[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20161009070525.GB5609@yexl-desktop>
Date: Sun, 9 Oct 2016 15:05:25 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Manfred Spraul <manfred@...orfullife.com>
Cc: Stephen Rothwell <sfr@...b.auug.org.au>,
"H. Peter Anvin" <hpa@...or.com>,
Peter Zijlstra <peterz@...radead.org>,
Davidlohr Bueso <dave@...olabs.net>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...e.hu>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp] [ipc/sem.c] 0882cba0a0: aim9.shared_memory.ops_per_sec -8.8%
regression
FYI, we noticed a -8.8% regression of aim9.shared_memory.ops_per_sec due to commit:
commit 0882cba0a03bca73acd8fab8fb50db04691908e9 ("ipc/sem.c: fix complex_count vs. simple op race")
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
in testcase: aim9
on test machine: 4 threads Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz with 4G memory
with following parameters:
testtime: 300s
test: shared_memory
cpufreq_governor: performance
Suite IX is the "AIM Independent Resource Benchmark:" the famous synthetic benchmark.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
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
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase/testtime:
gcc-6/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/lkp-ivb-d03/shared_memory/aim9/300s
commit:
bfe738a6c2 ("config: android: enable CONFIG_SECCOMP")
0882cba0a0 ("ipc/sem.c: fix complex_count vs. simple op race")
bfe738a6c274df47 0882cba0a03bca73acd8fab8fb
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
:4 25% 1:4 kmsg.DHCP/BOOTP:Reply_not_for_us,op[#]xid[#]
%stddev %change %stddev
\ | \
1377511 ± 0% -8.8% 1256420 ± 0% aim9.shared_memory.ops_per_sec
4133531 ± 0% -8.8% 3770259 ± 0% aim9.time.minor_page_faults
9.66 ± 0% -2.0% 9.46 ± 0% turbostat.CorWatt
7.90 ± 26% -30.4% 5.50 ± 37% sched_debug.rt_rq:/.rt_time.avg
31.58 ± 26% -30.4% 21.97 ± 37% sched_debug.rt_rq:/.rt_time.max
13.67 ± 26% -30.5% 9.51 ± 37% sched_debug.rt_rq:/.rt_time.stddev
2374 ± 5% -12.4% 2078 ± 1% slabinfo.kmalloc-256.active_objs
697.75 ± 4% +33.5% 931.25 ± 5% slabinfo.kmalloc-512.active_objs
719.50 ± 3% +32.3% 951.75 ± 5% slabinfo.kmalloc-512.num_objs
5184 ± 2% -12.3% 4544 ± 8% slabinfo.kmalloc-64.active_objs
5184 ± 2% -12.3% 4544 ± 8% slabinfo.kmalloc-64.num_objs
10295 ± 6% -8.9% 9376 ± 1% perf-stat.cpu-migrations
0.04 ± 24% +59.5% 0.06 ± 51% perf-stat.dTLB-load-miss-rate%
5.346e+11 ± 3% -13.1% 4.647e+11 ± 7% perf-stat.dTLB-loads
1.61 ± 1% -9.2% 1.46 ± 1% perf-stat.ipc
4417053 ± 0% -8.2% 4053763 ± 0% perf-stat.minor-faults
4417054 ± 0% -8.2% 4053763 ± 0% perf-stat.page-faults
3.17 ± 9% -26.7% 2.32 ± 13% perf-profile.calltrace.cycles-pp._raw_spin_lock.sys_semop.entry_SYSCALL_64_fastpath
1.16 ± 4% -15.9% 0.98 ± 14% perf-profile.calltrace.cycles-pp.do_munmap.sys_shmdt.entry_SYSCALL_64_fastpath
5.25 ± 8% -15.7% 4.43 ± 4% perf-profile.calltrace.cycles-pp.do_smart_update.SYSC_semtimedop.sys_semop.entry_SYSCALL_64_fastpath
1.50 ± 5% +68.6% 2.53 ± 10% perf-profile.calltrace.cycles-pp.pid_vnr.SYSC_semtimedop.sys_semop.entry_SYSCALL_64_fastpath
1.24 ± 4% -15.3% 1.05 ± 12% perf-profile.calltrace.cycles-pp.sys_shmdt.entry_SYSCALL_64_fastpath
0.99 ± 12% -20.5% 0.79 ± 6% perf-profile.calltrace.cycles-pp.wake_const_ops.do_smart_wakeup_zero.do_smart_update.SYSC_semtimedop.sys_semop
3.45 ± 9% -24.8% 2.60 ± 12% perf-profile.children.cycles-pp._raw_spin_lock
1.18 ± 4% -15.7% 0.99 ± 14% perf-profile.children.cycles-pp.do_munmap
5.61 ± 8% -15.4% 4.75 ± 3% perf-profile.children.cycles-pp.do_smart_update
1.78 ± 5% +56.7% 2.80 ± 11% perf-profile.children.cycles-pp.pid_vnr
1.24 ± 4% -15.3% 1.05 ± 12% perf-profile.children.cycles-pp.sys_shmdt
1.24 ± 13% -24.7% 0.93 ± 8% perf-profile.children.cycles-pp.wake_const_ops
9.86 ± 8% +47.0% 14.49 ± 9% perf-profile.self.cycles-pp.SYSC_semtimedop
3.45 ± 9% -25.2% 2.58 ± 13% perf-profile.self.cycles-pp._raw_spin_lock
2.26 ± 9% -26.8% 1.65 ± 7% perf-profile.self.cycles-pp.do_smart_update
1.78 ± 5% +56.7% 2.80 ± 11% perf-profile.self.cycles-pp.pid_vnr
1.03 ± 2% -15.3% 0.87 ± 8% perf-profile.self.cycles-pp.security_ipc_permission
1.24 ± 13% -24.7% 0.93 ± 8% perf-profile.self.cycles-pp.wake_const_ops
aim9.time.minor_page_faults
4.2e+06 ++---------------------------------------------------------------+
4.15e+06 ** ***. *.* **.* .** *.** ** |
| + : * * * *.** : :: * * :: * .* : ***.***
4.1e+06 ++ * *: :** * * * * * * * * |
4.05e+06 ++ :: :.* : : * : |
| :: * * : : : |
4e+06 ++ * : : : |
3.95e+06 ++ * ** |
3.9e+06 ++ |
| |
3.85e+06 ++ |
3.8e+06 ++ O |
| OO OO O O O |
3.75e+06 OO O O OOO O |
3.7e+06 ++-O-------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
View attachment "config-4.8.0-rc7-00280-g0882cba" of type "text/plain" (152564 bytes)
View attachment "job-script" of type "text/plain" (6313 bytes)
View attachment "job.yaml" of type "text/plain" (3925 bytes)
View attachment "reproduce" of type "text/plain" (103 bytes)
Powered by blists - more mailing lists