FYI, we noticed that will-it-scale.per_process_ops +5.2% improvement with your commit.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master commit 39a1aa8e194ab67983de3b9d0b204ccee12e689a ("mm: deduplicate memory overcommitment code") ========================================================================================= compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase: gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/ivb42/malloc1/will-it-scale commit: ea606cf5d8df370e7932460dfd960b21f20e7c6d 39a1aa8e194ab67983de3b9d0b204ccee12e689a ea606cf5d8df370e 39a1aa8e194ab67983de3b9d0b ---------------- -------------------------- %stddev %change %stddev \ | \ 101461 ± 0% +5.2% 106703 ± 0% will-it-scale.per_process_ops 0.10 ± 0% +31.8% 0.13 ± 0% will-it-scale.scalability 6966 ± 8% -9.9% 6278 ± 10% meminfo.AnonHugePages 62767556 ± 10% -24.3% 47486848 ± 7% cpuidle.C3-IVT.time 232686 ± 5% -18.4% 189919 ± 9% cpuidle.C3-IVT.usage 6823970 ± 3% -8.9% 6214309 ± 4% cpuidle.C6-IVT.usage 66703 ± 0% +12.2% 74872 ± 2% numa-vmstat.node0.numa_other 37441585 ± 0% +26.4% 47319887 ± 0% numa-vmstat.node1.numa_hit 37417000 ± 0% +26.4% 47303041 ± 0% numa-vmstat.node1.numa_local 24584 ± 0% -31.5% 16845 ± 11% numa-vmstat.node1.numa_other 6.15 ± 31% +36.2% 8.37 ± 15% sched_debug.cpu.cpu_load[4].stddev 20260 ± 6% +13.4% 22965 ± 5% sched_debug.cpu.nr_switches.min 4450 ± 9% +16.5% 5183 ± 8% sched_debug.cpu.ttwu_local.max 920.59 ± 10% +15.0% 1058 ± 7% sched_debug.cpu.ttwu_local.stddev 2.59e+08 ± 0% +13.9% 2.95e+08 ± 0% numa-numastat.node0.local_node 2.59e+08 ± 0% +13.9% 2.95e+08 ± 0% numa-numastat.node0.numa_hit 10.25 ±119% +75378.0% 7736 ± 19% numa-numastat.node0.other_node 1.097e+08 ± 0% +28.0% 1.404e+08 ± 0% numa-numastat.node1.local_node 1.097e+08 ± 0% +28.0% 1.404e+08 ± 0% numa-numastat.node1.numa_hit 9285 ± 0% -83.1% 1568 ± 98% numa-numastat.node1.other_node 3.687e+08 ± 0% +18.1% 4.354e+08 ± 0% proc-vmstat.numa_hit 3.687e+08 ± 0% +18.1% 4.354e+08 ± 0% proc-vmstat.numa_local 52281716 ± 0% +11.1% 58060959 ± 1% proc-vmstat.pgalloc_dma32 3.943e+08 ± 0% +16.7% 4.603e+08 ± 0% proc-vmstat.pgalloc_normal 1.854e+08 ± 0% +18.0% 2.187e+08 ± 0% proc-vmstat.pgfault 4.465e+08 ± 0% +16.1% 5.183e+08 ± 0% proc-vmstat.pgfree 0.00 ± -1% +Inf% 2.36 ± 12% perf-profile.cycles-pp.__split_vma.isra.36.do_munmap.vm_munmap.sys_munmap.entry_SYSCALL_64_fastpath 2.38 ± 8% -100.0% 0.00 ± -1% perf-profile.cycles-pp.__split_vma.isra.37.do_munmap.vm_munmap.sys_munmap.entry_SYSCALL_64_fastpath 4.37 ± 31% +32.9% 5.80 ± 15% perf-profile.cycles-pp.call_cpuidle.cpu_startup_entry.rest_init.start_kernel.x86_64_start_reservations 4.52 ± 28% +29.4% 5.85 ± 14% perf-profile.cycles-pp.cpu_startup_entry.rest_init.start_kernel.x86_64_start_reservations.x86_64_start_kernel 4.37 ± 31% +32.9% 5.80 ± 15% perf-profile.cycles-pp.cpuidle_enter.call_cpuidle.cpu_startup_entry.rest_init.start_kernel 4.08 ± 34% +39.8% 5.70 ± 15% perf-profile.cycles-pp.cpuidle_enter_state.cpuidle_enter.call_cpuidle.cpu_startup_entry.rest_init 0.89 ± 6% +16.3% 1.04 ± 5% perf-profile.cycles-pp.perf_event_aux.part.46.perf_event_mmap.mmap_region.do_mmap.vm_mmap_pgoff 4.52 ± 28% +29.4% 5.85 ± 14% perf-profile.cycles-pp.rest_init.start_kernel.x86_64_start_reservations.x86_64_start_kernel 4.52 ± 28% +29.4% 5.85 ± 14% perf-profile.cycles-pp.start_kernel.x86_64_start_reservations.x86_64_start_kernel 4.52 ± 28% +29.4% 5.85 ± 14% perf-profile.cycles-pp.x86_64_start_kernel 4.52 ± 28% +29.4% 5.85 ± 14% perf-profile.cycles-pp.x86_64_start_reservations.x86_64_start_kernel ivb42: Ivytown Ivy Bridge-EP Memory: 64G will-it-scale.scalability 0.14 ++-----------OOOO-O-------------------------------------------------+ 0.135 ++ O OOO | | OO O O | 0.13 OOOOOO OOOO O OO OOOOOOOO | 0.125 ++ O | | | 0.12 ++ | 0.115 ++ | 0.11 ++ | | * | 0.105 ++ * ***** : | 0.1 ********** ** ***************** ***************** | | * * * ** * ***** 0.095 ++ *** * ** | 0.09 ++------------------------------------------------------------------+ [*] 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, Xiaolong Ye
--- LKP_SERVER: inn LKP_CGI_PORT: 80 LKP_CIFS_PORT: 139 testcase: will-it-scale default-monitors: wait: activate-monitor kmsg: uptime: iostat: heartbeat: 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: performance default-watchdogs: oom-killer: watchdog: commit: 39a1aa8e194ab67983de3b9d0b204ccee12e689a model: Ivytown Ivy Bridge-EP nr_cpu: 48 memory: 64G swap_partitions: LABEL=SWAP rootfs_partition: LABEL=LKP-ROOTFS category: benchmark perf-profile: freq: 800 will-it-scale: test: malloc1 queue: bisect testbox: ivb42 tbox_group: ivb42 kconfig: x86_64-rhel enqueue_time: 2016-03-27 01:28:50.274043932 +08:00 compiler: gcc-4.9 rootfs: debian-x86_64-2015-02-07.cgz id: cbb727cf0abbc1788ae7a2be13107a8cd059a3ca user: lkp head_commit: 85060f056f13635ada31751734ceaa417fafa477 base_commit: b562e44f507e863c6792946e4e1b1449fbbac85d branch: linux-devel/devel-hourly-2016032608 result_root: "/result/will-it-scale/performance-malloc1/ivb42/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/0" job_file: "/lkp/scheduled/ivb42/bisect_will-it-scale-performance-malloc1-debian-x86_64-2015-02-07.cgz-x86_64-rhel-39a1aa8e194ab67983de3b9d0b204ccee12e689a-20160327-65598-ul4ews-0.yaml" max_uptime: 1500 initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz" bootloader_append: - root=/dev/ram0 - user=lkp - job=/lkp/scheduled/ivb42/bisect_will-it-scale-performance-malloc1-debian-x86_64-2015-02-07.cgz-x86_64-rhel-39a1aa8e194ab67983de3b9d0b204ccee12e689a-20160327-65598-ul4ews-0.yaml - ARCH=x86_64 - kconfig=x86_64-rhel - branch=linux-devel/devel-hourly-2016032608 - commit=39a1aa8e194ab67983de3b9d0b204ccee12e689a - BOOT_IMAGE=/pkg/linux/x86_64-rhel/gcc-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/vmlinuz-4.5.0-02567-g39a1aa8 - max_uptime=1500 - RESULT_ROOT=/result/will-it-scale/performance-malloc1/ivb42/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/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-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/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,/osimage/deps/debian-x86_64-2015-02-07.cgz/will-it-scale.cgz,/lkp/benchmarks/will-it-scale.cgz,/lkp/benchmarks/will-it-scale-x86_64.cgz" linux_headers_initrd: "/pkg/linux/x86_64-rhel/gcc-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/linux-headers.cgz" repeat_to: 2 kernel: "/pkg/linux/x86_64-rhel/gcc-4.9/39a1aa8e194ab67983de3b9d0b204ccee12e689a/vmlinuz-4.5.0-02567-g39a1aa8" dequeue_time: 2016-03-27 01:38:55.386064237 +08:00 job_state: finished loadavg: 37.77 18.15 7.19 1/544 9381 start_time: '1459013979' end_time: '1459014290' version: "/lkp/lkp/.src-20160325-205817"
2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu10/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu11/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu12/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu13/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu14/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu15/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu16/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu17/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu18/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu19/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu20/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu21/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu22/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu23/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu24/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu25/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu26/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu27/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu28/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu29/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu30/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu31/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu32/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu33/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu34/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu35/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu36/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu37/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu38/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu39/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu4/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu40/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu41/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu42/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu43/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu44/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu45/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu46/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu47/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu5/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu6/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu7/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu8/cpufreq/scaling_governor 2016-03-27 01:39:38 echo performance > /sys/devices/system/cpu/cpu9/cpufreq/scaling_governor 2016-03-27 01:39:39 ./runtest.py malloc1 25 both 1 12 24 36 48