[lkp] [SKL BOOT FAILURE unless idle=nomwait (was Re] 256126a34c: +6.5% blogbench.write_score

From: kernel test robot
Date: Wed Mar 16 2016 - 02:53:12 EST


FYI, we noticed that blogbench.write_score +6.5% improvement on

https://github.com/0day-ci/linux Rik-van-Riel/cpuidle-use-predicted_us-not-interactivity_req-to-consider-polling/20160312-043358
commit 256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4 ("SKL BOOT FAILURE unless idle=nomwait (was Re: PROBLEM: Cpufreq constantly keeps frequency at maximum on 4.5-rc4)")


=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/rootfs/tbox_group/testcase:
gcc-4.9/performance/1SSD/xfs/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-bdw01/blogbench

commit:
e6a4261e5a9e3ff89a4667afd6a314352654e2ef
256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4

e6a4261e5a9e3ff8 256126a34c2a087a2a9900c2c7
---------------- --------------------------
%stddev %change %stddev
\ | \
53652546 ± 1% +5.6% 56637238 ± 1% blogbench.time.file_system_outputs
632330 ± 1% -5.5% 597814 ± 1% blogbench.time.involuntary_context_switches
4861 ± 55% -40.8% 2880 ± 2% blogbench.time.maximum_resident_set_size
206.67 ± 0% -4.4% 197.50 ± 0% blogbench.time.percent_of_cpu_this_job_got
584.62 ± 0% -4.6% 557.91 ± 0% blogbench.time.system_time
4176142 ± 0% -1.7% 4105578 ± 0% blogbench.time.voluntary_context_switches
7471 ± 1% +6.5% 7955 ± 1% blogbench.write_score
2646 ± 8% +36.9% 3623 ± 14% meminfo.Writeback
107366 ± 1% +5.1% 112827 ± 0% vmstat.io.bo
28583 ± 0% +0.9% 28837 ± 1% vmstat.system.cs
85.70 ± 0% -31.3% 58.88 ± 0% turbostat.%Busy
1881 ± 0% -31.3% 1292 ± 0% turbostat.Avg_MHz
13.83 ± 0% +193.9% 40.66 ± 0% turbostat.CPU%c1
6.24 ± 0% -13.4% 5.40 ± 0% turbostat.CorWatt
8.11 ± 0% -7.7% 7.48 ± 0% turbostat.PkgWatt
1.392e+08 ± 0% +233.4% 4.639e+08 ± 0% cpuidle.C1-BDW.time
448770 ± 2% +494.6% 2668387 ± 1% cpuidle.C1-BDW.usage
250762 ± 12% -22.2% 195098 ± 15% cpuidle.C6-BDW.time
1002396 ± 24% -37.6% 625501 ± 14% cpuidle.C7s-BDW.time
3.056e+08 ± 2% -99.9% 220778 ± 33% cpuidle.POLL.time
2048094 ± 1% -98.9% 22873 ± 8% cpuidle.POLL.usage
90.78 ± 8% -23.4% 69.52 ± 20% sched_debug.cfs_rq:/.util_avg.stddev
-9028 ± -1% -29.9% -6332 ± -6% sched_debug.cpu.nr_uninterruptible.0
3003 ± 9% -35.5% 1938 ± 18% sched_debug.cpu.nr_uninterruptible.1
4372 ± 6% -24.9% 3281 ± 7% sched_debug.cpu.nr_uninterruptible.2
1725 ± 14% -31.4% 1183 ± 17% sched_debug.cpu.nr_uninterruptible.3
4393 ± 6% -24.4% 3319 ± 7% sched_debug.cpu.nr_uninterruptible.max
-9031 ± -1% -29.8% -6335 ± -6% sched_debug.cpu.nr_uninterruptible.min
5320 ± 1% -29.2% 3766 ± 6% sched_debug.cpu.nr_uninterruptible.stddev
142568 ± 9% +23.0% 175340 ± 13% proc-vmstat.kswapd_high_wmark_hit_quickly
184381 ± 7% +19.0% 219502 ± 11% proc-vmstat.kswapd_low_wmark_hit_quickly
288558 ± 3% -15.7% 243178 ± 9% proc-vmstat.nr_vmscan_immediate_reclaim
764.33 ± 8% +27.9% 977.25 ± 10% proc-vmstat.nr_writeback
330124 ± 8% +20.7% 398369 ± 12% proc-vmstat.pageoutrun
244293 ± 2% -15.9% 205562 ± 6% proc-vmstat.pgrotated
1777197 ± 3% +9.6% 1948586 ± 7% proc-vmstat.pgscan_direct_dma32
751311 ± 3% +9.8% 824826 ± 7% proc-vmstat.pgscan_direct_normal
1699363 ± 3% +10.2% 1872550 ± 6% proc-vmstat.pgsteal_direct_dma32
714246 ± 3% +10.5% 788950 ± 7% proc-vmstat.pgsteal_direct_normal
348656 ± 3% +4.4% 364123 ± 5% proc-vmstat.workingset_nodereclaim

lkp-bdw01: Broadwell ULT
Memory: 4G



cpuidle.POLL.time

3.5e+08 ++----------------------------------------------------------------+
| .* .** *. **. * .**. |
3e+08 ++ ** * *.**.**.**.** *.* * * *.* * **.**.***.**.* **
| : : : : : : :|
2.5e+08 ++ : : : : : : :|
| : : : : : : :|
2e+08 ++: : : : : : : |
| : : : : : : : |
1.5e+08 ++: : : : : :: |
| : : : : : :: |
1e+08 ++: : : : : :: |
| : : : : : :: |
5e+07 ++ : : : : : |
|: : : : : : |
0 OO-OO-OO-OOO-OO-OO-OO-OOO-OO-O-------*-*-----------------------*--+


cpuidle.POLL.usage

2.5e+06 ++----------------------------------------------------------------+
| |
| *.**.* .* * .**.** .***.* .* * .**.* *|
2e+06 ++ * ** *.**.**.*: * *.* * *.** *.* * : :*
| : : : : : : :|
| : : : : : : :|
1.5e+06 ++: : : : : : : |
| : : : : : : : |
1e+06 ++: : : : : :: |
| : : : : : :: |
| : : : : : :: |
500000 ++: : : : : :: |
|: : : : : : |
|: : : : : : |
0 OO-OO-OO-OOO-OO-OO-OO-OOO-OO-O-------*-*-----------------------*--+


cpuidle.C1-BDW.time

5e+08 ++----------------------------------------------------------------+
4.5e+08 OO OO OO OOO OO OO OO OOO OO O |
| |
4e+08 ++ |
3.5e+08 ++ |
| |
3e+08 ++ |
2.5e+08 ++ |
2e+08 ++ |
| |
1.5e+08 ++ **.**.***.**.**.**.** *.**.***.* *.***.**.**.**.***.**.* **
1e+08 ++ : : : : : : :|
| : : : : : :: |
5e+07 ++: : : : : :: |
0 **----------------------*-*----------*-*-----------------------*--+


cpuidle.C1-BDW.usage

3e+06 ++----------------------------------------------------------------+
| O O O O OO O O |
2.5e+06 OO OO OO O O O OO O O |
| |
| |
2e+06 ++ |
| |
1.5e+06 ++ |
| |
1e+06 ++ |
| |
| |
500000 ++ **.**.***.**.**.**.** *.**.***.* *.***.**.**.**.***.**.* **
| + : : : : :+ |
0 **----------------------*-*----------*-*-----------------------*--+


turbostat.Avg_MHz

2000 ++-------------------------------------------------------------------+
1800 ++ *.**.**.**.**.**.**.** **.**.**.* *.**.**.**.**.**.**.**.* **
| : : : : : : :|
1600 ++ : : : : : : :|
1400 ++ : : : : : : :|
O OO OO OO OO OO OO OO OO:OO:OO : : : : |
1200 ++ : : : : : : : |
1000 ++ : : : : : : : |
800 ++: : : : : :: |
| : : : : : :: |
600 ++: : : : : :: |
400 ++: :: : : : |
| : :: : : : |
200 ++: :: : : : |
0 *+*-----------------------**-----------*-*------------------------*--+


turbostat._Busy

90 ++---------------------------------------------------------------------+
| *.**.**.**.**.*.**.**.* *.**.*.**.* *.**.**.**.*.**.**.**.** *.*
80 ++ : : : : : : : |
70 ++ : : : : : : : |
| : : : : : : : |
60 O+OO OO OO OO OO O OO OO OO OO O : : : : |
50 ++ : : : : : : : |
| : : : : : : : |
40 ++: : : : : :: |
30 ++: : : : : :: |
| : : : : : :: |
20 ++: : : : : : |
10 ++: : : : : : |
| : : : : : : |
0 *+*-----------------------*-*-----------*-*-------------------------*--+


turbostat.CPU_c1

45 ++---------------------------------------------------------------------+
O OO O OO O O O O OO OO OO O |
40 ++ O O O O |
35 ++ |
| |
30 ++ |
25 ++ |
| |
20 ++ |
15 ++ .*.* |
| *.**.**.**.**.*.**.**.* *.**.*.**.* *.**.**.** *.**.**.** *.*
10 ++ : : : : : : : |
5 ++ : : : : : : : |
| : : : : : : |
0 *+*-----------------------*-*-----------*-*-------------------------*--+


turbostat.PkgWatt

9 ++----------------------------------------------------------------------+
| *.**.**.*.**.**.**.**.* **.**.*.** **.*.**.**.**.**.*.**.** *.*
8 O+OO OO OO O OO OO OO OO O OO OO : : : : |
7 ++ : : : : : : : |
| : : : : : : : |
6 ++ : : : : : : : |
5 ++ : : : : : : : |
| : : : : : : : |
4 ++: : : : : :: |
3 ++: : : : : :: |
| : : : : : :: |
2 ++: :: :: : |
1 ++: :: :: : |
| : :: :: : |
0 *+*------------------------**------------**--------------------------*--+


turbostat.CorWatt

7 ++----------------------------------------------------------------------+
| *. *. .*
6 ++ *.**.**.*.**.* **.**.* **.**.*.** **.*.**.**.**.* *.**.** * |
O OO OO OO O OO OO OO OO O OO OO : : : : |
5 ++ : : : : : : : |
| : : : : : : : |
4 ++ : : : : : : : |
| : : : : : : : |
3 ++ : : : : : : : |
| : : : : : :: |
2 ++: : : : : :: |
| : : : : : : |
1 ++: :: :: : |
| : :: :: : |
0 *+*------------------------**------------**--------------------------*--+


[*] 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,
Xiaolong Ye.
---
LKP_SERVER: inn
LKP_CGI_PORT: 80
LKP_CIFS_PORT: 139
testcase: blogbench
default-monitors:
wait: activate-monitor
kmsg:
uptime:
iostat:
heartbeat:
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: performance
default-watchdogs:
oom-killer:
watchdog:
commit: 256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4
model: Broadwell ULT
nr_cpu: 4
memory: 4G
nr_ssd_partitions: 1
ssd_partitions: "/dev/disk/by-id/ata-INTEL_SSDSC2CW120A3_CVCV252505YF120BGN-part1"
rootfs_partition: "/dev/disk/by-id/ata-INTEL_SSDSC2CW120A3_CVCV252505YF120BGN-part2"
category: benchmark
disk: 1SSD
fs: xfs
blogbench:
queue: bisect
testbox: lkp-bdw01
tbox_group: lkp-bdw01
kconfig: x86_64-rhel
enqueue_time: 2016-03-14 10:05:06.928750572 +08:00
compiler: gcc-4.9
rootfs: debian-x86_64-2015-02-07.cgz
id: fb599b2e44822b788d923a0908824e7dfe82e865
user: lkp
head_commit: e1eef6e9c27d24f398dc71e4fb13ebb6e2a13f60
base_commit: f6cede5b49e822ebc41a099fe41ab4989f64e2cb
branch: linux-devel/devel-hourly-2016031318
result_root: "/result/blogbench/performance-1SSD-xfs/lkp-bdw01/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/0"
job_file: "/lkp/scheduled/lkp-bdw01/bisect_blogbench-performance-1SSD-xfs-debian-x86_64-2015-02-07.cgz-x86_64-rhel-256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4-20160314-20015-1bwze2e-0.yaml"
max_uptime: 2613.3599999999997
initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz"
bootloader_append:
- root=/dev/ram0
- user=lkp
- job=/lkp/scheduled/lkp-bdw01/bisect_blogbench-performance-1SSD-xfs-debian-x86_64-2015-02-07.cgz-x86_64-rhel-256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4-20160314-20015-1bwze2e-0.yaml
- ARCH=x86_64
- kconfig=x86_64-rhel
- branch=linux-devel/devel-hourly-2016031318
- commit=256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4
- BOOT_IMAGE=/pkg/linux/x86_64-rhel/gcc-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/vmlinuz-4.5.0-rc7-00188-g256126a
- max_uptime=2613
- RESULT_ROOT=/result/blogbench/performance-1SSD-xfs/lkp-bdw01/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/0
- 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-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/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,/osimage/deps/debian-x86_64-2015-02-07.cgz/fs.cgz,/lkp/benchmarks/blogbench.cgz"
linux_headers_initrd: "/pkg/linux/x86_64-rhel/gcc-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/linux-headers.cgz"
repeat_to: 2
kernel: "/pkg/linux/x86_64-rhel/gcc-4.9/256126a34c2a087a2a9900c2c7ac9a7c4f5e54e4/vmlinuz-4.5.0-rc7-00188-g256126a"
dequeue_time: 2016-03-14 10:10:24.587691856 +08:00
job_state: finished
loadavg: 101.27 65.81 28.50 1/213 4731
start_time: '5752888769'
end_time: '5752889070'
version: "/lkp/lkp/.src-20160311-183612"
2152-04-20 16:39:14 echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
2152-04-20 16:39:14 echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor
2152-04-20 16:39:14 echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor
2152-04-20 16:39:14 echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor
2152-04-20 16:39:14 mkfs -t xfs /dev/sda1
2152-04-20 16:39:28 mount -t xfs -o nobarrier,inode64 /dev/sda1 /fs/sda1
2152-04-20 16:39:29 ./blogbench -d /fs/sda1