[<prev] [next>] [day] [month] [year] [list]
Message-ID: <874mifjcty.fsf@yhuang-dev.intel.com>
Date: Mon, 28 Sep 2015 14:08:09 +0800
From: kernel test robot <ying.huang@...el.com>
TO: Thomas Gleixner <tglx@...utronix.de>
CC: LKML <linux-kernel@...r.kernel.org>
Subject: [lkp] [genirq] 755d119a62: 2.7% unixbench.score
FYI, we noticed the below changes on
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit 755d119a6204974b2005a98549a48a75a7f5010b ("genirq: Simplify irq_data_to_desc()")
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/cpufreq_governor/test:
ivb42/unixbench/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/performance/dhry2reg
commit:
123236ccacc933daac3b39c5eb1f0011c70d41d8
755d119a6204974b2005a98549a48a75a7f5010b
123236ccacc933da 755d119a6204974b2005a98549
---------------- --------------------------
%stddev %change %stddev
\ | \
3332 ± 0% +2.7% 3423 ± 0% unixbench.score
2911 ± 0% -35.2% 1887 ± 31% numa-vmstat.node1.nr_mapped
65282 ± 3% -9.9% 58822 ± 6% numa-meminfo.node1.Active
4566 ± 19% -77.9% 1008 ±173% numa-meminfo.node1.AnonHugePages
224.43 ± 22% +913.2% 2273 ±139% sched_debug.cfs_rq[10]:/.exec_clock
14795 ± 13% +247.1% 51350 ±102% sched_debug.cfs_rq[10]:/.min_vruntime
11.00 ± 52% -81.8% 2.00 ± 93% sched_debug.cfs_rq[10]:/.util_avg
1.00 ± 70% +150.0% 2.50 ± 20% sched_debug.cfs_rq[19]:/.nr_spread_over
3.75 ± 22% -60.0% 1.50 ± 74% sched_debug.cfs_rq[2]:/.nr_spread_over
1803 ±160% +168.0% 4831 ± 47% sched_debug.cfs_rq[32]:/.exec_clock
19131 ±114% +333.1% 82857 ± 60% sched_debug.cfs_rq[32]:/.min_vruntime
-9020 ±-336% -734.2% 57208 ± 80% sched_debug.cfs_rq[32]:/.spread0
6.75 ± 91% -90.1% 0.67 ±141% sched_debug.cfs_rq[42]:/.util_avg
360.12 ± 7% +519.9% 2232 ±126% sched_debug.cfs_rq[4]:/.exec_clock
831.25 ± 6% +172.8% 2267 ± 29% sched_debug.cpu#12.ttwu_count
1673 ± 43% -38.5% 1029 ± 30% sched_debug.cpu#13.ttwu_count
-1.25 ±-198% -260.0% 2.00 ±154% sched_debug.cpu#16.nr_uninterruptible
1214 ± 11% -47.3% 639.50 ± 24% sched_debug.cpu#16.ttwu_count
-3.00 ±-23% -150.0% 1.50 ±137% sched_debug.cpu#19.nr_uninterruptible
1315 ± 10% +81.6% 2388 ± 18% sched_debug.cpu#2.ttwu_count
701.75 ± 68% -73.4% 186.75 ± 17% sched_debug.cpu#21.ttwu_local
432.75 ± 20% +132.1% 1004 ± 34% sched_debug.cpu#27.ttwu_count
4.00 ± 72% -156.2% -2.25 ±-164% sched_debug.cpu#3.nr_uninterruptible
907.50 ± 16% -20.3% 723.25 ± 9% sched_debug.cpu#34.nr_switches
377.50 ± 13% -17.0% 313.50 ± 9% sched_debug.cpu#34.sched_goidle
1886 ±129% -84.2% 299.00 ± 20% sched_debug.cpu#34.ttwu_count
165.00 ± 23% -29.4% 116.50 ± 3% sched_debug.cpu#34.ttwu_local
863.75 ± 32% +230.8% 2857 ± 68% sched_debug.cpu#37.sched_count
364.00 ± 30% +34.3% 488.75 ± 22% sched_debug.cpu#37.sched_goidle
160.00 ± 32% +235.9% 537.50 ± 84% sched_debug.cpu#37.ttwu_local
126.50 ± 4% +16.6% 147.50 ± 5% sched_debug.cpu#42.ttwu_local
751.00 ± 10% +32.0% 991.00 ± 17% sched_debug.cpu#45.nr_switches
754.50 ± 10% +31.8% 994.25 ± 17% sched_debug.cpu#45.sched_count
287.75 ± 11% +51.6% 436.25 ± 22% sched_debug.cpu#45.sched_goidle
-1.75 ±-74% -142.9% 0.75 ±110% sched_debug.cpu#5.nr_uninterruptible
4258 ± 27% -41.9% 2473 ± 14% sched_debug.cpu#6.nr_switches
5247 ± 16% -43.5% 2962 ± 13% sched_debug.cpu#6.sched_count
2022 ± 28% -44.8% 1116 ± 15% sched_debug.cpu#6.sched_goidle
0.00 ± 2% -Inf% -4.25 ±-45% sched_debug.cpu#8.nr_uninterruptible
ivb42: Ivytown Ivy Bridge-EP
Memory: 64G
unixbench.score
3440 ++-------------------------------------------------------------------+
| O O O |
3420 O+ O O O O O O O O O |
3400 ++ O O O O |
| O O |
3380 ++ |
| |
3360 ++ |
*.. |
3340 ++ . .*...*...*..* *.. ..*..*...*...*..*...|
3320 ++ *. + .. *. *
| + . |
3300 ++ + ..*...*..*...* |
| *..*. |
3280 ++-------------------------------------------------------------------+
[*] 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
View attachment "job.yaml" of type "text/plain" (3128 bytes)
View attachment "reproduce" of type "text/plain" (3558 bytes)
Powered by blists - more mailing lists