| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 08 Oct 2015 10:37:25 +0800
From: kernel test robot <ying.huang@...ux.intel.com>
TO: Andrea Arcangeli <aarcange@...hat.com>
CC: LKML <linux-kernel@...r.kernel.org>
Subject: [lkp] [mm] 81c72584a4: -4.3% will-it-scale.per_process_ops
FYI, we noticed the below changes on
https://git.kernel.org/pub/scm/linux/kernel/git/andrea/aa.git master
commit 81c72584a480c5a4b7eede527d0b990c83c2dcc9 ("mm: gup: make get_user_pages_fast and __get_user_pages_fast latency conscious")
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/cpufreq_governor/test:
ivb42/will-it-scale/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/performance/futex1
commit:
4ae904c494e475048050994f669137c12274da85
81c72584a480c5a4b7eede527d0b990c83c2dcc9
4ae904c494e47504 81c72584a480c5a4b7eede527d
---------------- --------------------------
%stddev %change %stddev
\ | \
5375911 ± 0% -4.3% 5146855 ± 0% will-it-scale.per_process_ops
1605249 ± 1% -3.1% 1555950 ± 0% will-it-scale.per_thread_ops
0.60 ± 1% -4.2% 0.58 ± 0% will-it-scale.scalability
9957 ± 27% -28.6% 7114 ± 0% numa-meminfo.node0.Mapped
1933 ± 17% +16.0% 2243 ± 6% numa-meminfo.node1.PageTables
2488 ± 27% -28.6% 1777 ± 0% numa-vmstat.node0.nr_mapped
483.00 ± 17% +16.0% 560.50 ± 6% numa-vmstat.node1.nr_page_table_pages
42.00 ± 12% -31.5% 28.75 ± 11% sched_debug.cfs_rq[0]:/.load
2032736 ± 5% -12.5% 1779371 ± 7% sched_debug.cfs_rq[0]:/.min_vruntime
-300090 ±-69% -103.1% 9378 ±1396% sched_debug.cfs_rq[10]:/.spread0
-235906 ±-47% -103.2% 7486 ±1760% sched_debug.cfs_rq[11]:/.spread0
-885383 ±-11% -29.4% -625333 ±-21% sched_debug.cfs_rq[13]:/.spread0
-883477 ±-12% -28.4% -632137 ±-19% sched_debug.cfs_rq[14]:/.spread0
-881069 ±-12% -28.6% -629181 ±-20% sched_debug.cfs_rq[15]:/.spread0
-888493 ±-12% -29.9% -622785 ±-19% sched_debug.cfs_rq[16]:/.spread0
-883314 ±-13% -28.9% -627753 ±-20% sched_debug.cfs_rq[17]:/.spread0
-1037778 ±-20% -39.9% -623972 ±-21% sched_debug.cfs_rq[18]:/.spread0
-882564 ±-12% -29.3% -623573 ±-20% sched_debug.cfs_rq[19]:/.spread0
-237868 ±-46% -106.0% 14369 ±854% sched_debug.cfs_rq[1]:/.spread0
-870685 ±-11% -29.7% -612118 ±-18% sched_debug.cfs_rq[20]:/.spread0
-879689 ±-12% -29.5% -620241 ±-20% sched_debug.cfs_rq[21]:/.spread0
-872185 ±-13% -27.7% -630771 ±-21% sched_debug.cfs_rq[22]:/.spread0
-882721 ±-12% -28.3% -633288 ±-21% sched_debug.cfs_rq[23]:/.spread0
13.25 ± 47% +98.1% 26.25 ± 29% sched_debug.cfs_rq[24]:/.tg_load_avg_contrib
-198518 ±-57% -127.2% 53978 ±241% sched_debug.cfs_rq[25]:/.spread0
15.00 ± 33% -53.3% 7.00 ± 0% sched_debug.cfs_rq[26]:/.load_avg
-166551 ±-60% -135.2% 58649 ±214% sched_debug.cfs_rq[26]:/.spread0
15.25 ± 34% -54.1% 7.00 ± 0% sched_debug.cfs_rq[26]:/.tg_load_avg_contrib
-195491 ±-57% -128.4% 55586 ±227% sched_debug.cfs_rq[27]:/.spread0
-189456 ±-56% -130.0% 56778 ±222% sched_debug.cfs_rq[28]:/.spread0
-198122 ±-56% -131.1% 61555 ±202% sched_debug.cfs_rq[29]:/.spread0
-267573 ±-52% -105.6% 14934 ±816% sched_debug.cfs_rq[2]:/.spread0
-196299 ±-56% -129.7% 58206 ±217% sched_debug.cfs_rq[30]:/.spread0
-188828 ±-53% -130.7% 57930 ±219% sched_debug.cfs_rq[31]:/.spread0
-197148 ±-54% -131.1% 61392 ±204% sched_debug.cfs_rq[32]:/.spread0
-191912 ±-55% -130.1% 57741 ±218% sched_debug.cfs_rq[33]:/.spread0
-196722 ±-57% -129.5% 58104 ±215% sched_debug.cfs_rq[35]:/.spread0
-802782 ±-14% -31.0% -554283 ±-22% sched_debug.cfs_rq[37]:/.spread0
183.25 ± 7% -7.9% 168.75 ± 0% sched_debug.cfs_rq[37]:/.util_avg
-798974 ±-14% -31.3% -548870 ±-24% sched_debug.cfs_rq[38]:/.spread0
-804061 ±-13% -31.9% -547569 ±-23% sched_debug.cfs_rq[39]:/.spread0
-241212 ±-46% -104.2% 10110 ±1225% sched_debug.cfs_rq[3]:/.spread0
-804833 ±-13% -32.5% -542990 ±-24% sched_debug.cfs_rq[40]:/.spread0
-802162 ±-13% -31.6% -548407 ±-23% sched_debug.cfs_rq[41]:/.spread0
-804352 ±-13% -33.8% -532778 ±-26% sched_debug.cfs_rq[43]:/.spread0
-803450 ±-13% -31.6% -549859 ±-22% sched_debug.cfs_rq[44]:/.spread0
-804660 ±-13% -32.2% -545711 ±-22% sched_debug.cfs_rq[45]:/.spread0
-803171 ±-14% -32.8% -540079 ±-22% sched_debug.cfs_rq[46]:/.spread0
-798603 ±-14% -32.2% -541575 ±-23% sched_debug.cfs_rq[47]:/.spread0
-236187 ±-45% -106.5% 15418 ±808% sched_debug.cfs_rq[4]:/.spread0
-240043 ±-46% -105.8% 13821 ±907% sched_debug.cfs_rq[5]:/.spread0
-241134 ±-45% -105.5% 13348 ±932% sched_debug.cfs_rq[6]:/.spread0
-232614 ±-43% -104.6% 10696 ±1210% sched_debug.cfs_rq[7]:/.spread0
-238112 ±-49% -104.9% 11721 ±1075% sched_debug.cfs_rq[8]:/.spread0
-239741 ±-47% -104.1% 9844 ±1305% sched_debug.cfs_rq[9]:/.spread0
42.00 ± 12% -31.5% 28.75 ± 11% sched_debug.cpu#0.load
2239 ± 9% +14.0% 2553 ± 11% sched_debug.cpu#0.sched_goidle
12835 ±102% -75.7% 3118 ± 24% sched_debug.cpu#12.ttwu_count
952259 ± 4% -10.0% 857091 ± 4% sched_debug.cpu#13.avg_idle
3427 ± 0% +19.0% 4078 ± 10% sched_debug.cpu#15.curr->pid
9061 ± 55% +132.5% 21068 ± 47% sched_debug.cpu#22.nr_switches
10463 ± 43% +118.0% 22806 ± 46% sched_debug.cpu#22.sched_count
1.00 ± 70% +75.0% 1.75 ± 93% sched_debug.cpu#28.nr_uninterruptible
228.25 ± 18% +22.0% 278.50 ± 11% sched_debug.cpu#29.sched_goidle
1880 ± 53% -62.9% 698.25 ± 21% sched_debug.cpu#31.nr_switches
2007 ± 50% -58.3% 837.50 ± 17% sched_debug.cpu#31.sched_count
422.50 ± 54% -42.1% 244.75 ± 28% sched_debug.cpu#31.sched_goidle
1014 ± 79% -66.5% 340.00 ± 43% sched_debug.cpu#31.ttwu_count
619.75 ± 70% -69.3% 190.50 ± 37% sched_debug.cpu#31.ttwu_local
2.00 ± 86% -50.0% 1.00 ± 70% sched_debug.cpu#34.nr_uninterruptible
0.50 ±300% +0.0% 0.50 ±100% sched_debug.cpu#35.nr_uninterruptible
1520 ± 12% +47.8% 2247 ± 41% sched_debug.cpu#40.curr->pid
5218 ± 20% -67.4% 1703 ± 15% sched_debug.cpu#41.ttwu_count
3739 ± 56% +101.7% 7542 ± 32% sched_debug.cpu#42.nr_switches
2.75 ± 30% -127.3% -0.75 ±-238% sched_debug.cpu#44.nr_uninterruptible
1870 ± 31% +167.9% 5011 ± 56% sched_debug.cpu#44.ttwu_count
1849 ± 27% -23.8% 1410 ± 0% sched_debug.cpu#46.curr->pid
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/cpufreq_governor/test:
lkp-xbm/will-it-scale/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/performance/futex2
commit:
4ae904c494e475048050994f669137c12274da85
81c72584a480c5a4b7eede527d0b990c83c2dcc9
4ae904c494e47504 81c72584a480c5a4b7eede527d
---------------- --------------------------
%stddev %change %stddev
\ | \
3024654 ± 0% -5.0% 2872390 ± 0% will-it-scale.per_process_ops
2475333 ± 0% -4.8% 2355651 ± 0% will-it-scale.per_thread_ops
7738 ± 15% +205.2% 23616 ± 41% cpuidle.C1E-NHM.time
1484 ± 8% -25.2% 1110 ± 9% sched_debug.cpu#2.curr->pid
1254 ± 12% -15.1% 1064 ± 1% slabinfo.kmalloc-512.active_objs
0.00 ± -1% +Inf% 1437029 ±134% latency_stats.avg.nfs_wait_on_request.nfs_updatepage.nfs_write_end.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.nfs_file_write.__vfs_write.vfs_write.SyS_write.entry_SYSCALL_64_fastpath
0.00 ± -1% +Inf% 1588478 ±120% latency_stats.max.nfs_wait_on_request.nfs_updatepage.nfs_write_end.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.nfs_file_write.__vfs_write.vfs_write.SyS_write.entry_SYSCALL_64_fastpath
0.00 ± -1% +Inf% 1699671 ±113% latency_stats.sum.nfs_wait_on_request.nfs_updatepage.nfs_write_end.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.nfs_file_write.__vfs_write.vfs_write.SyS_write.entry_SYSCALL_64_fastpath
0.66 ± 4% +47.1% 0.97 ± 6% perf-profile.cpu-cycles.___might_sleep.get_futex_key.futex_wait_setup.futex_wait.do_futex
0.00 ± -1% +Inf% 2.16 ± 3% perf-profile.cpu-cycles.___might_sleep.get_user_pages_fast.get_futex_key.futex_wait_setup.futex_wait
3.68 ± 5% -6.3% 3.45 ± 1% perf-profile.cpu-cycles._raw_spin_lock.futex_wait_setup.futex_wait.do_futex.sys_futex
1.29 ± 23% -25.7% 0.96 ± 4% perf-profile.cpu-cycles.get_futex_value_locked.futex_wait_setup.futex_wait.do_futex.sys_futex
21.11 ± 0% +13.5% 23.95 ± 0% perf-profile.cpu-cycles.get_user_pages_fast.get_futex_key.futex_wait_setup.futex_wait.do_futex
16.09 ± 1% -10.0% 14.48 ± 0% perf-profile.cpu-cycles.gup_pud_range.get_user_pages_fast.get_futex_key.futex_wait_setup.futex_wait
ivb42: Ivytown Ivy Bridge-EP
Memory: 64G
lkp-xbm: Sandy Bridge
Memory: 2G
will-it-scale.per_process_ops
5.45e+06 ++---------------------------------------------------------------+
5.4e+06 *+.*..*.*..*.. .*.. *.. .*.. *.. |
| *.. .* .. .*..*.. .*. + *..*
5.35e+06 ++ *..*. * *.. .* *. * |
5.3e+06 ++ *. |
| |
5.25e+06 ++ |
5.2e+06 ++ |
5.15e+06 ++ O O O |
| O |
5.1e+06 ++ O O |
5.05e+06 ++ O O O O O O O O O O O |
O O O O |
5e+06 ++ O O |
4.95e+06 ++---------------------------------------------------------------+
[*] 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" (3206 bytes)
View attachment "reproduce" of type "text/plain" (3585 bytes)
Powered by blists - more mailing lists