[lkp] [intel_pstate] 10e4d2e8d3: -13.9% will-it-scale.per_thread_ops

From: kernel test robot
Date: Wed Nov 11 2015 - 00:22:30 EST

FYI, we noticed the below changes on

https://github.com/0day-ci/linux Philippe-Longepe/intel_pstate-Use-the-cpu-load-to-determine-the-PercentPerformance/20151103-173647
commit 10e4d2e8d38473d3964068469dd03f8c69fca4e2 ("intel_pstate: Use the cpu load to determine the PercentPerformance")


=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/cpufreq_governor/test:
lituya/will-it-scale/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/powersave/page_fault2

commit:
1ab68460b1d0671968b35e04f21efcf1ce051916
10e4d2e8d38473d3964068469dd03f8c69fca4e2

1ab68460b1d06719 10e4d2e8d38473d3964068469d
---------------- --------------------------
%stddev %change %stddev
\ | \
298605 ± 0% -13.9% 257084 ± 0% will-it-scale.per_thread_ops
6070 ± 3% -12.0% 5344 ± 4% will-it-scale.time.involuntary_context_switches
2082000 ± 0% -4.4% 1990194 ± 4% will-it-scale.time.maximum_resident_set_size
2.431e+08 ± 0% -27.8% 1.755e+08 ± 0% will-it-scale.time.minor_page_faults
317.00 ± 0% -15.8% 267.00 ± 0% will-it-scale.time.percent_of_cpu_this_job_got
929.86 ± 0% -17.9% 763.32 ± 0% will-it-scale.time.system_time
38.72 ± 0% +36.8% 52.96 ± 1% will-it-scale.time.user_time
160590 ± 0% -30.9% 110986 ± 0% will-it-scale.time.voluntary_context_switches
82310 ± 4% -10.1% 74007 ± 2% softirqs.RCU
76219 ± 1% -11.4% 67558 ± 2% softirqs.SCHED
21099 ± 0% -12.8% 18403 ± 0% vmstat.system.cs
17755 ± 0% -9.1% 16139 ± 0% vmstat.system.in
50721188 ± 11% -24.3% 38373487 ± 7% cpuidle.C1-HSW.time
2915214 ± 0% -12.7% 2544540 ± 0% cpuidle.C1-HSW.usage
1349 ± 7% -43.6% 761.75 ± 16% cpuidle.C1E-HSW.usage
1016 ± 10% -29.3% 718.75 ± 14% cpuidle.C3-HSW.usage
209143 ± 0% -22.2% 162794 ± 0% cpuidle.C6-HSW.usage
134.00 ± 21% +342.4% 592.75 ± 13% cpuidle.POLL.usage
5.851e+08 ± 0% -11.6% 5.172e+08 ± 0% proc-vmstat.numa_hit
5.851e+08 ± 0% -11.6% 5.172e+08 ± 0% proc-vmstat.numa_local
84352492 ± 0% -11.0% 75114262 ± 0% proc-vmstat.pgalloc_dma32
5.008e+08 ± 0% -11.7% 4.421e+08 ± 0% proc-vmstat.pgalloc_normal
5.813e+08 ± 0% -11.6% 5.136e+08 ± 0% proc-vmstat.pgfault
5.843e+08 ± 0% -11.6% 5.165e+08 ± 0% proc-vmstat.pgfree
6070 ± 3% -12.0% 5344 ± 4% time.involuntary_context_switches
2.431e+08 ± 0% -27.8% 1.755e+08 ± 0% time.minor_page_faults
317.00 ± 0% -15.8% 267.00 ± 0% time.percent_of_cpu_this_job_got
929.86 ± 0% -17.9% 763.32 ± 0% time.system_time
38.72 ± 0% +36.8% 52.96 ± 1% time.user_time
160590 ± 0% -30.9% 110986 ± 0% time.voluntary_context_switches
49.45 ± 0% -6.1% 46.46 ± 0% turbostat.%Busy
1628 ± 0% -24.9% 1223 ± 0% turbostat.Avg_MHz
3292 ± 0% -20.1% 2632 ± 0% turbostat.Bzy_MHz
30.06 ± 0% +12.9% 33.94 ± 0% turbostat.CPU%c6
39.00 ± 3% -18.6% 31.75 ± 1% turbostat.CoreTmp
44.25 ± 0% -11.9% 39.00 ± 0% turbostat.PkgTmp
60.82 ± 0% -21.9% 47.48 ± 0% turbostat.PkgWatt
9.46 ± 1% -12.3% 8.30 ± 0% turbostat.RAMWatt
114.00 ± 6% -22.8% 88.00 ± 32% sched_debug.cfs_rq[0]:/.load_avg
114.75 ± 6% -22.4% 89.00 ± 31% sched_debug.cfs_rq[0]:/.tg_load_avg_contrib
747.75 ± 4% -20.2% 597.00 ± 13% sched_debug.cfs_rq[0]:/.util_avg
35.00 ± 7% -22.1% 27.25 ± 11% sched_debug.cfs_rq[10]:/.load_avg
35.00 ± 7% -22.1% 27.25 ± 11% sched_debug.cfs_rq[10]:/.tg_load_avg_contrib
65687 ± 9% -16.3% 55002 ± 10% sched_debug.cfs_rq[13]:/.exec_clock
796846 ± 7% -13.6% 688111 ± 9% sched_debug.cfs_rq[13]:/.min_vruntime
645.50 ± 3% -6.9% 601.00 ± 4% sched_debug.cfs_rq[13]:/.tg_load_avg
646.00 ± 3% -6.5% 604.25 ± 4% sched_debug.cfs_rq[14]:/.tg_load_avg
53581 ± 21% -34.5% 35083 ± 33% sched_debug.cfs_rq[15]:/.exec_clock
642502 ± 22% -32.0% 436623 ± 30% sched_debug.cfs_rq[15]:/.min_vruntime
645.75 ± 3% -6.4% 604.50 ± 4% sched_debug.cfs_rq[15]:/.tg_load_avg
675242 ± 13% -18.5% 550135 ± 2% sched_debug.cfs_rq[2]:/.min_vruntime
21.50 ± 34% -66.3% 7.25 ± 38% sched_debug.cfs_rq[3]:/.nr_spread_over
29.75 ± 24% -26.9% 21.75 ± 3% sched_debug.cfs_rq[3]:/.runnable_load_avg
523.50 ± 15% -21.6% 410.50 ± 19% sched_debug.cfs_rq[4]:/.util_avg
17.50 ± 48% -50.0% 8.75 ± 27% sched_debug.cfs_rq[6]:/.nr_spread_over
-306445 ±-46% -69.1% -94668 ±-159% sched_debug.cfs_rq[7]:/.spread0
475.50 ± 11% +14.8% 545.75 ± 12% sched_debug.cfs_rq[7]:/.util_avg
32.25 ± 7% -19.4% 26.00 ± 11% sched_debug.cpu#10.cpu_load[1]
30.50 ± 9% -18.0% 25.00 ± 12% sched_debug.cpu#10.cpu_load[3]
30.25 ± 10% -17.4% 25.00 ± 12% sched_debug.cpu#10.cpu_load[4]
71304 ± 16% -19.2% 57587 ± 9% sched_debug.cpu#13.nr_load_updates
8607 ± 29% -41.9% 4998 ± 32% sched_debug.cpu#14.ttwu_count
30.50 ± 24% -48.4% 15.75 ± 20% sched_debug.cpu#15.cpu_load[0]
43.50 ± 9% -21.3% 34.25 ± 10% sched_debug.cpu#2.cpu_load[2]
42.50 ± 15% -37.1% 26.75 ± 27% sched_debug.cpu#3.cpu_load[0]
43.00 ± 14% -34.9% 28.00 ± 20% sched_debug.cpu#3.cpu_load[1]
42.75 ± 13% -34.5% 28.00 ± 20% sched_debug.cpu#3.cpu_load[2]
42.50 ± 12% -34.7% 27.75 ± 18% sched_debug.cpu#3.cpu_load[3]
42.00 ± 10% -34.5% 27.50 ± 18% sched_debug.cpu#3.cpu_load[4]
37.75 ± 13% -26.5% 27.75 ± 27% sched_debug.cpu#4.cpu_load[4]
28.00 ± 37% +40.2% 39.25 ± 6% sched_debug.cpu#7.cpu_load[0]
1131 ± 16% +41.7% 1602 ± 19% sched_debug.cpu#7.curr->pid
42073 ± 30% +56.9% 66014 ± 6% sched_debug.cpu#7.nr_load_updates
4725 ± 34% -30.5% 3284 ± 6% sched_debug.cpu#8.sched_goidle


lituya: Grantley Haswell
Memory: 16G




turbostat.Avg_MHz

1650 ++-----------*-**-*-*-*-**-*-----------------------------------------+
*.*.**.*.*.* *.*.*.**.*.*.*.**.*.*.*.**.*.*.*.*.**.*.*
1600 ++ |
1550 ++ |
| |
1500 ++ O O O |
1450 O+O O O O O O O O O OO O O O O OO |
| |
1400 ++ |
1350 ++ |
| |
1300 ++ |
1250 ++ |
| O O O |
1200 ++------------------------------------O------------------------------+


turbostat._Busy

50 ++-------------------------------------------------------------------+
| .*.**.*.*.*.**.*. |
49.5 *+*.* .*.*.* *.*.*.**.*.*.*.**.*.*.*.**.*.*.*.*.**.*.*
49 ++ * |
| |
48.5 ++ |
| |
48 ++ O |
O O OO O O O O O O O |
47.5 ++ O O O O O O O OO |
47 ++ |
| |
46.5 ++ O O O |
| O |
46 ++-------------------------------------------------------------------+


turbostat.PkgWatt

64 ++---------------------------------------------------------------------+
| .* * |
62 ++*.*. *.*.*. .*. .**. .*.*.*.*.*.** + .*.*.* + .*.*.*.*.* .*.*.*
60 *+ * * *.* * *.* *.* * |
| |
58 ++ |
56 ++ |
O O OO O O OO O O O O O O |
54 ++O O O O O O O |
52 ++ |
| |
50 ++ |
48 ++ |
| O O O O |
46 ++---------------------------------------------------------------------+


will-it-scale.per_thread_ops

305000 ++-----------------------------------------------------------------+
300000 ++ .*.*.*. |
*.*.* *.*.**.*. *. .*.** **.*.*.**.*.*.**.*.*.**.*.*.**.*.*
295000 ++ : : *.* * |
290000 ++ : : |
| : : |
285000 O+ :: |
280000 ++O OO:O O O OO O |
275000 ++ :: O O O OO O O O OO |
| : O |
270000 ++ * |
265000 ++ |
| |
260000 ++ OO |
255000 ++-----------------------------------O-O---------------------------+


will-it-scale.time.system_time

940 ++--------------------------------------------------------------------+
*.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*
920 ++ |
900 ++ |
| |
880 ++ |
860 ++ |
O OO |
840 ++O O O O O O O O O O OO O O O O |
820 ++ O O |
| |
800 ++ |
780 ++ |
| |
760 ++-------------------------------------O-OO-O-------------------------+


will-it-scale.time.percent_of_cpu_this_job_got

320 ++--*------------**-*---*-*-*----*------------------------------------+
*.* **.*.*.*.* * *.* *.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*
310 ++ |
| |
| |
300 ++ |
| |
290 O+ O OO O O O O |
| O O O OO O O O OO O O O |
280 ++ |
| |
| |
270 ++ O O O |
| O |
260 ++--------------------------------------------------------------------+


will-it-scale.time.minor_page_faults

2.5e+08 ++----------------------------------------------------------------+
*.**. .*.**. .*.**.*.**.*.*.**.*.*.**.*.*.**.*.*.**.*
2.4e+08 ++ * *.*.**.*.*.**.* |
2.3e+08 ++ |
| |
2.2e+08 ++ |
O |
2.1e+08 ++OO O O O OO O O OO O O OO O O |
| O O O |
2e+08 ++ |
1.9e+08 ++ |
| |
1.8e+08 ++ |
| O O O O |
1.7e+08 ++----------------------------------------------------------------+


will-it-scale.time.voluntary_context_switches

170000 ++-----------------------------------------------------------------+
| |
160000 *+*.**.*.*.* .*.*.*.**.*.*.**.*.*.**.*.*.**.*.*.**.*.*
| *.*.*.**.*.*.** |
| |
150000 ++ |
| |
140000 O+ OO O |
| O O O OO O O OO O O O OO |
130000 ++ O O O |
| |
| |
120000 ++ |
| |
110000 ++-----------------------------------O-O-OO------------------------+


time.system_time

940 ++--------------------------------------------------------------------+
*.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*
920 ++ |
900 ++ |
| |
880 ++ |
860 ++ |
O OO |
840 ++O O O O O O O O O O OO O O O O |
820 ++ O O |
| |
800 ++ |
780 ++ |
| |
760 ++-------------------------------------O-OO-O-------------------------+


time.percent_of_cpu_this_job_got

320 ++--*------------**-*---*-*-*----*------------------------------------+
*.* **.*.*.*.* * *.* *.*.*.**.*.*.*.*.**.*.*.*.*.**.*.*.*
310 ++ |
| |
| |
300 ++ |
| |
290 O+ O OO O O O O |
| O O O OO O O O OO O O O |
280 ++ |
| |
| |
270 ++ O O O |
| O |
260 ++--------------------------------------------------------------------+


time.minor_page_faults

2.5e+08 ++----------------------------------------------------------------+
*.**. .*.**. .*.**.*.**.*.*.**.*.*.**.*.*.**.*.*.**.*
2.4e+08 ++ * *.*.**.*.*.**.* |
2.3e+08 ++ |
| |
2.2e+08 ++ |
O |
2.1e+08 ++OO O O O OO O O OO O O OO O O |
| O O O |
2e+08 ++ |
1.9e+08 ++ |
| |
1.8e+08 ++ |
| O O O O |
1.7e+08 ++----------------------------------------------------------------+


time.voluntary_context_switches

170000 ++-----------------------------------------------------------------+
| |
160000 *+*.**.*.*.* .*.*.*.**.*.*.**.*.*.**.*.*.**.*.*.**.*.*
| *.*.*.**.*.*.** |
| |
150000 ++ |
| |
140000 O+ OO O |
| O O O OO O O OO O O O OO |
130000 ++ O O O |
| |
| |
120000 ++ |
| |
110000 ++-----------------------------------O-O-OO------------------------+


[*] bisect-good sample
[O] bisect-bad sample

To reproduce:

git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml


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.


Thanks,
Ying Huang
---
LKP_SERVER: inn
LKP_CGI_PORT: 80
LKP_CIFS_PORT: 139
testcase: will-it-scale
default-monitors:
wait: activate-monitor
kmsg:
uptime:
iostat:
vmstat:
numa-numastat:
numa-vmstat:
numa-meminfo:
proc-vmstat:
proc-stat:
interval: 10
meminfo:
slabinfo:
interrupts:
lock_stat:
latency_stats:
softirqs:
bdi_dev_mapping:
diskstats:
nfsstat:
cpuidle:
cpufreq-stats:
turbostat:
pmeter:
sched_debug:
interval: 60
cpufreq_governor: powersave
default-watchdogs:
oom-killer:
watchdog:
commit: fe77e83e9cb25d71fce9de8782d6d75c63145d68
model: Grantley Haswell
nr_cpu: 16
memory: 16G
hdd_partitions:
swap_partitions:
rootfs_partition:
category: benchmark
perf-profile:
freq: 800
will-it-scale:
test: page_fault2
queue: cyclic
testbox: lituya
tbox_group: lituya
kconfig: x86_64-rhel
enqueue_time: 2015-11-07 08:04:55.596421079 +08:00
id: cd8fb8ca5316f6746c21d702bac20042856023e2
user: lkp
compiler: gcc-4.9
head_commit: fe77e83e9cb25d71fce9de8782d6d75c63145d68
base_commit: 6a13feb9c82803e2b815eca72fa7a9f5561d7861
branch: linux-devel/devel-hourly-2015110812
kernel: "/pkg/linux/x86_64-rhel/gcc-4.9/fe77e83e9cb25d71fce9de8782d6d75c63145d68/vmlinuz-4.3.0-bochs-virtio-gpu-wl-ath-13338-gfe77e83"
rootfs: debian-x86_64-2015-02-07.cgz
result_root: "/result/will-it-scale/powersave-page_fault2/lituya/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/fe77e83e9cb25d71fce9de8782d6d75c63145d68/0"
job_file: "/lkp/scheduled/lituya/cyclic_will-it-scale-powersave-page_fault2-x86_64-rhel-CYCLIC_HEAD-fe77e83e9cb25d71fce9de8782d6d75c63145d68-20151107-41532-2wu2r3-0.yaml"
dequeue_time: 2015-11-08 19:55:34.445916281 +08:00
max_uptime: 1500
initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz"
bootloader_append:
- root=/dev/ram0
- user=lkp
- job=/lkp/scheduled/lituya/cyclic_will-it-scale-powersave-page_fault2-x86_64-rhel-CYCLIC_HEAD-fe77e83e9cb25d71fce9de8782d6d75c63145d68-20151107-41532-2wu2r3-0.yaml
- ARCH=x86_64
- kconfig=x86_64-rhel
- branch=linux-devel/devel-hourly-2015110812
- commit=fe77e83e9cb25d71fce9de8782d6d75c63145d68
- BOOT_IMAGE=/pkg/linux/x86_64-rhel/gcc-4.9/fe77e83e9cb25d71fce9de8782d6d75c63145d68/vmlinuz-4.3.0-bochs-virtio-gpu-wl-ath-13338-gfe77e83
- max_uptime=1500
- RESULT_ROOT=/result/will-it-scale/powersave-page_fault2/lituya/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/fe77e83e9cb25d71fce9de8782d6d75c63145d68/0
- LKP_SERVER=inn
- |2-


earlyprintk=ttyS0,115200 systemd.log_level=err
debug apic=debug sysrq_always_enabled rcupdate.rcu_cpu_stall_timeout=100
panic=-1 softlockup_panic=1 nmi_watchdog=panic oops=panic load_ramdisk=2 prompt_ramdisk=0
console=ttyS0,115200 console=tty0 vga=normal

rw
lkp_initrd: "/lkp/lkp/lkp-x86_64.cgz"
modules_initrd: "/pkg/linux/x86_64-rhel/gcc-4.9/fe77e83e9cb25d71fce9de8782d6d75c63145d68/modules.cgz"
bm_initrd: "/osimage/deps/debian-x86_64-2015-02-07.cgz/lkp.cgz,/osimage/deps/debian-x86_64-2015-02-07.cgz/run-ipconfig.cgz,/osimage/deps/debian-x86_64-2015-02-07.cgz/turbostat.cgz,/lkp/benchmarks/turbostat.cgz,/lkp/benchmarks/will-it-scale.cgz"
job_state: finished
loadavg: 13.24 6.73 2.70 1/220 4882
start_time: '1446983758'
end_time: '1446984063'
version: "/lkp/lkp/.src-20151106-190021"
echo powersave > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu10/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu11/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu12/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu13/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu14/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu15/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu4/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu5/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu6/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu7/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu8/cpufreq/scaling_governor
echo powersave > /sys/devices/system/cpu/cpu9/cpufreq/scaling_governor
./runtest.py page_fault2 32 both 1 8 12 16