[<prev] [next>] [day] [month] [year] [list]
Message-ID: <202308091624.d97ae058-oliver.sang@intel.com>
Date: Wed, 9 Aug 2023 16:42:30 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Peter Zijlstra <peterz@...radead.org>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>,
<linux-kernel@...r.kernel.org>, <x86@...nel.org>,
Ingo Molnar <mingo@...nel.org>, <ying.huang@...el.com>,
<feng.tang@...el.com>, <fengwei.yin@...el.com>,
<aubrey.li@...ux.intel.com>, <yu.c.chen@...el.com>,
<oliver.sang@...el.com>
Subject: [tip:sched/eevdf] [sched/fair] e0c2ff903c:
pft.faults_per_sec_per_cpu 7.0% improvement
Hello,
kernel test robot noticed a 7.0% improvement of pft.faults_per_sec_per_cpu on:
commit: e0c2ff903c320d3fd3c2c604dc401b3b7c0a1d13 ("sched/fair: Remove sched_feat(START_DEBIT)")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git sched/eevdf
testcase: pft
test machine: 8 threads 1 sockets Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (Haswell) with 8G memory
parameters:
runtime: 300s
nr_task: 100%
cpufreq_governor: performance
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/nr_task/rootfs/runtime/tbox_group/testcase:
gcc-12/performance/x86_64-rhel-8.3/100%/debian-11.1-x86_64-20220510.cgz/300s/lkp-hsw-d04/pft
commit:
af4cf40470 ("sched/fair: Add cfs_rq::avg_vruntime")
e0c2ff903c ("sched/fair: Remove sched_feat(START_DEBIT)")
af4cf40470c22efa e0c2ff903c320d3fd3c2c604dc4
---------------- ---------------------------
%stddev %change %stddev
\ | \
163.50 ± 16% +20.9% 197.67 ± 7% perf-c2c.DRAM.local
43.12 ± 2% -11.8% 38.01 ± 4% boot-time.boot
271.81 ± 2% -14.9% 231.42 ± 6% boot-time.idle
1.654e+08 +37.6% 2.275e+08 cpuidle..time
559114 ± 4% +30.8% 731468 cpuidle..usage
25.00 -44.0% 14.00 vmstat.cpu.us
13841 -6.9% 12883 vmstat.system.cs
11914 -3.2% 11533 vmstat.system.in
821983 ± 3% -15.3% 695985 ± 2% meminfo.AnonHugePages
888922 ± 2% -14.2% 762401 meminfo.AnonPages
920495 ± 2% -14.9% 782918 meminfo.Inactive
920323 ± 2% -14.9% 782743 meminfo.Inactive(anon)
6.49 +2.6 9.13 ± 2% mpstat.cpu.all.idle%
0.89 ± 4% +0.3 1.21 ± 3% mpstat.cpu.all.iowait%
0.08 +0.0 0.11 mpstat.cpu.all.soft%
65.47 +7.9 73.37 mpstat.cpu.all.sys%
25.89 -11.0 14.90 mpstat.cpu.all.usr%
677259 +7.0% 724636 pft.faults_per_sec_per_cpu
1159214 -18.4% 945943 pft.time.involuntary_context_switches
4080036 +20.1% 4898865 pft.time.minor_page_faults
595.00 -5.0% 565.17 pft.time.percent_of_cpu_this_job_got
1293 +12.4% 1453 pft.time.system_time
497.18 -50.2% 247.37 pft.time.user_time
60499 +6.0% 64102 pft.time.voluntary_context_switches
0.50 +50.0% 0.75 ± 11% sched_debug.cfs_rq:/.h_nr_running.min
43825 ± 13% +50.6% 65997 ± 16% sched_debug.cfs_rq:/.load.min
0.50 +50.0% 0.75 ± 11% sched_debug.cfs_rq:/.nr_running.min
15767 +14.5% 18054 sched_debug.cpu.curr->pid.max
162.42 +78.7% 290.25 ± 47% sched_debug.cpu.curr->pid.min
6414 ± 4% +13.9% 7303 ± 4% sched_debug.cpu.curr->pid.stddev
0.50 +44.4% 0.72 ± 10% sched_debug.cpu.nr_running.min
503383 ± 6% -16.3% 421140 ± 8% sched_debug.cpu.nr_switches.max
80519 ± 16% -32.7% 54225 ± 27% sched_debug.cpu.nr_switches.stddev
58611259 -50.0% 29305629 sched_debug.sysctl_sched.sysctl_sched_features
67033 ± 4% +23.9% 83040 ± 8% turbostat.C1
0.10 ± 4% +0.0 0.14 ± 9% turbostat.C1%
147021 ± 6% +40.4% 206477 ± 3% turbostat.C1E
0.50 ± 4% +0.2 0.68 ± 2% turbostat.C1E%
88168 +20.5% 106201 turbostat.C3
1.51 ± 2% +0.4 1.86 ± 2% turbostat.C3%
22474 +16.2% 26125 turbostat.C6
0.49 +0.1 0.58 turbostat.C6%
131356 +41.6% 186066 turbostat.C7s
4.20 +1.9 6.08 turbostat.C7s%
3.80 +48.9% 5.66 turbostat.CPU%c1
1.36 ± 2% +10.3% 1.50 ± 7% turbostat.CPU%c3
1.48 ± 2% +37.1% 2.02 turbostat.CPU%c7
0.13 -46.2% 0.07 turbostat.IPC
102788 ± 12% +19.7% 123028 ± 6% turbostat.POLL
221126 ± 3% -13.0% 192274 proc-vmstat.nr_anon_pages
398.75 ± 4% -14.1% 342.67 proc-vmstat.nr_anon_transparent_hugepages
101439 +3.1% 104537 proc-vmstat.nr_dirty_background_threshold
203128 +3.1% 209330 proc-vmstat.nr_dirty_threshold
1048986 +3.0% 1080005 proc-vmstat.nr_free_pages
228255 ± 3% -13.7% 196876 proc-vmstat.nr_inactive_anon
1178 -4.7% 1122 proc-vmstat.nr_page_table_pages
228254 ± 3% -13.7% 196875 proc-vmstat.nr_zone_inactive_anon
5631573 +19.4% 6724155 proc-vmstat.numa_hit
5630822 +19.4% 6724458 proc-vmstat.numa_local
14607 ± 2% +3.9% 15178 proc-vmstat.pgactivate
8.776e+08 +20.0% 1.053e+09 proc-vmstat.pgalloc_normal
4392806 +18.9% 5223352 proc-vmstat.pgfault
8.776e+08 +20.0% 1.053e+09 proc-vmstat.pgfree
135963 +18.5% 161056 proc-vmstat.pgreuse
1706299 +20.0% 2047009 proc-vmstat.thp_fault_alloc
6294 +2.1% 6428 proc-vmstat.unevictable_pgs_culled
1.76 +114.7% 3.78 perf-stat.i.MPKI
3.495e+09 -46.7% 1.862e+09 perf-stat.i.branch-instructions
0.14 ± 7% +0.1 0.26 ± 4% perf-stat.i.branch-miss-rate%
69.66 +1.1 70.77 perf-stat.i.cache-miss-rate%
14993359 +19.8% 17969257 perf-stat.i.cache-misses
21541685 +17.9% 25407698 perf-stat.i.cache-references
13839 -7.0% 12866 perf-stat.i.context-switches
2.24 +77.3% 3.97 perf-stat.i.cpi
2.742e+10 -2.7% 2.669e+10 perf-stat.i.cpu-cycles
151.96 +18.4% 179.96 perf-stat.i.cpu-migrations
1838 -18.9% 1491 perf-stat.i.cycles-between-cache-misses
0.01 +0.0 0.02 perf-stat.i.dTLB-load-miss-rate%
374992 +8.3% 406273 perf-stat.i.dTLB-load-misses
3.604e+09 -45.1% 1.98e+09 perf-stat.i.dTLB-loads
157969 +14.5% 180881 perf-stat.i.dTLB-store-misses
6.677e+08 +13.5% 7.58e+08 perf-stat.i.dTLB-stores
168175 +9.2% 183614 ± 2% perf-stat.i.iTLB-load-misses
121633 +4.8% 127485 perf-stat.i.iTLB-loads
1.235e+10 -44.5% 6.848e+09 perf-stat.i.instructions
84770 -51.2% 41334 ± 2% perf-stat.i.instructions-per-iTLB-miss
0.45 -42.9% 0.26 perf-stat.i.ipc
10.60 ± 7% -13.3% 9.19 ± 6% perf-stat.i.major-faults
3.43 -2.7% 3.34 perf-stat.i.metric.GHz
456.38 +22.6% 559.66 perf-stat.i.metric.K/sec
974.72 -40.5% 579.74 perf-stat.i.metric.M/sec
14414 +18.9% 17133 perf-stat.i.minor-faults
3327923 +23.7% 4117288 perf-stat.i.node-loads
11044858 +19.8% 13227908 perf-stat.i.node-stores
14425 +18.8% 17142 perf-stat.i.page-faults
1.74 +112.7% 3.71 perf-stat.overall.MPKI
0.15 ± 9% +0.1 0.29 ± 5% perf-stat.overall.branch-miss-rate%
69.60 +1.1 70.72 perf-stat.overall.cache-miss-rate%
2.22 +75.5% 3.90 perf-stat.overall.cpi
1828 -18.8% 1485 perf-stat.overall.cycles-between-cache-misses
0.01 +0.0 0.02 perf-stat.overall.dTLB-load-miss-rate%
58.03 +1.0 59.01 perf-stat.overall.iTLB-load-miss-rate%
73450 -49.2% 37305 ± 2% perf-stat.overall.instructions-per-iTLB-miss
0.45 -43.0% 0.26 perf-stat.overall.ipc
3.483e+09 -46.7% 1.855e+09 perf-stat.ps.branch-instructions
14941964 +19.9% 17908901 perf-stat.ps.cache-misses
21466897 +18.0% 25321945 perf-stat.ps.cache-references
13786 -7.0% 12824 perf-stat.ps.context-switches
2.733e+10 -2.7% 2.66e+10 perf-stat.ps.cpu-cycles
151.43 +18.4% 179.36 perf-stat.ps.cpu-migrations
373625 +8.4% 404838 perf-stat.ps.dTLB-load-misses
3.591e+09 -45.1% 1.973e+09 perf-stat.ps.dTLB-loads
157422 +14.5% 180263 perf-stat.ps.dTLB-store-misses
6.653e+08 +13.5% 7.554e+08 perf-stat.ps.dTLB-stores
167570 +9.2% 182983 ± 2% perf-stat.ps.iTLB-load-misses
121187 +4.9% 127066 perf-stat.ps.iTLB-loads
1.23e+10 -44.5% 6.823e+09 perf-stat.ps.instructions
10.56 ± 7% -13.3% 9.15 ± 6% perf-stat.ps.major-faults
14364 +18.9% 17075 perf-stat.ps.minor-faults
3316084 +23.7% 4102992 perf-stat.ps.node-loads
11007613 +19.8% 13183904 perf-stat.ps.node-stores
14375 +18.8% 17084 perf-stat.ps.page-faults
3.715e+12 -44.5% 2.063e+12 perf-stat.total.instructions
0.02 ± 55% +500.0% 0.12 ± 15% perf-sched.sch_delay.avg.ms.__cond_resched.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
1.48 ± 57% -99.6% 0.01 ± 50% perf-sched.sch_delay.avg.ms.__cond_resched.down_write_killable.exec_mmap.begin_new_exec.load_elf_binary
7.29 ± 23% -99.9% 0.00 ±103% perf-sched.sch_delay.avg.ms.__cond_resched.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
7.73 ± 23% -93.6% 0.49 ±107% perf-sched.sch_delay.avg.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
0.06 ± 21% -70.4% 0.02 ±100% perf-sched.sch_delay.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
0.04 ±170% +2291.2% 0.99 ±124% perf-sched.sch_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_common_interrupt
0.99 ± 5% -35.8% 0.63 ± 10% perf-sched.sch_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
0.01 ± 17% +89.9% 0.02 ± 39% perf-sched.sch_delay.avg.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
0.02 ± 37% +148.2% 0.04 ± 41% perf-sched.sch_delay.avg.ms.pipe_write.vfs_write.ksys_write.do_syscall_64
0.81 ± 60% -87.9% 0.10 ±129% perf-sched.sch_delay.avg.ms.schedule_hrtimeout_range_clock.usleep_range_state.ata_msleep.sata_link_hardreset
8.79 ± 69% -90.9% 0.80 ±171% perf-sched.sch_delay.avg.ms.schedule_timeout.__wait_for_common.__wait_rcu_gp.synchronize_rcu
0.55 ± 39% -44.0% 0.31 ± 66% perf-sched.sch_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
0.74 ± 5% -15.7% 0.62 ± 8% perf-sched.sch_delay.avg.ms.syslog_print.do_syslog.kmsg_read.vfs_read
0.77 ± 54% -99.3% 0.01 ± 20% perf-sched.sch_delay.avg.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
3.22 ± 7% -17.8% 2.64 ± 3% perf-sched.sch_delay.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
0.00 ±173% +1e+06% 7.71 ± 86% perf-sched.sch_delay.max.ms.__cond_resched.__alloc_pages.pte_alloc_one.__do_huge_pmd_anonymous_page.__handle_mm_fault
9.38 ± 63% -99.7% 0.03 ±123% perf-sched.sch_delay.max.ms.__cond_resched.down_write_killable.exec_mmap.begin_new_exec.load_elf_binary
29.87 ± 2% -99.9% 0.02 ±114% perf-sched.sch_delay.max.ms.__cond_resched.lock_mm_and_find_vma.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
16.37 ± 12% -73.1% 4.41 ±105% perf-sched.sch_delay.max.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
18.81 ± 30% -62.8% 7.00 ±108% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_exc_page_fault
31.32 ± 10% -62.0% 11.89 ± 26% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
27.23 ± 9% -69.5% 8.29 ± 15% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi
6.93 ± 38% +351.8% 31.29 ±129% perf-sched.sch_delay.max.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
5.58 ± 36% -83.9% 0.90 ±141% perf-sched.sch_delay.max.ms.schedule_hrtimeout_range_clock.usleep_range_state.ata_msleep.sata_link_hardreset
8.02 ± 51% -99.7% 0.02 ± 10% perf-sched.sch_delay.max.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
799.71 -54.0% 367.99 ± 37% perf-sched.wait_and_delay.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
7.24 ± 3% -25.5% 5.39 ± 5% perf-sched.wait_and_delay.avg.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
10.54 ± 10% -48.1% 5.47 ± 55% perf-sched.wait_and_delay.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
46.27 ± 5% -9.9% 41.67 ± 2% perf-sched.wait_and_delay.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
1.94 ± 10% -42.3% 1.12 ± 28% perf-sched.wait_and_delay.avg.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
0.51 ± 27% +238.5% 1.74 ± 40% perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
43.05 -15.9% 36.21 perf-sched.wait_and_delay.avg.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
8.31 ± 2% -10.6% 7.43 ± 3% perf-sched.wait_and_delay.avg.ms.syslog_print.do_syslog.kmsg_read.vfs_read
91.25 -12.2% 80.15 ± 3% perf-sched.wait_and_delay.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
2766 ± 4% +39.6% 3861 ± 13% perf-sched.wait_and_delay.count.__cond_resched.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
429.00 +17.4% 503.50 perf-sched.wait_and_delay.count.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
721.75 ± 4% -41.7% 421.00 ± 6% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
1705 ± 4% -65.4% 589.83 ± 9% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi
451.00 +19.7% 539.67 perf-sched.wait_and_delay.count.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
542.50 ± 2% +15.5% 626.50 perf-sched.wait_and_delay.count.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
26.57 ± 5% +42.4% 37.83 ± 8% perf-sched.wait_and_delay.max.ms.__cond_resched.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
97.44 ± 14% -37.8% 60.58 ± 28% perf-sched.wait_and_delay.max.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
563.22 ± 80% -55.4% 251.36 ±135% perf-sched.wait_and_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
339.91 ±112% +197.7% 1011 perf-sched.wait_and_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
161.04 ± 3% -19.3% 129.89 perf-sched.wait_and_delay.max.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
0.70 ± 70% -78.5% 0.15 ±115% perf-sched.wait_time.avg.ms.__cond_resched.__wait_for_common.ata_exec_internal_sg.ata_exec_internal.atapi_eh_tur
4.22 ± 61% -89.6% 0.44 ±130% perf-sched.wait_time.avg.ms.__cond_resched.dput.__fput.task_work_run.exit_to_user_mode_loop
0.00 ±173% +39814.3% 0.70 ±160% perf-sched.wait_time.avg.ms.__cond_resched.mutex_lock.pipe_write.vfs_write.ksys_write
799.69 -54.1% 367.27 ± 37% perf-sched.wait_time.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
6.66 -27.1% 4.86 ± 4% perf-sched.wait_time.avg.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
10.50 ± 10% -48.3% 5.43 ± 56% perf-sched.wait_time.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
46.21 ± 5% -9.9% 41.65 ± 2% perf-sched.wait_time.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
1.90 ± 10% -43.2% 1.08 ± 29% perf-sched.wait_time.avg.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
0.50 ± 27% +242.1% 1.72 ± 40% perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
1.27 ± 57% -99.3% 0.01 ± 44% perf-sched.wait_time.avg.ms.io_schedule.folio_wait_bit_common.filemap_fault.__do_fault
43.03 -16.0% 36.15 perf-sched.wait_time.avg.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
2.87 ± 16% -37.8% 1.79 ± 25% perf-sched.wait_time.avg.ms.schedule_timeout.__wait_for_common.ata_exec_internal_sg.ata_dev_read_id
1.46 ± 37% -28.4% 1.04 perf-sched.wait_time.avg.ms.schedule_timeout.msleep.ata_msleep.sata_link_resume
7.57 -10.1% 6.81 ± 3% perf-sched.wait_time.avg.ms.syslog_print.do_syslog.kmsg_read.vfs_read
88.03 -12.0% 77.51 ± 3% perf-sched.wait_time.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
2.87 ±106% -91.8% 0.23 ±143% perf-sched.wait_time.max.ms.__cond_resched.__wait_for_common.ata_exec_internal_sg.ata_exec_internal.atapi_eh_tur
0.00 ±173% +1.4e+05% 2.53 ±159% perf-sched.wait_time.max.ms.__cond_resched.mutex_lock.pipe_write.vfs_write.ksys_write
87.30 ± 29% -47.2% 46.07 ± 10% perf-sched.wait_time.max.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
563.20 ± 80% -55.4% 251.35 ±135% perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
339.86 ±112% +196.2% 1006 perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
13.75 ± 53% -99.7% 0.04 ± 66% perf-sched.wait_time.max.ms.io_schedule.folio_wait_bit_common.filemap_fault.__do_fault
161.02 ± 3% -19.3% 129.87 perf-sched.wait_time.max.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
250.51 ±172% -100.0% 0.03 ± 18% perf-sched.wait_time.max.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
18.99 ± 3% -10.4 8.56 ± 5% perf-profile.calltrace.cycles-pp.test_main
14.46 ± 7% -1.5 12.94 ± 7% perf-profile.calltrace.cycles-pp.vprintk_emit.devkmsg_emit.devkmsg_write.vfs_write.ksys_write
14.47 ± 7% -1.5 12.99 ± 6% perf-profile.calltrace.cycles-pp.devkmsg_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
14.46 ± 7% -1.5 12.99 ± 7% perf-profile.calltrace.cycles-pp.devkmsg_emit.devkmsg_write.vfs_write.ksys_write.do_syscall_64
11.18 ± 8% -1.5 9.71 ± 6% perf-profile.calltrace.cycles-pp.console_flush_all.console_unlock.vprintk_emit.devkmsg_emit.devkmsg_write
11.19 ± 8% -1.5 9.73 ± 6% perf-profile.calltrace.cycles-pp.console_unlock.vprintk_emit.devkmsg_emit.devkmsg_write.vfs_write
14.55 ± 7% -1.5 13.10 ± 6% perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
14.54 ± 7% -1.4 13.10 ± 6% perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
14.58 ± 7% -1.4 13.14 ± 6% perf-profile.calltrace.cycles-pp.write
14.56 ± 7% -1.4 13.12 ± 6% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.write
14.56 ± 7% -1.4 13.12 ± 6% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
8.69 ± 9% -1.1 7.57 ± 7% perf-profile.calltrace.cycles-pp.serial8250_console_write.console_flush_all.console_unlock.vprintk_emit.devkmsg_emit
7.27 ± 10% -1.0 6.30 ± 6% perf-profile.calltrace.cycles-pp.wait_for_lsr.serial8250_console_write.console_flush_all.console_unlock.vprintk_emit
2.96 ± 7% -0.4 2.52 ± 7% perf-profile.calltrace.cycles-pp.delay_tsc.wait_for_lsr.serial8250_console_write.console_flush_all.console_unlock
2.38 ± 5% -0.4 1.99 ± 7% perf-profile.calltrace.cycles-pp.vt_console_print.console_flush_all.console_unlock.vprintk_emit.devkmsg_emit
2.33 ± 5% -0.4 1.95 ± 8% perf-profile.calltrace.cycles-pp.lf.vt_console_print.console_flush_all.console_unlock.vprintk_emit
2.33 ± 5% -0.4 1.95 ± 8% perf-profile.calltrace.cycles-pp.con_scroll.lf.vt_console_print.console_flush_all.console_unlock
2.33 ± 5% -0.4 1.95 ± 8% perf-profile.calltrace.cycles-pp.fbcon_scroll.con_scroll.lf.vt_console_print.console_flush_all
2.29 ± 4% -0.4 1.92 ± 8% perf-profile.calltrace.cycles-pp.fbcon_redraw.fbcon_scroll.con_scroll.lf.vt_console_print
2.14 ± 4% -0.3 1.81 ± 8% perf-profile.calltrace.cycles-pp.fbcon_putcs.fbcon_redraw.fbcon_scroll.con_scroll.lf
2.08 ± 4% -0.3 1.76 ± 8% perf-profile.calltrace.cycles-pp.bit_putcs.fbcon_putcs.fbcon_redraw.fbcon_scroll.con_scroll
1.16 ± 5% -0.2 0.96 ± 8% perf-profile.calltrace.cycles-pp.intel_fbdev_defio_imageblit.bit_putcs.fbcon_putcs.fbcon_redraw.fbcon_scroll
1.12 ± 5% -0.2 0.92 ± 8% perf-profile.calltrace.cycles-pp.fast_imageblit.cfb_imageblit.intel_fbdev_defio_imageblit.bit_putcs.fbcon_putcs
1.14 ± 5% -0.2 0.95 ± 8% perf-profile.calltrace.cycles-pp.cfb_imageblit.intel_fbdev_defio_imageblit.bit_putcs.fbcon_putcs.fbcon_redraw
0.91 ± 2% +0.2 1.08 ± 3% perf-profile.calltrace.cycles-pp.__cond_resched.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
1.41 ± 3% +0.3 1.70 ± 3% perf-profile.calltrace.cycles-pp.prep_compound_page.get_page_from_freelist.__alloc_pages.__folio_alloc.vma_alloc_folio
1.54 ± 3% +0.3 1.85 ± 3% perf-profile.calltrace.cycles-pp.do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault
1.50 ± 3% +0.3 1.82 ± 3% perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.__folio_alloc.vma_alloc_folio.do_huge_pmd_anonymous_page
1.51 ± 4% +0.3 1.82 ± 3% perf-profile.calltrace.cycles-pp.__folio_alloc.vma_alloc_folio.do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
1.51 ± 3% +0.3 1.82 ± 3% perf-profile.calltrace.cycles-pp.__alloc_pages.__folio_alloc.vma_alloc_folio.do_huge_pmd_anonymous_page.__handle_mm_fault
1.52 ± 3% +0.3 1.84 ± 3% perf-profile.calltrace.cycles-pp.vma_alloc_folio.do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault.do_user_addr_fault
1.43 ± 4% +0.5 1.92 ± 6% perf-profile.calltrace.cycles-pp.free_unref_page_prepare.free_unref_page.release_pages.tlb_batch_pages_flush.zap_pte_range
1.48 ± 4% +0.5 1.99 ± 6% perf-profile.calltrace.cycles-pp.free_unref_page.release_pages.tlb_batch_pages_flush.zap_pte_range.zap_pmd_range
1.58 ± 5% +0.5 2.10 ± 6% perf-profile.calltrace.cycles-pp.release_pages.tlb_batch_pages_flush.zap_pte_range.zap_pmd_range.unmap_page_range
1.59 ± 4% +0.5 2.11 ± 6% perf-profile.calltrace.cycles-pp.tlb_batch_pages_flush.zap_pte_range.zap_pmd_range.unmap_page_range.unmap_vmas
1.64 ± 5% +0.5 2.18 ± 6% perf-profile.calltrace.cycles-pp.zap_pte_range.zap_pmd_range.unmap_page_range.unmap_vmas.exit_mmap
1.70 ± 4% +0.6 2.26 ± 6% perf-profile.calltrace.cycles-pp.zap_pmd_range.unmap_page_range.unmap_vmas.exit_mmap.__mmput
1.70 ± 4% +0.6 2.26 ± 6% perf-profile.calltrace.cycles-pp.unmap_page_range.unmap_vmas.exit_mmap.__mmput.exit_mm
1.70 ± 5% +0.6 2.28 ± 6% perf-profile.calltrace.cycles-pp.unmap_vmas.exit_mmap.__mmput.exit_mm.do_exit
1.81 ± 4% +0.6 2.42 ± 5% perf-profile.calltrace.cycles-pp.__mmput.exit_mm.do_exit.do_group_exit.__x64_sys_exit_group
1.82 ± 4% +0.6 2.44 ± 5% perf-profile.calltrace.cycles-pp.exit_mm.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
1.80 ± 4% +0.6 2.42 ± 5% perf-profile.calltrace.cycles-pp.exit_mmap.__mmput.exit_mm.do_exit.do_group_exit
1.85 ± 5% +0.6 2.47 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_exit_group.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.85 ± 5% +0.6 2.47 ± 5% perf-profile.calltrace.cycles-pp.do_group_exit.__x64_sys_exit_group.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.85 ± 5% +0.6 2.47 ± 5% perf-profile.calltrace.cycles-pp.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.93 ± 4% +0.6 2.56 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
1.93 ± 4% +0.6 2.56 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.66 +1.1 2.77 ± 2% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
1.79 ± 2% +1.2 2.94 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
1.78 ± 2% +1.2 2.93 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
2.12 ± 4% +1.2 3.29 ± 2% perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
1.80 ± 2% +1.2 2.97 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
1.85 ± 2% +1.2 3.03 ± 3% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
1.85 ± 2% +1.2 3.03 ± 3% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
1.85 ± 2% +1.2 3.03 ± 3% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
52.37 +10.0 62.37 perf-profile.calltrace.cycles-pp.clear_page_erms.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault
54.49 +10.4 64.85 perf-profile.calltrace.cycles-pp.clear_huge_page.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault.do_user_addr_fault
55.10 +10.5 65.59 perf-profile.calltrace.cycles-pp.__do_huge_pmd_anonymous_page.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault
56.72 +10.8 67.53 perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault
56.80 +10.8 67.62 perf-profile.calltrace.cycles-pp.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.pft_loop
56.91 +10.9 67.76 perf-profile.calltrace.cycles-pp.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.pft_loop
56.92 +10.9 67.77 perf-profile.calltrace.cycles-pp.exc_page_fault.asm_exc_page_fault.pft_loop
57.10 +10.9 67.99 perf-profile.calltrace.cycles-pp.asm_exc_page_fault.pft_loop
58.84 +11.2 70.06 perf-profile.calltrace.cycles-pp.pft_loop
19.00 ± 3% -10.4 8.56 ± 5% perf-profile.children.cycles-pp.test_main
14.47 ± 7% -1.5 12.99 ± 6% perf-profile.children.cycles-pp.devkmsg_write
14.46 ± 7% -1.5 12.99 ± 7% perf-profile.children.cycles-pp.devkmsg_emit
14.58 ± 7% -1.4 13.14 ± 6% perf-profile.children.cycles-pp.write
14.56 ± 7% -1.4 13.13 ± 6% perf-profile.children.cycles-pp.vfs_write
14.56 ± 7% -1.4 13.13 ± 6% perf-profile.children.cycles-pp.ksys_write
14.84 ± 7% -1.4 13.44 ± 7% perf-profile.children.cycles-pp.vprintk_emit
3.63 ± 7% -0.6 3.06 ± 8% perf-profile.children.cycles-pp.delay_tsc
2.38 ± 5% -0.4 2.01 ± 8% perf-profile.children.cycles-pp.vt_console_print
2.34 ± 5% -0.4 1.97 ± 8% perf-profile.children.cycles-pp.lf
2.34 ± 5% -0.4 1.97 ± 8% perf-profile.children.cycles-pp.con_scroll
2.34 ± 5% -0.4 1.97 ± 8% perf-profile.children.cycles-pp.fbcon_scroll
2.30 ± 4% -0.4 1.94 ± 8% perf-profile.children.cycles-pp.fbcon_redraw
2.18 ± 4% -0.3 1.85 ± 8% perf-profile.children.cycles-pp.fbcon_putcs
2.12 ± 4% -0.3 1.80 ± 8% perf-profile.children.cycles-pp.bit_putcs
1.15 ± 5% -0.2 0.95 ± 8% perf-profile.children.cycles-pp.fast_imageblit
1.18 ± 5% -0.2 0.99 ± 8% perf-profile.children.cycles-pp.intel_fbdev_defio_imageblit
1.17 ± 5% -0.2 0.98 ± 8% perf-profile.children.cycles-pp.cfb_imageblit
0.16 ± 9% -0.0 0.11 ± 11% perf-profile.children.cycles-pp.irqentry_exit_to_user_mode
0.07 ± 17% -0.0 0.04 ± 45% perf-profile.children.cycles-pp.exit_to_user_mode_loop
0.08 ± 11% +0.0 0.10 ± 8% perf-profile.children.cycles-pp.kernel_clone
0.07 ± 6% +0.0 0.09 ± 6% perf-profile.children.cycles-pp.copy_process
0.05 +0.0 0.07 ± 15% perf-profile.children.cycles-pp.pipe_write
0.07 ± 17% +0.0 0.10 ± 10% perf-profile.children.cycles-pp.open64
0.06 ± 14% +0.0 0.08 ± 16% perf-profile.children.cycles-pp.do_filp_open
0.06 ± 14% +0.0 0.08 ± 16% perf-profile.children.cycles-pp.path_openat
0.07 ± 24% +0.0 0.10 ± 10% perf-profile.children.cycles-pp.free_pcppages_bulk
0.05 ± 58% +0.0 0.08 ± 17% perf-profile.children.cycles-pp.finish_task_switch
0.10 ± 11% +0.0 0.13 ± 8% perf-profile.children.cycles-pp.pick_next_task_fair
0.12 ± 5% +0.0 0.16 ± 7% perf-profile.children.cycles-pp.__list_del_entry_valid
0.08 ± 13% +0.0 0.12 ± 12% perf-profile.children.cycles-pp.__irq_exit_rcu
0.14 ± 3% +0.0 0.19 ± 5% perf-profile.children.cycles-pp.rmqueue
0.02 ±173% +0.1 0.06 ± 7% perf-profile.children.cycles-pp.mas_walk
0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.rcu_do_batch
0.00 +0.1 0.06 ± 19% perf-profile.children.cycles-pp.kmem_cache_free
0.08 ± 14% +0.1 0.14 ± 9% perf-profile.children.cycles-pp.__do_softirq
0.00 +0.1 0.07 ± 14% perf-profile.children.cycles-pp.rcu_core
0.94 ± 2% +0.2 1.12 ± 3% perf-profile.children.cycles-pp.__cond_resched
1.42 ± 3% +0.3 1.72 ± 3% perf-profile.children.cycles-pp.prep_compound_page
1.54 ± 3% +0.3 1.85 ± 3% perf-profile.children.cycles-pp.do_huge_pmd_anonymous_page
1.56 ± 4% +0.3 1.88 ± 3% perf-profile.children.cycles-pp.__folio_alloc
1.58 ± 4% +0.3 1.90 ± 3% perf-profile.children.cycles-pp.vma_alloc_folio
1.71 ± 2% +0.3 2.05 ± 3% perf-profile.children.cycles-pp.get_page_from_freelist
1.79 ± 3% +0.4 2.14 ± 3% perf-profile.children.cycles-pp.__alloc_pages
1.45 ± 4% +0.5 1.95 ± 7% perf-profile.children.cycles-pp.free_unref_page_prepare
1.58 ± 5% +0.5 2.11 ± 6% perf-profile.children.cycles-pp.release_pages
1.53 ± 4% +0.5 2.06 ± 6% perf-profile.children.cycles-pp.free_unref_page
1.59 ± 4% +0.5 2.13 ± 6% perf-profile.children.cycles-pp.tlb_batch_pages_flush
1.64 ± 5% +0.5 2.19 ± 6% perf-profile.children.cycles-pp.zap_pte_range
1.70 ± 5% +0.6 2.27 ± 6% perf-profile.children.cycles-pp.zap_pmd_range
1.70 ± 5% +0.6 2.27 ± 6% perf-profile.children.cycles-pp.unmap_page_range
1.71 ± 5% +0.6 2.28 ± 6% perf-profile.children.cycles-pp.unmap_vmas
1.82 ± 4% +0.6 2.44 ± 5% perf-profile.children.cycles-pp.__mmput
1.82 ± 4% +0.6 2.44 ± 5% perf-profile.children.cycles-pp.exit_mm
1.82 ± 4% +0.6 2.44 ± 5% perf-profile.children.cycles-pp.exit_mmap
1.86 ± 5% +0.6 2.48 ± 5% perf-profile.children.cycles-pp.do_exit
1.86 ± 5% +0.6 2.49 ± 5% perf-profile.children.cycles-pp.__x64_sys_exit_group
1.86 ± 5% +0.6 2.49 ± 5% perf-profile.children.cycles-pp.do_group_exit
1.91 ± 3% +1.1 3.00 ± 2% perf-profile.children.cycles-pp.intel_idle
2.06 ± 4% +1.1 3.19 ± 2% perf-profile.children.cycles-pp.cpuidle_enter
2.06 ± 4% +1.1 3.19 ± 2% perf-profile.children.cycles-pp.cpuidle_enter_state
2.08 ± 4% +1.2 3.23 ± 2% perf-profile.children.cycles-pp.cpuidle_idle_call
2.12 ± 4% +1.2 3.29 ± 2% perf-profile.children.cycles-pp.do_idle
2.12 ± 4% +1.2 3.29 ± 2% perf-profile.children.cycles-pp.secondary_startup_64_no_verify
2.12 ± 4% +1.2 3.29 ± 2% perf-profile.children.cycles-pp.cpu_startup_entry
1.85 ± 2% +1.2 3.03 ± 3% perf-profile.children.cycles-pp.start_secondary
52.86 +10.0 62.88 perf-profile.children.cycles-pp.clear_page_erms
54.55 +10.4 64.92 perf-profile.children.cycles-pp.clear_huge_page
55.10 +10.5 65.59 perf-profile.children.cycles-pp.__do_huge_pmd_anonymous_page
56.86 +10.8 67.70 perf-profile.children.cycles-pp.__handle_mm_fault
56.94 +10.9 67.80 perf-profile.children.cycles-pp.handle_mm_fault
57.08 +10.9 67.97 perf-profile.children.cycles-pp.do_user_addr_fault
57.09 +10.9 67.98 perf-profile.children.cycles-pp.exc_page_fault
57.29 +10.9 68.23 perf-profile.children.cycles-pp.asm_exc_page_fault
58.96 +11.2 70.20 perf-profile.children.cycles-pp.pft_loop
18.81 ± 3% -10.3 8.52 ± 5% perf-profile.self.cycles-pp.test_main
3.57 ± 8% -0.5 3.06 ± 8% perf-profile.self.cycles-pp.delay_tsc
1.15 ± 5% -0.2 0.95 ± 8% perf-profile.self.cycles-pp.fast_imageblit
0.12 ± 6% -0.0 0.09 ± 6% perf-profile.self.cycles-pp.fbcon_redraw
0.12 ± 5% +0.0 0.16 ± 8% perf-profile.self.cycles-pp.__list_del_entry_valid
0.62 ± 3% +0.2 0.79 ± 4% perf-profile.self.cycles-pp.__cond_resched
0.94 ± 2% +0.2 1.14 ± 5% perf-profile.self.cycles-pp.clear_huge_page
1.41 ± 3% +0.3 1.69 ± 4% perf-profile.self.cycles-pp.prep_compound_page
1.86 ± 3% +0.4 2.21 ± 3% perf-profile.self.cycles-pp.pft_loop
1.39 ± 4% +0.5 1.87 ± 6% perf-profile.self.cycles-pp.free_unref_page_prepare
1.91 ± 3% +1.1 3.00 ± 2% perf-profile.self.cycles-pp.intel_idle
52.25 +9.9 62.15 perf-profile.self.cycles-pp.clear_page_erms
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
View attachment "config-6.5.0-rc2-00017-ge0c2ff903c32" of type "text/plain" (159818 bytes)
View attachment "job-script" of type "text/plain" (8647 bytes)
View attachment "job.yaml" of type "text/plain" (5979 bytes)
View attachment "reproduce" of type "text/plain" (72261 bytes)
Powered by blists - more mailing lists