.00 perf-profile.children.cycles-pp._raw_spin_lock_irq
73.39 -72.7 0.74 perf-profile.children.cycles-pp.asm_exc_page_fault
72.63 -72.6 0.06 ± 6% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
72.58 -72.1 0.49 perf-profile.children.cycles-pp.exc_page_fault
72.57 -72.1 0.49 perf-profile.children.cycles-pp.do_user_addr_fault
69.93 -69.9 0.00 perf-profile.children.cycles-pp.lock_mm_and_find_vma
69.12 -69.1 0.00 perf-profile.children.cycles-pp.down_read_killable
68.81 -68.8 0.00 perf-profile.children.cycles-pp.rwsem_down_read_slowpath
13.67 -13.7 0.00 perf-profile.children.cycles-pp.__mmap
10.72 ± 3% -10.6 0.12 ± 3% perf-profile.children.cycles-pp.common_startup_64
10.72 ± 3% -10.6 0.12 ± 3% perf-profile.children.cycles-pp.cpu_startup_entry
10.72 ± 3% -10.6 0.12 ± 3% perf-profile.children.cycles-pp.do_idle
10.68 ± 3% -10.6 0.12 ± 3% perf-profile.children.cycles-pp.start_secondary
8.00 ± 4% -7.9 0.08 ± 4% perf-profile.children.cycles-pp.cpuidle_idle_call
7.42 ± 4% -7.3 0.08 perf-profile.children.cycles-pp.cpuidle_enter
7.41 ± 4% -7.3 0.08 perf-profile.children.cycles-pp.cpuidle_enter_state
3.11 ± 3% -3.0 0.07 perf-profile.children.cycles-pp.__schedule
2.91 ± 9% -2.2 0.72 ± 4% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
2.69 ± 10% -2.0 0.69 ± 4% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
1.91 ± 3% -1.9 0.05 ± 8% perf-profile.children.cycles-pp.schedule
1.39 ± 3% -1.3 0.09 perf-profile.children.cycles-pp.up_write
1.61 ± 3% -0.9 0.72 perf-profile.children.cycles-pp.do_rw_once
1.49 ± 19% -0.9 0.60 ± 4% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
1.43 ± 19% -0.8 0.60 ± 5% perf-profile.children.cycles-pp.hrtimer_interrupt
1.08 ± 3% -0.8 0.26 ± 2% perf-profile.children.cycles-pp.handle_mm_fault
0.99 ± 3% -0.8 0.23 ± 4% perf-profile.children.cycles-pp.__handle_mm_fault
0.83 ± 4% -0.7 0.09 ± 4% perf-profile.children.cycles-pp.irq_exit_rcu
0.80 ± 5% -0.7 0.09 ± 5% perf-profile.children.cycles-pp.__do_softirq
0.72 ± 3% -0.6 0.11 ± 4% perf-profile.children.cycles-pp._raw_spin_lock
0.91 ± 3% -0.5 0.40 perf-profile.children.cycles-pp.do_mmap
0.90 ± 15% -0.4 0.50 ± 6% perf-profile.children.cycles-pp.__hrtimer_run_queues
0.68 ± 3% -0.4 0.31 perf-profile.children.cycles-pp.mmap_region
0.41 ± 34% -0.4 0.05 perf-profile.children.cycles-pp.clockevents_program_event
0.54 ± 2% -0.4 0.18 ± 3% perf-profile.children.cycles-pp.lock_vma_under_rcu
0.85 ± 16% -0.4 0.50 ± 6% perf-profile.children.cycles-pp.tick_nohz_handler
0.44 ± 2% -0.3 0.09 ± 5% perf-profile.children.cycles-pp.update_load_avg
0.73 ± 14% -0.3 0.47 ± 5% perf-profile.children.cycles-pp.update_process_times
0.32 ± 3% -0.2 0.08 ± 4% perf-profile.children.cycles-pp.native_irq_return_iret
0.27 ± 4% -0.2 0.07 perf-profile.children.cycles-pp.rcu_core
0.29 ± 3% -0.2 0.11 perf-profile.children.cycles-pp.do_anonymous_page
0.25 ± 3% -0.2 0.09 ± 5% perf-profile.children.cycles-pp.vma_interval_tree_insert
0.26 ± 3% -0.2 0.10 ± 5% perf-profile.children.cycles-pp.__pte_offset_map_lock
0.23 ± 47% -0.2 0.08 ± 14% perf-profile.children.cycles-pp.tmigr_requires_handle_remote
0.22 ± 49% -0.1 0.08 ± 14% perf-profile.children.cycles-pp.get_jiffies_update
0.22 ± 4% -0.1 0.08 ± 4% perf-profile.children.cycles-pp.get_unmapped_area
0.21 ± 6% -0.1 0.08 ± 4% perf-profile.children.cycles-pp.sync_regs
0.20 ± 5% -0.1 0.07 perf-profile.children.cycles-pp.vm_unmapped_area
0.20 ± 4% -0.1 0.08 ± 6% perf-profile.children.cycles-pp.arch_get_unmapped_area_topdown
0.18 ± 5% -0.1 0.06 perf-profile.children.cycles-pp.mas_empty_area_rev
0.17 ± 5% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
0.16 ± 3% -0.1 0.07 ± 5% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.14 ± 4% -0.1 0.05 perf-profile.children.cycles-pp.mas_rev_awalk
0.16 ± 4% -0.1 0.09 ± 5% perf-profile.children.cycles-pp.mas_walk
0.11 ± 6% -0.1 0.05 ± 7% perf-profile.children.cycles-pp.mas_store_prealloc
0.03 ± 70% +0.0 0.07 ± 5% perf-profile.children.cycles-pp.kmem_cache_free
0.00 +0.1 0.05 perf-profile.children.cycles-pp.__put_partials
0.00 +0.1 0.06 ± 9% perf-profile.children.cycles-pp.shmem_file_write_iter
0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.vfs_write
0.00 +0.1 0.06 ± 11% perf-profile.children.cycles-pp.ksys_write
0.00 +0.1 0.07 ± 7% perf-profile.children.cycles-pp.record__pushfn
0.00 +0.1 0.07 ± 7% perf-profile.children.cycles-pp.write
0.00 +0.1 0.07 ± 7% perf-profile.children.cycles-pp.writen
0.00 +0.1 0.11 ± 7% perf-profile.children.cycles-pp.perf_mmap__push
0.00 +0.1 0.12 ± 9% perf-profile.children.cycles-pp.record__mmap_read_evlist
0.00 +0.1 0.12 ± 6% perf-profile.children.cycles-pp.__cmd_record
0.00 +0.1 0.12 ± 6% perf-profile.children.cycles-pp.cmd_record
0.00 +0.1 0.12 ± 7% perf-profile.children.cycles-pp.main
0.00 +0.1 0.12 ± 7% perf-profile.children.cycles-pp.run_builtin
0.18 ± 3% +0.2 0.42 perf-profile.children.cycles-pp.rwsem_spin_on_owner
0.00 +0.3 0.27 ± 6% perf-profile.children.cycles-pp.task_tick_fair
13.63 +84.6 98.24 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
13.63 +84.6 98.24 perf-profile.children.cycles-pp.do_syscall_64
13.54 +84.6 98.16 perf-profile.children.cycles-pp.ksys_mmap_pgoff
13.51 +84.6 98.15 perf-profile.children.cycles-pp.vm_mmap_pgoff
11.22 +86.5 97.68 perf-profile.children.cycles-pp.down_write_killable
11.14 +86.5 97.66 perf-profile.children.cycles-pp.rwsem_down_write_slowpath
3.17 ± 2% +94.0 97.14 perf-profile.children.cycles-pp.osq_lock
3.46 ± 2% +94.1 97.59 perf-profile.children.cycles-pp.rwsem_optimistic_spin
72.63 -72.6 0.06 ± 6% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
1.47 ± 3% -0.8 0.62 perf-profile.self.cycles-pp.do_rw_once
0.64 ± 3% -0.5 0.09 ± 5% perf-profile.self.cycles-pp._raw_spin_lock
0.65 ± 5% -0.5 0.11 ± 9% perf-profile.self.cycles-pp.__handle_mm_fault
0.62 ± 3% -0.4 0.27 perf-profile.self.cycles-pp.do_access
0.35 ± 2% -0.3 0.08 ± 4% perf-profile.self.cycles-pp.lock_vma_under_rcu
0.32 ± 3% -0.2 0.08 ± 4% perf-profile.self.cycles-pp.native_irq_return_iret
0.25 ± 3% -0.2 0.08 ± 5% perf-profile.self.cycles-pp.vma_interval_tree_insert
0.22 ± 49% -0.1 0.08 ± 12% perf-profile.self.cycles-pp.get_jiffies_update
0.21 ± 6% -0.1 0.07 ± 6% perf-profile.self.cycles-pp.sync_regs
0.16 ± 2% -0.1 0.06 ± 6% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
0.16 ± 4% -0.1 0.09 ± 4% perf-profile.self.cycles-pp.mas_walk
0.17 ± 2% +0.3 0.42 perf-profile.self.cycles-pp.rwsem_spin_on_owner
3.17 ± 2% +93.3 96.49 perf-profile.self.cycles-pp.osq_lock
***************************************************************************************************
lkp-icl-2sp9: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/runtime/tbox_group/test/testcase:
gcc-13/performance/x86_64-rhel-8.3/debian-12-x86_64-20240206.cgz/300s/lkp-icl-2sp9/small-allocs-mt/vm-scalability
commit:
b6adf494d7 ("mm: Assert the mmap_lock is held in __anon_vma_prepare()")
06d7da17eb ("mm: Delay the check for a NULL anon_vma")
b6adf494d78314b6 06d7da17eb40ba4d1b68f894ee1
---------------- ---------------------------
%stddev %change %stddev
\ | \
17955 -61.1% 6980 uptime.idle
1.611e+10 -69.1% 4.982e+09 cpuidle..time
1.853e+08 -92.3% 14289120 ± 3% cpuidle..usage
11230 -20.6% 8914 ± 3% perf-c2c.HITM.remote
27682 -12.1% 24320 ± 2% perf-c2c.HITM.total
848844 ± 2% +128.5% 1939396 ± 2% numa-numastat.node0.local_node
883369 +124.3% 1981542 numa-numastat.node0.numa_hit
1319303 +58.6% 2092949 ± 2% numa-numastat.node1.local_node
1351183 +56.7% 2117225 ± 2% numa-numastat.node1.numa_hit
78.83 -71.8% 22.21 vmstat.cpu.id
19.93 +272.2% 74.18 vmstat.cpu.sy
12.17 ± 7% +311.6% 50.10 vmstat.procs.r
1067521 -92.6% 79321 ± 3% vmstat.system.cs
602485 -81.7% 110420 vmstat.system.in
78.73 -56.9 21.82 mpstat.cpu.all.idle%
0.97 -0.7 0.29 mpstat.cpu.all.irq%
0.08 -0.0 0.07 mpstat.cpu.all.soft%
19.00 +55.2 74.19 mpstat.cpu.all.sys%
1.23 +2.4 3.64 mpstat.cpu.all.usr%
25.38 +270.9% 94.11 mpstat.max_utilization_pct
1196280 -65.2% 416708 meminfo.Active
1195992 -65.2% 416549 meminfo.Active(anon)
4439550 -18.5% 3619917 meminfo.Cached
2629628 -32.9% 1763715 meminfo.Committed_AS
69593 -40.1% 41658 meminfo.Mapped
9113710 +65.8% 15109985 meminfo.Memused
690373 +211.0% 2147376 meminfo.PageTables
2511830 +211.4% 7822144 meminfo.SUnreclaim
1379430 -59.4% 560283 meminfo.Shmem
2606486 +203.7% 7914759 meminfo.Slab
9217244 +72.2% 15868922 meminfo.max_used_kB
41551 +208.9% 128340 vm-scalability.median
7.22 ± 14% +6.5 13.71 ± 7% vm-scalability.stddev%
2659286 +208.9% 8214820 vm-scalability.throughput
317.52 +10.4% 350.62 vm-scalability.time.elapsed_time
317.52 +10.4% 350.62 vm-scalability.time.elapsed_time.max
600.00 ± 5% +9879.2% 59875 vm-scalability.time.involuntary_context_switches
1.776e+08 +208.9% 5.487e+08 vm-scalability.time.minor_page_faults
1278 +289.3% 4976 vm-scalability.time.percent_of_cpu_this_job_got
3852 +332.8% 16671 vm-scalability.time.system_time
208.45 +274.3% 780.21 vm-scalability.time.user_time
1.708e+08 -92.0% 13751285 ± 3% vm-scalability.time.voluntary_context_switches
7.991e+08 +208.9% 2.469e+09 vm-scalability.workload
26462 ± 30% +355.1% 120436 ± 13% numa-meminfo.node0.Active
26355 ± 30% +356.6% 120335 ± 13% numa-meminfo.node0.Active(anon)
3744138 ± 24% +88.4% 7053908 ± 10% numa-meminfo.node0.MemUsed
342419 +214.8% 1077823 numa-meminfo.node0.PageTables
1259794 +212.4% 3935134 numa-meminfo.node0.SUnreclaim
52164 ± 87% +265.6% 190719 ± 34% numa-meminfo.node0.Shmem
1306848 +205.1% 3986890 numa-meminfo.node0.Slab
1170263 -74.7% 295991 ± 6% numa-meminfo.node1.Active
1170083 -74.7% 295932 ± 6% numa-meminfo.node1.Active(anon)
42683 ± 13% -62.3% 16073 ± 20% numa-meminfo.node1.Mapped
5368570 ± 17% +50.2% 8064145 ± 10% numa-meminfo.node1.MemUsed
348271 ± 2% +207.6% 1071248 numa-meminfo.node1.PageTables
1250327 +211.4% 3893129 numa-meminfo.node1.SUnreclaim
1327536 ± 3% -72.2% 369272 ± 18% numa-meminfo.node1.Shmem
1297929 +203.1% 3933988 numa-meminfo.node1.Slab
6574 ± 30% +357.4% 30074 ± 13% numa-vmstat.node0.nr_active_anon
85549 ± 2% +214.6% 269122 numa-vmstat.node0.nr_page_table_pages
13054 ± 87% +265.4% 47702 ± 34% numa-vmstat.node0.nr_shmem
314916 +212.2% 983311 numa-vmstat.node0.nr_slab_unreclaimable
6574 ± 30% +357.4% 30074 ± 13% numa-vmstat.node0.nr_zone_active_anon
882369 +124.5% 1980880 numa-vmstat.node0.numa_hit
847844 ± 2% +128.7% 1938734 ± 2% numa-vmstat.node0.numa_local
292334 -74.7% 74088 ± 6% numa-vmstat.node1.nr_active_anon
10960 ± 14% -63.8% 3968 ± 21% numa-vmstat.node1.nr_mapped
87015 ± 2% +207.4% 267494 numa-vmstat.node1.nr_page_table_pages
331863 ± 3% -72.2% 92348 ± 18% numa-vmstat.node1.nr_shmem
312570 +211.2% 972821 numa-vmstat.node1.nr_slab_unreclaimable
292334 -74.7% 74088 ± 6% numa-vmstat.node1.nr_zone_active_anon
1349954 +56.7% 2115569 ± 2% numa-vmstat.node1.numa_hit
1318072 +58.7% 2091293 ± 2% numa-vmstat.node1.numa_local
299113 -65.2% 104075 proc-vmstat.nr_active_anon
6328555 -2.4% 6178825 proc-vmstat.nr_dirty_background_threshold
12672583 -2.4% 12372759 proc-vmstat.nr_dirty_threshold
1110217 -18.5% 905199 proc-vmstat.nr_file_pages
63662675 -2.4% 62163313 proc-vmstat.nr_free_pages
207228 -5.4% 196031 proc-vmstat.nr_inactive_anon
15199 -1.4% 14990 proc-vmstat.nr_kernel_stack
17628 -39.2% 10716 proc-vmstat.nr_mapped
172696 +210.3% 535803 proc-vmstat.nr_page_table_pages
344923 -59.4% 140027 proc-vmstat.nr_shmem
23663 -2.2% 23153 proc-vmstat.nr_slab_reclaimable
627282 +211.9% 1956390 proc-vmstat.nr_slab_unreclaimable
299113 -65.2% 104075 proc-vmstat.nr_zone_active_anon
207228 -5.4% 196031 proc-vmstat.nr_zone_inactive_anon
2236707 +83.3% 4100262 proc-vmstat.numa_hit
2170302 +85.9% 4033840 proc-vmstat.numa_local
389394 ± 2% -62.6% 145653 ± 5% proc-vmstat.pgactivate
2904299 +102.3% 5874354 proc-vmstat.pgalloc_normal
1.786e+08 +207.8% 5.497e+08 proc-vmstat.pgfault
2441060 +132.2% 5667896 proc-vmstat.pgfree
1.70 ± 4% -35.6% 1.09 ± 2% perf-stat.i.MPKI
4.873e+09 +228.7% 1.602e+10 perf-stat.i.branch-instructions
0.43 -0.3 0.15 perf-stat.i.branch-miss-rate%
21584013 -42.2% 12485827 perf-stat.i.branch-misses
40.69 +6.3 47.01 perf-stat.i.cache-miss-rate%
1078369 -92.6% 79670 ± 3% perf-stat.i.context-switches
3.03 -15.7% 2.55 perf-stat.i.cpi
5.702e+10 +215.8% 1.801e+11 perf-stat.i.cpu-cycles
2722 ± 4% -89.6% 284.25 ± 2% perf-stat.i.cpu-migrations
1990 ± 5% +195.6% 5883 ± 3% perf-stat.i.cycles-between-cache-misses
1.856e+10 +252.1% 6.536e+10 perf-stat.i.instructions
0.37 +26.4% 0.46 perf-stat.i.ipc
0.01 ± 68% +943.9% 0.15 ± 14% perf-stat.i.major-faults
34.41 +45.2% 49.98 perf-stat.i.metric.K/sec
562396 +177.8% 1562226 perf-stat.i.minor-faults
562396 +177.8% 1562226 perf-stat.i.page-faults
1.52 ± 5% -71.2% 0.44 ± 2% perf-stat.overall.MPKI
0.44 -0.4 0.08 perf-stat.overall.branch-miss-rate%
38.89 +4.0 42.88 perf-stat.overall.cache-miss-rate%
3.07 -10.2% 2.76 perf-stat.overall.cpi
2025 ± 5% +211.2% 6303 ± 3% perf-stat.overall.cycles-between-cache-misses
0.33 +11.4% 0.36 perf-stat.overall.ipc
7377 +26.2% 9311 perf-stat.overall.path-length
4.855e+09 +229.7% 1.601e+10 perf-stat.ps.branch-instructions
21554937 -42.1% 12473394 perf-stat.ps.branch-misses
1073957 -92.6% 79637 ± 3% perf-stat.ps.context-switches
5.68e+10 +216.9% 1.8e+11 perf-stat.ps.cpu-cycles
2738 ± 5% -89.6% 284.08 ± 2% perf-stat.ps.cpu-migrations
1.85e+10 +253.1% 6.531e+10 perf-stat.ps.instructions
0.01 ± 68% +946.4% 0.15 ± 15% perf-stat.ps.major-faults
560100 +178.8% 1561640 perf-stat.ps.minor-faults
560100 +178.8% 1561641 perf-stat.ps.page-faults
5.896e+12 +289.9% 2.299e+13 perf-stat.total.instructions
483686 +1579.1% 8121726 sched_debug.cfs_rq:/.avg_vruntime.avg
561686 ± 2% +1361.1% 8207028 sched_debug.cfs_rq:/.avg_vruntime.max
468154 +1582.7% 7877712 sched_debug.cfs_rq:/.avg_vruntime.min
18117 ± 10% +179.2% 50584 ± 2% sched_debug.cfs_rq:/.avg_vruntime.stddev
0.24 ± 11% +223.0% 0.77 ± 10% sched_debug.cfs_rq:/.h_nr_running.avg
1.03 ± 6% +81.1% 1.86 ± 13% sched_debug.cfs_rq:/.h_nr_running.max
0.42 ± 4% -29.5% 0.30 ± 16% sched_debug.cfs_rq:/.h_nr_running.stddev
1.28 ± 14% +530.4% 8.06 ± 19% sched_debug.cfs_rq:/.load_avg.min
483686 +1579.1% 8121726 sched_debug.cfs_rq:/.min_vruntime.avg
561686 ± 2% +1361.1% 8207028 sched_debug.cfs_rq:/.min_vruntime.max
468154 +1582.7% 7877712 sched_debug.cfs_rq:/.min_vruntime.min
18117 ± 10% +179.2% 50584 ± 2% sched_debug.cfs_rq:/.min_vruntime.stddev
0.24 ± 11% +215.2% 0.75 ± 10% sched_debug.cfs_rq:/.nr_running.avg
0.42 ± 4% -47.7% 0.22 ± 19% sched_debug.cfs_rq:/.nr_running.stddev
270.42 +218.0% 859.87 ± 2% sched_debug.cfs_rq:/.runnable_avg.avg
617.81 ± 4% +168.7% 1660 ± 3% sched_debug.cfs_rq:/.runnable_avg.max
44.31 ± 61% +476.7% 255.53 ± 36% sched_debug.cfs_rq:/.runnable_avg.min
106.53 ± 6% +76.9% 188.47 ± 10% sched_debug.cfs_rq:/.runnable_avg.stddev
269.85 +214.6% 849.07 ± 2% sched_debug.cfs_rq:/.util_avg.avg
617.75 ± 4% +159.0% 1600 ± 3% sched_debug.cfs_rq:/.util_avg.max
44.31 ± 60% +379.6% 212.50 ± 46% sched_debug.cfs_rq:/.util_avg.min
106.57 ± 6% +72.9% 184.25 ± 11% sched_debug.cfs_rq:/.util_avg.stddev
49.69 ± 10% +1250.9% 671.34 ± 10% sched_debug.cfs_rq:/.util_est.avg
367.69 ± 9% +240.3% 1251 ± 8% sched_debug.cfs_rq:/.util_est.max
102.66 ± 4% +103.6% 209.05 ± 16% sched_debug.cfs_rq:/.util_est.stddev
188245 +207.7% 579233 ± 7% sched_debug.cpu.avg_idle.avg
314020 ± 12% +223.8% 1016940 ± 2% sched_debug.cpu.avg_idle.max
48870 ± 6% -92.1% 3879 ± 2% sched_debug.cpu.avg_idle.min
54347 ± 6% +618.7% 390582 ± 2% sched_debug.cpu.avg_idle.stddev
1.48 ± 3% +80.6% 2.68 ± 10% sched_debug.cpu.clock.stddev
711.92 ± 7% +202.4% 2152 ± 10% sched_debug.cpu.curr->pid.avg
1348 -36.6% 854.78 ± 16% sched_debug.cpu.curr->pid.stddev
0.00 ± 39% +125.9% 0.00 ± 31% sched_debug.cpu.next_balance.stddev
0.25 ± 7% +210.8% 0.77 ± 10% sched_debug.cpu.nr_running.avg
1.03 ± 6% +83.8% 1.89 ± 11% sched_debug.cpu.nr_running.max
0.43 ± 2% -30.2% 0.30 ± 16% sched_debug.cpu.nr_running.stddev
2626862 -91.6% 220090 ± 3% sched_debug.cpu.nr_switches.avg
2651045 -87.1% 342508 ± 6% sched_debug.cpu.nr_switches.max
2522596 -93.6% 161790 ± 4% sched_debug.cpu.nr_switches.min
25115 ± 9% +43.3% 35978 ± 10% sched_debug.cpu.nr_switches.stddev
0.65 ± 2% -79.2% 0.14 ± 55% sched_debug.cpu.nr_uninterruptible.avg
31.06 ± 49% +409.1% 158.11 ± 11% sched_debug.cpu.nr_uninterruptible.max
-25.14 +265.5% -91.89 sched_debug.cpu.nr_uninterruptible.min
9.78 ± 37% +403.5% 49.25 ± 7% sched_debug.cpu.nr_uninterruptible.stddev
59.37 -54.5 4.82 perf-profile.calltrace.cycles-pp.do_access
56.91 -54.2 2.73 perf-profile.calltrace.cycles-pp.asm_exc_page_fault.do_access
55.42 -53.5 1.96 ± 2% perf-profile.calltrace.cycles-pp.exc_page_fault.asm_exc_page_fault.do_access
55.35 -53.4 1.94 ± 2% perf-profile.calltrace.cycles-pp.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
49.60 -49.6 0.00 perf-profile.calltrace.cycles-pp.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
48.04 -48.0 0.00 perf-profile.calltrace.cycles-pp.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
47.40 -47.4 0.00 perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault
41.75 -41.8 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma.do_user_addr_fault
40.48 -40.5 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_read_slowpath.down_read_killable.lock_mm_and_find_vma
21.24 -21.2 0.00 perf-profile.calltrace.cycles-pp.__mmap
21.08 -21.1 0.00 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__mmap
21.08 -21.1 0.00 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
21.03 -21.0 0.00 perf-profile.calltrace.cycles-pp.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
20.97 -21.0 0.00 perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap
18.03 -18.0 0.00 perf-profile.calltrace.cycles-pp.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
17.47 -17.5 0.00 perf-profile.calltrace.cycles-pp.common_startup_64
17.19 -17.2 0.00 perf-profile.calltrace.cycles-pp.start_secondary.common_startup_64
17.18 -17.2 0.00 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.common_startup_64
17.16 -17.2 0.00 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.common_startup_64
14.97 -15.0 0.00 perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.common_startup_64
14.25 -14.3 0.00 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
14.19 -14.2 0.00 perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
13.57 -13.6 0.00 perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
8.13 ± 2% -8.1 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff
7.97 ± 2% -8.0 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff
5.97 -6.0 0.00 perf-profile.calltrace.cycles-pp.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
2.34 ± 2% -1.2 1.09 ± 3% perf-profile.calltrace.cycles-pp.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
2.07 ± 2% -1.2 0.85 ± 4% perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
1.58 -0.9 0.70 perf-profile.calltrace.cycles-pp.lock_vma_under_rcu.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.do_access
0.64 ± 4% -0.4 0.26 ±100% perf-profile.calltrace.cycles-pp.do_anonymous_page.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault
1.59 -0.1 1.48 perf-profile.calltrace.cycles-pp.do_mmap.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.14 -0.0 1.09 perf-profile.calltrace.cycles-pp.mmap_region.do_mmap.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64
1.20 +0.4 1.55 perf-profile.calltrace.cycles-pp.rwsem_spin_on_owner.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff
2.28 +0.9 3.21 perf-profile.calltrace.cycles-pp.do_rw_once
17.49 +73.1 90.62 perf-profile.calltrace.cycles-pp.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
17.34 +73.2 90.57 perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64
7.01 +81.8 88.79 perf-profile.calltrace.cycles-pp.osq_lock.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff
8.59 +81.8 90.43 perf-profile.calltrace.cycles-pp.rwsem_optimistic_spin.rwsem_down_write_slowpath.down_write_killable.vm_mmap_pgoff.ksys_mmap_pgoff
0.00 +92.4 92.36 perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +92.4 92.42 perf-profile.calltrace.cycles-pp.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +92.4 92.44 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +92.4 92.44 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
59.07 -54.3 4.82 perf-profile.children.cycles-pp.do_access
56.71 -53.9 2.83 perf-profile.children.cycles-pp.asm_exc_page_fault
55.44 -53.5 1.97 ± 2% perf-profile.children.cycles-pp.exc_page_fault
55.39 -53.4 1.95 ± 2% perf-profile.children.cycles-pp.do_user_addr_fault
49.89 -49.9 0.00 perf-profile.children.cycles-pp._raw_spin_lock_irq
49.60 -49.6 0.00 perf-profile.children.cycles-pp.lock_mm_and_find_vma
48.76 -48.6 0.16 ± 8% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
48.05 -48.1 0.00 perf-profile.children.cycles-pp.down_read_killable
47.42 -47.4 0.00 perf-profile.children.cycles-pp.rwsem_down_read_slowpath
21.25 -21.3 0.00 perf-profile.children.cycles-pp.__mmap
17.47 -17.0 0.46 ± 2% perf-profile.children.cycles-pp.common_startup_64
17.47 -17.0 0.46 ± 2% perf-profile.children.cycles-pp.cpu_startup_entry
17.45 -17.0 0.46 ± 2% perf-profile.children.cycles-pp.do_idle
17.19 -16.7 0.45 ± 3% perf-profile.children.cycles-pp.start_secondary
15.22 -14.8 0.41 ± 3% perf-profile.children.cycles-pp.cpuidle_idle_call
14.48 -14.1 0.40 ± 3% perf-profile.children.cycles-pp.cpuidle_enter
14.42 -14.0 0.40 ± 3% perf-profile.children.cycles-pp.cpuidle_enter_state
13.79 -13.4 0.39 ± 2% perf-profile.children.cycles-pp.acpi_idle_enter
13.77 -13.4 0.39 ± 3% perf-profile.children.cycles-pp.acpi_safe_halt
11.27 -11.0 0.28 ± 2% perf-profile.children.cycles-pp.asm_sysvec_call_function_single
5.02 ± 2% -4.9 0.13 perf-profile.children.cycles-pp.__schedule
3.97 -3.9 0.10 perf-profile.children.cycles-pp.sysvec_call_function_single
3.24 -3.2 0.08 ± 4% perf-profile.children.cycles-pp.__sysvec_call_function_single
3.18 ± 2% -3.1 0.09 perf-profile.children.cycles-pp.schedule_preempt_disabled
3.17 ± 2% -3.1 0.10 ± 5% perf-profile.children.cycles-pp.schedule
3.09 -3.0 0.08 perf-profile.children.cycles-pp.__flush_smp_call_function_queue
2.33 -2.3 0.06 perf-profile.children.cycles-pp.sched_ttwu_pending
1.86 -1.8 0.05 perf-profile.children.cycles-pp.ttwu_do_activate
1.90 -1.8 0.13 ± 10% perf-profile.children.cycles-pp.rwsem_wake
1.90 -1.6 0.28 ± 4% perf-profile.children.cycles-pp.up_write
1.51 -1.4 0.06 ± 7% perf-profile.children.cycles-pp.wake_up_q
1.45 -1.4 0.06 ± 7% perf-profile.children.cycles-pp.try_to_wake_up
1.62 ± 4% -1.3 0.36 ± 3% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
2.36 ± 2% -1.3 1.10 ± 3% perf-profile.children.cycles-pp.handle_mm_fault
2.09 ± 2% -1.2 0.86 ± 4% perf-profile.children.cycles-pp.__handle_mm_fault
1.58 -0.9 0.70 perf-profile.children.cycles-pp.lock_vma_under_rcu
0.94 ± 8% -0.6 0.33 ± 3% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
0.79 -0.5 0.26 perf-profile.children.cycles-pp.native_irq_return_iret
0.76 ± 3% -0.3 0.44 ± 3% perf-profile.children.cycles-pp._raw_spin_lock
0.40 ± 2% -0.3 0.09 perf-profile.children.cycles-pp.irq_exit_rcu
0.51 ± 15% -0.3 0.24 ± 4% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
0.49 ± 15% -0.3 0.23 ± 5% perf-profile.children.cycles-pp.hrtimer_interrupt
0.31 ± 2% -0.2 0.11 perf-profile.children.cycles-pp.__do_softirq
0.60 ± 4% -0.2 0.45 ± 4% perf-profile.children.cycles-pp.__pte_offset_map_lock
0.64 ± 4% -0.1 0.51 ± 3% perf-profile.children.cycles-pp.do_anonymous_page
1.60 -0.1 1.49 perf-profile.children.cycles-pp.do_mmap
0.27 ± 10% -0.1 0.17 ± 6% perf-profile.children.cycles-pp.__hrtimer_run_queues
0.38 -0.1 0.28 perf-profile.children.cycles-pp.vm_unmapped_area
0.48 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.mas_walk
0.26 ± 10% -0.1 0.16 ± 6% perf-profile.children.cycles-pp.tick_nohz_handler
0.17 ± 4% -0.1 0.08 ± 13% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.30 ± 3% -0.1 0.22 ± 3% perf-profile.children.cycles-pp.___perf_sw_event
0.33 -0.1 0.24 perf-profile.children.cycles-pp.mas_empty_area_rev
0.18 ± 2% -0.1 0.09 ± 4% perf-profile.children.cycles-pp.rcu_core
0.39 -0.1 0.31 perf-profile.children.cycles-pp.arch_get_unmapped_area_topdown
0.35 ± 2% -0.1 0.28 perf-profile.children.cycles-pp.sync_regs
0.12 ± 3% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.osq_unlock
0.20 ± 7% -0.1 0.14 ± 6% perf-profile.children.cycles-pp.update_process_times
0.40 ± 2% -0.1 0.34 perf-profile.children.cycles-pp.get_unmapped_area
1.15 -0.1 1.09 perf-profile.children.cycles-pp.mmap_region
0.31 ± 3% -0.1 0.25 perf-profile.children.cycles-pp.vma_interval_tree_insert
0.26 -0.1 0.20 perf-profile.children.cycles-pp.mas_rev_awalk
0.12 ± 3% -0.0 0.08 perf-profile.children.cycles-pp.__rb_insert_augmented
0.12 -0.0 0.09 ± 4% perf-profile.children.cycles-pp.perf_event_mmap
0.12 ± 4% -0.0 0.09 perf-profile.children.cycles-pp.perf_event_mmap_event
0.08 ± 5% -0.0 0.06 perf-profile.children.cycles-pp.handle_pte_fault
0.09 ± 7% -0.0 0.07 ± 5% perf-profile.children.cycles-pp.mas_preallocate
0.08 ± 4% -0.0 0.06 ± 6% perf-profile.children.cycles-pp.mas_alloc_nodes
0.09 -0.0 0.08 perf-profile.children.cycles-pp.mas_wr_bnode
0.06 ± 6% +0.0 0.07 ± 6% perf-profile.children.cycles-pp.vm_area_alloc
0.20 ± 2% +0.0 0.22 ± 2% perf-profile.children.cycles-pp.mas_store_prealloc
0.09 ± 4% +0.0 0.12 ± 6% perf-profile.children.cycles-pp.mas_wr_store_entry
0.08 ± 5% +0.0 0.11 ± 3% perf-profile.children.cycles-pp.mas_wr_node_store
0.04 ± 44% +0.0 0.07 ± 5% perf-profile.children.cycles-pp.down_write
0.19 ± 3% +0.0 0.23 ± 4% perf-profile.children.cycles-pp.__perf_sw_event
0.00 +0.1 0.05 ± 8% perf-profile.children.cycles-pp.task_tick_fair
0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.__call_rcu_common
1.20 +0.4 1.56 perf-profile.children.cycles-pp.rwsem_spin_on_owner
3.36 +0.4 3.76 perf-profile.children.cycles-pp.do_rw_once
21.18 +71.3 92.48 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
21.17 +71.3 92.48 perf-profile.children.cycles-pp.do_syscall_64
21.04 +71.4 92.42 perf-profile.children.cycles-pp.ksys_mmap_pgoff
20.98 +71.4 92.36 perf-profile.children.cycles-pp.vm_mmap_pgoff
17.49 +73.1 90.62 perf-profile.children.cycles-pp.down_write_killable
17.34 +73.2 90.57 perf-profile.children.cycles-pp.rwsem_down_write_slowpath
7.01 +81.8 88.80 perf-profile.children.cycles-pp.osq_lock
8.64 +81.8 90.43 perf-profile.children.cycles-pp.rwsem_optimistic_spin
48.76 -48.6 0.16 ± 8% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
8.50 -8.3 0.21 ± 3% perf-profile.self.cycles-pp.acpi_safe_halt
1.34 ± 2% -1.1 0.28 ± 8% perf-profile.self.cycles-pp.__handle_mm_fault
1.07 ± 3% -0.8 0.30 ± 5% perf-profile.self.cycles-pp.lock_vma_under_rcu
0.79 -0.5 0.26 perf-profile.self.cycles-pp.native_irq_return_iret
0.50 -0.2 0.30 ± 2% perf-profile.self.cycles-pp._raw_spin_lock
0.15 ± 2% -0.1 0.05 perf-profile.self.cycles-pp.down_write_killable
0.47 ± 2% -0.1 0.38 ± 3% perf-profile.self.cycles-pp.mas_walk
0.35 ± 2% -0.1 0.28 perf-profile.self.cycles-pp.sync_regs
0.12 ± 3% -0.1 0.06 ± 6% perf-profile.self.cycles-pp.osq_unlock
0.11 ± 4% -0.1 0.05 ± 45% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.25 ± 2% -0.1 0.20 ± 3% perf-profile.self.cycles-pp.___perf_sw_event
0.30 ± 3% -0.1 0.25 perf-profile.self.cycles-pp.vma_interval_tree_insert
0.11 -0.0 0.08 perf-profile.self.cycles-pp.__rb_insert_augmented
0.19 ± 3% -0.0 0.16 ± 2% perf-profile.self.cycles-pp.mas_rev_awalk
0.06 ± 6% -0.0 0.05 perf-profile.self.cycles-pp.handle_mm_fault
0.02 ± 99% +0.0 0.07 ± 8% perf-profile.self.cycles-pp.down_write
0.00 +0.1 0.05 perf-profile.self.cycles-pp.mas_wr_node_store
1.10 +0.1 1.16 perf-profile.self.cycles-pp.do_access
0.07 ± 9% +0.1 0.16 ± 3% perf-profile.self.cycles-pp.up_write
3.00 +0.2 3.22 perf-profile.self.cycles-pp.do_rw_once
1.16 +0.4 1.55 perf-profile.self.cycles-pp.rwsem_spin_on_owner
6.99 +81.6 88.57 perf-profile.self.cycles-pp.osq_lock
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
reply other threads:[~2024-04-26 2:47 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=202404261055.c5e24608-oliver.sang@intel.com \
--to=oliver.sang@intel.com \
--cc=lkp@intel.com \
--cc=oe-lkp@lists.linux.dev \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).