FYI, we noticed the below changes on git://git.kernel.org/pub/scm/linux/kernel/git/andrea/aa.git master commit 1732e8d84b5fa950d6533284dcc63dfee93e39f1 ("mm: gup: make get_user_pages_fast and __get_user_pages_fast latency conscious")
========================================================================================= tbox_group/testcase/rootfs/kconfig/compiler/test: lkp-sb03/will-it-scale/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/futex1 commit: 7201f254ee6b51b1549ecec1cffe4d59b3e53935 1732e8d84b5fa950d6533284dcc63dfee93e39f1 7201f254ee6b51b1 1732e8d84b5fa950d6533284dc ---------------- -------------------------- %stddev %change %stddev \ | \ 5363330 ± 0% -6.4% 5021398 ± 0% will-it-scale.per_process_ops 1810294 ± 0% -5.0% 1720041 ± 0% will-it-scale.per_thread_ops 209850 ± 5% +13.0% 237196 ± 4% cpuidle.C1-SNB.usage 53.75 ± 62% -100.9% -0.50 ±-1300% numa-numastat.node0.other_node 0.00 ± -1% +Inf% 1.11 ± 3% perf-profile.cpu-cycles.___might_sleep.get_user_pages_fast.get_futex_key.futex_wake.do_futex 2791 ± 2% +15.8% 3231 ± 1% vmstat.system.cs 290504 ± 2% +16.8% 339313 ± 1% latency_stats.hits.pipe_wait.pipe_read.__vfs_read.vfs_read.SyS_read.entry_SYSCALL_64_fastpath 4203979 ± 0% +5.3% 4424982 ± 2% latency_stats.sum.pipe_wait.pipe_read.__vfs_read.vfs_read.SyS_read.entry_SYSCALL_64_fastpath 2941 ± 15% -23.0% 2266 ± 11% numa-vmstat.node0.nr_anon_pages 3377 ± 13% +19.7% 4040 ± 6% numa-vmstat.node1.nr_anon_pages 2090 ± 27% +49.7% 3129 ± 0% numa-vmstat.node1.nr_mapped 11769 ± 15% -22.9% 9070 ± 11% numa-meminfo.node0.AnonPages 13509 ± 13% +19.7% 16167 ± 6% numa-meminfo.node1.AnonPages 2457 ± 1% +8.9% 2675 ± 3% numa-meminfo.node1.KernelStack 8363 ± 27% +49.7% 12519 ± 0% numa-meminfo.node1.Mapped 11075 ± 24% +95.4% 21637 ± 17% sched_debug.cfs_rq[24]:/.avg->runnable_avg_sum 37436 ± 10% +29.7% 48571 ± 11% sched_debug.cfs_rq[24]:/.exec_clock 854911 ± 11% +25.9% 1076265 ± 9% sched_debug.cfs_rq[24]:/.min_vruntime 241.25 ± 24% +95.4% 471.50 ± 16% sched_debug.cfs_rq[24]:/.tg_runnable_contrib 12705 ± 27% -32.3% 8597 ± 2% sched_debug.cfs_rq[25]:/.avg->runnable_avg_sum 40588 ± 13% -13.7% 35043 ± 0% sched_debug.cfs_rq[25]:/.exec_clock 276.00 ± 27% -32.3% 186.75 ± 2% sched_debug.cfs_rq[25]:/.tg_runnable_contrib 631.75 ±101% -71.4% 180.75 ±164% sched_debug.cfs_rq[3]:/.blocked_load_avg 689.75 ± 96% -68.1% 220.00 ±134% sched_debug.cfs_rq[3]:/.tg_load_contrib 4.50 ± 57% -94.4% 0.25 ±173% sched_debug.cfs_rq[6]:/.nr_spread_over 23334 ± 10% -41.3% 13699 ± 18% sched_debug.cfs_rq[8]:/.avg->runnable_avg_sum 508.50 ± 10% -41.6% 296.75 ± 18% sched_debug.cfs_rq[8]:/.tg_runnable_contrib 36.75 ± 1% +15.6% 42.50 ± 11% sched_debug.cpu#1.cpu_load[0] 7238 ± 31% +167.1% 19330 ± 16% sched_debug.cpu#1.nr_switches 8723 ± 23% +147.9% 21622 ± 10% sched_debug.cpu#1.sched_count 3283 ± 33% +179.5% 9179 ± 18% sched_debug.cpu#1.sched_goidle 31624 ± 30% -44.4% 17585 ± 12% sched_debug.cpu#11.sched_count 1170 ± 32% +84.8% 2163 ± 27% sched_debug.cpu#18.sched_goidle 8659 ± 35% +158.8% 22411 ± 18% sched_debug.cpu#2.nr_switches 10200 ± 44% +200.8% 30686 ± 38% sched_debug.cpu#2.sched_count 4063 ± 38% +167.8% 10881 ± 18% sched_debug.cpu#2.sched_goidle 2.00 ±154% +37.5% 2.75 ± 39% sched_debug.cpu#21.nr_uninterruptible 57326 ± 6% +16.9% 67039 ± 7% sched_debug.cpu#24.nr_load_updates 62286 ± 4% -8.8% 56812 ± 4% sched_debug.cpu#25.nr_load_updates 5467 ± 46% +315.6% 22723 ± 49% sched_debug.cpu#26.nr_switches 5588 ± 45% +312.3% 23036 ± 48% sched_debug.cpu#26.sched_count 2274 ± 57% +357.8% 10412 ± 57% sched_debug.cpu#26.sched_goidle 2440 ± 29% -58.6% 1011 ± 20% sched_debug.cpu#27.ttwu_local 39.25 ± 1% +7.0% 42.00 ± 2% sched_debug.cpu#3.cpu_load[3] 4907 ± 50% +215.8% 15497 ± 49% sched_debug.cpu#5.nr_switches 2213 ± 53% +239.4% 7512 ± 51% sched_debug.cpu#5.sched_goidle 370.00 ± 13% +97.0% 728.75 ± 23% sched_debug.cpu#6.ttwu_local 882811 ± 2% +12.7% 995138 ± 0% sched_debug.cpu#9.avg_idle lkp-sb03: Sandy Bridge-EP Memory: 64G will-it-scale.per_process_ops 5.4e+06 ++---------------------------------------------------------------+ *..*...*..*.. .*..*..*...*.. .*...*..*..* 5.35e+06 ++ *..*...*..*..*..*...*. *..*. | 5.3e+06 ++ | | | 5.25e+06 ++ | 5.2e+06 ++ | | | 5.15e+06 ++ | 5.1e+06 ++ | | O O O O | 5.05e+06 ++ O O O O O | 5e+06 ++ O O O O O O O O O O O O | 4.95e+06 ++---------------------------------------------------------------+ will-it-scale.per_thread_ops 1.82e+06 ++---------------------------------------------------------*-----+ | .*.. ..*.. .*. *..* 1.8e+06 ++ ..*..*.. .*..*.. *...*. *..*. .*. | *..*. *.. .. .. *. | | * * | 1.78e+06 ++ | | | 1.76e+06 ++ | | | 1.74e+06 ++ | | O O O O O O O O O O O O O | 1.72e+06 ++ O O O O O | | O O | 1.7e+06 ++-----------------------------------------------------O---------+ [*] 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
--- LKP_SERVER: inn LKP_CGI_PORT: 80 LKP_CIFS_PORT: 139 testcase: will-it-scale default-monitors: wait: activate-monitor kmsg: uptime: iostat: 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: default-watchdogs: oom-killer: watchdog: commit: d251a8b0d2064813afb90defd4e09cb599d28cdb model: Sandy Bridge-EP memory: 64G hdd_partitions: "/dev/disk/by-id/ata-WDC_WD10EARS-00Y5B1_WD-WCAV5F059499-part3" swap_partitions: rootfs_partition: "/dev/disk/by-id/ata-WDC_WD10EARS-00Y5B1_WD-WCAV5F059499-part4" category: benchmark perf-profile: freq: 800 will-it-scale: test: futex1 queue: cyclic testbox: lkp-sb03 tbox_group: lkp-sb03 kconfig: x86_64-rhel enqueue_time: 2015-08-20 15:21:54.413251757 +08:00 id: adef54f2678f23c18a992979f63fbf192e4a7dfc user: lkp compiler: gcc-4.9 head_commit: d251a8b0d2064813afb90defd4e09cb599d28cdb base_commit: 2c6625cd545bdd66acff14f3394865d43920a5c7 branch: linux-devel/devel-hourly-2015082018 kernel: "/pkg/linux/x86_64-rhel/gcc-4.9/d251a8b0d2064813afb90defd4e09cb599d28cdb/vmlinuz-4.2.0-rc7-04825-gd251a8b" rootfs: debian-x86_64-2015-02-07.cgz result_root: "/result/will-it-scale/futex1/lkp-sb03/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/d251a8b0d2064813afb90defd4e09cb599d28cdb/0" job_file: "/lkp/scheduled/lkp-sb03/cyclic_will-it-scale-futex1-x86_64-rhel-CYCLIC_HEAD-d251a8b0d2064813afb90defd4e09cb599d28cdb-20150820-65529-1m10j6i-0.yaml" dequeue_time: 2015-08-20 21:30:13.693386688 +08:00 nr_cpu: "$(nproc)" max_uptime: 1500 initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz" bootloader_append: - root=/dev/ram0 - user=lkp - job=/lkp/scheduled/lkp-sb03/cyclic_will-it-scale-futex1-x86_64-rhel-CYCLIC_HEAD-d251a8b0d2064813afb90defd4e09cb599d28cdb-20150820-65529-1m10j6i-0.yaml - ARCH=x86_64 - kconfig=x86_64-rhel - branch=linux-devel/devel-hourly-2015082018 - commit=d251a8b0d2064813afb90defd4e09cb599d28cdb - BOOT_IMAGE=/pkg/linux/x86_64-rhel/gcc-4.9/d251a8b0d2064813afb90defd4e09cb599d28cdb/vmlinuz-4.2.0-rc7-04825-gd251a8b - max_uptime=1500 - RESULT_ROOT=/result/will-it-scale/futex1/lkp-sb03/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/d251a8b0d2064813afb90defd4e09cb599d28cdb/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/d251a8b0d2064813afb90defd4e09cb599d28cdb/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,/lkp/benchmarks/will-it-scale.cgz" job_state: finished loadavg: 27.85 12.45 4.86 1/353 8939 start_time: '1440077671' end_time: '1440077981' version: "/lkp/lkp/.src-20150820-194306"
./runtest.py futex1 25 both 1 8 16 24 32