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  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [day] [month] [year] [list]
Date:   Tue, 15 Dec 2020 17:36:18 +0800
From:   kernel test robot <rong.a.chen@...el.com>
To:     Filipe Manana <fdmanana@...e.com>
Cc:     David Sterba <dsterba@...e.com>,
        LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org,
        lkp@...el.com, ying.huang@...el.com, feng.tang@...el.com,
        zhengjun.xing@...el.com, linux-btrfs@...r.kernel.org
Subject: [btrfs] 639bd575b7: stress-ng.fallocate.ops_per_sec 29.2% improvement

Greeting,

FYI, we noticed a 29.2% improvement of stress-ng.fallocate.ops_per_sec due to commit:


commit: 639bd575b7c7fa326abadd2ef3e374a5a24eb40b ("btrfs: fix race leading to unnecessary transaction commit when logging inode")
https://git.kernel.org/cgit/linux/kernel/git/kdave/linux.git for-5.11


in testcase: stress-ng
on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory
with following parameters:

	nr_threads: 10%
	disk: 1HDD
	testtime: 30s
	class: filesystem
	cpufreq_governor: performance
	ucode: 0x5003003
	fs: btrfs






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/fs/kconfig/nr_threads/rootfs/tbox_group/testcase/testtime/ucode:
  filesystem/gcc-9/performance/1HDD/btrfs/x86_64-rhel-8.3/10%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp7/stress-ng/30s/0x5003003

commit: 
  47d3db41e1 ("btrfs: fix race that makes inode logging fallback to transaction commit")
  639bd575b7 ("btrfs: fix race leading to unnecessary transaction commit when logging inode")

47d3db41e190ca4a 639bd575b7c7fa326abadd2ef3e 
---------------- --------------------------- 
       fail:runs  %reproduction    fail:runs
           |             |             |    
           :4           25%           1:4     last_state.exit_fail
           :4           25%           1:4     last_state.is_incomplete_run
         %stddev     %change         %stddev
             \          |                \  
      2651           +12.2%       2975        stress-ng.copy-file.ops
     88.13           +12.2%      98.92        stress-ng.copy-file.ops_per_sec
    235137 ±  2%     -10.9%     209428        stress-ng.dnotify.ops
      7837 ±  2%     -10.9%       6980        stress-ng.dnotify.ops_per_sec
     87982 ±  2%     +29.3%     113796 ±  2%  stress-ng.fallocate.ops
      2929           +29.2%       3785 ±  2%  stress-ng.fallocate.ops_per_sec
      9735 ±  2%     +12.5%      10952 ±  4%  vmstat.io.bo
     77531            +2.4%      79363        vmstat.system.cs
      0.01 ±  8%     -27.9%       0.01 ± 25%  perf-sched.sch_delay.max.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
      1.57 ± 98%     -97.0%       0.05 ± 70%  perf-sched.sch_delay.max.ms.rwsem_down_write_slowpath.chmod_common.do_fchmodat.__x64_sys_fchmodat
      4.11 ± 14%     -13.6%       3.55        perf-sched.total_sch_delay.max.ms
      1.68 ± 11%     -17.8%       1.38 ±  4%  perf-sched.wait_time.avg.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
      1.69 ± 11%     -17.5%       1.39 ±  4%  perf-sched.wait_time.avg.ms.do_syslog.part.0.kmsg_read.vfs_read
      3.36 ± 11%     -17.9%       2.76 ±  4%  perf-sched.wait_time.max.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64
      3.38 ± 11%     -17.5%       2.79 ±  4%  perf-sched.wait_time.max.ms.do_syslog.part.0.kmsg_read.vfs_read
   6021597            +4.0%    6260885        proc-vmstat.nr_dirtied
   2867201 ±  2%     +13.2%    3245422 ±  4%  proc-vmstat.nr_written
     43993 ±  4%     -34.5%      28827 ± 22%  proc-vmstat.numa_pages_migrated
    385987 ±  3%      -9.4%     349671 ±  5%  proc-vmstat.numa_pte_updates
   1367672            +2.6%    1403411        proc-vmstat.pgactivate
     43993 ±  4%     -34.5%      28827 ± 22%  proc-vmstat.pgmigrate_success
  11946072 ±  2%     +12.4%   13426061 ±  4%  proc-vmstat.pgpgout
     52487 ±  5%     -10.0%      47236 ±  4%  slabinfo.Acpi-Parse.active_objs
    719.25 ±  5%      -9.6%     650.33 ±  4%  slabinfo.Acpi-Parse.active_slabs
     52538 ±  5%      -9.5%      47525 ±  4%  slabinfo.Acpi-Parse.num_objs
    719.25 ±  5%      -9.6%     650.33 ±  4%  slabinfo.Acpi-Parse.num_slabs
      1978 ± 14%     -27.0%       1444 ± 20%  slabinfo.biovec-64.active_objs
      1978 ± 14%     -27.0%       1444 ± 20%  slabinfo.biovec-64.num_objs
     29323            -9.6%      26504 ±  4%  slabinfo.kmalloc-192.active_objs
     29468            -9.5%      26676 ±  4%  slabinfo.kmalloc-192.num_objs
     17656 ±  7%      -6.0%      16600 ±  6%  slabinfo.kmalloc-rcl-64.num_objs
      3502 ±  5%     -10.0%       3152 ±  3%  slabinfo.sock_inode_cache.active_objs
      3502 ±  5%     -10.0%       3152 ±  3%  slabinfo.sock_inode_cache.num_objs
     13.41 ± 19%     -20.6%      10.66        perf-stat.i.MPKI
      1.10 ± 24%      -0.3        0.83        perf-stat.i.branch-miss-rate%
     78169            +2.4%      80056        perf-stat.i.context-switches
      2.76 ±  3%      -3.8%       2.66        perf-stat.i.cpi
     68.47            -1.5       66.99        perf-stat.i.iTLB-load-miss-rate%
   3241453 ±  5%      +7.2%    3474825        perf-stat.i.iTLB-loads
      0.44            +2.7%       0.45        perf-stat.i.ipc
    947672            +2.3%     969530        perf-stat.i.node-loads
     80.19            -1.1       79.06        perf-stat.overall.iTLB-load-miss-rate%
     77621            +2.3%      79439        perf-stat.ps.context-switches
   3235337 ±  5%      +7.2%    3468144        perf-stat.ps.iTLB-loads
    946313            +2.4%     968610        perf-stat.ps.node-loads
    338636 ± 10%     -35.3%     219050 ± 13%  sched_debug.cfs_rq:/.load.max
     65313 ± 12%     -23.1%      50201 ± 15%  sched_debug.cfs_rq:/.load.stddev
      3.57 ± 24%     -31.8%       2.43 ± 28%  sched_debug.cfs_rq:/.removed.load_avg.avg
    110.38 ± 21%     -40.6%      65.53 ± 33%  sched_debug.cfs_rq:/.removed.load_avg.max
     19.11 ± 22%     -36.8%      12.08 ± 23%  sched_debug.cfs_rq:/.removed.load_avg.stddev
      1.56 ± 28%     -49.1%       0.80 ± 39%  sched_debug.cfs_rq:/.removed.runnable_avg.avg
     55.38 ± 22%     -43.2%      31.44 ± 29%  sched_debug.cfs_rq:/.removed.runnable_avg.max
      8.78 ± 26%     -50.3%       4.37 ± 25%  sched_debug.cfs_rq:/.removed.runnable_avg.stddev
      1.56 ± 28%     -49.1%       0.80 ± 39%  sched_debug.cfs_rq:/.removed.util_avg.avg
     55.38 ± 22%     -43.2%      31.44 ± 29%  sched_debug.cfs_rq:/.removed.util_avg.max
      8.78 ± 26%     -50.3%       4.37 ± 25%  sched_debug.cfs_rq:/.removed.util_avg.stddev
    101399 ± 22%     +57.1%     159259 ± 18%  sched_debug.cpu.avg_idle.min
    100591 ±  5%     -17.4%      83116 ± 10%  softirqs.CPU1.RCU
     76493 ±  4%      +9.2%      83510        softirqs.CPU21.RCU
     90799 ±  7%     -13.7%      78317 ±  2%  softirqs.CPU3.RCU
      1840 ±100%    +514.5%      11310 ± 66%  softirqs.CPU35.BLOCK
      1305 ± 77%    +681.6%      10206 ± 46%  softirqs.CPU36.BLOCK
      1.00 ±173%  +1.1e+06%      11219 ±137%  softirqs.CPU37.NET_RX
      2968 ±110%    +178.8%       8276 ± 39%  softirqs.CPU40.BLOCK
    143346 ±  2%      -8.4%     131373        softirqs.CPU62.SCHED
     72798 ±  3%     +15.5%      84051 ±  6%  softirqs.CPU69.RCU
     88925 ±  2%     -16.6%      74161 ±  4%  softirqs.CPU73.RCU
     80135 ±  8%     -11.7%      70793 ±  7%  softirqs.CPU79.RCU
    927.50 ± 28%   +1082.2%      10965 ±123%  softirqs.CPU80.BLOCK
      1323 ± 96%    +690.3%      10462 ± 44%  softirqs.CPU83.BLOCK
    524.75 ± 33%    +987.9%       5709 ± 64%  softirqs.CPU85.BLOCK
     80997 ±  7%     -12.3%      71034 ±  2%  softirqs.CPU89.RCU
     78331 ±  6%      -8.3%      71848 ±  5%  softirqs.CPU92.RCU
      0.70 ±  7%      +0.1        0.84 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_get_delayed_node.btrfs_get_or_create_delayed_node.btrfs_delayed_update_inode.btrfs_update_inode.btrfs_dirty_inode
      0.71 ±  6%      +0.1        0.85 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_get_or_create_delayed_node.btrfs_delayed_update_inode.btrfs_update_inode.btrfs_dirty_inode.btrfs_setattr
      0.57 ±  6%      +0.2        0.73 ±  9%  perf-profile.calltrace.cycles-pp.mutex_lock.btrfs_delayed_update_inode.btrfs_update_inode.btrfs_dirty_inode.btrfs_setattr
      1.40 ± 11%      +0.2        1.59 ±  2%  perf-profile.calltrace.cycles-pp.__kmalloc.security_prepare_creds.prepare_creds.do_faccessat.do_syscall_64
      2.10 ± 10%      +0.3        2.40        perf-profile.calltrace.cycles-pp.apparmor_cred_free.security_cred_free.put_cred_rcu.do_faccessat.do_syscall_64
      0.29 ±100%      +0.3        0.60 ±  2%  perf-profile.calltrace.cycles-pp.inode_permission.link_path_walk.path_lookupat.filename_lookup.do_faccessat
      3.04 ± 10%      +0.4        3.42        perf-profile.calltrace.cycles-pp.security_cred_free.put_cred_rcu.do_faccessat.do_syscall_64.entry_SYSCALL_64_after_hwframe
      0.09 ±  4%      +0.0        0.11        perf-profile.children.cycles-pp.__put_cred
      0.11 ±  9%      +0.0        0.14        perf-profile.children.cycles-pp.inode_get_bytes
      0.20 ±  5%      +0.0        0.22 ±  2%  perf-profile.children.cycles-pp.syscall_enter_from_user_mode
      0.27 ±  9%      +0.0        0.31 ±  4%  perf-profile.children.cycles-pp.__check_heap_object
      0.01 ±173%      +0.0        0.06 ±  8%  perf-profile.children.cycles-pp.posix_acl_chmod
      0.30 ±  8%      +0.0        0.34 ±  3%  perf-profile.children.cycles-pp.vfs_getattr
      0.07 ± 62%      +0.0        0.11 ±  8%  perf-profile.children.cycles-pp.calc_global_load_tick
      0.40 ±  9%      +0.1        0.45        perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
      0.00            +0.1        0.05 ±  8%  perf-profile.children.cycles-pp.__fdget_raw
      0.33 ±  4%      +0.1        0.39 ±  5%  perf-profile.children.cycles-pp.__list_del_entry_valid
      0.41 ± 13%      +0.1        0.49 ±  4%  perf-profile.children.cycles-pp.tick_sched_handle
      0.40 ± 14%      +0.1        0.49 ±  3%  perf-profile.children.cycles-pp.update_process_times
      0.72 ±  7%      +0.1        0.85 ±  2%  perf-profile.children.cycles-pp.btrfs_get_or_create_delayed_node
      0.70 ±  7%      +0.1        0.84 ±  2%  perf-profile.children.cycles-pp.btrfs_get_delayed_node
      1.44 ± 10%      +0.2        1.64 ±  2%  perf-profile.children.cycles-pp.__kmalloc
      1.44 ± 11%      +0.2        1.64        perf-profile.children.cycles-pp.inode_permission
      1.76 ± 10%      +0.2        1.97        perf-profile.children.cycles-pp.link_path_walk
      2.10 ± 10%      +0.3        2.41        perf-profile.children.cycles-pp.apparmor_cred_free
      1.52 ±  7%      +0.3        1.84 ±  7%  perf-profile.children.cycles-pp.mutex_lock
      3.04 ± 10%      +0.4        3.42        perf-profile.children.cycles-pp.security_cred_free
      0.08 ±  5%      +0.0        0.10 ±  4%  perf-profile.self.cycles-pp.__put_cred
      0.13 ± 10%      +0.0        0.15 ±  6%  perf-profile.self.cycles-pp.rcu_read_unlock_strict
      0.19 ±  4%      +0.0        0.22 ±  3%  perf-profile.self.cycles-pp.syscall_enter_from_user_mode
      0.26 ±  9%      +0.0        0.30 ±  5%  perf-profile.self.cycles-pp.__check_heap_object
      0.07 ± 62%      +0.0        0.11 ±  8%  perf-profile.self.cycles-pp.calc_global_load_tick
      0.33 ±  6%      +0.1        0.38 ±  3%  perf-profile.self.cycles-pp.generic_permission
      0.32 ±  5%      +0.1        0.39 ±  4%  perf-profile.self.cycles-pp.__list_del_entry_valid
      0.69 ±  7%      +0.1        0.83 ±  2%  perf-profile.self.cycles-pp.btrfs_get_delayed_node
      2.09 ± 10%      +0.3        2.39        perf-profile.self.cycles-pp.apparmor_cred_free
      1.43 ±  7%      +0.3        1.74 ±  7%  perf-profile.self.cycles-pp.mutex_lock
      0.50 ±173%  +4.4e+05%       2190 ±141%  interrupts.43:PCI-MSI.31981576-edge.i40e-eth0-TxRx-7
     46.50 ±158%     -99.3%       0.33 ±141%  interrupts.59:PCI-MSI.31981592-edge.i40e-eth0-TxRx-23
      3.00 ±117%  +7.3e+05%      21877 ±137%  interrupts.73:PCI-MSI.31981606-edge.i40e-eth0-TxRx-37
    417.00 ±170%     -99.9%       0.33 ±141%  interrupts.78:PCI-MSI.31981611-edge.i40e-eth0-TxRx-42
    400.00 ±170%     -99.4%       2.33 ±141%  interrupts.94:PCI-MSI.31981627-edge.i40e-eth0-TxRx-58
     39402 ± 19%     +38.0%      54359 ± 17%  interrupts.CPU0.CAL:Function_call_interrupts
      2079 ±161%     -94.7%     111.00 ± 26%  interrupts.CPU1.NMI:Non-maskable_interrupts
      2079 ±161%     -94.7%     111.00 ± 26%  interrupts.CPU1.PMI:Performance_monitoring_interrupts
     30657 ± 22%     +79.4%      55013 ± 13%  interrupts.CPU1.TLB:TLB_shootdowns
     38766 ± 15%     -16.5%      32388 ± 13%  interrupts.CPU10.CAL:Function_call_interrupts
      2996 ± 24%    +100.4%       6003 ± 32%  interrupts.CPU10.RES:Rescheduling_interrupts
     41076 ± 11%     -19.7%      32991 ± 21%  interrupts.CPU10.TLB:TLB_shootdowns
      5914 ± 13%     -42.2%       3419 ± 11%  interrupts.CPU11.RES:Rescheduling_interrupts
      2082 ±161%     -93.5%     134.67 ±  2%  interrupts.CPU12.NMI:Non-maskable_interrupts
      2082 ±161%     -93.5%     134.67 ±  2%  interrupts.CPU12.PMI:Performance_monitoring_interrupts
     38621 ± 17%     -20.9%      30553 ± 14%  interrupts.CPU13.CAL:Function_call_interrupts
     41286 ± 26%     -31.2%      28408 ±  3%  interrupts.CPU13.TLB:TLB_shootdowns
    158.00 ±  4%     -14.8%     134.67 ±  4%  interrupts.CPU14.NMI:Non-maskable_interrupts
    158.00 ±  4%     -14.8%     134.67 ±  4%  interrupts.CPU14.PMI:Performance_monitoring_interrupts
     29511 ± 32%    +156.3%      75635 ± 48%  interrupts.CPU15.CAL:Function_call_interrupts
     31482 ± 34%    +169.2%      84756 ± 47%  interrupts.CPU15.TLB:TLB_shootdowns
      1610 ±156%     -93.1%     111.33 ± 29%  interrupts.CPU16.NMI:Non-maskable_interrupts
      1610 ±156%     -93.1%     111.33 ± 29%  interrupts.CPU16.PMI:Performance_monitoring_interrupts
      4311 ± 46%    +136.6%      10203 ± 28%  interrupts.CPU16.RES:Rescheduling_interrupts
     30592 ± 14%     +79.6%      54930 ± 12%  interrupts.CPU17.CAL:Function_call_interrupts
     33043 ± 20%     +74.3%      57598 ± 10%  interrupts.CPU17.TLB:TLB_shootdowns
    153.25 ±  4%     -11.7%     135.33 ±  2%  interrupts.CPU18.NMI:Non-maskable_interrupts
    153.25 ±  4%     -11.7%     135.33 ±  2%  interrupts.CPU18.PMI:Performance_monitoring_interrupts
      2083 ±160%     -95.8%      88.33 ± 32%  interrupts.CPU2.NMI:Non-maskable_interrupts
      2083 ±160%     -95.8%      88.33 ± 32%  interrupts.CPU2.PMI:Performance_monitoring_interrupts
      4705 ±  5%     +61.1%       7578 ± 20%  interrupts.CPU2.RES:Rescheduling_interrupts
     28936 ± 18%     +74.1%      50369 ± 14%  interrupts.CPU21.CAL:Function_call_interrupts
     27459 ±  6%     +25.7%      34512 ± 12%  interrupts.CPU22.CAL:Function_call_interrupts
     45.75 ±161%    -100.0%       0.00        interrupts.CPU23.59:PCI-MSI.31981592-edge.i40e-eth0-TxRx-23
      3617 ± 95%     -96.1%     140.00        interrupts.CPU29.NMI:Non-maskable_interrupts
      3617 ± 95%     -96.1%     140.00        interrupts.CPU29.PMI:Performance_monitoring_interrupts
     37715 ± 15%     +90.9%      71983 ±  8%  interrupts.CPU3.CAL:Function_call_interrupts
      2587 ±122%     -95.6%     114.33 ± 28%  interrupts.CPU3.NMI:Non-maskable_interrupts
      2587 ±122%     -95.6%     114.33 ± 28%  interrupts.CPU3.PMI:Performance_monitoring_interrupts
     34590 ± 19%    +135.2%      81364 ±  9%  interrupts.CPU3.TLB:TLB_shootdowns
    156.75 ±  4%     -24.3%     118.67 ± 29%  interrupts.CPU30.NMI:Non-maskable_interrupts
    156.75 ±  4%     -24.3%     118.67 ± 29%  interrupts.CPU30.PMI:Performance_monitoring_interrupts
      7562 ± 21%     -64.7%       2670 ± 27%  interrupts.CPU31.RES:Rescheduling_interrupts
      1656 ±156%     -91.6%     139.00        interrupts.CPU32.NMI:Non-maskable_interrupts
      1656 ±156%     -91.6%     139.00        interrupts.CPU32.PMI:Performance_monitoring_interrupts
      5667 ± 56%     -97.6%     137.67        interrupts.CPU33.NMI:Non-maskable_interrupts
      5667 ± 56%     -97.6%     137.67        interrupts.CPU33.PMI:Performance_monitoring_interrupts
      7325 ± 56%     -55.6%       3254 ± 62%  interrupts.CPU34.RES:Rescheduling_interrupts
     47968 ± 40%     -35.4%      31008 ± 30%  interrupts.CPU35.TLB:TLB_shootdowns
      5151 ± 17%     -43.4%       2914 ± 32%  interrupts.CPU36.RES:Rescheduling_interrupts
      2.25 ±148%  +9.7e+05%      21877 ±137%  interrupts.CPU37.73:PCI-MSI.31981606-edge.i40e-eth0-TxRx-37
     34879 ± 26%     -29.5%      24577 ±  5%  interrupts.CPU38.CAL:Function_call_interrupts
     35800 ± 29%     -30.8%      24771 ±  5%  interrupts.CPU38.TLB:TLB_shootdowns
     55336 ± 29%     -32.9%      37155 ± 18%  interrupts.CPU39.TLB:TLB_shootdowns
      3979 ± 35%     +85.1%       7363 ± 10%  interrupts.CPU41.RES:Rescheduling_interrupts
    416.25 ±170%    -100.0%       0.00        interrupts.CPU42.78:PCI-MSI.31981611-edge.i40e-eth0-TxRx-42
     39832 ± 40%     -37.6%      24870 ±  8%  interrupts.CPU43.CAL:Function_call_interrupts
     45399 ± 40%     -44.6%      25157 ±  8%  interrupts.CPU43.TLB:TLB_shootdowns
     32705 ± 17%     -18.2%      26756 ±  6%  interrupts.CPU45.TLB:TLB_shootdowns
      1106 ±147%     -86.6%     148.33 ±  3%  interrupts.CPU47.NMI:Non-maskable_interrupts
      1106 ±147%     -86.6%     148.33 ±  3%  interrupts.CPU47.PMI:Performance_monitoring_interrupts
     40893 ± 31%     -34.3%      26855 ± 13%  interrupts.CPU47.TLB:TLB_shootdowns
      3222 ± 41%     +83.4%       5908 ± 31%  interrupts.CPU53.RES:Rescheduling_interrupts
     91.25 ± 27%     +45.0%     132.33 ±  5%  interrupts.CPU55.NMI:Non-maskable_interrupts
     91.25 ± 27%     +45.0%     132.33 ±  5%  interrupts.CPU55.PMI:Performance_monitoring_interrupts
      3438 ± 12%     +85.4%       6375 ± 33%  interrupts.CPU55.RES:Rescheduling_interrupts
     90.50 ± 26%     +61.0%     145.67 ±  8%  interrupts.CPU57.NMI:Non-maskable_interrupts
     90.50 ± 26%     +61.0%     145.67 ±  8%  interrupts.CPU57.PMI:Performance_monitoring_interrupts
     40603 ±  7%     -19.7%      32584 ± 10%  interrupts.CPU58.CAL:Function_call_interrupts
      3412 ± 28%     +96.2%       6696 ± 31%  interrupts.CPU58.RES:Rescheduling_interrupts
     45704 ±  6%     -26.4%      33632 ± 12%  interrupts.CPU58.TLB:TLB_shootdowns
      5961 ± 15%     -32.6%       4015 ± 24%  interrupts.CPU59.RES:Rescheduling_interrupts
      3823 ± 96%     -96.3%     143.00 ± 72%  interrupts.CPU6.NMI:Non-maskable_interrupts
      3823 ± 96%     -96.3%     143.00 ± 72%  interrupts.CPU6.PMI:Performance_monitoring_interrupts
      7698 ± 40%     -45.7%       4182 ± 27%  interrupts.CPU63.RES:Rescheduling_interrupts
     34611 ± 20%     +40.9%      48764 ±  8%  interrupts.CPU64.CAL:Function_call_interrupts
      5193 ± 42%     +92.1%       9977 ± 22%  interrupts.CPU64.RES:Rescheduling_interrupts
     33042 ±  8%     +54.5%      51036 ± 14%  interrupts.CPU64.TLB:TLB_shootdowns
     31485 ± 27%     +66.2%      52337 ± 37%  interrupts.CPU65.CAL:Function_call_interrupts
    150.75 ±  4%     -27.3%     109.67 ± 27%  interrupts.CPU66.NMI:Non-maskable_interrupts
    150.75 ±  4%     -27.3%     109.67 ± 27%  interrupts.CPU66.PMI:Performance_monitoring_interrupts
     32638 ± 13%     +49.0%      48628 ± 15%  interrupts.CPU69.CAL:Function_call_interrupts
      0.25 ±173%  +8.8e+05%       2189 ±141%  interrupts.CPU7.43:PCI-MSI.31981576-edge.i40e-eth0-TxRx-7
     31333 ± 11%     +56.0%      48893 ± 23%  interrupts.CPU71.CAL:Function_call_interrupts
     43604 ± 23%     -24.4%      32971 ± 21%  interrupts.CPU75.CAL:Function_call_interrupts
      1794 ± 91%     -92.3%     138.33        interrupts.CPU77.NMI:Non-maskable_interrupts
      1794 ± 91%     -92.3%     138.33        interrupts.CPU77.PMI:Performance_monitoring_interrupts
    160.75 ±  6%     -10.4%     144.00 ±  3%  interrupts.CPU78.NMI:Non-maskable_interrupts
    160.75 ±  6%     -10.4%     144.00 ±  3%  interrupts.CPU78.PMI:Performance_monitoring_interrupts
      7759 ± 20%     -66.7%       2583 ± 15%  interrupts.CPU79.RES:Rescheduling_interrupts
      1272 ±151%     -89.1%     138.33        interrupts.CPU80.NMI:Non-maskable_interrupts
      1272 ±151%     -89.1%     138.33        interrupts.CPU80.PMI:Performance_monitoring_interrupts
      3192 ± 66%     -95.7%     137.67        interrupts.CPU81.NMI:Non-maskable_interrupts
      3192 ± 66%     -95.7%     137.67        interrupts.CPU81.PMI:Performance_monitoring_interrupts
     41009 ± 23%     -25.3%      30627 ± 13%  interrupts.CPU83.CAL:Function_call_interrupts
     42888 ± 26%     -30.9%      29645 ±  2%  interrupts.CPU83.TLB:TLB_shootdowns
      5727 ± 20%     -37.3%       3590 ± 37%  interrupts.CPU84.RES:Rescheduling_interrupts
     39107 ± 25%     -28.9%      27794 ± 14%  interrupts.CPU85.CAL:Function_call_interrupts
      7873 ± 75%     -61.4%       3036 ± 42%  interrupts.CPU85.RES:Rescheduling_interrupts
     43902 ± 32%     -28.6%      31363 ± 11%  interrupts.CPU85.TLB:TLB_shootdowns
     45248 ± 36%     -31.2%      31146 ± 28%  interrupts.CPU86.CAL:Function_call_interrupts
     47668 ± 38%     -26.2%      35171 ± 27%  interrupts.CPU86.TLB:TLB_shootdowns
     41769 ± 23%     -26.9%      30537 ± 23%  interrupts.CPU88.CAL:Function_call_interrupts
    152.50 ±  5%     -25.5%     113.67 ± 28%  interrupts.CPU88.NMI:Non-maskable_interrupts
    152.50 ±  5%     -25.5%     113.67 ± 28%  interrupts.CPU88.PMI:Performance_monitoring_interrupts
     46135 ± 24%     -25.8%      34241 ± 24%  interrupts.CPU88.TLB:TLB_shootdowns
     46305 ± 23%     -38.7%      28402 ±  8%  interrupts.CPU89.CAL:Function_call_interrupts
      4112 ± 26%     +83.9%       7564 ±  6%  interrupts.CPU89.RES:Rescheduling_interrupts
    148.50 ±  9%     -22.6%     115.00 ± 27%  interrupts.CPU9.NMI:Non-maskable_interrupts
    148.50 ±  9%     -22.6%     115.00 ± 27%  interrupts.CPU9.PMI:Performance_monitoring_interrupts
     43780 ± 40%     -34.3%      28764 ±  3%  interrupts.CPU90.CAL:Function_call_interrupts
      4730 ± 45%     -43.5%       2671 ± 27%  interrupts.CPU90.RES:Rescheduling_interrupts
     44682 ± 41%     -31.0%      30833 ±  6%  interrupts.CPU90.TLB:TLB_shootdowns
     48742 ± 20%     -44.3%      27151 ± 11%  interrupts.CPU91.CAL:Function_call_interrupts
     53696 ± 22%     -45.8%      29108 ±  3%  interrupts.CPU91.TLB:TLB_shootdowns
    157.25 ±  5%     -13.1%     136.67        interrupts.CPU92.NMI:Non-maskable_interrupts
    157.25 ±  5%     -13.1%     136.67        interrupts.CPU92.PMI:Performance_monitoring_interrupts
    846.00 ±138%     -81.8%     153.67 ±  3%  interrupts.CPU95.NMI:Non-maskable_interrupts
    846.00 ±138%     -81.8%     153.67 ±  3%  interrupts.CPU95.PMI:Performance_monitoring_interrupts


                                                                                
                              stress-ng.copy-file.ops                           
                                                                                
  3000 +--------------------------------------------------------------------+   
       |                                                                    |   
  2500 |..+.+..+..+    +..+.+..+..+.+..+..+.+..+.+..+..+.+..+..+.+..+       |   
       |          :    :                                                    |   
       |          :    :                                                    |   
  2000 |-+         :  :                                                     |   
       |           :  :                                                     |   
  1500 |-+         :  :                                                     |   
       |           :  :                                                     |   
  1000 |-+         : :                                                      |   
       |           : :                                                      |   
       |            ::                                                      |   
   500 |-+          ::                                                      |   
       |            :                                                       |   
     0 +--------------------------------------------------------------------+   
                                                                                
                                                                                                                                                                
                          stress-ng.copy-file.ops_per_sec                       
                                                                                
  100 +---------------------------------------------------------------------+   
   90 |-+                                                                   |   
      |..+.+..+..+    +..+..+.+..+..+.+..+..+.+..+..+.+..+..+..+.+..+       |   
   80 |-+        :    :                                                     |   
   70 |-+        :    :                                                     |   
      |           :  :                                                      |   
   60 |-+         :  :                                                      |   
   50 |-+         :  :                                                      |   
   40 |-+         :  :                                                      |   
      |           : :                                                       |   
   30 |-+         : :                                                       |   
   20 |-+          ::                                                       |   
      |            ::                                                       |   
   10 |-+          :                                                        |   
    0 +---------------------------------------------------------------------+   
                                                                                
                                                                                
[*] 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-5.10.0-rc7-g639bd575b7c7" of type "text/plain" (171047 bytes)

View attachment "job-script" of type "text/plain" (8268 bytes)

View attachment "job.yaml" of type "text/plain" (5768 bytes)

View attachment "reproduce" of type "text/plain" (587 bytes)

Powered by blists - more mailing lists