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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190412142005.GB24200@shao2-debian>
Date:   Fri, 12 Apr 2019 22:20:05 +0800
From:   kernel test robot <rong.a.chen@...el.com>
To:     Waiman Long <longman@...hat.com>
Cc:     Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <a.p.zijlstra@...llo.nl>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Davidlohr Bueso <dave@...olabs.net>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Will Deacon <will.deacon@....com>,
        LKML <linux-kernel@...r.kernel.org>,
        "H. Peter Anvin" <hpa@...or.com>, tipbuild@...or.com, lkp@...org
Subject: [locking/rwsem] 1b94536f2d: stress-ng.bad-altstack.ops_per_sec
 -32.7% regression

Greeting,

FYI, we noticed a -32.7% regression of stress-ng.bad-altstack.ops_per_sec due to commit:


commit: 1b94536f2debc98260fb17b44f7f262e3336f7e0 ("locking/rwsem: Implement lock handoff to prevent lock starvation")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git WIP.locking/core

in testcase: stress-ng
on test machine: 272 threads Intel(R) Xeon Phi(TM) CPU 7255 @ 1.10GHz with 112G memory
with following parameters:

	nr_threads: 100%
	disk: 1HDD
	testtime: 5s
	class: memory
	cpufreq_governor: performance




Details are as below:
-------------------------------------------------------------------------------------------------->


To reproduce:

        git clone https://github.com/intel/lkp-tests.git
        cd lkp-tests
        bin/lkp install job.yaml  # job file is attached in this email
        bin/lkp run     job.yaml

=========================================================================================
class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/testcase/testtime:
  memory/gcc-7/performance/1HDD/x86_64-rhel-7.6/100%/debian-x86_64-2018-04-03.cgz/lkp-knm02/stress-ng/5s

commit: 
  1bcfe0e4cb ("locking/rwsem: Improve scalability via a new locking scheme")
  1b94536f2d ("locking/rwsem: Implement lock handoff to prevent lock starvation")

1bcfe0e4cb0efdba 1b94536f2debc98260fb17b44f7 
---------------- --------------------------- 
       fail:runs  %reproduction    fail:runs
           |             |             |    
          1:4          -25%            :4     dmesg.WARNING:at_ip__mutex_lock/0x
           :4           25%           1:4     kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[#]
         %stddev     %change         %stddev
             \          |                \  
     52766 ± 19%     -32.8%      35434 ±  3%  stress-ng.bad-altstack.ops
     10521 ± 19%     -32.7%       7081 ±  3%  stress-ng.bad-altstack.ops_per_sec
     71472 ± 16%     -37.1%      44986        stress-ng.stackmmap.ops
     14281 ± 16%     -37.0%       9001        stress-ng.stackmmap.ops_per_sec
  82779573            -6.0%   77812734        stress-ng.time.minor_page_faults
     92256           -43.9%      51723        stress-ng.vm-segv.ops
     18416           -43.9%      10340        stress-ng.vm-segv.ops_per_sec
     52143 ±  3%     -11.7%      46067 ± 12%  stress-ng.vm.ops
     10429 ±  3%     -11.7%       9211 ± 12%  stress-ng.vm.ops_per_sec
    275453 ±  3%     +21.7%     335113 ±  7%  cpuidle.POLL.usage
   2483631 ± 13%     -16.3%    2077801        meminfo.AnonHugePages
   5815007 ±  5%      -7.8%    5363463        meminfo.Memused
      2549 ± 22%     -41.7%       1487 ± 17%  numa-meminfo.node1.Active
      2549 ± 22%     -41.7%       1487 ± 17%  numa-meminfo.node1.Active(anon)
      3076 ± 23%     -45.0%       1693 ± 28%  numa-meminfo.node1.AnonPages
      9607 ±  4%     -11.8%       8476 ±  9%  softirqs.CPU1.SCHED
      9325 ± 11%     -18.0%       7646 ±  4%  softirqs.CPU177.SCHED
     10078 ±  8%     -20.7%       7992 ± 10%  softirqs.CPU68.SCHED
    731566 ± 10%     -16.3%     612334 ±  2%  numa-vmstat.node0.nr_active_anon
    677284 ± 10%     -17.0%     562176 ±  3%  numa-vmstat.node0.nr_anon_pages
    590.50 ± 11%     -39.1%     359.75 ± 17%  numa-vmstat.node0.nr_isolated_anon
    731282 ± 10%     -16.3%     612130 ±  2%  numa-vmstat.node0.nr_zone_active_anon
    654.75 ± 24%     -48.6%     336.25 ±  9%  numa-vmstat.node1.nr_active_anon
    764.75 ± 20%     -49.0%     389.75 ± 23%  numa-vmstat.node1.nr_anon_pages
    615.50 ± 15%     -42.1%     356.25 ± 30%  numa-vmstat.node1.nr_isolated_anon
    646.00 ± 26%     -49.8%     324.50 ±  9%  numa-vmstat.node1.nr_zone_active_anon
    103726            -1.8%     101867        proc-vmstat.nr_inactive_anon
      1319 ± 14%     -33.8%     873.00 ± 33%  proc-vmstat.nr_isolated_anon
    156768 ±  2%      -4.9%     149062        proc-vmstat.nr_shmem
    129637            -1.2%     128122        proc-vmstat.nr_slab_unreclaimable
    103726            -1.8%     101867        proc-vmstat.nr_zone_inactive_anon
    152368 ±  3%      -4.0%     146334        proc-vmstat.numa_huge_pte_updates
  78212819 ±  3%      -3.9%   75124681        proc-vmstat.numa_pte_updates
  83661669            -5.9%   78716234        proc-vmstat.pgfault
      4.57 ± 14%     +28.0%       5.85 ± 12%  sched_debug.cfs_rq:/.runnable_load_avg.stddev
   2981436 ± 17%     -25.9%    2209429 ± 17%  sched_debug.cfs_rq:/.spread0.max
    416297 ± 10%     -14.7%     355039 ± 10%  sched_debug.cfs_rq:/.spread0.stddev
      4.57 ± 12%     +23.4%       5.64 ± 13%  sched_debug.cpu.cpu_load[0].stddev
     89872 ± 21%     -33.6%      59685 ±  8%  sched_debug.cpu.curr->pid.avg
    102019 ± 18%     -30.7%      70749 ±  8%  sched_debug.cpu.curr->pid.max
     19999 ± 34%     -36.5%      12707 ± 24%  sched_debug.cpu.curr->pid.stddev
      5636 ± 14%     -24.7%       4242 ±  9%  sched_debug.cpu.nr_switches.min
      1962 ±  6%      -7.9%       1807 ±  2%  slabinfo.TCPv6.active_objs
      1962 ±  6%      -7.9%       1807 ±  2%  slabinfo.TCPv6.num_objs
     12816 ±  6%     -16.2%      10742        slabinfo.UNIX.active_objs
     12816 ±  6%     -16.2%      10742        slabinfo.UNIX.num_objs
     14245 ±  4%      -7.4%      13193        slabinfo.kmalloc-192.active_objs
     14306 ±  4%      -7.6%      13219        slabinfo.kmalloc-192.num_objs
      1020 ±  6%     -10.0%     918.75 ±  5%  slabinfo.skbuff_fclone_cache.active_objs
      1020 ±  6%     -10.0%     918.75 ±  5%  slabinfo.skbuff_fclone_cache.num_objs
     20792 ±  6%     -14.1%      17854        slabinfo.sock_inode_cache.active_objs
     20792 ±  6%     -14.1%      17854        slabinfo.sock_inode_cache.num_objs
      4.88 ± 60%      -2.7        2.14 ±173%  perf-profile.calltrace.cycles-pp.alloc_new_node_page.migrate_pages.do_move_pages_to_node.kernel_move_pages.__x64_sys_move_pages
      4.87 ± 60%      -2.7        2.13 ±173%  perf-profile.calltrace.cycles-pp.__alloc_pages_nodemask.alloc_new_node_page.migrate_pages.do_move_pages_to_node.kernel_move_pages
      4.84 ± 60%      -2.7        2.12 ±173%  perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages_nodemask.alloc_new_node_page.migrate_pages.do_move_pages_to_node
      4.13 ± 59%      -2.4        1.77 ±173%  perf-profile.calltrace.cycles-pp.__free_pages_ok.migrate_pages.do_move_pages_to_node.kernel_move_pages.__x64_sys_move_pages
      4.21 ± 60%      -2.3        1.91 ±173%  perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.get_page_from_freelist.__alloc_pages_nodemask.alloc_new_node_page.migrate_pages
      4.21 ± 60%      -2.3        1.91 ±173%  perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.get_page_from_freelist.__alloc_pages_nodemask.alloc_new_node_page
      0.39 ±100%      +0.6        0.96 ± 19%  perf-profile.calltrace.cycles-pp.rmap_walk_file.try_to_unmap.migrate_pages.migrate_to_node.do_migrate_pages
      0.39 ±100%      +0.6        0.96 ± 19%  perf-profile.calltrace.cycles-pp.try_to_unmap.migrate_pages.migrate_to_node.do_migrate_pages.kernel_migrate_pages
      0.42 ±100%      +0.7        1.17 ± 21%  perf-profile.calltrace.cycles-pp.migrate_pages.migrate_to_node.do_migrate_pages.kernel_migrate_pages.__x64_sys_migrate_pages
      0.45 ±100%      +0.8        1.20 ± 21%  perf-profile.calltrace.cycles-pp.do_migrate_pages.kernel_migrate_pages.__x64_sys_migrate_pages.do_syscall_64.entry_SYSCALL_64_after_hwframe
      0.45 ±100%      +0.8        1.20 ± 21%  perf-profile.calltrace.cycles-pp.migrate_to_node.do_migrate_pages.kernel_migrate_pages.__x64_sys_migrate_pages.do_syscall_64
      0.45 ±100%      +0.8        1.21 ± 20%  perf-profile.calltrace.cycles-pp.__x64_sys_migrate_pages.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall
      0.45 ±100%      +0.8        1.21 ± 20%  perf-profile.calltrace.cycles-pp.kernel_migrate_pages.__x64_sys_migrate_pages.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall
 1.102e+10            +1.8%  1.121e+10        perf-stat.i.branch-instructions
     23.75 ±  2%      +1.3       25.02 ±  2%  perf-stat.i.cache-miss-rate%
 1.308e+08            -4.8%  1.244e+08        perf-stat.i.cache-misses
 8.874e+08            -4.4%  8.487e+08        perf-stat.i.cache-references
      5277            +3.8%       5479 ±  3%  perf-stat.i.cycles-between-cache-misses
 5.288e+10            +2.2%  5.405e+10        perf-stat.i.iTLB-loads
 5.298e+10            +2.2%  5.415e+10        perf-stat.i.instructions
    633.05            +4.7%     662.92 ±  5%  perf-stat.i.instructions-per-iTLB-miss
    171328 ±  3%      -7.6%     158307        perf-stat.i.minor-faults
    172988 ±  3%      -7.7%     159604        perf-stat.i.page-faults
     17.18            -6.2%      16.11        perf-stat.overall.MPKI
     10.94            -0.3       10.69        perf-stat.overall.branch-miss-rate%
      5.04            -1.7%       4.96        perf-stat.overall.cpi
      1946            +5.6%       2055        perf-stat.overall.cycles-between-cache-misses
      0.86            -0.0        0.84        perf-stat.overall.iTLB-load-miss-rate%
    115.71            +2.7%     118.87        perf-stat.overall.instructions-per-iTLB-miss
      0.20            +1.8%       0.20        perf-stat.overall.ipc
 1.062e+10            +2.0%  1.083e+10        perf-stat.ps.branch-instructions
 1.322e+08            -4.8%  1.258e+08        perf-stat.ps.cache-misses
 8.765e+08            -4.1%   8.41e+08        perf-stat.ps.cache-references
 5.096e+10            +2.3%  5.214e+10        perf-stat.ps.iTLB-loads
 5.101e+10            +2.3%  5.219e+10        perf-stat.ps.instructions
    169847 ±  3%      -7.7%     156839        perf-stat.ps.minor-faults
    171241 ±  3%      -7.9%     157736        perf-stat.ps.page-faults
 1.394e+13            +2.8%  1.433e+13        perf-stat.total.instructions
    509.25 ± 20%     -43.8%     286.00 ± 20%  interrupts.32:IR-PCI-MSI.2621442-edge.eth0-TxRx-1
      1235 ±112%     -77.3%     280.50 ± 27%  interrupts.CPU0.TLB:TLB_shootdowns
    385.25 ± 15%     -39.1%     234.50 ± 37%  interrupts.CPU104.TLB:TLB_shootdowns
    490.00 ± 29%     -68.2%     155.75 ± 28%  interrupts.CPU106.TLB:TLB_shootdowns
      2539 ± 41%     -37.5%       1587 ± 12%  interrupts.CPU11.NMI:Non-maskable_interrupts
      2539 ± 41%     -37.5%       1587 ± 12%  interrupts.CPU11.PMI:Performance_monitoring_interrupts
    509.25 ± 20%     -43.8%     286.00 ± 20%  interrupts.CPU12.32:IR-PCI-MSI.2621442-edge.eth0-TxRx-1
      1629 ± 83%     -71.7%     460.50 ±120%  interrupts.CPU123.TLB:TLB_shootdowns
      1244 ± 75%     -85.1%     185.25 ± 61%  interrupts.CPU125.TLB:TLB_shootdowns
    395.00 ± 62%    +783.4%       3489 ± 46%  interrupts.CPU127.TLB:TLB_shootdowns
      3031 ± 33%     -63.7%       1101 ± 33%  interrupts.CPU128.NMI:Non-maskable_interrupts
      3031 ± 33%     -63.7%       1101 ± 33%  interrupts.CPU128.PMI:Performance_monitoring_interrupts
      2805 ± 46%     -49.5%       1417 ± 10%  interrupts.CPU132.NMI:Non-maskable_interrupts
      2805 ± 46%     -49.5%       1417 ± 10%  interrupts.CPU132.PMI:Performance_monitoring_interrupts
      1864 ± 21%     -43.7%       1049 ± 26%  interrupts.CPU132.RES:Rescheduling_interrupts
      2397 ± 24%     -53.3%       1120 ± 20%  interrupts.CPU133.RES:Rescheduling_interrupts
    418.50 ± 19%    +377.1%       1996 ± 72%  interrupts.CPU134.TLB:TLB_shootdowns
      2183 ± 38%     -51.3%       1062 ± 32%  interrupts.CPU136.NMI:Non-maskable_interrupts
      2183 ± 38%     -51.3%       1062 ± 32%  interrupts.CPU136.PMI:Performance_monitoring_interrupts
      2182 ±117%     -82.1%     391.75 ± 54%  interrupts.CPU136.TLB:TLB_shootdowns
    449.50 ± 71%    +272.7%       1675 ± 52%  interrupts.CPU14.TLB:TLB_shootdowns
    599.00 ± 61%     -63.4%     219.50 ± 31%  interrupts.CPU141.TLB:TLB_shootdowns
      1489 ± 14%     -26.0%       1101 ± 18%  interrupts.CPU146.RES:Rescheduling_interrupts
      1777 ± 26%     -34.9%       1157 ± 23%  interrupts.CPU148.RES:Rescheduling_interrupts
      1011 ±106%    +258.4%       3623 ± 26%  interrupts.CPU15.TLB:TLB_shootdowns
      2042 ± 26%     -36.9%       1289 ± 17%  interrupts.CPU156.NMI:Non-maskable_interrupts
      2042 ± 26%     -36.9%       1289 ± 17%  interrupts.CPU156.PMI:Performance_monitoring_interrupts
    370.50 ± 24%     -48.6%     190.50 ± 41%  interrupts.CPU156.TLB:TLB_shootdowns
      3133 ± 25%     -45.4%       1711 ± 53%  interrupts.CPU157.NMI:Non-maskable_interrupts
      3133 ± 25%     -45.4%       1711 ± 53%  interrupts.CPU157.PMI:Performance_monitoring_interrupts
      2533 ± 28%     -50.6%       1252 ± 27%  interrupts.CPU161.NMI:Non-maskable_interrupts
      2533 ± 28%     -50.6%       1252 ± 27%  interrupts.CPU161.PMI:Performance_monitoring_interrupts
      2727 ± 31%     -37.3%       1710 ±  8%  interrupts.CPU162.NMI:Non-maskable_interrupts
      2727 ± 31%     -37.3%       1710 ±  8%  interrupts.CPU162.PMI:Performance_monitoring_interrupts
      2701 ± 28%     -56.7%       1169 ± 46%  interrupts.CPU163.NMI:Non-maskable_interrupts
      2701 ± 28%     -56.7%       1169 ± 46%  interrupts.CPU163.PMI:Performance_monitoring_interrupts
    384.50 ±  9%     -63.8%     139.25 ± 43%  interrupts.CPU163.TLB:TLB_shootdowns
      4114 ± 10%     +47.4%       6062 ± 23%  interrupts.CPU167.CAL:Function_call_interrupts
    421.75 ± 19%     -66.5%     141.25 ± 60%  interrupts.CPU168.TLB:TLB_shootdowns
      2027 ± 94%     -67.1%     666.75 ±130%  interrupts.CPU172.TLB:TLB_shootdowns
      2792 ± 25%     -56.4%       1217 ± 47%  interrupts.CPU173.NMI:Non-maskable_interrupts
      2792 ± 25%     -56.4%       1217 ± 47%  interrupts.CPU173.PMI:Performance_monitoring_interrupts
      2768 ± 42%     -54.8%       1251 ± 40%  interrupts.CPU176.RES:Rescheduling_interrupts
      3623 ± 55%     -71.3%       1040 ±  9%  interrupts.CPU177.RES:Rescheduling_interrupts
      2962 ± 39%     -65.8%       1011 ± 45%  interrupts.CPU184.NMI:Non-maskable_interrupts
      2962 ± 39%     -65.8%       1011 ± 45%  interrupts.CPU184.PMI:Performance_monitoring_interrupts
      2369 ± 36%     -48.0%       1231 ± 29%  interrupts.CPU190.NMI:Non-maskable_interrupts
      2369 ± 36%     -48.0%       1231 ± 29%  interrupts.CPU190.PMI:Performance_monitoring_interrupts
      2072 ± 45%     -52.9%     976.25 ± 36%  interrupts.CPU192.NMI:Non-maskable_interrupts
      2072 ± 45%     -52.9%     976.25 ± 36%  interrupts.CPU192.PMI:Performance_monitoring_interrupts
      2256 ± 37%     -56.3%     986.50 ± 41%  interrupts.CPU196.NMI:Non-maskable_interrupts
      2256 ± 37%     -56.3%     986.50 ± 41%  interrupts.CPU196.PMI:Performance_monitoring_interrupts
      5017 ± 18%     +36.5%       6850 ± 16%  interrupts.CPU2.CAL:Function_call_interrupts
      2325 ± 12%     -48.0%       1210 ± 27%  interrupts.CPU200.RES:Rescheduling_interrupts
      2743 ± 46%     -58.2%       1147 ± 33%  interrupts.CPU201.NMI:Non-maskable_interrupts
      2743 ± 46%     -58.2%       1147 ± 33%  interrupts.CPU201.PMI:Performance_monitoring_interrupts
      2375 ± 18%     -50.7%       1170 ± 25%  interrupts.CPU201.RES:Rescheduling_interrupts
    327.75 ± 34%     -53.6%     152.00 ± 46%  interrupts.CPU201.TLB:TLB_shootdowns
      2648 ± 39%     -41.5%       1550 ± 16%  interrupts.CPU203.NMI:Non-maskable_interrupts
      2648 ± 39%     -41.5%       1550 ± 16%  interrupts.CPU203.PMI:Performance_monitoring_interrupts
      2356 ± 34%     -37.3%       1478 ± 17%  interrupts.CPU204.NMI:Non-maskable_interrupts
      2356 ± 34%     -37.3%       1478 ± 17%  interrupts.CPU204.PMI:Performance_monitoring_interrupts
      3069 ± 27%     -60.6%       1210 ± 45%  interrupts.CPU206.NMI:Non-maskable_interrupts
      3069 ± 27%     -60.6%       1210 ± 45%  interrupts.CPU206.PMI:Performance_monitoring_interrupts
      2338 ± 32%     -44.8%       1289 ± 15%  interrupts.CPU212.NMI:Non-maskable_interrupts
      2338 ± 32%     -44.8%       1289 ± 15%  interrupts.CPU212.PMI:Performance_monitoring_interrupts
      1809 ± 20%     -44.9%     996.50 ± 36%  interrupts.CPU214.NMI:Non-maskable_interrupts
      1809 ± 20%     -44.9%     996.50 ± 36%  interrupts.CPU214.PMI:Performance_monitoring_interrupts
      1743 ± 24%     -37.1%       1096 ± 33%  interrupts.CPU215.RES:Rescheduling_interrupts
      2866 ± 26%     -48.6%       1472 ± 34%  interrupts.CPU218.NMI:Non-maskable_interrupts
      2866 ± 26%     -48.6%       1472 ± 34%  interrupts.CPU218.PMI:Performance_monitoring_interrupts
      2051 ± 20%     -45.3%       1121 ± 36%  interrupts.CPU219.NMI:Non-maskable_interrupts
      2051 ± 20%     -45.3%       1121 ± 36%  interrupts.CPU219.PMI:Performance_monitoring_interrupts
      1488 ± 76%     -87.6%     185.00 ± 40%  interrupts.CPU219.TLB:TLB_shootdowns
      2513 ± 22%     -36.5%       1597 ± 15%  interrupts.CPU221.NMI:Non-maskable_interrupts
      2513 ± 22%     -36.5%       1597 ± 15%  interrupts.CPU221.PMI:Performance_monitoring_interrupts
      2294 ± 33%     -49.3%       1162 ± 35%  interrupts.CPU222.NMI:Non-maskable_interrupts
      2294 ± 33%     -49.3%       1162 ± 35%  interrupts.CPU222.PMI:Performance_monitoring_interrupts
      1384 ± 64%     -89.8%     141.00 ± 43%  interrupts.CPU222.TLB:TLB_shootdowns
      4116 ± 10%     +38.3%       5694 ±  9%  interrupts.CPU225.CAL:Function_call_interrupts
      2770 ± 29%     -35.7%       1781 ± 46%  interrupts.CPU226.NMI:Non-maskable_interrupts
      2770 ± 29%     -35.7%       1781 ± 46%  interrupts.CPU226.PMI:Performance_monitoring_interrupts
      2402 ± 38%     -58.0%       1008 ± 43%  interrupts.CPU230.NMI:Non-maskable_interrupts
      2402 ± 38%     -58.0%       1008 ± 43%  interrupts.CPU230.PMI:Performance_monitoring_interrupts
    212.50 ± 77%    +632.5%       1556 ±112%  interrupts.CPU234.TLB:TLB_shootdowns
      2079 ± 40%     -53.2%     973.00 ± 41%  interrupts.CPU238.NMI:Non-maskable_interrupts
      2079 ± 40%     -53.2%     973.00 ± 41%  interrupts.CPU238.PMI:Performance_monitoring_interrupts
      1701 ± 14%     -42.1%     985.00 ± 44%  interrupts.CPU239.NMI:Non-maskable_interrupts
      1701 ± 14%     -42.1%     985.00 ± 44%  interrupts.CPU239.PMI:Performance_monitoring_interrupts
      2795 ± 20%     -47.9%       1456 ± 44%  interrupts.CPU24.NMI:Non-maskable_interrupts
      2795 ± 20%     -47.9%       1456 ± 44%  interrupts.CPU24.PMI:Performance_monitoring_interrupts
      2524 ± 25%     -45.0%       1388 ± 18%  interrupts.CPU241.NMI:Non-maskable_interrupts
      2524 ± 25%     -45.0%       1388 ± 18%  interrupts.CPU241.PMI:Performance_monitoring_interrupts
      1664 ± 10%     -38.1%       1029 ± 38%  interrupts.CPU244.NMI:Non-maskable_interrupts
      1664 ± 10%     -38.1%       1029 ± 38%  interrupts.CPU244.PMI:Performance_monitoring_interrupts
      3116 ± 43%     -40.3%       1860 ± 45%  interrupts.CPU25.NMI:Non-maskable_interrupts
      3116 ± 43%     -40.3%       1860 ± 45%  interrupts.CPU25.PMI:Performance_monitoring_interrupts
      3872 ± 39%     -63.5%       1413 ±115%  interrupts.CPU25.TLB:TLB_shootdowns
      1868 ± 70%     -78.2%     407.75 ± 86%  interrupts.CPU251.TLB:TLB_shootdowns
      2974 ± 35%     -59.5%       1203 ± 45%  interrupts.CPU253.NMI:Non-maskable_interrupts
      2974 ± 35%     -59.5%       1203 ± 45%  interrupts.CPU253.PMI:Performance_monitoring_interrupts
      1494 ± 77%     -53.8%     691.25 ±133%  interrupts.CPU256.TLB:TLB_shootdowns
      2996 ± 34%     -63.0%       1109 ± 35%  interrupts.CPU259.NMI:Non-maskable_interrupts
      2996 ± 34%     -63.0%       1109 ± 35%  interrupts.CPU259.PMI:Performance_monitoring_interrupts
      1033 ±  3%     +40.3%       1449 ± 26%  interrupts.CPU259.RES:Rescheduling_interrupts
      1042 ±104%     -83.4%     172.75 ± 48%  interrupts.CPU259.TLB:TLB_shootdowns
      1761 ± 18%     -34.6%       1151 ± 19%  interrupts.CPU260.NMI:Non-maskable_interrupts
      1761 ± 18%     -34.6%       1151 ± 19%  interrupts.CPU260.PMI:Performance_monitoring_interrupts
      1738 ± 10%     -31.7%       1187 ± 31%  interrupts.CPU266.NMI:Non-maskable_interrupts
      1738 ± 10%     -31.7%       1187 ± 31%  interrupts.CPU266.PMI:Performance_monitoring_interrupts
      2311 ± 18%     -40.8%       1367 ±  5%  interrupts.CPU268.RES:Rescheduling_interrupts
      2893 ± 32%     -52.4%       1375 ± 31%  interrupts.CPU269.NMI:Non-maskable_interrupts
      2893 ± 32%     -52.4%       1375 ± 31%  interrupts.CPU269.PMI:Performance_monitoring_interrupts
      2200 ± 15%     -43.8%       1237 ± 17%  interrupts.CPU269.RES:Rescheduling_interrupts
      1821 ±  9%     -26.7%       1335 ± 25%  interrupts.CPU271.RES:Rescheduling_interrupts
      2554 ± 54%     -56.4%       1113 ± 29%  interrupts.CPU31.NMI:Non-maskable_interrupts
      2554 ± 54%     -56.4%       1113 ± 29%  interrupts.CPU31.PMI:Performance_monitoring_interrupts
      1145 ± 90%     -76.1%     274.00 ± 52%  interrupts.CPU31.TLB:TLB_shootdowns
      2850 ±  9%     -53.6%       1322 ± 78%  interrupts.CPU33.TLB:TLB_shootdowns
      2536 ± 33%     -52.6%       1201 ± 29%  interrupts.CPU35.NMI:Non-maskable_interrupts
      2536 ± 33%     -52.6%       1201 ± 29%  interrupts.CPU35.PMI:Performance_monitoring_interrupts
      1102 ± 20%     +28.2%       1413 ±  8%  interrupts.CPU38.RES:Rescheduling_interrupts
      1985 ± 10%     -36.1%       1268 ± 37%  interrupts.CPU41.NMI:Non-maskable_interrupts
      1985 ± 10%     -36.1%       1268 ± 37%  interrupts.CPU41.PMI:Performance_monitoring_interrupts
      5682 ±  4%     -28.2%       4080 ± 22%  interrupts.CPU46.CAL:Function_call_interrupts
      2780 ± 46%     -83.2%     466.50 ±114%  interrupts.CPU47.TLB:TLB_shootdowns
      4596 ± 21%     +30.4%       5994 ± 13%  interrupts.CPU5.CAL:Function_call_interrupts
      1176 ± 28%     +46.6%       1723 ± 17%  interrupts.CPU51.RES:Rescheduling_interrupts
      2555 ± 26%     -36.7%       1617 ±  7%  interrupts.CPU57.NMI:Non-maskable_interrupts
      2555 ± 26%     -36.7%       1617 ±  7%  interrupts.CPU57.PMI:Performance_monitoring_interrupts
      2670 ± 34%     -45.2%       1464 ± 21%  interrupts.CPU58.NMI:Non-maskable_interrupts
      2670 ± 34%     -45.2%       1464 ± 21%  interrupts.CPU58.PMI:Performance_monitoring_interrupts
      3217 ± 50%     -51.4%       1563 ± 40%  interrupts.CPU61.RES:Rescheduling_interrupts
      2631 ± 36%     -48.1%       1366 ± 32%  interrupts.CPU62.NMI:Non-maskable_interrupts
      2631 ± 36%     -48.1%       1366 ± 32%  interrupts.CPU62.PMI:Performance_monitoring_interrupts
      3742 ± 43%     -69.9%       1127 ± 91%  interrupts.CPU62.TLB:TLB_shootdowns
      2291 ± 27%     -48.8%       1172 ± 22%  interrupts.CPU64.RES:Rescheduling_interrupts
      2047 ± 14%     -38.1%       1268 ± 27%  interrupts.CPU65.RES:Rescheduling_interrupts
      2116 ± 37%     -36.6%       1341 ± 31%  interrupts.CPU67.NMI:Non-maskable_interrupts
      2116 ± 37%     -36.6%       1341 ± 31%  interrupts.CPU67.PMI:Performance_monitoring_interrupts
      2021 ±  6%     -26.6%       1484 ± 26%  interrupts.CPU70.NMI:Non-maskable_interrupts
      2021 ±  6%     -26.6%       1484 ± 26%  interrupts.CPU70.PMI:Performance_monitoring_interrupts
      3464 ± 33%     -60.0%       1387 ± 19%  interrupts.CPU71.NMI:Non-maskable_interrupts
      3464 ± 33%     -60.0%       1387 ± 19%  interrupts.CPU71.PMI:Performance_monitoring_interrupts
      1752 ± 24%     -37.9%       1087 ±  7%  interrupts.CPU78.RES:Rescheduling_interrupts
      2622 ± 42%     -63.4%     959.75 ± 40%  interrupts.CPU79.NMI:Non-maskable_interrupts
      2622 ± 42%     -63.4%     959.75 ± 40%  interrupts.CPU79.PMI:Performance_monitoring_interrupts
      1856 ± 29%     -35.3%       1200 ± 22%  interrupts.CPU81.RES:Rescheduling_interrupts
      2612 ± 29%     -61.6%       1003 ± 37%  interrupts.CPU82.NMI:Non-maskable_interrupts
      2612 ± 29%     -61.6%       1003 ± 37%  interrupts.CPU82.PMI:Performance_monitoring_interrupts
      1823 ± 97%     -89.1%     198.75 ± 50%  interrupts.CPU82.TLB:TLB_shootdowns
      2753 ± 45%     -64.9%     966.50 ± 43%  interrupts.CPU83.NMI:Non-maskable_interrupts
      2753 ± 45%     -64.9%     966.50 ± 43%  interrupts.CPU83.PMI:Performance_monitoring_interrupts
      2822 ± 39%     -39.0%       1720 ± 46%  interrupts.CPU89.NMI:Non-maskable_interrupts
      2822 ± 39%     -39.0%       1720 ± 46%  interrupts.CPU89.PMI:Performance_monitoring_interrupts
      2729 ± 33%     -48.4%       1409 ± 37%  interrupts.CPU9.NMI:Non-maskable_interrupts
      2729 ± 33%     -48.4%       1409 ± 37%  interrupts.CPU9.PMI:Performance_monitoring_interrupts
      2267 ± 34%     -44.5%       1257 ± 26%  interrupts.CPU92.NMI:Non-maskable_interrupts
      2267 ± 34%     -44.5%       1257 ± 26%  interrupts.CPU92.PMI:Performance_monitoring_interrupts
    985.25 ± 25%     +69.4%       1668 ± 37%  interrupts.CPU93.RES:Rescheduling_interrupts
    349.00 ± 13%    +436.6%       1872 ± 80%  interrupts.CPU95.TLB:TLB_shootdowns
      2435 ± 39%     -53.3%       1137 ± 28%  interrupts.CPU96.NMI:Non-maskable_interrupts
      2435 ± 39%     -53.3%       1137 ± 28%  interrupts.CPU96.PMI:Performance_monitoring_interrupts
      2198 ± 84%     -88.5%     252.50 ± 71%  interrupts.CPU96.TLB:TLB_shootdowns
      2729 ± 32%     -55.2%       1223 ± 36%  interrupts.CPU97.NMI:Non-maskable_interrupts
      2729 ± 32%     -55.2%       1223 ± 36%  interrupts.CPU97.PMI:Performance_monitoring_interrupts
      2800 ± 29%     -50.7%       1380 ± 29%  interrupts.CPU98.NMI:Non-maskable_interrupts
      2800 ± 29%     -50.7%       1380 ± 29%  interrupts.CPU98.PMI:Performance_monitoring_interrupts
    613407 ±  7%     -27.5%     444631 ± 17%  interrupts.NMI:Non-maskable_interrupts
    613407 ±  7%     -27.5%     444631 ± 17%  interrupts.PMI:Performance_monitoring_interrupts


                                                                                
                                stress-ng.vm-segv.ops                           
                                                                                
  100000 +-+----------------------------------------------------------------+   
   95000 +-++..           +..            .. + .. +                          |   
         |.             ..    .+..+..+..+    +    +    .+..  .+..+          |   
   90000 +-+   +.+..+..+     +                     +..+    +.               |   
   85000 +-+                                                                |   
   80000 +-+                                                                |   
   75000 +-+                                                                |   
         |                                                                  |   
   70000 +-+                                                                |   
   65000 +-+                                                                |   
   60000 O-+O  O O  O  O     O O  O  O     O O     O    O  O                |   
   55000 +-+              O             O       O     O                     |   
         |                                                       O  O    O  O   
   50000 +-+                                                  O       O     |   
   45000 +-+----------------------------------------------------------------+   
                                                                                
                                                                                                                                                                
                            stress-ng.vm-segv.ops_per_sec                       
                                                                                
  20000 +-+-----------------------------------------------------------------+   
  19000 +-++..           +..            ..    .. +                          |   
        |.             ..     .+..+.+..+     +    +    .+..  .+..+          |   
  18000 +-+   +..+.+..+     +.                     +.+.    +.               |   
  17000 +-+                                                                 |   
  16000 +-+                                                                 |   
  15000 +-+                                                                 |   
        |                                                                   |   
  14000 +-+                                                                 |   
  13000 +-+                                                                 |   
  12000 O-+O  O  O O  O     O  O  O O        O     O    O  O                |   
  11000 +-+              O             O  O     O    O                      |   
        |                                                        O  O    O  O   
  10000 +-+                                                   O       O     |   
   9000 +-+-----------------------------------------------------------------+   
                                                                                
                                                                                
[*] bisect-good sample
[O] bisect-bad  sample



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,
Rong Chen


View attachment "config-5.1.0-rc4-00074-g1b94536" of type "text/plain" (188821 bytes)

View attachment "job-script" of type "text/plain" (7297 bytes)

View attachment "job.yaml" of type "text/plain" (4878 bytes)

View attachment "reproduce" of type "text/plain" (406 bytes)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ