| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20220622055559.GA29357@xsang-OptiPlex-9020>
Date: Wed, 22 Jun 2022 13:55:59 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Mel Gorman <mgorman@...hsingularity.net>
Cc: Peter Zijlstra <peterz@...radead.org>,
K Prateek Nayak <kprateek.nayak@....com>,
LKML <linux-kernel@...r.kernel.org>, x86@...nel.org,
lkp@...ts.01.org, lkp@...el.com, ying.huang@...el.com,
feng.tang@...el.com, zhengjun.xing@...ux.intel.com,
fengwei.yin@...el.com, guobing.chen@...el.com,
ming.a.chen@...el.com, frank.du@...el.com, Shuhua.Fan@...el.com,
wangyang.guo@...el.com, Wenhuan.Huang@...el.com,
jessica.ji@...el.com, shan.kang@...el.com, guangli.li@...el.com,
tiejun.li@...el.com, yu.ma@...el.com, dapeng1.mi@...el.com,
jiebin.sun@...el.com, gengxin.xie@...el.com, fan.zhao@...el.com,
aubrey.li@...ux.intel.com, yu.c.chen@...el.com
Subject: [sched/numa] cb29a5c19d:
phoronix-test-suite.vpxenc.Speed5.frames_per_second -8.0% regression
Hi, Mel Gorman,
we reported "[sched/numa] bb2dee337b: unixbench.score -11.2% regression"
last month at
https://lore.kernel.org/all/20220518092414.GA15472@xsang-OptiPlex-9020/
and according to your inputs and experiments from Ying, we got the idea this
commit could benefit some workloads but cause regression on others.
now we noticed this commit in tip now, and we found another regression in one
PTS test (the fsmark regression reported in bb2dee337b report is also
reproduced). just FYI
Greeting,
FYI, we noticed a -8.0% regression of phoronix-test-suite.vpxenc.Speed5.frames_per_second due to commit:
commit: cb29a5c19d2d68afc641fb1949e1a1c565b582ea ("sched/numa: Apply imbalance limitations consistently")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git sched/core
in testcase: phoronix-test-suite
on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory
with following parameters:
test: vpxenc-3.0.0
option_a: Speed 5 [Fastest - Default]
cpufreq_governor: performance
ucode: 0x500320a
test-description: The Phoronix Test Suite is the most comprehensive testing and benchmarking platform available that provides an extensible framework for which new tests can be easily added.
test-url: http://www.phoronix-test-suite.com/
In addition to that, the commit also has significant impact on the following tests:
+------------------+-------------------------------------------------------------------------------------+
| testcase: change | fsmark: fsmark.files_per_sec -13.8% regression |
| test machine | 192 threads 4 sockets Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory |
| test parameters | cpufreq_governor=performance |
| | disk=1SSD |
| | filesize=9B |
| | fs=btrfs |
| | iterations=8 |
| | nr_directories=16d |
| | nr_files_per_directory=256fpd |
| | nr_threads=4 |
| | sync_method=fsyncBeforeClose |
| | test_size=16G |
| | ucode=0x500320a |
+------------------+-------------------------------------------------------------------------------------+
If you fix the issue, kindly add following tag
Reported-by: kernel test robot <oliver.sang@...el.com>
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
sudo bin/lkp install job.yaml # job file is attached in this email
bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
sudo bin/lkp run generated-yaml-file
# if come across any failure that blocks the test,
# please remove ~/.lkp and /lkp dir to run from a clean state.
=========================================================================================
compiler/cpufreq_governor/kconfig/option_a/rootfs/tbox_group/test/testcase/ucode:
gcc-11/performance/x86_64-rhel-8.3/Speed 5 [Fastest - Default]/debian-x86_64-phoronix/lkp-csl-2sp7/vpxenc-3.0.0/phoronix-test-suite/0x500320a
commit:
13ede33150 ("sched/numa: Do not swap tasks between nodes when spare capacity is available")
cb29a5c19d ("sched/numa: Apply imbalance limitations consistently")
13ede33150877d44 cb29a5c19d2d68afc641fb1949e
---------------- ---------------------------
%stddev %change %stddev
\ | \
139.88 +7.1% 149.87 phoronix-test-suite.time.elapsed_time
139.88 +7.1% 149.87 phoronix-test-suite.time.elapsed_time.max
687138 -14.5% 587750 ± 5% phoronix-test-suite.time.minor_page_faults
350.44 +5.1% 368.43 phoronix-test-suite.time.user_time
549751 +97.1% 1083494 ± 13% phoronix-test-suite.time.voluntary_context_switches
16.12 -8.0% 14.83 phoronix-test-suite.vpxenc.Speed5.frames_per_second
257.88 +5.9% 273.13 pmeter.Average_Active_Power
1.43 ± 18% -0.4 1.05 ± 11% mpstat.cpu.all.irq%
0.07 ± 20% -0.0 0.05 ± 12% mpstat.cpu.all.soft%
13365 -6.7% 12465 vmstat.io.bi
9186 +69.7% 15590 ± 11% vmstat.system.cs
904355 ± 4% -35.7% 581776 ± 28% numa-numastat.node0.local_node
939756 ± 3% -34.3% 616963 ± 26% numa-numastat.node0.numa_hit
301216 ± 13% +127.0% 683764 ± 24% numa-numastat.node1.local_node
334322 ± 10% +114.4% 716912 ± 23% numa-numastat.node1.numa_hit
1957 ± 5% +13.0% 2212 ± 4% turbostat.Bzy_MHz
456458 ± 36% +279.2% 1731028 ± 85% turbostat.C1
139875 ± 11% -40.7% 83002 ± 32% turbostat.POLL
132.56 +9.2% 144.73 turbostat.PkgWatt
401285 ± 2% -19.1% 324795 ± 8% proc-vmstat.numa_hint_faults
401245 ± 2% -35.5% 258744 ± 11% proc-vmstat.numa_hint_faults_local
1280393 +4.7% 1340600 proc-vmstat.numa_hit
2195 ± 2% -20.9% 1737 ± 9% proc-vmstat.numa_huge_pte_updates
1211885 +5.0% 1272264 proc-vmstat.numa_local
209.67 ±223% +77390.1% 162471 ± 14% proc-vmstat.numa_pages_migrated
1553858 -20.1% 1242134 ± 9% proc-vmstat.numa_pte_updates
1285673 +4.5% 1344022 proc-vmstat.pgalloc_normal
841292 +7.2% 901606 proc-vmstat.pgfree
209.67 ±223% +77390.1% 162471 ± 14% proc-vmstat.pgmigrate_success
124876 +4.4% 130409 proc-vmstat.pgreuse
937171 -49.9% 469141 ± 67% numa-meminfo.node0.Active
931124 -50.3% 463046 ± 68% numa-meminfo.node0.Active(file)
325304 -51.6% 157469 ± 12% numa-meminfo.node0.AnonHugePages
584407 -50.4% 289749 ± 12% numa-meminfo.node0.AnonPages
651845 -38.4% 401650 ± 14% numa-meminfo.node0.AnonPages.max
4571 ± 3% -17.6% 3766 ± 9% numa-meminfo.node0.PageTables
25612 ± 70% +1863.0% 502765 ± 62% numa-meminfo.node1.Active
22402 ± 78% +2130.4% 499671 ± 63% numa-meminfo.node1.Active(file)
3895 ± 25% +4533.5% 180514 ± 13% numa-meminfo.node1.AnonHugePages
30561 ± 17% +981.9% 330644 ± 9% numa-meminfo.node1.AnonPages
39832 ± 31% +1131.7% 490599 ± 7% numa-meminfo.node1.AnonPages.max
166333 ±190% +346.7% 742978 ± 59% numa-meminfo.node1.Inactive(file)
1192724 ± 42% +108.8% 2490726 ± 33% numa-meminfo.node1.MemUsed
2059 ± 7% +38.4% 2849 ± 12% numa-meminfo.node1.PageTables
232829 -50.3% 115776 ± 68% numa-vmstat.node0.nr_active_file
146027 -50.4% 72440 ± 12% numa-vmstat.node0.nr_anon_pages
158.33 -51.7% 76.50 ± 13% numa-vmstat.node0.nr_anon_transparent_hugepages
1142 ± 3% -17.6% 941.33 ± 9% numa-vmstat.node0.nr_page_table_pages
232829 -50.3% 115776 ± 68% numa-vmstat.node0.nr_zone_active_file
939744 ± 3% -34.4% 616740 ± 26% numa-vmstat.node0.numa_hit
904344 ± 4% -35.7% 581554 ± 28% numa-vmstat.node0.numa_local
5600 ± 78% +2126.1% 124669 ± 63% numa-vmstat.node1.nr_active_file
7640 ± 17% +982.8% 82731 ± 9% numa-vmstat.node1.nr_anon_pages
1.33 ± 35% +6475.0% 87.67 ± 13% numa-vmstat.node1.nr_anon_transparent_hugepages
41583 ±190% +347.0% 185880 ± 59% numa-vmstat.node1.nr_inactive_file
515.00 ± 7% +38.3% 712.50 ± 12% numa-vmstat.node1.nr_page_table_pages
5600 ± 78% +2126.1% 124669 ± 63% numa-vmstat.node1.nr_zone_active_file
41583 ±190% +347.0% 185880 ± 59% numa-vmstat.node1.nr_zone_inactive_file
334298 ± 10% +114.5% 717103 ± 23% numa-vmstat.node1.numa_hit
301191 ± 13% +127.1% 683955 ± 24% numa-vmstat.node1.numa_local
1.088e+09 -4.6% 1.037e+09 perf-stat.i.branch-instructions
8.85 ± 15% +7.7 16.53 ± 6% perf-stat.i.cache-miss-rate%
6329981 ± 9% +61.9% 10246918 ± 4% perf-stat.i.cache-misses
9280 +71.2% 15887 ± 11% perf-stat.i.context-switches
2.70 ± 28% +104.5% 5.51 ± 19% perf-stat.i.cpu-migrations
1857 ± 12% -30.1% 1298 ± 18% perf-stat.i.cycles-between-cache-misses
1.519e+10 -5.9% 1.429e+10 perf-stat.i.instructions
13279 ± 7% -12.6% 11603 ± 3% perf-stat.i.instructions-per-iTLB-miss
12.53 ± 4% -10.7% 11.18 perf-stat.i.major-faults
8576 -11.7% 7571 ± 3% perf-stat.i.minor-faults
18.61 ± 13% +52.9 71.50 ± 2% perf-stat.i.node-load-miss-rate%
148299 ± 27% +1647.6% 2591752 ± 5% perf-stat.i.node-load-misses
1255857 ± 2% -35.2% 814130 ± 9% perf-stat.i.node-loads
13.10 ± 14% +50.3 63.44 ± 4% perf-stat.i.node-store-miss-rate%
42020 ± 17% +1835.3% 813224 ± 6% perf-stat.i.node-store-misses
772924 ± 3% -49.4% 391419 ± 8% perf-stat.i.node-stores
8589 -11.7% 7583 ± 3% perf-stat.i.page-faults
1867 ±103% +222.2% 6016 ± 89% sched_debug.cfs_rq:/.load_avg.max
155431 ± 16% -32.6% 104751 ± 14% sched_debug.cfs_rq:/.min_vruntime.max
24303 ± 19% -37.6% 15171 ± 16% sched_debug.cfs_rq:/.min_vruntime.stddev
104.41 ± 6% -14.8% 88.92 ± 7% sched_debug.cfs_rq:/.runnable_avg.avg
200.61 ± 3% -11.9% 176.79 ± 4% sched_debug.cfs_rq:/.runnable_avg.stddev
8638 ± 90% -358.6% -22341 sched_debug.cfs_rq:/.spread0.avg
107100 ± 21% -70.1% 32044 ± 42% sched_debug.cfs_rq:/.spread0.max
-20872 +120.5% -46014 sched_debug.cfs_rq:/.spread0.min
24303 ± 19% -37.6% 15174 ± 16% sched_debug.cfs_rq:/.spread0.stddev
103.49 ± 6% -14.7% 88.31 ± 7% sched_debug.cfs_rq:/.util_avg.avg
198.85 ± 3% -12.1% 174.80 ± 4% sched_debug.cfs_rq:/.util_avg.stddev
37.33 ± 18% -39.3% 22.66 ± 19% sched_debug.cfs_rq:/.util_est_enqueued.avg
704.67 ± 10% -22.2% 548.33 ± 14% sched_debug.cfs_rq:/.util_est_enqueued.max
131.21 ± 11% -33.0% 87.86 ± 11% sched_debug.cfs_rq:/.util_est_enqueued.stddev
79565 ± 32% +98.9% 158227 ± 39% sched_debug.cpu.avg_idle.min
341.80 ± 39% -62.7% 127.44 ± 27% sched_debug.cpu.clock_task.stddev
245.03 ± 15% -21.4% 192.50 ± 9% sched_debug.cpu.curr->pid.avg
1016 ± 8% -15.3% 860.84 ± 5% sched_debug.cpu.curr->pid.stddev
7305 +48.3% 10834 ± 10% sched_debug.cpu.nr_switches.avg
99341 ± 16% +79.6% 178446 ± 25% sched_debug.cpu.nr_switches.max
17397 ± 10% +63.1% 28380 ± 18% sched_debug.cpu.nr_switches.stddev
0.18 ±142% +0.6 0.80 ± 25% perf-profile.calltrace.cycles-pp.tick_nohz_irq_exit.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter
0.54 ± 46% +0.8 1.38 ± 33% perf-profile.calltrace.cycles-pp.timekeeping_max_deferment.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call
1.15 ± 17% +1.0 2.16 ± 26% perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call.do_idle
1.46 ± 21% +1.1 2.52 ± 24% perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call.do_idle.cpu_startup_entry
0.73 ± 27% -0.2 0.52 ± 17% perf-profile.children.cycles-pp.perf_trace_sched_stat_runtime
0.53 ± 31% -0.2 0.34 ± 11% perf-profile.children.cycles-pp.task_tick_fair
0.02 ±142% +0.1 0.09 ± 34% perf-profile.children.cycles-pp.flush_smp_call_function_queue
0.04 ±104% +0.1 0.15 ± 36% perf-profile.children.cycles-pp.do_anonymous_page
0.04 ±104% +0.1 0.17 ± 30% perf-profile.children.cycles-pp.clear_page_erms
0.23 ± 26% +0.1 0.37 ± 13% perf-profile.children.cycles-pp.arch_cpu_idle_enter
0.22 ± 22% +0.1 0.36 ± 14% perf-profile.children.cycles-pp.tsc_verify_tsc_adjust
0.04 ±101% +0.1 0.18 ± 29% perf-profile.children.cycles-pp.__do_huge_pmd_anonymous_page
0.04 ±101% +0.1 0.18 ± 29% perf-profile.children.cycles-pp.clear_huge_page
0.29 ± 28% +0.2 0.46 ± 33% perf-profile.children.cycles-pp.ret_from_fork
0.28 ± 28% +0.2 0.46 ± 34% perf-profile.children.cycles-pp.kthread
0.19 ± 26% +0.2 0.42 ± 14% perf-profile.children.cycles-pp.calc_global_load_tick
0.39 ± 26% +0.2 0.63 ± 13% perf-profile.children.cycles-pp.arch_scale_freq_tick
0.60 ± 11% +0.3 0.89 ± 15% perf-profile.children.cycles-pp.asm_exc_page_fault
0.35 ± 13% +0.3 0.66 ± 15% perf-profile.children.cycles-pp.do_user_addr_fault
0.39 ± 11% +0.3 0.70 ± 16% perf-profile.children.cycles-pp.exc_page_fault
0.30 ± 16% +0.3 0.61 ± 17% perf-profile.children.cycles-pp.handle_mm_fault
0.27 ± 19% +0.3 0.59 ± 17% perf-profile.children.cycles-pp.__handle_mm_fault
0.45 ± 19% +0.4 0.84 ± 24% perf-profile.children.cycles-pp.tick_nohz_irq_exit
0.63 ± 17% +0.8 1.38 ± 33% perf-profile.children.cycles-pp.timekeeping_max_deferment
1.18 ± 17% +1.0 2.20 ± 26% perf-profile.children.cycles-pp.tick_nohz_next_event
1.48 ± 20% +1.1 2.55 ± 23% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length
0.04 ±107% +0.1 0.17 ± 31% perf-profile.self.cycles-pp.clear_page_erms
0.20 ± 20% +0.1 0.34 ± 19% perf-profile.self.cycles-pp.tsc_verify_tsc_adjust
0.19 ± 25% +0.2 0.41 ± 16% perf-profile.self.cycles-pp.calc_global_load_tick
0.39 ± 26% +0.2 0.63 ± 13% perf-profile.self.cycles-pp.arch_scale_freq_tick
0.16 ± 19% +0.2 0.40 ± 35% perf-profile.self.cycles-pp.tick_sched_do_timer
0.62 ± 17% +0.8 1.38 ± 33% perf-profile.self.cycles-pp.timekeeping_max_deferment
***************************************************************************************************
lkp-csl-2ap4: 192 threads 4 sockets Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory
=========================================================================================
compiler/cpufreq_governor/disk/filesize/fs/iterations/kconfig/nr_directories/nr_files_per_directory/nr_threads/rootfs/sync_method/tbox_group/test_size/testcase/ucode:
gcc-11/performance/1SSD/9B/btrfs/8/x86_64-rhel-8.3/16d/256fpd/4/debian-11.1-x86_64-20220510.cgz/fsyncBeforeClose/lkp-csl-2ap4/16G/fsmark/0x500320a
commit:
13ede33150 ("sched/numa: Do not swap tasks between nodes when spare capacity is available")
cb29a5c19d ("sched/numa: Apply imbalance limitations consistently")
13ede33150877d44 cb29a5c19d2d68afc641fb1949e
---------------- ---------------------------
%stddev %change %stddev
\ | \
2267984 +10.3% 2501971 fsmark.app_overhead
12670 -13.8% 10919 fsmark.files_per_sec
350.44 +18.9% 416.58 fsmark.time.elapsed_time
350.44 +18.9% 416.58 fsmark.time.elapsed_time.max
3.15e+08 +5.9% 3.335e+08 fsmark.time.file_system_outputs
161.50 +19.1% 192.33 fsmark.time.percent_of_cpu_this_job_got
552.36 ± 3% +42.5% 787.14 fsmark.time.system_time
14387779 +13.0% 16251439 fsmark.time.voluntary_context_switches
2.71 ± 13% -19.4% 2.19 iostat.cpu.system
12275 ± 5% +22.8% 15070 ± 5% meminfo.Active(anon)
6.525e+10 +19.6% 7.807e+10 cpuidle..time
1.476e+08 ± 8% +24.0% 1.83e+08 ± 2% cpuidle..usage
387.74 +17.1% 453.90 uptime.boot
71567 +17.8% 84337 uptime.idle
423821 -10.2% 380430 vmstat.io.bo
88136 -4.7% 83981 vmstat.system.cs
1.75 ± 18% -0.7 1.09 mpstat.cpu.all.irq%
0.12 ± 24% -0.0 0.08 mpstat.cpu.all.soft%
0.85 ± 2% +0.2 1.02 mpstat.cpu.all.sys%
0.05 ± 2% -0.0 0.04 ± 2% mpstat.cpu.all.usr%
6212 ± 94% +196.8% 18437 ± 49% numa-vmstat.node2.nr_anon_pages
6331 ± 92% +193.8% 18600 ± 49% numa-vmstat.node2.nr_inactive_anon
6331 ± 92% +193.8% 18600 ± 49% numa-vmstat.node2.nr_zone_inactive_anon
1969 ± 14% +25.2% 2465 ± 15% numa-vmstat.node3.nr_active_anon
1969 ± 14% +25.2% 2465 ± 15% numa-vmstat.node3.nr_zone_active_anon
17059 ±116% +234.6% 57086 ± 54% numa-meminfo.node2.AnonHugePages
24850 ± 94% +196.8% 73756 ± 50% numa-meminfo.node2.AnonPages
46859 ± 83% +221.6% 150678 ± 19% numa-meminfo.node2.AnonPages.max
25324 ± 92% +193.8% 74408 ± 49% numa-meminfo.node2.Inactive(anon)
7877 ± 14% +25.2% 9864 ± 15% numa-meminfo.node3.Active(anon)
23395 ± 95% +153.4% 59277 ± 45% numa-meminfo.node3.AnonHugePages
4.41 ± 19% -1.1 3.27 turbostat.Busy%
1673 ± 7% +32.3% 2214 turbostat.Bzy_MHz
7354409 ± 5% +26.5% 9300908 ± 2% turbostat.C1
11.52 ± 99% -99.8% 0.03 ± 37% turbostat.CPU%c6
1.36e+08 ± 9% +23.8% 1.683e+08 turbostat.IRQ
5069307 ± 2% +22.1% 6190906 ± 2% turbostat.POLL
93.82 ± 13% +19.6% 112.16 ± 5% turbostat.PkgWatt
8.09 ± 33% -45.9% 4.38 ± 53% sched_debug.cfs_rq:/.removed.load_avg.avg
1635183 ± 24% -29.7% 1149085 ± 4% sched_debug.cpu.avg_idle.max
171308 ± 13% +29.3% 221521 ± 4% sched_debug.cpu.clock.avg
171317 ± 13% +29.3% 221530 ± 4% sched_debug.cpu.clock.max
171298 ± 13% +29.3% 221511 ± 4% sched_debug.cpu.clock.min
168797 ± 13% +29.9% 219332 ± 4% sched_debug.cpu.clock_task.avg
170371 ± 13% +29.2% 220131 ± 4% sched_debug.cpu.clock_task.max
167274 ± 13% +29.9% 217305 ± 4% sched_debug.cpu.clock_task.min
186.80 ± 11% +26.5% 236.24 ± 7% sched_debug.cpu.curr->pid.avg
11025 ± 6% +14.8% 12654 ± 2% sched_debug.cpu.curr->pid.max
1294 ± 10% +23.1% 1593 ± 4% sched_debug.cpu.curr->pid.stddev
171297 ± 13% +29.3% 221510 ± 4% sched_debug.cpu_clk
170281 ± 13% +29.5% 220495 ± 4% sched_debug.ktime
173027 ± 13% +29.0% 223193 ± 4% sched_debug.sched_clk
3069 ± 5% +22.5% 3758 ± 4% proc-vmstat.nr_active_anon
39505514 +5.9% 41822347 proc-vmstat.nr_dirtied
67438 -3.1% 65331 proc-vmstat.nr_dirty
7699 -1.6% 7578 proc-vmstat.nr_mapped
56.17 ± 12% +148.1% 139.33 proc-vmstat.nr_mlock
5984 ± 3% +5.8% 6333 ± 4% proc-vmstat.nr_shmem
804117 +1.1% 813202 proc-vmstat.nr_slab_reclaimable
39504067 +5.9% 41820963 proc-vmstat.nr_written
3069 ± 5% +22.5% 3758 ± 4% proc-vmstat.nr_zone_active_anon
67557 -3.1% 65462 proc-vmstat.nr_zone_write_pending
3133 ± 80% +546.1% 20248 ± 13% proc-vmstat.numa_hint_faults
1705 ± 98% +491.9% 10092 ± 29% proc-vmstat.numa_hint_faults_local
4767 ±126% +405.7% 24107 ± 22% proc-vmstat.numa_pages_migrated
280411 +33.0% 372905 ± 4% proc-vmstat.numa_pte_updates
4082927 ± 3% -7.8% 3763069 proc-vmstat.pgactivate
1214665 +15.3% 1400569 proc-vmstat.pgfault
4767 ±126% +405.7% 24107 ± 22% proc-vmstat.pgmigrate_success
1.498e+08 +6.6% 1.597e+08 proc-vmstat.pgpgout
50215 +12.9% 56670 proc-vmstat.pgreuse
18.49 ± 44% -46.7% 9.86 perf-stat.i.MPKI
1.327e+09 ± 2% -8.5% 1.214e+09 perf-stat.i.branch-instructions
23501825 ± 43% -44.7% 12986923 perf-stat.i.branch-misses
10.68 ± 30% +26.1 36.81 ± 3% perf-stat.i.cache-miss-rate%
10372759 ± 24% +102.9% 21042523 ± 2% perf-stat.i.cache-misses
1.196e+08 ± 43% -50.4% 59271260 perf-stat.i.cache-references
88799 -4.8% 84528 perf-stat.i.context-switches
1382 ± 15% -54.6% 627.98 ± 2% perf-stat.i.cycles-between-cache-misses
1.761e+09 ± 2% -8.7% 1.608e+09 perf-stat.i.dTLB-loads
8.631e+08 ± 2% -8.8% 7.875e+08 perf-stat.i.dTLB-stores
3220005 ± 4% +7.9% 3474453 ± 3% perf-stat.i.iTLB-load-misses
6.638e+09 ± 2% -8.7% 6.062e+09 perf-stat.i.instructions
2077 ± 2% -15.7% 1750 ± 3% perf-stat.i.instructions-per-iTLB-miss
1.35 ± 11% -24.1% 1.02 perf-stat.i.major-faults
666.06 ± 39% -41.0% 392.91 perf-stat.i.metric.K/sec
20.59 ± 2% -8.7% 18.80 perf-stat.i.metric.M/sec
34.66 ± 29% +53.9 88.61 perf-stat.i.node-load-miss-rate%
1031595 ± 62% +589.3% 7111040 ± 2% perf-stat.i.node-load-misses
1777642 ± 6% -50.1% 887280 ± 6% perf-stat.i.node-loads
40.72 ± 35% +44.6 85.35 perf-stat.i.node-store-miss-rate%
530303 ± 51% +265.1% 1935875 ± 2% perf-stat.i.node-store-misses
729861 ± 18% -55.2% 327192 ± 11% perf-stat.i.node-stores
18.12 ± 44% -46.0% 9.78 perf-stat.overall.MPKI
9.67 ± 25% +25.8 35.51 ± 3% perf-stat.overall.cache-miss-rate%
1249 ± 13% -51.3% 608.83 perf-stat.overall.cycles-between-cache-misses
2063 ± 2% -15.3% 1747 ± 3% perf-stat.overall.instructions-per-iTLB-miss
34.25 ± 38% +54.6 88.89 perf-stat.overall.node-load-miss-rate%
40.46 ± 35% +45.1 85.54 perf-stat.overall.node-store-miss-rate%
1.323e+09 ± 2% -8.5% 1.211e+09 perf-stat.ps.branch-instructions
23433121 ± 43% -44.7% 12956511 perf-stat.ps.branch-misses
10344317 ± 24% +102.9% 20990278 ± 2% perf-stat.ps.cache-misses
1.193e+08 ± 43% -50.4% 59122669 perf-stat.ps.cache-references
88533 -4.8% 84309 perf-stat.ps.context-switches
1.756e+09 ± 2% -8.6% 1.605e+09 perf-stat.ps.dTLB-loads
8.606e+08 ± 2% -8.7% 7.856e+08 perf-stat.ps.dTLB-stores
3210622 ± 4% +8.0% 3465877 ± 3% perf-stat.ps.iTLB-load-misses
6.619e+09 ± 2% -8.6% 6.048e+09 perf-stat.ps.instructions
1.35 ± 11% -24.1% 1.02 perf-stat.ps.major-faults
1028434 ± 62% +589.7% 7092993 ± 2% perf-stat.ps.node-load-misses
1773152 ± 6% -50.1% 885261 ± 6% perf-stat.ps.node-loads
528782 ± 51% +265.2% 1931070 ± 2% perf-stat.ps.node-store-misses
727924 ± 18% -55.2% 326470 ± 11% perf-stat.ps.node-stores
2.326e+12 +8.6% 2.525e+12 perf-stat.total.instructions
59.09 ± 4% -5.1 54.02 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
58.31 ± 4% -4.9 53.46 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
63.06 ± 4% -4.5 58.54 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
64.98 ± 4% -4.3 60.72 ± 2% perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
64.76 ± 4% -4.2 60.56 ± 2% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
64.76 ± 4% -4.2 60.56 ± 2% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
64.72 ± 4% -4.2 60.53 ± 2% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
4.53 ± 10% -1.3 3.20 ± 10% perf-profile.calltrace.cycles-pp.wait_log_commit.btrfs_sync_log.btrfs_sync_file.__x64_sys_fsync.do_syscall_64
3.57 ± 10% -1.2 2.40 ± 10% perf-profile.calltrace.cycles-pp.__mutex_lock.wait_log_commit.btrfs_sync_log.btrfs_sync_file.__x64_sys_fsync
2.63 ± 12% -0.9 1.69 ± 9% perf-profile.calltrace.cycles-pp.mutex_spin_on_owner.__mutex_lock.wait_log_commit.btrfs_sync_log.btrfs_sync_file
3.93 ± 8% -0.6 3.34 ± 8% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
0.92 ± 10% -0.2 0.68 ± 15% perf-profile.calltrace.cycles-pp.osq_lock.__mutex_lock.wait_log_commit.btrfs_sync_log.btrfs_sync_file
1.16 ± 9% -0.2 0.95 ± 12% perf-profile.calltrace.cycles-pp.__btrfs_tree_lock.btrfs_search_slot.btrfs_insert_empty_items.btrfs_create_new_inode.btrfs_create_common
1.13 ± 9% -0.2 0.94 ± 12% perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_search_slot.btrfs_insert_empty_items.btrfs_create_new_inode
0.82 ± 7% -0.2 0.64 ± 11% perf-profile.calltrace.cycles-pp.__schedule.schedule.wait_log_commit.btrfs_sync_log.btrfs_sync_file
0.82 ± 7% -0.2 0.64 ± 12% perf-profile.calltrace.cycles-pp.schedule.wait_log_commit.btrfs_sync_log.btrfs_sync_file.__x64_sys_fsync
1.56 ± 6% +0.2 1.76 ± 5% perf-profile.calltrace.cycles-pp.write
1.55 ± 6% +0.2 1.75 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.write
1.54 ± 6% +0.2 1.74 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
1.45 ± 6% +0.2 1.65 ± 6% perf-profile.calltrace.cycles-pp.btrfs_buffered_write.btrfs_do_write_iter.new_sync_write.vfs_write.ksys_write
1.52 ± 6% +0.2 1.73 ± 5% perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
1.53 ± 6% +0.2 1.74 ± 5% perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
1.50 ± 6% +0.2 1.70 ± 5% perf-profile.calltrace.cycles-pp.new_sync_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.47 ± 7% +0.2 1.68 ± 6% perf-profile.calltrace.cycles-pp.btrfs_do_write_iter.new_sync_write.vfs_write.ksys_write.do_syscall_64
0.90 ± 13% +0.2 1.12 ± 5% perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.btrfs_drop_extents.cow_file_range_inline.cow_file_range.btrfs_run_delalloc_range
0.90 ± 13% +0.2 1.11 ± 5% perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_drop_extents.cow_file_range_inline.cow_file_range
1.30 ± 13% +0.3 1.57 ± 5% perf-profile.calltrace.cycles-pp.btrfs_drop_extents.cow_file_range_inline.cow_file_range.btrfs_run_delalloc_range.writepage_delalloc
0.64 ± 14% +0.3 0.93 ± 6% perf-profile.calltrace.cycles-pp.btrfs_alloc_tree_block.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot.btrfs_insert_empty_items
1.98 ± 12% +0.3 2.32 ± 5% perf-profile.calltrace.cycles-pp.cow_file_range_inline.cow_file_range.btrfs_run_delalloc_range.writepage_delalloc.__extent_writepage
2.58 ± 11% +0.4 2.94 ± 5% perf-profile.calltrace.cycles-pp.start_ordered_ops.btrfs_sync_file.__x64_sys_fsync.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.56 ± 11% +0.4 2.93 ± 5% perf-profile.calltrace.cycles-pp.__filemap_fdatawrite_range.start_ordered_ops.btrfs_sync_file.__x64_sys_fsync.do_syscall_64
2.51 ± 11% +0.4 2.88 ± 5% perf-profile.calltrace.cycles-pp.extent_write_cache_pages.extent_writepages.do_writepages.filemap_fdatawrite_wbc.__filemap_fdatawrite_range
2.53 ± 11% +0.4 2.90 ± 5% perf-profile.calltrace.cycles-pp.do_writepages.filemap_fdatawrite_wbc.__filemap_fdatawrite_range.start_ordered_ops.btrfs_sync_file
2.52 ± 11% +0.4 2.90 ± 5% perf-profile.calltrace.cycles-pp.extent_writepages.do_writepages.filemap_fdatawrite_wbc.__filemap_fdatawrite_range.start_ordered_ops
2.55 ± 11% +0.4 2.92 ± 5% perf-profile.calltrace.cycles-pp.filemap_fdatawrite_wbc.__filemap_fdatawrite_range.start_ordered_ops.btrfs_sync_file.__x64_sys_fsync
2.34 ± 12% +0.4 2.74 ± 4% perf-profile.calltrace.cycles-pp.__extent_writepage.extent_write_cache_pages.extent_writepages.do_writepages.filemap_fdatawrite_wbc
2.25 ± 12% +0.4 2.66 ± 5% perf-profile.calltrace.cycles-pp.cow_file_range.btrfs_run_delalloc_range.writepage_delalloc.__extent_writepage.extent_write_cache_pages
2.25 ± 12% +0.4 2.67 ± 5% perf-profile.calltrace.cycles-pp.btrfs_run_delalloc_range.writepage_delalloc.__extent_writepage.extent_write_cache_pages.extent_writepages
0.77 ± 10% +0.5 1.23 ± 4% perf-profile.calltrace.cycles-pp.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot.btrfs_update_root.btrfs_sync_log
0.78 ± 10% +0.5 1.24 ± 5% perf-profile.calltrace.cycles-pp.btrfs_cow_block.btrfs_search_slot.btrfs_update_root.btrfs_sync_log.btrfs_sync_file
0.84 ± 9% +0.5 1.35 ± 4% perf-profile.calltrace.cycles-pp.btrfs_update_root.btrfs_sync_log.btrfs_sync_file.__x64_sys_fsync.do_syscall_64
0.82 ± 11% +0.5 1.33 ± 4% perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_update_root.btrfs_sync_log.btrfs_sync_file.__x64_sys_fsync
0.09 ±223% +0.5 0.60 ± 9% perf-profile.calltrace.cycles-pp.btrfs_init_new_buffer.btrfs_alloc_tree_block.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot
0.88 ± 10% +0.5 1.39 ± 10% perf-profile.calltrace.cycles-pp.__mem_cgroup_flush_stats.mem_cgroup_wb_stats.balance_dirty_pages.balance_dirty_pages_ratelimited.btrfs_create_common
0.87 ± 9% +0.5 1.39 ± 10% perf-profile.calltrace.cycles-pp.cgroup_rstat_flush_irqsafe.__mem_cgroup_flush_stats.mem_cgroup_wb_stats.balance_dirty_pages.balance_dirty_pages_ratelimited
0.86 ± 9% +0.5 1.38 ± 10% perf-profile.calltrace.cycles-pp.cgroup_rstat_flush_locked.cgroup_rstat_flush_irqsafe.__mem_cgroup_flush_stats.mem_cgroup_wb_stats.balance_dirty_pages
0.89 ± 10% +0.5 1.41 ± 10% perf-profile.calltrace.cycles-pp.mem_cgroup_wb_stats.balance_dirty_pages.balance_dirty_pages_ratelimited.btrfs_create_common.lookup_open
0.90 ± 10% +0.5 1.43 ± 10% perf-profile.calltrace.cycles-pp.balance_dirty_pages.balance_dirty_pages_ratelimited.btrfs_create_common.lookup_open.open_last_lookups
0.92 ± 9% +0.5 1.46 ± 9% perf-profile.calltrace.cycles-pp.balance_dirty_pages_ratelimited.btrfs_create_common.lookup_open.open_last_lookups.path_openat
0.00 +0.6 0.62 ± 6% perf-profile.calltrace.cycles-pp.btrfs_search_slot.inode_logged.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe
0.00 +0.7 0.66 ± 6% perf-profile.calltrace.cycles-pp.inode_logged.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file
0.00 +0.7 0.69 ± 12% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.cgroup_rstat_flush_locked.cgroup_rstat_flush_irqsafe.__mem_cgroup_flush_stats.mem_cgroup_wb_stats
0.92 ± 11% +0.8 1.68 ± 11% perf-profile.calltrace.cycles-pp.copy_extent_buffer_full.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot.btrfs_insert_empty_items
0.00 +0.8 0.76 ± 7% perf-profile.calltrace.cycles-pp.osq_lock.__mutex_lock.start_log_trans.btrfs_log_inode_parent.btrfs_log_dentry_safe
4.71 ± 7% +0.8 5.52 ± 4% perf-profile.calltrace.cycles-pp.btrfs_create_common.lookup_open.open_last_lookups.path_openat.do_filp_open
5.99 ± 7% +0.8 6.82 ± 4% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.open64
5.97 ± 7% +0.8 6.81 ± 4% perf-profile.calltrace.cycles-pp.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
6.00 ± 7% +0.8 6.85 ± 4% perf-profile.calltrace.cycles-pp.open64
5.96 ± 7% +0.8 6.80 ± 4% perf-profile.calltrace.cycles-pp.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
5.90 ± 7% +0.8 6.74 ± 4% perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe
5.98 ± 7% +0.8 6.82 ± 4% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
5.89 ± 7% +0.8 6.74 ± 4% perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64
5.57 ± 6% +0.9 6.44 ± 4% perf-profile.calltrace.cycles-pp.lookup_open.open_last_lookups.path_openat.do_filp_open.do_sys_openat2
5.63 ± 7% +0.9 6.50 ± 4% perf-profile.calltrace.cycles-pp.open_last_lookups.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat
0.48 ±100% +1.0 1.45 ± 25% perf-profile.calltrace.cycles-pp.timekeeping_max_deferment.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call
1.54 ± 28% +1.1 2.64 ± 15% perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call.do_idle.cpu_startup_entry
0.80 ± 8% +1.1 1.91 ± 5% perf-profile.calltrace.cycles-pp.__mutex_lock.start_log_trans.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file
0.00 +1.1 1.11 ± 6% perf-profile.calltrace.cycles-pp.mutex_spin_on_owner.__mutex_lock.start_log_trans.btrfs_log_inode_parent.btrfs_log_dentry_safe
0.84 ± 8% +1.1 1.98 ± 4% perf-profile.calltrace.cycles-pp.start_log_trans.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file.__x64_sys_fsync
1.18 ± 39% +1.2 2.34 ± 16% perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.cpuidle_idle_call.do_idle
0.91 ± 11% +1.2 2.14 ± 18% perf-profile.calltrace.cycles-pp.copy_page.copy_extent_buffer_full.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot
2.22 ± 8% +1.4 3.65 ± 6% perf-profile.calltrace.cycles-pp.__btrfs_cow_block.btrfs_cow_block.btrfs_search_slot.btrfs_insert_empty_items.copy_items
2.23 ± 8% +1.4 3.67 ± 6% perf-profile.calltrace.cycles-pp.btrfs_cow_block.btrfs_search_slot.btrfs_insert_empty_items.copy_items.copy_inode_items_to_log
2.84 ± 7% +2.2 5.01 ± 6% perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_insert_empty_items.copy_items.copy_inode_items_to_log.btrfs_log_inode
2.90 ± 7% +2.2 5.07 ± 6% perf-profile.calltrace.cycles-pp.btrfs_insert_empty_items.copy_items.copy_inode_items_to_log.btrfs_log_inode.btrfs_log_inode_parent
3.07 ± 6% +2.2 5.28 ± 6% perf-profile.calltrace.cycles-pp.copy_items.copy_inode_items_to_log.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe
4.44 ± 7% +2.3 6.76 ± 5% perf-profile.calltrace.cycles-pp.copy_inode_items_to_log.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file
5.24 ± 7% +2.8 8.02 ± 4% perf-profile.calltrace.cycles-pp.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file.__x64_sys_fsync
22.32 ± 8% +3.4 25.74 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.fsync
22.40 ± 8% +3.4 25.83 ± 3% perf-profile.calltrace.cycles-pp.fsync
22.31 ± 8% +3.4 25.74 ± 3% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.fsync
22.29 ± 8% +3.4 25.72 ± 3% perf-profile.calltrace.cycles-pp.__x64_sys_fsync.do_syscall_64.entry_SYSCALL_64_after_hwframe.fsync
22.28 ± 8% +3.4 25.71 ± 3% perf-profile.calltrace.cycles-pp.btrfs_sync_file.__x64_sys_fsync.do_syscall_64.entry_SYSCALL_64_after_hwframe.fsync
6.19 ± 7% +4.0 10.18 ± 3% perf-profile.calltrace.cycles-pp.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file.__x64_sys_fsync.do_syscall_64
6.20 ± 7% +4.0 10.20 ± 4% perf-profile.calltrace.cycles-pp.btrfs_log_dentry_safe.btrfs_sync_file.__x64_sys_fsync.do_syscall_64.entry_SYSCALL_64_after_hwframe
59.30 ± 4% -5.1 54.15 ± 2% perf-profile.children.cycles-pp.cpuidle_enter
59.24 ± 4% -5.1 54.10 ± 2% perf-profile.children.cycles-pp.cpuidle_enter_state
63.31 ± 4% -4.6 58.71 ± 2% perf-profile.children.cycles-pp.cpuidle_idle_call
64.98 ± 4% -4.3 60.71 ± 2% perf-profile.children.cycles-pp.do_idle
64.98 ± 4% -4.3 60.72 ± 2% perf-profile.children.cycles-pp.secondary_startup_64_no_verify
64.98 ± 4% -4.3 60.72 ± 2% perf-profile.children.cycles-pp.cpu_startup_entry
64.76 ± 4% -4.2 60.56 ± 2% perf-profile.children.cycles-pp.start_secondary
4.53 ± 10% -1.3 3.20 ± 10% perf-profile.children.cycles-pp.wait_log_commit
4.24 ± 7% -0.6 3.68 ± 8% perf-profile.children.cycles-pp.__hrtimer_run_queues
0.60 ± 5% -0.1 0.48 ± 15% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler
0.57 ± 6% -0.1 0.46 ± 10% perf-profile.children.cycles-pp.load_balance
0.19 ± 41% -0.1 0.10 ± 11% perf-profile.children.cycles-pp.enqueue_hrtimer
0.54 ± 8% -0.1 0.46 ± 10% perf-profile.children.cycles-pp.autoremove_wake_function
0.26 ± 20% -0.1 0.19 ± 9% perf-profile.children.cycles-pp.__hrtimer_next_event_base
0.44 ± 8% -0.1 0.38 ± 11% perf-profile.children.cycles-pp.find_busiest_group
0.40 ± 8% -0.1 0.34 ± 6% perf-profile.children.cycles-pp.update_rq_clock
0.27 ± 11% -0.1 0.21 ± 12% perf-profile.children.cycles-pp.get_next_timer_interrupt
0.20 ± 13% -0.1 0.14 ± 21% perf-profile.children.cycles-pp.hrtimer_update_next_event
0.31 ± 6% -0.1 0.25 ± 13% perf-profile.children.cycles-pp.pick_next_task_fair
0.08 ± 23% -0.1 0.03 ±100% perf-profile.children.cycles-pp.perf_event_task_tick
0.22 ± 7% -0.0 0.18 ± 9% perf-profile.children.cycles-pp.btrfs_comp_cpu_keys
0.28 ± 5% -0.0 0.25 ± 6% perf-profile.children.cycles-pp.mkdir
0.07 ± 11% +0.0 0.09 ± 7% perf-profile.children.cycles-pp.btrfs_delalloc_reserve_metadata
0.07 ± 20% +0.0 0.10 ± 6% perf-profile.children.cycles-pp.rcu_do_batch
0.10 ± 13% +0.0 0.13 ± 8% perf-profile.children.cycles-pp.select_task_rq
0.20 ± 10% +0.0 0.24 ± 5% perf-profile.children.cycles-pp.kmem_cache_free
0.03 ±100% +0.0 0.07 ± 11% perf-profile.children.cycles-pp.log_all_new_ancestors
0.03 ±100% +0.0 0.07 ± 15% perf-profile.children.cycles-pp.btrfs_get_delayed_node
0.10 ± 14% +0.0 0.14 ± 9% perf-profile.children.cycles-pp.up_read
0.08 ± 23% +0.0 0.12 ± 23% perf-profile.children.cycles-pp.xas_start
0.02 ±142% +0.0 0.06 ± 14% perf-profile.children.cycles-pp.btrfs_clean_tree_block
0.18 ± 8% +0.0 0.23 ± 4% perf-profile.children.cycles-pp.btrfs_read_node_slot
0.09 ± 12% +0.0 0.14 ± 12% perf-profile.children.cycles-pp.btrfs_use_block_rsv
0.16 ± 13% +0.0 0.21 ± 8% perf-profile.children.cycles-pp.__process_pages_contig
0.16 ± 13% +0.0 0.21 ± 13% perf-profile.children.cycles-pp.read_tree_block
0.08 ± 18% +0.0 0.12 ± 7% perf-profile.children.cycles-pp.mark_page_accessed
0.01 ±223% +0.0 0.06 ± 11% perf-profile.children.cycles-pp.__btrfs_add_delayed_item
0.17 ± 16% +0.1 0.22 ± 6% perf-profile.children.cycles-pp.release_extent_buffer
0.02 ±141% +0.1 0.07 ± 16% perf-profile.children.cycles-pp.xas_set_mark
0.03 ±100% +0.1 0.08 ± 8% perf-profile.children.cycles-pp.crc32c_pcl_intel_digest
0.10 ± 21% +0.1 0.16 ± 10% perf-profile.children.cycles-pp.percpu_counter_add_batch
0.06 ± 23% +0.1 0.12 ± 12% perf-profile.children.cycles-pp.need_preemptive_reclaim
0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.sb_mark_inode_writeback
0.23 ± 3% +0.1 0.29 ± 6% perf-profile.children.cycles-pp.pin_down_extent
0.26 ± 10% +0.1 0.32 ± 4% perf-profile.children.cycles-pp.__folio_start_writeback
0.03 ±100% +0.1 0.09 ± 6% perf-profile.children.cycles-pp.rwsem_mark_wake
0.12 ± 16% +0.1 0.18 ± 10% perf-profile.children.cycles-pp.folio_account_dirtied
0.06 ± 49% +0.1 0.13 ± 10% perf-profile.children.cycles-pp.cgroup_rstat_updated
0.30 ± 8% +0.1 0.37 ± 7% perf-profile.children.cycles-pp.btrfs_unlock_up_safe
0.01 ±223% +0.1 0.08 ± 11% perf-profile.children.cycles-pp.verify_parent_transid
0.29 ± 7% +0.1 0.36 ± 5% perf-profile.children.cycles-pp.btrfs_free_tree_block
0.05 ± 73% +0.1 0.12 ± 12% perf-profile.children.cycles-pp.btrfs_setup_item_for_insert
0.20 ± 10% +0.1 0.28 ± 11% perf-profile.children.cycles-pp.find_free_extent
0.00 +0.1 0.08 ± 19% perf-profile.children.cycles-pp.llist_add_batch
0.22 ± 12% +0.1 0.30 ± 5% perf-profile.children.cycles-pp.write_dev_supers
0.00 +0.1 0.08 ± 14% perf-profile.children.cycles-pp.__smp_call_single_queue
0.25 ± 15% +0.1 0.33 ± 21% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
0.00 +0.1 0.09 ± 19% perf-profile.children.cycles-pp.__flush_smp_call_function_queue
0.11 ± 17% +0.1 0.21 ± 11% perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
0.17 ± 17% +0.1 0.27 ± 6% perf-profile.children.cycles-pp.btrfs_reserve_metadata_bytes
0.26 ± 16% +0.1 0.36 ± 8% perf-profile.children.cycles-pp.unlock_up
0.08 ± 21% +0.1 0.18 ± 9% perf-profile.children.cycles-pp.btrfs_buffer_uptodate
0.17 ± 10% +0.1 0.26 ± 10% perf-profile.children.cycles-pp.btrfs_root_node
0.23 ± 19% +0.1 0.34 ± 14% perf-profile.children.cycles-pp.start_transaction
0.26 ± 12% +0.1 0.38 ± 10% perf-profile.children.cycles-pp.down_read
0.21 ± 17% +0.1 0.32 ± 7% perf-profile.children.cycles-pp.mutex_lock
0.18 ± 14% +0.1 0.29 ± 6% perf-profile.children.cycles-pp.__reserve_bytes
0.60 ± 10% +0.1 0.71 ± 7% perf-profile.children.cycles-pp.xas_load
0.36 ± 9% +0.1 0.48 ± 4% perf-profile.children.cycles-pp.btrfs_write_check
0.35 ± 10% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.file_remove_privs
0.34 ± 11% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.security_inode_need_killpriv
0.34 ± 10% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.cap_inode_need_killpriv
0.34 ± 10% +0.1 0.46 ± 3% perf-profile.children.cycles-pp.__vfs_getxattr
0.66 ± 9% +0.1 0.78 ± 4% perf-profile.children.cycles-pp.generic_bin_search
0.26 ± 13% +0.1 0.39 ± 3% perf-profile.children.cycles-pp.btrfs_lookup_xattr
0.03 ±100% +0.1 0.16 ± 8% perf-profile.children.cycles-pp.ttwu_queue_wakelist
0.31 ± 12% +0.1 0.44 ± 3% perf-profile.children.cycles-pp.btrfs_getxattr
0.19 ± 16% +0.1 0.34 ± 22% perf-profile.children.cycles-pp.tsc_verify_tsc_adjust
0.20 ± 14% +0.1 0.35 ± 23% perf-profile.children.cycles-pp.arch_cpu_idle_enter
0.34 ± 16% +0.2 0.50 ± 3% perf-profile.children.cycles-pp.btrfs_log_all_xattrs
0.25 ± 17% +0.2 0.40 ± 12% perf-profile.children.cycles-pp.__folio_mark_dirty
0.42 ± 10% +0.2 0.58 ± 8% perf-profile.children.cycles-pp.mem_cgroup_css_rstat_flush
0.17 ± 14% +0.2 0.32 ± 10% perf-profile.children.cycles-pp.inode_tree_add
0.12 ± 20% +0.2 0.28 ± 11% perf-profile.children.cycles-pp.btrfs_lock_root_node
0.83 ± 8% +0.2 1.01 ± 7% perf-profile.children.cycles-pp.wake_up_q
0.72 ± 9% +0.2 0.91 ± 14% perf-profile.children.cycles-pp.end_bio_extent_buffer_writepage
0.02 ±144% +0.2 0.21 ± 15% perf-profile.children.cycles-pp.sched_ttwu_pending
0.48 ± 12% +0.2 0.67 ± 12% perf-profile.children.cycles-pp.filemap_dirty_folio
1.57 ± 6% +0.2 1.77 ± 6% perf-profile.children.cycles-pp.write
1.45 ± 6% +0.2 1.65 ± 6% perf-profile.children.cycles-pp.btrfs_buffered_write
0.74 ± 12% +0.2 0.94 ± 4% perf-profile.children.cycles-pp.find_extent_buffer_nolock
0.37 ± 14% +0.2 0.58 ± 7% perf-profile.children.cycles-pp.set_extent_buffer_dirty
1.47 ± 7% +0.2 1.68 ± 6% perf-profile.children.cycles-pp.btrfs_do_write_iter
0.90 ± 13% +0.2 1.12 ± 4% perf-profile.children.cycles-pp.btrfs_lookup_file_extent
0.40 ± 13% +0.2 0.62 ± 7% perf-profile.children.cycles-pp.btrfs_mark_buffer_dirty
1.79 ± 8% +0.2 2.02 ± 4% perf-profile.children.cycles-pp.ksys_write
1.78 ± 8% +0.2 2.02 ± 4% perf-profile.children.cycles-pp.vfs_write
0.62 ± 11% +0.2 0.86 ± 8% perf-profile.children.cycles-pp.rwsem_spin_on_owner
0.88 ± 9% +0.2 1.11 ± 7% perf-profile.children.cycles-pp.rwsem_wake
1.75 ± 8% +0.2 1.99 ± 4% perf-profile.children.cycles-pp.new_sync_write
0.97 ± 12% +0.3 1.22 ± 4% perf-profile.children.cycles-pp.find_extent_buffer
1.30 ± 13% +0.3 1.57 ± 5% perf-profile.children.cycles-pp.btrfs_drop_extents
0.57 ± 24% +0.3 0.86 ± 15% perf-profile.children.cycles-pp.btrfs_init_new_buffer
0.36 ± 11% +0.3 0.66 ± 6% perf-profile.children.cycles-pp.inode_logged
0.00 +0.3 0.30 ± 11% perf-profile.children.cycles-pp.flush_smp_call_function_queue
1.09 ± 12% +0.3 1.41 ± 6% perf-profile.children.cycles-pp.read_block_for_search
0.95 ± 12% +0.3 1.28 ± 5% perf-profile.children.cycles-pp.rwsem_down_read_slowpath
1.98 ± 12% +0.3 2.32 ± 5% perf-profile.children.cycles-pp.cow_file_range_inline
2.58 ± 11% +0.4 2.94 ± 5% perf-profile.children.cycles-pp.start_ordered_ops
2.52 ± 11% +0.4 2.90 ± 5% perf-profile.children.cycles-pp.extent_write_cache_pages
2.55 ± 11% +0.4 2.94 ± 4% perf-profile.children.cycles-pp.extent_writepages
2.34 ± 12% +0.4 2.74 ± 4% perf-profile.children.cycles-pp.__extent_writepage
0.95 ± 16% +0.4 1.35 ± 10% perf-profile.children.cycles-pp.btrfs_alloc_tree_block
2.25 ± 12% +0.4 2.66 ± 5% perf-profile.children.cycles-pp.cow_file_range
2.26 ± 12% +0.4 2.67 ± 5% perf-profile.children.cycles-pp.btrfs_run_delalloc_range
1.20 ± 10% +0.4 1.62 ± 4% perf-profile.children.cycles-pp.__btrfs_tree_read_lock
0.64 ± 11% +0.5 1.09 ± 3% perf-profile.children.cycles-pp.btrfs_read_lock_root_node
0.84 ± 9% +0.5 1.35 ± 4% perf-profile.children.cycles-pp.btrfs_update_root
1.13 ± 5% +0.5 1.64 ± 9% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.92 ± 9% +0.5 1.45 ± 10% perf-profile.children.cycles-pp.__mem_cgroup_flush_stats
0.92 ± 10% +0.5 1.45 ± 10% perf-profile.children.cycles-pp.cgroup_rstat_flush_irqsafe
0.92 ± 9% +0.5 1.44 ± 10% perf-profile.children.cycles-pp.cgroup_rstat_flush_locked
0.94 ± 10% +0.5 1.48 ± 10% perf-profile.children.cycles-pp.mem_cgroup_wb_stats
0.95 ± 10% +0.5 1.50 ± 10% perf-profile.children.cycles-pp.balance_dirty_pages
0.98 ± 10% +0.6 1.54 ± 10% perf-profile.children.cycles-pp.balance_dirty_pages_ratelimited
4.71 ± 7% +0.8 5.52 ± 4% perf-profile.children.cycles-pp.btrfs_create_common
6.00 ± 7% +0.8 6.84 ± 4% perf-profile.children.cycles-pp.__x64_sys_openat
5.99 ± 7% +0.8 6.83 ± 4% perf-profile.children.cycles-pp.do_sys_openat2
5.93 ± 7% +0.8 6.76 ± 4% perf-profile.children.cycles-pp.do_filp_open
5.92 ± 7% +0.8 6.76 ± 4% perf-profile.children.cycles-pp.path_openat
6.01 ± 7% +0.8 6.85 ± 4% perf-profile.children.cycles-pp.open64
5.58 ± 6% +0.9 6.44 ± 4% perf-profile.children.cycles-pp.lookup_open
5.63 ± 7% +0.9 6.50 ± 4% perf-profile.children.cycles-pp.open_last_lookups
0.57 ± 70% +0.9 1.46 ± 25% perf-profile.children.cycles-pp.timekeeping_max_deferment
1.26 ± 10% +1.0 2.27 ± 10% perf-profile.children.cycles-pp.copy_page
1.26 ± 10% +1.0 2.27 ± 10% perf-profile.children.cycles-pp.copy_extent_buffer_full
1.56 ± 28% +1.1 2.65 ± 14% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length
0.84 ± 8% +1.1 1.98 ± 4% perf-profile.children.cycles-pp.start_log_trans
1.20 ± 38% +1.2 2.36 ± 16% perf-profile.children.cycles-pp.tick_nohz_next_event
3.13 ± 9% +1.9 5.00 ± 5% perf-profile.children.cycles-pp.__btrfs_cow_block
3.15 ± 9% +1.9 5.03 ± 5% perf-profile.children.cycles-pp.btrfs_cow_block
5.98 ± 6% +2.0 8.02 ± 6% perf-profile.children.cycles-pp.btrfs_insert_empty_items
3.07 ± 6% +2.2 5.29 ± 6% perf-profile.children.cycles-pp.copy_items
4.44 ± 7% +2.3 6.76 ± 5% perf-profile.children.cycles-pp.copy_inode_items_to_log
5.24 ± 7% +2.8 8.02 ± 4% perf-profile.children.cycles-pp.btrfs_log_inode
22.41 ± 8% +3.4 25.83 ± 3% perf-profile.children.cycles-pp.fsync
9.25 ± 8% +3.4 12.68 ± 4% perf-profile.children.cycles-pp.btrfs_search_slot
22.29 ± 8% +3.4 25.72 ± 3% perf-profile.children.cycles-pp.__x64_sys_fsync
22.28 ± 8% +3.4 25.71 ± 3% perf-profile.children.cycles-pp.btrfs_sync_file
6.19 ± 7% +4.0 10.18 ± 3% perf-profile.children.cycles-pp.btrfs_log_inode_parent
6.20 ± 7% +4.0 10.20 ± 3% perf-profile.children.cycles-pp.btrfs_log_dentry_safe
31.26 ± 7% +4.4 35.71 ± 3% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
31.24 ± 7% +4.4 35.69 ± 3% perf-profile.children.cycles-pp.do_syscall_64
1.76 ± 5% -0.3 1.46 ± 9% perf-profile.self.cycles-pp.cpuidle_enter_state
0.14 ± 34% -0.1 0.08 ± 9% perf-profile.self.cycles-pp.nr_iowait_cpu
0.11 ± 43% -0.1 0.04 ± 75% perf-profile.self.cycles-pp.scheduler_tick
0.22 ± 17% -0.1 0.16 ± 9% perf-profile.self.cycles-pp.__hrtimer_next_event_base
0.14 ± 18% -0.0 0.10 ± 14% perf-profile.self.cycles-pp.perf_mux_hrtimer_handler
0.08 ± 23% -0.0 0.03 ±101% perf-profile.self.cycles-pp.error_entry
0.08 ± 18% -0.0 0.04 ± 71% perf-profile.self.cycles-pp.clockevents_program_event
0.16 ± 9% -0.0 0.12 ± 13% perf-profile.self.cycles-pp.do_idle
0.06 ± 23% +0.0 0.09 ± 12% perf-profile.self.cycles-pp.up_write
0.07 ± 10% +0.0 0.10 ± 21% perf-profile.self.cycles-pp.end_bio_extent_buffer_writepage
0.06 ± 17% +0.0 0.10 ± 6% perf-profile.self.cycles-pp.set_extent_buffer_dirty
0.02 ±141% +0.0 0.06 ± 18% perf-profile.self.cycles-pp.__mark_inode_dirty
0.04 ± 73% +0.0 0.09 ± 17% perf-profile.self.cycles-pp.start_transaction
0.09 ± 20% +0.0 0.13 ± 13% perf-profile.self.cycles-pp.percpu_counter_add_batch
0.09 ± 19% +0.0 0.14 ± 9% perf-profile.self.cycles-pp.up_read
0.02 ±142% +0.0 0.06 ± 11% perf-profile.self.cycles-pp.btrfs_clean_tree_block
0.16 ± 15% +0.0 0.21 ± 9% perf-profile.self.cycles-pp.set_extent_bit
0.01 ±223% +0.0 0.06 ± 13% perf-profile.self.cycles-pp.available_idle_cpu
0.02 ±141% +0.1 0.07 ± 14% perf-profile.self.cycles-pp.xas_set_mark
0.06 ± 17% +0.1 0.12 ± 9% perf-profile.self.cycles-pp.mark_page_accessed
0.08 ± 10% +0.1 0.13 ± 14% perf-profile.self.cycles-pp.__mod_memcg_lruvec_state
0.09 ± 24% +0.1 0.14 ± 13% perf-profile.self.cycles-pp.free_extent_buffer
0.02 ± 99% +0.1 0.08 ± 13% perf-profile.self.cycles-pp.rwsem_mark_wake
0.18 ± 5% +0.1 0.25 ± 19% perf-profile.self.cycles-pp.__btrfs_cow_block
0.00 +0.1 0.08 ± 9% perf-profile.self.cycles-pp.verify_parent_transid
0.00 +0.1 0.08 ± 19% perf-profile.self.cycles-pp.llist_add_batch
0.01 ±223% +0.1 0.09 ± 14% perf-profile.self.cycles-pp.btrfs_sync_log
0.01 ±223% +0.1 0.09 ± 14% perf-profile.self.cycles-pp.need_preemptive_reclaim
0.25 ± 15% +0.1 0.33 ± 21% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
0.16 ± 9% +0.1 0.26 ± 10% perf-profile.self.cycles-pp.btrfs_root_node
0.10 ± 19% +0.1 0.19 ± 10% perf-profile.self.cycles-pp.__filemap_get_folio
0.02 ±145% +0.1 0.12 ± 9% perf-profile.self.cycles-pp.btrfs_buffer_uptodate
0.21 ± 14% +0.1 0.32 ± 12% perf-profile.self.cycles-pp.down_read
0.17 ± 18% +0.1 0.28 ± 10% perf-profile.self.cycles-pp.mutex_lock
0.12 ± 11% +0.1 0.24 ± 11% perf-profile.self.cycles-pp.inode_tree_add
0.65 ± 9% +0.1 0.77 ± 4% perf-profile.self.cycles-pp.generic_bin_search
0.30 ± 15% +0.1 0.44 ± 4% perf-profile.self.cycles-pp.btrfs_search_slot
0.40 ± 9% +0.2 0.56 ± 10% perf-profile.self.cycles-pp.mem_cgroup_css_rstat_flush
0.34 ± 15% +0.2 0.50 ± 7% perf-profile.self.cycles-pp.find_extent_buffer_nolock
0.17 ± 33% +0.2 0.34 ± 24% perf-profile.self.cycles-pp.tsc_verify_tsc_adjust
0.45 ± 14% +0.3 0.72 ± 8% perf-profile.self.cycles-pp.rwsem_spin_on_owner
0.30 ± 34% +0.4 0.65 ± 19% perf-profile.self.cycles-pp.tick_nohz_next_event
1.01 ± 4% +0.5 1.47 ± 9% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.56 ± 74% +0.9 1.46 ± 25% perf-profile.self.cycles-pp.timekeeping_max_deferment
1.24 ± 10% +1.0 2.24 ± 10% perf-profile.self.cycles-pp.copy_page
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://01.org/lkp
View attachment "config-5.19.0-rc2-00003-gcb29a5c19d2d" of type "text/plain" (163951 bytes)
View attachment "job-script" of type "text/plain" (7702 bytes)
View attachment "job.yaml" of type "text/plain" (5036 bytes)
View attachment "reproduce" of type "text/plain" (298 bytes)
Powered by blists - more mailing lists