[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20220427131532.GA18279@xsang-OptiPlex-9020>
Date: Wed, 27 Apr 2022 21:15:32 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Abel Wu <wuyun.abel@...edance.com>
Cc: 0day robot <lkp@...el.com>, LKML <linux-kernel@...r.kernel.org>,
lkp@...ts.01.org, ying.huang@...el.com, feng.tang@...el.com,
zhengjun.xing@...ux.intel.com, fengwei.yin@...el.com,
Peter Zijlstra <peterz@...radead.org>,
Mel Gorman <mgorman@...e.de>,
Vincent Guittot <vincent.guittot@...aro.org>,
joshdon@...gle.com, Abel Wu <wuyun.abel@...edance.com>,
aubrey.li@...ux.intel.com, yu.c.chen@...el.com
Subject: [sched/fair] ae44f2177f: reaim.jobs_per_min 2.3% improvement
Greeting,
FYI, we noticed a 2.3% improvement of reaim.jobs_per_min due to commit:
commit: ae44f2177fa75c271734d5963972faecc3686c12 ("[RFC v2 2/2] sched/fair: introduce sched-idle balance")
url: https://github.com/intel-lab-lkp/linux/commits/Abel-Wu/introduece-sched-idle-balance/20220409-215303
base: https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git 089c02ae2771a14af2928c59c56abfb9b885a8d7
patch link: https://lore.kernel.org/lkml/20220409135104.3733193-3-wuyun.abel@bytedance.com
in testcase: reaim
on test machine: 16 threads 1 sockets Intel(R) Xeon(R) E-2278G CPU @ 3.40GHz with 32G memory
with following parameters:
runtime: 300s
nr_task: 100%
test: new_fserver
cpufreq_governor: performance
ucode: 0xec
test-description: REAIM is an updated and improved version of AIM 7 benchmark.
test-url: https://sourceforge.net/projects/re-aim-7/
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/test/testcase/ucode:
gcc-11/performance/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/300s/lkp-cfl-e1/new_fserver/reaim/0xec
commit:
6b433275e3 ("sched/fair: filter out overloaded cpus in SIS")
ae44f2177f ("sched/fair: introduce sched-idle balance")
6b433275e3a3cf18 ae44f2177fa75c271734d596397
---------------- ---------------------------
%stddev %change %stddev
\ | \
356517 +2.3% 364606 reaim.jobs_per_min
22282 +2.3% 22787 reaim.jobs_per_min_child
0.26 -2.2% 0.26 reaim.parent_time
1.87 ± 3% -33.1% 1.25 ± 4% reaim.std_dev_percent
0.00 ± 11% -83.0% 0.00 ± 22% reaim.std_dev_time
71394 +5.5% 75296 reaim.time.involuntary_context_switches
412752 +2.9% 424628 reaim.time.voluntary_context_switches
7647401 ± 24% -39.7% 4609658 cpuidle..usage
27840 ± 21% -34.3% 18280 vmstat.system.in
3736 +4.2% 3894 proc-vmstat.nr_active_anon
6959 +2.2% 7111 proc-vmstat.nr_shmem
3736 +4.2% 3894 proc-vmstat.nr_zone_active_anon
0.33 ± 18% -23.8% 0.25 ± 8% sched_debug.cfs_rq:/.h_nr_running.avg
0.31 ± 14% -20.7% 0.24 ± 7% sched_debug.cfs_rq:/.nr_running.avg
0.00 ± 25% -31.1% 0.00 ± 36% sched_debug.cpu.next_balance.stddev
3.20 ± 4% +0.5 3.71 ± 8% perf-stat.i.cache-miss-rate%
1818 ± 3% -10.2% 1632 ± 6% perf-stat.i.cycles-between-cache-misses
987044 ± 2% -3.8% 949746 perf-stat.i.iTLB-load-misses
442185 ± 8% -10.4% 395984 perf-stat.i.iTLB-loads
5920 ± 3% +3.8% 6144 perf-stat.i.instructions-per-iTLB-miss
0.05 ± 13% -0.0 0.05 perf-stat.overall.dTLB-load-miss-rate%
8510 ± 2% +3.6% 8814 perf-stat.overall.instructions-per-iTLB-miss
983682 ± 2% -3.8% 946402 perf-stat.ps.iTLB-load-misses
440691 ± 8% -10.5% 394589 perf-stat.ps.iTLB-loads
345730 ± 80% -92.5% 25933 ± 7% turbostat.C3
1.73 ± 86% -1.7 0.07 ± 7% turbostat.C3%
5033041 ± 31% -19.9% 4033568 turbostat.C6
59141 ±141% +395.4% 292968 ± 12% turbostat.C8
1.16 ±141% +4.9 6.03 ± 13% turbostat.C8%
24.98 ± 22% -29.1% 17.71 turbostat.CPU%c1
1.14 ± 84% -95.9% 0.05 ± 9% turbostat.CPU%c3
0.66 ±141% +540.9% 4.25 ± 15% turbostat.CPU%c7
20.56 ± 5% -8.4% 18.84 turbostat.CorWatt
8504754 ± 21% -34.5% 5573672 turbostat.IRQ
36.52 ± 29% +31.0% 47.86 turbostat.Pkg%pc3
21.00 ± 5% -8.3% 19.24 turbostat.PkgWatt
13.92 ± 7% -4.9 9.06 ± 2% perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
13.08 ± 5% -4.7 8.36 ± 3% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.secondary_startup_64_no_verify
13.09 ± 5% -4.7 8.37 ± 3% perf-profile.calltrace.cycles-pp.cpu_startup_entry.secondary_startup_64_no_verify
12.92 ± 5% -4.7 8.24 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.secondary_startup_64_no_verify
12.45 ± 6% -4.4 8.01 ± 5% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
11.98 ± 4% -4.3 7.72 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.secondary_startup_64_no_verify
9.04 ± 9% -3.5 5.53 ± 5% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
9.00 ± 9% -3.5 5.52 ± 5% perf-profile.calltrace.cycles-pp.mwait_idle_with_hints.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
2.68 ± 4% -0.8 1.88 ± 6% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
2.40 ± 2% -0.7 1.74 ± 6% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
2.34 ± 21% -0.6 1.72 ± 17% perf-profile.calltrace.cycles-pp.call_console_drivers.console_unlock.vprintk_emit.devkmsg_emit.devkmsg_write.cold
2.34 ± 21% -0.6 1.72 ± 17% perf-profile.calltrace.cycles-pp.console_unlock.vprintk_emit.devkmsg_emit.devkmsg_write.cold.new_sync_write
2.49 ± 11% -0.6 1.90 ± 11% perf-profile.calltrace.cycles-pp.drm_fb_helper_damage_blit_real.drm_fb_helper_damage_work.process_one_work.worker_thread.kthread
2.50 ± 11% -0.6 1.90 ± 11% perf-profile.calltrace.cycles-pp.drm_fb_helper_damage_work.process_one_work.worker_thread.kthread.ret_from_fork
2.52 ± 11% -0.6 1.93 ± 10% perf-profile.calltrace.cycles-pp.process_one_work.worker_thread.kthread.ret_from_fork
2.44 ± 11% -0.6 1.85 ± 11% perf-profile.calltrace.cycles-pp.memcpy_toio.drm_fb_helper_damage_blit_real.drm_fb_helper_damage_work.process_one_work.worker_thread
2.52 ± 11% -0.6 1.94 ± 10% perf-profile.calltrace.cycles-pp.worker_thread.kthread.ret_from_fork
2.97 ± 11% -0.6 2.40 ± 9% perf-profile.calltrace.cycles-pp.ret_from_fork
2.96 ± 11% -0.6 2.40 ± 9% perf-profile.calltrace.cycles-pp.kthread.ret_from_fork
1.61 ± 3% -0.5 1.11 ± 5% perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter
1.49 ± 3% -0.4 1.05 ± 6% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state
1.14 ± 5% -0.3 0.87 ± 4% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
4.69 ± 3% +0.3 5.00 perf-profile.calltrace.cycles-pp.div_long
0.90 ± 29% +0.4 1.34 ± 7% perf-profile.calltrace.cycles-pp.copy_process.kernel_clone.__do_sys_clone.do_syscall_64.entry_SYSCALL_64_after_hwframe
12.40 ± 5% +1.4 13.85 ± 2% perf-profile.calltrace.cycles-pp.string_rtns_1
13.92 ± 7% -4.9 9.06 ± 2% perf-profile.children.cycles-pp.do_idle
13.92 ± 7% -4.9 9.06 ± 2% perf-profile.children.cycles-pp.secondary_startup_64_no_verify
13.92 ± 7% -4.9 9.06 ± 2% perf-profile.children.cycles-pp.cpu_startup_entry
13.76 ± 7% -4.8 8.94 ± 2% perf-profile.children.cycles-pp.cpuidle_idle_call
12.74 ± 6% -4.4 8.37 ± 3% perf-profile.children.cycles-pp.cpuidle_enter_state
12.74 ± 6% -4.4 8.37 ± 3% perf-profile.children.cycles-pp.cpuidle_enter
9.14 ± 7% -3.4 5.73 ± 3% perf-profile.children.cycles-pp.intel_idle
9.10 ± 7% -3.4 5.71 ± 3% perf-profile.children.cycles-pp.mwait_idle_with_hints
3.42 ± 5% -0.8 2.58 ± 6% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
3.02 ± 3% -0.7 2.34 ± 6% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
2.49 ± 11% -0.6 1.90 ± 11% perf-profile.children.cycles-pp.memcpy_toio
2.49 ± 11% -0.6 1.90 ± 11% perf-profile.children.cycles-pp.drm_fb_helper_damage_blit_real
2.50 ± 11% -0.6 1.90 ± 11% perf-profile.children.cycles-pp.drm_fb_helper_damage_work
2.52 ± 11% -0.6 1.93 ± 10% perf-profile.children.cycles-pp.process_one_work
2.52 ± 11% -0.6 1.94 ± 10% perf-profile.children.cycles-pp.worker_thread
2.96 ± 11% -0.6 2.40 ± 9% perf-profile.children.cycles-pp.kthread
3.00 ± 11% -0.6 2.44 ± 9% perf-profile.children.cycles-pp.ret_from_fork
1.99 ± 2% -0.5 1.45 ± 5% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
1.85 -0.5 1.38 ± 5% perf-profile.children.cycles-pp.hrtimer_interrupt
0.81 ± 19% -0.4 0.44 ± 7% perf-profile.children.cycles-pp.menu_select
1.44 ± 3% -0.3 1.14 ± 5% perf-profile.children.cycles-pp.__hrtimer_run_queues
0.41 ± 5% -0.1 0.32 ± 14% perf-profile.children.cycles-pp.io_serial_out
0.12 ± 27% -0.1 0.06 ± 36% perf-profile.children.cycles-pp.rcu_idle_exit
0.16 ± 16% -0.1 0.10 ± 17% perf-profile.children.cycles-pp.clockevents_program_event
0.09 ± 25% -0.1 0.04 ± 69% perf-profile.children.cycles-pp.native_apic_msr_eoi_write
0.14 ± 22% -0.0 0.09 ± 13% perf-profile.children.cycles-pp.enqueue_hrtimer
0.15 ± 10% -0.0 0.11 ± 19% perf-profile.children.cycles-pp.sched_clock_cpu
0.08 ± 14% -0.0 0.04 ± 69% perf-profile.children.cycles-pp.cpuidle_governor_latency_req
0.12 ± 23% -0.0 0.08 ± 15% perf-profile.children.cycles-pp.timerqueue_add
4.70 ± 3% +0.3 5.00 perf-profile.children.cycles-pp.div_long
12.46 ± 5% +1.5 13.91 ± 2% perf-profile.children.cycles-pp.string_rtns_1
9.10 ± 7% -3.4 5.71 ± 3% perf-profile.self.cycles-pp.mwait_idle_with_hints
2.46 ± 11% -0.6 1.84 ± 10% perf-profile.self.cycles-pp.memcpy_toio
0.42 ± 29% -0.2 0.20 ± 13% perf-profile.self.cycles-pp.menu_select
0.40 ± 23% -0.2 0.24 ± 15% perf-profile.self.cycles-pp.cpuidle_enter_state
0.41 ± 5% -0.1 0.32 ± 14% perf-profile.self.cycles-pp.io_serial_out
0.09 ± 25% -0.1 0.04 ± 69% perf-profile.self.cycles-pp.native_apic_msr_eoi_write
0.08 ± 19% -0.0 0.04 ± 52% perf-profile.self.cycles-pp.cpuidle_idle_call
4.67 ± 3% +0.3 4.98 perf-profile.self.cycles-pp.div_long
12.36 ± 5% +1.4 13.78 ± 2% perf-profile.self.cycles-pp.string_rtns_1
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-5.18.0-rc1-00005-gae44f2177fa7" of type "text/plain" (162672 bytes)
View attachment "job-script" of type "text/plain" (7849 bytes)
View attachment "job.yaml" of type "text/plain" (5301 bytes)
View attachment "reproduce" of type "text/plain" (14149 bytes)
Powered by blists - more mailing lists