FYI, we noticed the below changes on https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master commit 65d8fc777f6dcfee12785c057a6b57f679641c90 ("futex: Remove requirement for lock_page() in get_futex_key()") ========================================================================================= compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase: gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-sbx04/futex1/will-it-scale commit: 8ad7b378d0d016309014cae0f640434bca7b5e11 65d8fc777f6dcfee12785c057a6b57f679641c90 8ad7b378d0d01630 65d8fc777f6dcfee12785c057a ---------------- -------------------------- %stddev %change %stddev \ | \ 5076304 ± 0% +25.6% 6374220 ± 0% will-it-scale.per_process_ops 1194117 ± 0% +14.4% 1366153 ± 1% will-it-scale.per_thread_ops 0.58 ± 0% -2.0% 0.57 ± 0% will-it-scale.scalability 6820 ± 0% -19.6% 5483 ± 15% meminfo.AnonHugePages 2652 ± 5% -10.4% 2375 ± 2% vmstat.system.cs 2848 ± 32% +141.2% 6870 ± 65% numa-meminfo.node1.Active(anon) 2832 ± 31% +57.6% 4465 ± 27% numa-meminfo.node1.AnonPages 15018 ± 12% -23.3% 11515 ± 15% numa-meminfo.node2.AnonPages 1214 ± 14% -22.8% 936.75 ± 20% numa-meminfo.node3.PageTables 712.25 ± 32% +141.2% 1718 ± 65% numa-vmstat.node1.nr_active_anon 708.25 ± 31% +57.7% 1116 ± 27% numa-vmstat.node1.nr_anon_pages 3754 ± 12% -23.3% 2879 ± 15% numa-vmstat.node2.nr_anon_pages 304.75 ± 14% -23.1% 234.50 ± 20% numa-vmstat.node3.nr_page_table_pages 3.53 ± 1% -100.0% 0.00 ± -1% perf-profile.cycles.___might_sleep.__might_sleep.get_futex_key.futex_wake.do_futex 4.34 ± 1% -100.0% 0.00 ± -1% perf-profile.cycles.__might_sleep.get_futex_key.futex_wake.do_futex.sys_futex 1.27 ± 3% -100.0% 0.00 ± -1% perf-profile.cycles.__wake_up_bit.unlock_page.get_futex_key.futex_wake.do_futex 4.36 ± 1% +29.6% 5.65 ± 1% perf-profile.cycles.drop_futex_key_refs.isra.12.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 6.69 ± 1% +28.1% 8.57 ± 0% perf-profile.cycles.entry_SYSCALL_64 6.73 ± 0% +30.6% 8.79 ± 0% perf-profile.cycles.entry_SYSCALL_64_after_swapgs 74.21 ± 0% -11.0% 66.06 ± 0% perf-profile.cycles.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 59.05 ± 0% -21.4% 46.40 ± 0% perf-profile.cycles.get_futex_key.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 4.12 ± 0% +78.5% 7.36 ± 1% perf-profile.cycles.get_futex_key_refs.isra.11.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 2.27 ± 3% +24.1% 2.82 ± 4% perf-profile.cycles.get_user_pages_fast.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 26.95 ± 0% +30.0% 35.04 ± 1% perf-profile.cycles.get_user_pages_fast.get_futex_key.futex_wake.do_futex.sys_futex 13.43 ± 0% +27.2% 17.09 ± 1% perf-profile.cycles.gup_pte_range.gup_pud_range.get_user_pages_fast.get_futex_key.futex_wake 19.66 ± 1% +28.4% 25.24 ± 0% perf-profile.cycles.gup_pud_range.get_user_pages_fast.get_futex_key.futex_wake.do_futex 4.33 ± 1% +37.0% 5.93 ± 4% perf-profile.cycles.hash_futex.do_futex.sys_futex.entry_SYSCALL_64_fastpath 13.59 ± 0% -100.0% 0.00 ± -1% perf-profile.cycles.unlock_page.get_futex_key.futex_wake.do_futex.sys_futex 15160 ± 19% -34.8% 9883 ± 0% sched_debug.cfs_rq:/.exec_clock.min 27.25 ± 15% -37.6% 17.00 ± 8% sched_debug.cfs_rq:/.load_avg.7 21.00 ± 38% -27.4% 15.25 ± 2% sched_debug.cpu.cpu_load[2].1 21.00 ± 38% -27.4% 15.25 ± 2% sched_debug.cpu.cpu_load[3].1 21.00 ± 38% -27.4% 15.25 ± 2% sched_debug.cpu.cpu_load[4].1 1790 ± 0% +42.4% 2549 ± 45% sched_debug.cpu.curr->pid.21 50033 ± 4% -6.8% 46622 ± 4% sched_debug.cpu.nr_load_updates.29 4398 ± 42% +103.5% 8949 ± 23% sched_debug.cpu.nr_switches.11 7452 ± 34% +111.3% 15744 ± 54% sched_debug.cpu.nr_switches.20 3739 ± 13% +213.5% 11723 ± 40% sched_debug.cpu.nr_switches.23 1648 ± 53% +96.5% 3239 ± 63% sched_debug.cpu.nr_switches.51 0.25 ±519% -1300.0% -3.00 ±-52% sched_debug.cpu.nr_uninterruptible.24 8632 ± 16% -32.5% 5823 ± 19% sched_debug.cpu.sched_count.1 5091 ± 36% +137.5% 12092 ± 31% sched_debug.cpu.sched_count.11 12453 ± 90% -74.6% 3159 ± 24% sched_debug.cpu.sched_count.2 7782 ± 32% +118.2% 16977 ± 46% sched_debug.cpu.sched_count.20 2665 ± 48% -49.8% 1337 ± 30% sched_debug.cpu.sched_count.32 1365 ± 11% -14.0% 1174 ± 3% sched_debug.cpu.sched_count.45 1693 ± 51% +147.7% 4193 ± 42% sched_debug.cpu.sched_count.51 5023 ± 57% -51.5% 2434 ± 43% sched_debug.cpu.sched_count.57 1705 ± 16% +129.6% 3915 ± 48% sched_debug.cpu.sched_goidle.23 536.25 ± 14% -18.7% 435.75 ± 2% sched_debug.cpu.sched_goidle.45 1228 ± 19% -27.3% 892.50 ± 17% sched_debug.cpu.sched_goidle.5 1919 ± 55% +88.5% 3617 ± 37% sched_debug.cpu.ttwu_count.11 7699 ± 35% -43.7% 4335 ± 43% sched_debug.cpu.ttwu_count.24 5380 ± 36% -45.6% 2926 ± 18% sched_debug.cpu.ttwu_count.30 563.25 ± 20% +140.3% 1353 ± 38% sched_debug.cpu.ttwu_local.11 4297 ± 46% -49.1% 2186 ± 39% sched_debug.cpu.ttwu_local.24 2828 ± 47% -47.8% 1475 ± 34% sched_debug.cpu.ttwu_local.27 3243 ± 36% -54.3% 1482 ± 32% sched_debug.cpu.ttwu_local.30 199.25 ± 6% +100.6% 399.75 ± 32% sched_debug.cpu.ttwu_local.44 1158 ± 64% -67.3% 379.00 ± 46% sched_debug.cpu.ttwu_local.54 242.25 ± 21% +51.0% 365.75 ± 19% sched_debug.cpu.ttwu_local.55 1009 ± 26% -50.8% 496.50 ± 44% sched_debug.cpu.ttwu_local.59 1736 ± 53% -67.8% 559.25 ± 22% sched_debug.cpu.ttwu_local.9 lkp-sbx04: Sandy Bridge-EX Memory: 64G perf-profile.cycles.futex_wake.do_futex.sys_futex.entry_SYSCALL_64_fastpath 76 ++---------------------------------------------------------------------+ | | 74 ++ .*.. .*..*..*.. .*.. .*.. .*.. .*.. .*..*..*..* | *..*. *..*..*. *..*. *.*. *. *. *. | | | 72 ++ | | | 70 ++ | | | 68 ++ | | | | O O O O O O O O O O O | 66 O+ O O O O O | O O O O O O O | 64 ++-------------O-------------------------------------------------------+ will-it-scale.per_process_ops 6.6e+06 O+----O-O--O------------------------------------------------------+ | O O O O O | 6.4e+06 ++ O O O O O O O O O O O O O O O O | | 6.2e+06 ++ | 6e+06 ++ | | | 5.8e+06 ++ | | | 5.6e+06 ++ | 5.4e+06 ++ | | | 5.2e+06 ++ | *..*..*.*..*..*..*.*..*..*..*.*..*..*..*.*..*..*..*.*..*..*..*.* | 5e+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