Re: [lkp] [zsmalloc] 44f43e99fe: will-it-scale.scalability +15.0% improvement

[Sergey Senozhatsky]

Hello,

On (05/13/16 09:40), kernel test robot wrote:
> FYI, we noticed will-it-scale.scalability +15.0% improvement due to commit:

which is a good thing, isn't it?  :)

thanks!

	-ss

> commit 44f43e99fe70833058482d183e99fdfd11220996 ("zsmalloc: fix zs_can_compact() integer overflow")
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> 
> in testcase - will-it-scale
> on test machine - xps: 8 threads Nehalem with 4G memory
> 
> 
> =========================================================================================
> compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
>   gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/xps/write1/will-it-scale
> 
> commit: 
>   1e92a61c4c7ed85c1bec037c046e92d6dc762f32
>   44f43e99fe70833058482d183e99fdfd11220996
> 
> 1e92a61c4c7ed85c 44f43e99fe70833058482d183e 
> ---------------- -------------------------- 
>        fail:runs  %reproduction    fail:runs
>            |             |             |    
>          %stddev     %change         %stddev
>              \          |                \  
>    1269910 ±  0%      -7.7%    1172297 ±  0%  will-it-scale.per_process_ops
>    1219902 ±  0%      -7.7%    1125807 ±  0%  will-it-scale.per_thread_ops
>       0.22 ±  2%     +15.0%       0.25 ±  0%  will-it-scale.scalability
>     962.50 ±  2%      -4.4%     920.00 ±  2%  vmstat.system.cs
>      56.78 ±  7%     +99.5%     113.28 ± 53%  sched_debug.cpu.load.stddev
>       0.41 ±  5%     +13.7%       0.47 ±  5%  sched_debug.cpu.nr_running.stddev
>       5576 ±  3%     +19.1%       6642 ±  4%  slabinfo.anon_vma_chain.active_objs
>       5681 ±  3%     +17.9%       6696 ±  4%  slabinfo.anon_vma_chain.num_objs
>       1610 ± 15%     +22.5%       1973 ±  4%  slabinfo.cred_jar.active_objs
> 
> =========================================================================================
> compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
>   gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/xps/writeseek2/will-it-scale
> 
> commit: 
>   1e92a61c4c7ed85c1bec037c046e92d6dc762f32
>   44f43e99fe70833058482d183e99fdfd11220996
> 
> 1e92a61c4c7ed85c 44f43e99fe70833058482d183e 
> ---------------- -------------------------- 
>        fail:runs  %reproduction    fail:runs
>            |             |             |    
>            :4           25%           1:4     kmsg.do_IRQ:#No_irq_handler_for_vector
>          %stddev     %change         %stddev
>              \          |                \  
>     768011 ±  0%      -8.7%     701413 ±  0%  will-it-scale.per_process_ops
>     660490 ±  0%      -7.9%     608530 ±  0%  will-it-scale.per_thread_ops
>       0.06 ±  2%     +13.8%       0.07 ±  0%  will-it-scale.scalability
>     702840 ± 11%     +56.7%    1101645 ± 11%  cpuidle.C1E-NHM.time
>      23738 ±  4%      -7.5%      21947 ±  1%  softirqs.RCU
>     173.21 ±  8%     +13.9%     197.33 ±  3%  sched_debug.cfs_rq:/.load.max
>      56.64 ±  8%     +24.1%      70.31 ±  3%  sched_debug.cfs_rq:/.load.stddev
>      36.58 ±  5%     -12.2%      32.12 ±  4%  sched_debug.cpu.cpu_load[3].min
>     173.21 ±  8%     +13.9%     197.33 ±  3%  sched_debug.cpu.load.max
>      56.65 ±  8%     +24.1%      70.32 ±  3%  sched_debug.cpu.load.stddev
> 
> 
> 
>                              will-it-scale.scalability
> 
>   0.27 ++-------------------------------------------------------------------+
>        |                O                                                   |
>   0.26 ++     O  O                                                          |
>        O  O          O      O  O   O      O  O  O      O                    |
>   0.25 ++                             O             O                       |
>        |                                                                    |
>   0.24 ++                                                                   |
>        |                                                                    |
>   0.23 ++                                                                   |
>        |                                                             *...*..|
>   0.22 ++.*...  .*..    *...*..  ..*..  ..*..     ..*..  ..*..      +       *
>        *.     *.    . ..       *.     *.       .*.     *.          +        |
>   0.21 ++            *                       *.               *...*         |
>        |                                                                    |
>    0.2 ++-------------------------------------------------------------------+
> 
> 
>                              will-it-scale.per_process_ops
> 
>    1.3e+06 ++---------------------------------------------------------------+
>            |                                                                |
>   1.28e+06 ++                ..*..                                         .*
>   1.26e+06 *+.*...*..*..*..*.     *..*..*...*..*..*..*...*..*..*..*...*..*. |
>            |                                                                |
>   1.24e+06 ++                                                               |
>            |                                                                |
>   1.22e+06 ++                                                               |
>            |                                                                |
>    1.2e+06 ++                                                               |
>   1.18e+06 ++                                                               |
>            |                      O  O  O      O  O  O                      |
>   1.16e+06 ++           O      O            O            O                  |
>            O      O  O     O                                                |
>   1.14e+06 ++-O-------------------------------------------------------------+
> 
> 
>                              will-it-scale.per_thread_ops
> 
>   1.24e+06 ++---------------------------------------------------------------+
>            |                                                               .*
>   1.22e+06 ++       .*..*..  ..*..        ..*..*..         .*..*..*...*..*. |
>            *..*...*.       *.     *..*..*.        *..*...*.                 |
>    1.2e+06 ++                                                               |
>            |                                                                |
>   1.18e+06 ++                                                               |
>            |                                                                |
>   1.16e+06 ++                                                               |
>            |                                                                |
>   1.14e+06 ++                                                               |
>            |                      O     O      O     O                      |
>   1.12e+06 ++ O      O     O         O      O     O      O                  |
>            O      O     O      O                                            |
>    1.1e+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,
> Xiaolong

> ---
> 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
> NFS_HANG_DF_TIMEOUT: 200
> NFS_HANG_CHECK_INTERVAL: 900
> default-watchdogs:
>   oom-killer: 
>   watchdog: 
>   nfs-hang: 
> commit: 44f43e99fe70833058482d183e99fdfd11220996
> model: Nehalem
> nr_cpu: 8
> memory: 4G
> hdd_partitions: 
> swap_partitions: "/dev/disk/by-id/ata-HDT722516DLA380_VDK91GTE0WMZBR-part2"
> rootfs_partition: "/dev/disk/by-id/ata-HDT722516DLA380_VDK91GTE0WMZBR-part1"
> netconsole_port: 6666
> category: benchmark
> perf-profile:
>   freq: 800
> will-it-scale:
>   test: write1
> queue: bisect
> testbox: xps
> tbox_group: xps
> kconfig: x86_64-rhel
> enqueue_time: 2016-05-13 00:36:18.600897786 +08:00
> compiler: gcc-4.9
> rootfs: debian-x86_64-2015-02-07.cgz
> id: 1ac9e260f98b0f5fa5cc2ddba9adbebc94694b67
> user: lkp
> head_commit: 2d0bd9534c8ddaebee64e1b4b7d621915f65e994
> base_commit: 1b46bac6275506db73592aa8b9bd1d67c79b95dc
> branch: linus/master
> result_root: "/result/will-it-scale/performance-write1/xps/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/44f43e99fe70833058482d183e99fdfd11220996/0"
> job_file: "/lkp/scheduled/xps/bisect_will-it-scale-performance-write1-debian-x86_64-2015-02-07.cgz-x86_64-rhel-44f43e99fe70833058482d183e99fdfd11220996-20160513-19998-10wxcv0-0.yaml"
> max_uptime: 1500
> initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz"
> bootloader_append:
> - root=/dev/ram0
> - user=lkp
> - job=/lkp/scheduled/xps/bisect_will-it-scale-performance-write1-debian-x86_64-2015-02-07.cgz-x86_64-rhel-44f43e99fe70833058482d183e99fdfd11220996-20160513-19998-10wxcv0-0.yaml
> - ARCH=x86_64
> - kconfig=x86_64-rhel
> - branch=linus/master
> - commit=44f43e99fe70833058482d183e99fdfd11220996
> - BOOT_IMAGE=/pkg/linux/x86_64-rhel/gcc-4.9/44f43e99fe70833058482d183e99fdfd11220996/vmlinuz-4.6.0-rc7-00002-g44f43e9
> - max_uptime=1500
> - RESULT_ROOT=/result/will-it-scale/performance-write1/xps/debian-x86_64-2015-02-07.cgz/x86_64-rhel/gcc-4.9/44f43e99fe70833058482d183e99fdfd11220996/0
> - 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-4.9/44f43e99fe70833058482d183e99fdfd11220996/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/perf-profile-x86_64.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-4.9/44f43e99fe70833058482d183e99fdfd11220996/linux-headers.cgz"
> repeat_to: 2
> kernel: "/pkg/linux/x86_64-rhel/gcc-4.9/44f43e99fe70833058482d183e99fdfd11220996/vmlinuz-4.6.0-rc7-00002-g44f43e9"
> dequeue_time: 2016-05-13 00:45:48.766806189 +08:00
> job_state: finished
> loadavg: 7.24 3.46 1.38 1/166 4778
> start_time: '1463071573'
> end_time: '1463071878'
> version: "/lkp/lkp/.src-20160513-001235"

> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu4/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu5/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu6/cpufreq/scaling_governor
> 2016-05-13 00:46:12 echo performance > /sys/devices/system/cpu/cpu7/cpufreq/scaling_governor
> 2016-05-13 00:46:13 ./runtest.py write1 32 both 1 4 6 8