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>] [day] [month] [year] [list]
Message-ID: <20220421140849.GA7803@xsang-OptiPlex-9020>
Date:   Thu, 21 Apr 2022 22:08:49 +0800
From:   kernel test robot <oliver.sang@...el.com>
To:     "Darrick J. Wong" <djwong@...nel.org>
Cc:     David Sterba <dsterba@...e.com>, Filipe Manana <fdmanana@...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@...ux.intel.com, fengwei.yin@...el.com,
        linux-btrfs@...r.kernel.org
Subject: [btrfs]  05fd9564e9:  fio.write_iops 29.1% improvement



Greeting,

FYI, we noticed a 29.1% improvement of fio.write_iops due to commit:


commit: 05fd9564e9faf0f23b4676385e27d9405cef6637 ("btrfs: fix fallocate to use file_modified to update permissions consistently")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

in testcase: fio-basic
on test machine: 96 threads 2 sockets Ice Lake with 256G memory
with following parameters:

	runtime: 300s
	disk: 1HDD
	fs: btrfs
	nr_task: 100%
	test_size: 128G
	rw: randwrite
	bs: 4k
	ioengine: ftruncate
	cpufreq_governor: performance
	ucode: 0xb000280

test-description: Fio is a tool that will spawn a number of threads or processes doing a particular type of I/O action as specified by the user.
test-url: https://github.com/axboe/fio

In addition to that, the commit also has significant impact on the following tests:

+------------------+------------------------------------------------+
| testcase: change | fio-basic: fio.write_iops 7.9% improvement     |
| test machine     | 96 threads 2 sockets Ice Lake with 256G memory |
| test parameters  | bs=4k                                          |
|                  | cpufreq_governor=performance                   |
|                  | disk=1HDD                                      |
|                  | fs=btrfs                                       |
|                  | ioengine=ftruncate                             |
|                  | nr_task=100%                                   |
|                  | runtime=300s                                   |
|                  | rw=write                                       |
|                  | test_size=128G                                 |
|                  | ucode=0xb000280                                |
+------------------+------------------------------------------------+




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


To reproduce:

        git clone https://github.com/intel/lkp-tests.git
        cd lkp-tests
        sudo bin/lkp install job.yaml           # job file is attached in this email
        bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
        sudo bin/lkp run generated-yaml-file

        # if come across any failure that blocks the test,
        # please remove ~/.lkp and /lkp dir to run from a clean state.

=========================================================================================
bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/ucode:
  4k/gcc-11/performance/1HDD/btrfs/ftruncate/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/300s/randwrite/lkp-icl-2sp1/128G/fio-basic/0xb000280

commit: 
  bbac58698a ("btrfs: remove device item and update super block in the same transaction")
  05fd9564e9 ("btrfs: fix fallocate to use file_modified to update permissions consistently")

bbac58698a55cc0a 05fd9564e9faf0f23b4676385e2 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
     25.40           -15.6        9.83        fio.latency_1000us%
      8.90 ±  2%      +9.8       18.66        fio.latency_10us%
     10.14            +3.7       13.86 ±  2%  fio.latency_20us%
      0.31 ± 18%      +0.3        0.65 ± 17%  fio.latency_250us%
     31.58            -4.2       27.37        fio.latency_2ms%
      0.26 ± 49%      +2.0        2.28 ± 12%  fio.latency_4us%
      4.22 ±  2%      -1.8        2.44 ±  2%  fio.latency_500us%
      1.38 ±  6%      +0.3        1.72 ±  4%  fio.latency_50us%
     16.74            +5.3       22.04        fio.latency_750us%
    273.42           -22.5%     211.92        fio.time.elapsed_time
    273.42           -22.5%     211.92        fio.time.elapsed_time.max
      4138           -26.1%       3056 ±  2%  fio.time.involuntary_context_switches
     40335           -18.9%      32724        fio.time.minor_page_faults
    945.17           -11.5%     836.83        fio.time.percent_of_cpu_this_job_got
      2554           -31.7%       1745        fio.time.system_time
 1.047e+08           -31.5%   71777844        fio.time.voluntary_context_switches
    480.12           +29.1%     619.64        fio.write_bw_MBps
   1316181            -6.0%    1236992        fio.write_clat_90%_us
   1381717            -5.9%    1299797        fio.write_clat_95%_us
    775018           -22.9%     597761        fio.write_clat_mean_us
    122910           +29.1%     158627        fio.write_iops
  2.35e+10           -21.3%  1.849e+10        cpuidle..time
 1.495e+08           -28.5%  1.069e+08        cpuidle..usage
     89.86            +1.3%      91.00        iostat.cpu.idle
      9.99           -11.7%       8.81        iostat.cpu.system
     88619 ± 10%     -37.1%      55734 ± 19%  numa-meminfo.node1.Active
     87580 ± 11%     -37.3%      54905 ± 20%  numa-meminfo.node1.Active(anon)
     22986 ± 10%     -37.5%      14363 ± 20%  numa-vmstat.node1.nr_active_anon
     22985 ± 10%     -37.5%      14363 ± 20%  numa-vmstat.node1.nr_zone_active_anon
    323.17           -19.6%     259.85        uptime.boot
     27716           -18.8%      22505        uptime.idle
    267.33 ±  2%     +18.9%     317.83 ±  2%  vmstat.io.bo
    758980           -11.9%     668586        vmstat.system.cs
      2412 ± 13%     -21.1%       1902 ± 15%  meminfo.Active(file)
     16496 ±  7%      -9.0%      15016 ±  8%  meminfo.Inactive(file)
   5772819 ±  5%     -13.3%    5004460 ±  2%  meminfo.max_used_kB
      0.01 ±  4%      +0.0        0.01 ±  2%  mpstat.cpu.all.iowait%
      9.36            -1.2        8.19        mpstat.cpu.all.sys%
      0.15 ±  5%      +0.0        0.18 ±  4%  mpstat.cpu.all.usr%
    377.33           -10.4%     338.17        turbostat.Avg_MHz
     11.81            -1.2       10.60        turbostat.Busy%
    812801 ±  5%     -20.5%     645955 ±  8%  turbostat.C1
      0.03            +0.0        0.04        turbostat.C1%
 1.482e+08           -28.7%  1.056e+08        turbostat.C1E
      0.08           +12.5%       0.09        turbostat.IPC
  56260225           -22.1%   43803622        turbostat.IRQ
    224180 ±  2%     -29.8%     157291 ±  4%  turbostat.POLL
      0.05            -0.0        0.04        turbostat.POLL%
    207.52            +2.3%     212.24        turbostat.RAMWatt
    602.83 ± 13%     -21.5%     473.00 ± 16%  proc-vmstat.nr_active_file
     73967            +2.2%      75587        proc-vmstat.nr_anon_pages
     17830 ±  2%     -12.4%      15614 ±  2%  proc-vmstat.nr_dirtied
      4124 ±  7%      -9.0%       3755 ±  8%  proc-vmstat.nr_inactive_file
      3177            +2.7%       3264        proc-vmstat.nr_page_table_pages
     16914            -9.8%      15258        proc-vmstat.nr_written
    602.83 ± 13%     -21.5%     473.00 ± 16%  proc-vmstat.nr_zone_active_file
      4124 ±  7%      -9.0%       3755 ±  8%  proc-vmstat.nr_zone_inactive_file
   1309619 ±  4%     -18.8%    1063146 ±  4%  proc-vmstat.pgfault
     74094 ±  2%      -7.5%      68521 ±  2%  proc-vmstat.pgpgout
     60814           -19.9%      48741        proc-vmstat.pgreuse
    121.03 ± 11%     -18.8%      98.28 ±  4%  sched_debug.cfs_rq:/.load_avg.avg
     24831 ±  9%     -18.9%      20137 ±  7%  sched_debug.cfs_rq:/.min_vruntime.avg
     19950 ± 10%     -21.8%      15604 ± 12%  sched_debug.cfs_rq:/.min_vruntime.min
    168.83 ± 44%     +76.0%     297.08 ± 32%  sched_debug.cfs_rq:/.removed.load_avg.max
     71.63 ± 48%    +103.5%     145.79 ± 28%  sched_debug.cfs_rq:/.removed.runnable_avg.max
      9.02 ± 50%    +108.9%      18.85 ± 20%  sched_debug.cfs_rq:/.removed.runnable_avg.stddev
     71.63 ± 48%    +103.5%     145.79 ± 28%  sched_debug.cfs_rq:/.removed.util_avg.max
      9.02 ± 50%    +109.0%      18.85 ± 20%  sched_debug.cfs_rq:/.removed.util_avg.stddev
    413.63 ±  9%     +22.4%     506.33 ±  7%  sched_debug.cfs_rq:/.util_est_enqueued.max
    311854           +14.3%     356298        sched_debug.cpu.avg_idle.avg
     91093 ± 12%     +22.8%     111829 ± 13%  sched_debug.cpu.avg_idle.stddev
    169164           -18.9%     137248        sched_debug.cpu.clock.avg
    169169           -18.9%     137252        sched_debug.cpu.clock.max
    169159           -18.9%     137244        sched_debug.cpu.clock.min
    168298           -18.8%     136600        sched_debug.cpu.clock_task.avg
    168393           -18.8%     136672        sched_debug.cpu.clock_task.max
    166762           -19.0%     135130        sched_debug.cpu.clock_task.min
      8765            -9.3%       7953        sched_debug.cpu.curr->pid.max
    969306           -32.0%     659576        sched_debug.cpu.nr_switches.avg
   1003541           -31.3%     689574        sched_debug.cpu.nr_switches.max
    948867           -31.6%     648806        sched_debug.cpu.nr_switches.min
      7270 ±  8%     -23.7%       5544 ±  5%  sched_debug.cpu.nr_switches.stddev
    169160           -18.9%     137244        sched_debug.cpu_clk
    167991           -19.0%     136075        sched_debug.ktime
    172942           -18.4%     141106        sched_debug.sched_clk
 1.741e+09            +3.4%  1.801e+09        perf-stat.i.branch-instructions
  45218969            +5.2%   47575740        perf-stat.i.cache-misses
    767180           -11.6%     678333        perf-stat.i.context-switches
      4.35           -14.6%       3.72        perf-stat.i.cpi
 3.751e+10           -10.6%  3.354e+10        perf-stat.i.cpu-cycles
      2068           -14.7%       1764        perf-stat.i.cpu-migrations
    832.32           -14.3%     713.62 ±  2%  perf-stat.i.cycles-between-cache-misses
 2.387e+09            +4.7%    2.5e+09        perf-stat.i.dTLB-loads
 1.266e+09            +6.4%  1.347e+09        perf-stat.i.dTLB-stores
   8.7e+09            +4.5%  9.089e+09        perf-stat.i.instructions
      0.24           +16.3%       0.28 ±  2%  perf-stat.i.ipc
     18.80           +28.8%      24.21        perf-stat.i.major-faults
      0.39           -10.6%       0.35        perf-stat.i.metric.GHz
     57.59            +4.6%      60.27        perf-stat.i.metric.M/sec
    311721 ±  2%      +7.1%     333874 ±  2%  perf-stat.i.node-loads
     55.73            +0.8       56.48        perf-stat.i.node-store-miss-rate%
   6403206            +3.5%    6629367        perf-stat.i.node-store-misses
      4.31           -14.4%       3.69        perf-stat.overall.cpi
    829.44           -15.0%     705.03        perf-stat.overall.cycles-between-cache-misses
      0.23           +16.8%       0.27        perf-stat.overall.ipc
     55.77            +1.0       56.78        perf-stat.overall.node-store-miss-rate%
     70909           -19.0%      57442        perf-stat.overall.path-length
  45052177            +5.1%   47349517        perf-stat.ps.cache-misses
    764317           -11.7%     675094        perf-stat.ps.context-switches
 3.737e+10           -10.7%  3.338e+10        perf-stat.ps.cpu-cycles
      2062           -14.8%       1757        perf-stat.ps.cpu-migrations
 2.378e+09            +4.6%  2.488e+09        perf-stat.ps.dTLB-loads
 1.261e+09            +6.2%   1.34e+09        perf-stat.ps.dTLB-stores
 8.669e+09            +4.4%  9.047e+09        perf-stat.ps.instructions
     18.69           +28.7%      24.05        perf-stat.ps.major-faults
    310664 ±  2%      +7.0%     332362 ±  2%  perf-stat.ps.node-loads
   6379550            +3.4%    6597795        perf-stat.ps.node-store-misses
 2.379e+12           -19.0%  1.927e+12        perf-stat.total.instructions
     17.99            -7.7       10.32 ±  3%  perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot
     17.52            -7.7        9.87        perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node
     21.08            -7.6       13.50 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_truncate_inode_items.btrfs_truncate.btrfs_setsize.btrfs_setattr
     24.06            -7.4       16.68        perf-profile.calltrace.cycles-pp.btrfs_truncate_inode_items.btrfs_truncate.btrfs_setsize.btrfs_setattr.notify_change
     25.62            -6.9       18.74        perf-profile.calltrace.cycles-pp.btrfs_truncate.btrfs_setsize.btrfs_setattr.notify_change.do_truncate
      5.82            -4.8        1.04 ±  2%  perf-profile.calltrace.cycles-pp.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_get_extent
      5.92            -4.7        1.18 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_cont_expand
      5.64 ±  2%      -4.7        0.95 ±  2%  perf-profile.calltrace.cycles-pp.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items.btrfs_truncate
      5.76 ±  2%      -4.7        1.10 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items.btrfs_truncate.btrfs_setsize
      5.45 ±  2%      -4.6        0.87        perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items
      7.06            -4.1        2.93 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_cont_expand.btrfs_setsize
      7.07            -4.1        2.94 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_cont_expand.btrfs_setsize.btrfs_setattr
      7.78            -3.9        3.92        perf-profile.calltrace.cycles-pp.btrfs_get_extent.btrfs_cont_expand.btrfs_setsize.btrfs_setattr.notify_change
     14.06 ±  2%      -3.2       10.84 ±  3%  perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items
     14.27            -3.2       11.08 ±  3%  perf-profile.calltrace.cycles-pp.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items.btrfs_truncate
     14.32            -3.2       11.13 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_truncate_inode_items.btrfs_truncate.btrfs_setsize
     10.18            -2.5        7.70        perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent
     77.45            -0.8       76.70        perf-profile.calltrace.cycles-pp.do_truncate.do_sys_ftruncate.do_syscall_64.entry_SYSCALL_64_after_hwframe.ftruncate64
     77.55            -0.7       76.84        perf-profile.calltrace.cycles-pp.do_sys_ftruncate.do_syscall_64.entry_SYSCALL_64_after_hwframe.ftruncate64
     77.62            -0.7       76.92        perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.ftruncate64
     77.65            -0.7       76.96        perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.ftruncate64
     77.96            -0.7       77.28        perf-profile.calltrace.cycles-pp.ftruncate64
      1.38 ±  2%      -0.1        1.26 ±  2%  perf-profile.calltrace.cycles-pp.try_to_wake_up.wake_up_q.rwsem_wake.btrfs_release_path.btrfs_free_path
      1.42 ±  2%      -0.1        1.30 ±  2%  perf-profile.calltrace.cycles-pp.wake_up_q.rwsem_wake.btrfs_release_path.btrfs_free_path.btrfs_truncate_inode_items
      0.65            -0.1        0.56 ±  3%  perf-profile.calltrace.cycles-pp.rwsem_spin_on_owner.rwsem_optimistic_spin.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node
      0.72 ±  5%      +0.1        0.85 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_del_items.btrfs_truncate_inode_items.btrfs_truncate.btrfs_setsize.btrfs_setattr
      0.60 ±  4%      +0.2        0.79 ±  3%  perf-profile.calltrace.cycles-pp.try_to_wake_up.wake_up_q.rwsem_wake.btrfs_unlock_up_safe.btrfs_search_slot
      0.64 ±  3%      +0.2        0.83 ±  3%  perf-profile.calltrace.cycles-pp.wake_up_q.rwsem_wake.btrfs_unlock_up_safe.btrfs_search_slot.btrfs_insert_empty_items
      0.78 ±  6%      +0.3        1.04 ±  3%  perf-profile.calltrace.cycles-pp.memmove.memcpy_extent_buffer.setup_items_for_insert.btrfs_insert_empty_items.btrfs_insert_file_extent
      0.84 ±  6%      +0.3        1.11 ±  3%  perf-profile.calltrace.cycles-pp.memcpy_extent_buffer.setup_items_for_insert.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole
      0.86 ±  2%      +0.3        1.20 ±  2%  perf-profile.calltrace.cycles-pp.rwsem_wake.btrfs_unlock_up_safe.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent
      0.89 ±  2%      +0.4        1.25 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_unlock_up_safe.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole
      0.60 ±  2%      +0.5        1.08 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_dirty_inode.btrfs_setattr.notify_change.do_truncate.do_sys_ftruncate
      0.00            +0.5        0.53 ±  2%  perf-profile.calltrace.cycles-pp.schedule.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot
      1.72 ±  4%      +0.6        2.27 ±  2%  perf-profile.calltrace.cycles-pp.setup_items_for_insert.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole.btrfs_cont_expand
      0.00            +0.6        0.58 ±  5%  perf-profile.calltrace.cycles-pp.btrfs_update_inode.btrfs_dirty_inode.btrfs_setattr.notify_change.do_truncate
      0.00            +0.6        0.58 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_update_inode.btrfs_truncate.btrfs_setsize.btrfs_setattr.notify_change
      0.00            +0.6        0.63 ±  4%  perf-profile.calltrace.cycles-pp.btrfs_get_token_32.setup_items_for_insert.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole
      0.00            +0.6        0.64 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_update_inode.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize.btrfs_setattr
      3.76 ±  2%      +1.3        5.05 ±  2%  perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items
      3.97 ±  2%      +1.4        5.33 ±  2%  perf-profile.calltrace.cycles-pp.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent
      4.08 ±  2%      +1.4        5.48 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole
     15.51            +1.7       17.20        perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node
     16.02            +1.8       17.78        perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot
     16.67 ±  4%      +2.0       18.63 ±  6%  perf-profile.calltrace.cycles-pp.osq_lock.rwsem_optimistic_spin.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node
     18.16 ±  4%      +2.0       20.18 ±  5%  perf-profile.calltrace.cycles-pp.rwsem_optimistic_spin.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot
      4.81            +2.2        7.04        perf-profile.calltrace.cycles-pp.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_drop_extents
      4.94            +2.3        7.19        perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_drop_extents.maybe_insert_hole
      6.10            +2.8        8.88        perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.btrfs_drop_extents.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize
      6.10            +2.8        8.87        perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_drop_extents.maybe_insert_hole.btrfs_cont_expand
      6.77            +3.1        9.83        perf-profile.calltrace.cycles-pp.btrfs_drop_extents.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize.btrfs_setattr
     72.02            +3.4       75.44        perf-profile.calltrace.cycles-pp.btrfs_setsize.btrfs_setattr.notify_change.do_truncate.do_sys_ftruncate
     72.68            +3.9       76.59        perf-profile.calltrace.cycles-pp.btrfs_setattr.notify_change.do_truncate.do_sys_ftruncate.do_syscall_64
     72.73            +3.9       76.65        perf-profile.calltrace.cycles-pp.notify_change.do_truncate.do_sys_ftruncate.do_syscall_64.entry_SYSCALL_64_after_hwframe
     21.66 ±  2%      +7.2       28.82        perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items
     21.82 ±  2%      +7.2       29.02        perf-profile.calltrace.cycles-pp.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent
     21.85 ±  2%      +7.2       29.07        perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole
     27.72            +9.3       37.02        perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole.btrfs_cont_expand
     45.73            +9.8       55.52        perf-profile.calltrace.cycles-pp.btrfs_cont_expand.btrfs_setsize.btrfs_setattr.notify_change.do_truncate
     29.50            +9.9       39.35        perf-profile.calltrace.cycles-pp.btrfs_insert_empty_items.btrfs_insert_file_extent.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize
     29.74            +9.9       39.68        perf-profile.calltrace.cycles-pp.btrfs_insert_file_extent.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize.btrfs_setattr
     37.52           +13.5       51.04        perf-profile.calltrace.cycles-pp.maybe_insert_hole.btrfs_cont_expand.btrfs_setsize.btrfs_setattr.notify_change
     24.06            -7.4       16.69        perf-profile.children.cycles-pp.btrfs_truncate_inode_items
     22.86            -7.3       15.52        perf-profile.children.cycles-pp.btrfs_read_lock_root_node
     22.36            -7.3       15.03 ±  2%  perf-profile.children.cycles-pp.__btrfs_tree_read_lock
     21.28            -7.1       14.20        perf-profile.children.cycles-pp.rwsem_down_read_slowpath
     25.62            -6.9       18.74        perf-profile.children.cycles-pp.btrfs_truncate
     34.34            -4.9       29.40        perf-profile.children.cycles-pp._raw_spin_lock_irq
     33.85            -4.5       29.35        perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
      7.78            -3.9        3.92        perf-profile.children.cycles-pp.btrfs_get_extent
     66.61            -3.6       63.03        perf-profile.children.cycles-pp.btrfs_search_slot
     13.18            -1.4       11.82        perf-profile.children.cycles-pp.btrfs_lookup_file_extent
     77.46            -0.8       76.70        perf-profile.children.cycles-pp.do_truncate
     77.56            -0.7       76.84        perf-profile.children.cycles-pp.do_sys_ftruncate
     77.85            -0.7       77.18        perf-profile.children.cycles-pp.do_syscall_64
     77.88            -0.7       77.22        perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
      1.36            -0.3        1.09 ±  2%  perf-profile.children.cycles-pp.generic_bin_search
      1.03 ±  3%      -0.2        0.79 ±  4%  perf-profile.children.cycles-pp.down_read
      1.63 ±  2%      -0.2        1.40 ±  3%  perf-profile.children.cycles-pp.read_block_for_search
      2.55 ±  2%      -0.2        2.32        perf-profile.children.cycles-pp.btrfs_free_path
      0.99 ±  3%      -0.2        0.80 ±  2%  perf-profile.children.cycles-pp.up_read
      0.61 ±  3%      -0.1        0.48 ±  3%  perf-profile.children.cycles-pp.btrfs_get_64
      0.50            -0.0        0.47 ±  4%  perf-profile.children.cycles-pp.flush_smp_call_function_queue
      0.05 ±  8%      +0.0        0.07 ± 13%  perf-profile.children.cycles-pp.syscall_exit_to_user_mode
      0.06 ± 11%      +0.0        0.08 ±  4%  perf-profile.children.cycles-pp.btrfs_leaf_free_space
      0.10 ±  6%      +0.0        0.12 ±  7%  perf-profile.children.cycles-pp.__lookup_extent_mapping
      0.08 ± 10%      +0.0        0.10 ±  7%  perf-profile.children.cycles-pp.leaf_space_used
      0.07 ±  8%      +0.0        0.09 ±  5%  perf-profile.children.cycles-pp.td_io_queue
      0.08 ±  6%      +0.0        0.10 ±  8%  perf-profile.children.cycles-pp.fill_stack_inode_item
      0.08 ± 11%      +0.0        0.10 ± 10%  perf-profile.children.cycles-pp.btrfs_block_rsv_migrate
      0.07 ±  8%      +0.0        0.10 ±  4%  perf-profile.children.cycles-pp.btrfs_get_delayed_node
      0.04 ± 45%      +0.0        0.07 ±  5%  perf-profile.children.cycles-pp.ktime_get_real_ts64
      0.08 ±  8%      +0.0        0.11 ±  8%  perf-profile.children.cycles-pp.btrfs_get_or_create_delayed_node
      0.17 ± 12%      +0.0        0.20 ±  6%  perf-profile.children.cycles-pp.set_extent_bit
      0.12 ±  6%      +0.0        0.15 ±  4%  perf-profile.children.cycles-pp.btrfs_get_32
      0.17 ±  5%      +0.0        0.20 ±  2%  perf-profile.children.cycles-pp.__might_resched
      0.07 ± 10%      +0.0        0.10 ±  3%  perf-profile.children.cycles-pp.free_extent_map
      0.10 ± 13%      +0.0        0.14 ± 11%  perf-profile.children.cycles-pp.clear_extent_bit
      0.10 ±  5%      +0.0        0.13 ±  6%  perf-profile.children.cycles-pp.up_write
      0.10 ±  7%      +0.0        0.14 ±  8%  perf-profile.children.cycles-pp.alloc_extent_state
      0.19 ±  9%      +0.0        0.23 ±  4%  perf-profile.children.cycles-pp.scheduler_tick
      0.08 ±  7%      +0.0        0.12 ±  7%  perf-profile.children.cycles-pp.fio_gettime
      0.02 ±141%      +0.0        0.06 ±  9%  perf-profile.children.cycles-pp.rcu_all_qs
      0.24 ±  5%      +0.0        0.27 ±  3%  perf-profile.children.cycles-pp.check_setget_bounds
      0.12 ± 10%      +0.0        0.16 ±  8%  perf-profile.children.cycles-pp.btrfs_inode_clear_file_extent_range
      0.01 ±223%      +0.0        0.06 ±  9%  perf-profile.children.cycles-pp._raw_write_lock
      0.38 ±  4%      +0.0        0.43 ±  7%  perf-profile.children.cycles-pp.update_process_times
      0.13 ±  6%      +0.0        0.18 ±  6%  perf-profile.children.cycles-pp.btrfs_mark_buffer_dirty
      0.18 ±  3%      +0.1        0.24 ±  4%  perf-profile.children.cycles-pp.alloc_extent_map
      0.34 ±  7%      +0.1        0.40 ±  5%  perf-profile.children.cycles-pp.memmove_extent_buffer
      0.18 ±  7%      +0.1        0.24 ±  6%  perf-profile.children.cycles-pp.__reserve_bytes
      0.20 ±  8%      +0.1        0.26 ±  6%  perf-profile.children.cycles-pp.kmem_cache_free
      0.44 ±  2%      +0.1        0.52 ±  3%  perf-profile.children.cycles-pp.down_write
      0.23 ±  6%      +0.1        0.31 ±  6%  perf-profile.children.cycles-pp.btrfs_reserve_metadata_bytes
      0.06 ± 11%      +0.1        0.14 ±  6%  perf-profile.children.cycles-pp.btrfs_put_transaction
      0.25 ±  6%      +0.1        0.34 ±  3%  perf-profile.children.cycles-pp.wake_q_add
      0.24 ± 14%      +0.1        0.33 ±  6%  perf-profile.children.cycles-pp.__clear_extent_bit
      0.24 ±  7%      +0.1        0.33 ±  2%  perf-profile.children.cycles-pp.btrfs_set_token_32
      0.18 ±  5%      +0.1        0.27 ±  4%  perf-profile.children.cycles-pp.wait_current_trans
      0.19 ±  3%      +0.1        0.29 ±  6%  perf-profile.children.cycles-pp.mutex_lock
      0.99            +0.1        1.10 ±  2%  perf-profile.children.cycles-pp.rwsem_spin_on_owner
      0.20 ±  7%      +0.1        0.31 ±  4%  perf-profile.children.cycles-pp.btrfs_update_root_times
      0.47 ±  3%      +0.1        0.58 ±  3%  perf-profile.children.cycles-pp.kmem_cache_alloc
      0.45 ±  3%      +0.1        0.57 ±  4%  perf-profile.children.cycles-pp.btrfs_drop_extent_cache
      2.68 ±  3%      +0.1        2.82        perf-profile.children.cycles-pp.wake_up_q
      0.73 ±  5%      +0.1        0.87 ±  2%  perf-profile.children.cycles-pp.btrfs_del_items
      0.38 ±  5%      +0.2        0.53 ±  3%  perf-profile.children.cycles-pp.btrfs_block_rsv_add
      0.70 ±  3%      +0.2        0.87 ±  3%  perf-profile.children.cycles-pp.btrfs_get_token_32
      0.30 ±  7%      +0.2        0.49 ±  5%  perf-profile.children.cycles-pp.join_transaction
      0.32 ±  7%      +0.2        0.52 ±  9%  perf-profile.children.cycles-pp.mutex_unlock
      0.61 ±  2%      +0.2        0.83 ±  3%  perf-profile.children.cycles-pp._raw_spin_lock_irqsave
      0.24 ±  6%      +0.2        0.46 ±  3%  perf-profile.children.cycles-pp.btrfs_trans_release_metadata
      0.25 ±  6%      +0.2        0.48 ±  2%  perf-profile.children.cycles-pp.btrfs_block_rsv_release
      0.51 ± 17%      +0.3        0.79 ± 12%  perf-profile.children.cycles-pp.btrfs_next_old_leaf
      3.24 ±  2%      +0.3        3.54        perf-profile.children.cycles-pp.rwsem_wake
      0.94 ±  6%      +0.3        1.25 ±  3%  perf-profile.children.cycles-pp.memcpy_extent_buffer
      1.18 ±  6%      +0.3        1.52 ±  3%  perf-profile.children.cycles-pp.memmove
      0.90 ±  2%      +0.4        1.25 ±  2%  perf-profile.children.cycles-pp.btrfs_unlock_up_safe
      0.51 ±  4%      +0.4        0.95 ±  2%  perf-profile.children.cycles-pp.__btrfs_end_transaction
      0.70 ±  2%      +0.4        1.14 ±  3%  perf-profile.children.cycles-pp.__btrfs_release_delayed_node
      0.60 ±  2%      +0.5        1.08 ±  3%  perf-profile.children.cycles-pp.btrfs_dirty_inode
      1.16 ±  3%      +0.6        1.71 ±  3%  perf-profile.children.cycles-pp.start_transaction
      1.75 ±  4%      +0.6        2.32 ±  2%  perf-profile.children.cycles-pp.setup_items_for_insert
      1.04 ±  2%      +0.6        1.65 ±  2%  perf-profile.children.cycles-pp.btrfs_delayed_update_inode
      2.03 ±  2%      +0.7        2.77        perf-profile.children.cycles-pp._raw_spin_lock
      1.35 ±  2%      +0.8        2.14 ±  3%  perf-profile.children.cycles-pp.btrfs_update_inode
     16.68 ±  4%      +2.0       18.64 ±  6%  perf-profile.children.cycles-pp.osq_lock
     18.28 ±  4%      +2.1       20.38 ±  5%  perf-profile.children.cycles-pp.rwsem_optimistic_spin
      6.78            +3.1        9.83        perf-profile.children.cycles-pp.btrfs_drop_extents
     72.03            +3.4       75.45        perf-profile.children.cycles-pp.btrfs_setsize
     72.68            +3.9       76.60        perf-profile.children.cycles-pp.btrfs_setattr
     72.73            +3.9       76.65        perf-profile.children.cycles-pp.notify_change
     35.84 ±  2%      +4.0       39.86 ±  2%  perf-profile.children.cycles-pp.rwsem_down_write_slowpath
     36.17 ±  2%      +4.0       40.20 ±  2%  perf-profile.children.cycles-pp.btrfs_lock_root_node
     36.26 ±  2%      +4.1       40.36 ±  2%  perf-profile.children.cycles-pp.__btrfs_tree_lock
     45.74            +9.8       55.53        perf-profile.children.cycles-pp.btrfs_cont_expand
     29.50            +9.9       39.35        perf-profile.children.cycles-pp.btrfs_insert_empty_items
     29.74            +9.9       39.69        perf-profile.children.cycles-pp.btrfs_insert_file_extent
     37.52           +13.5       51.04        perf-profile.children.cycles-pp.maybe_insert_hole
     33.84            -4.5       29.34        perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
      1.35            -0.3        1.08 ±  2%  perf-profile.self.cycles-pp.generic_bin_search
      0.98 ±  3%      -0.2        0.74 ±  3%  perf-profile.self.cycles-pp.down_read
      1.28 ±  2%      -0.2        1.06 ±  2%  perf-profile.self.cycles-pp.rwsem_down_read_slowpath
      0.98 ±  3%      -0.2        0.80 ±  2%  perf-profile.self.cycles-pp.up_read
      0.51 ±  4%      -0.1        0.39 ±  4%  perf-profile.self.cycles-pp.btrfs_get_64
      1.66            -0.1        1.55 ±  2%  perf-profile.self.cycles-pp.btrfs_search_slot
      0.45 ±  6%      -0.0        0.41 ±  3%  perf-profile.self.cycles-pp.find_extent_buffer_nolock
      0.16 ±  5%      -0.0        0.14 ±  3%  perf-profile.self.cycles-pp.read_block_for_search
      0.05 ±  7%      +0.0        0.07 ±  8%  perf-profile.self.cycles-pp.btrfs_drop_extent_cache
      0.09 ±  7%      +0.0        0.12 ±  4%  perf-profile.self.cycles-pp.memset_erms
      0.06 ± 14%      +0.0        0.09 ±  8%  perf-profile.self.cycles-pp.td_io_queue
      0.09 ±  6%      +0.0        0.11 ±  6%  perf-profile.self.cycles-pp.setup_items_for_insert
      0.04 ± 44%      +0.0        0.06 ±  7%  perf-profile.self.cycles-pp.btrfs_reserve_metadata_bytes
      0.06 ± 11%      +0.0        0.09 ±  6%  perf-profile.self.cycles-pp.get_io_u
      0.10 ±  7%      +0.0        0.13 ±  6%  perf-profile.self.cycles-pp.btrfs_get_32
      0.07 ±  7%      +0.0        0.09 ±  5%  perf-profile.self.cycles-pp.free_extent_map
      0.07 ± 10%      +0.0        0.10 ±  4%  perf-profile.self.cycles-pp.btrfs_get_delayed_node
      0.10 ±  5%      +0.0        0.12 ±  8%  perf-profile.self.cycles-pp.up_write
      0.04 ± 71%      +0.0        0.07 ± 11%  perf-profile.self.cycles-pp.__cond_resched
      0.16 ±  6%      +0.0        0.19        perf-profile.self.cycles-pp.__might_resched
      0.08 ±  8%      +0.0        0.11 ±  8%  perf-profile.self.cycles-pp.fio_gettime
      0.07 ±  6%      +0.0        0.11 ±  5%  perf-profile.self.cycles-pp.__btrfs_release_delayed_node
      0.04 ± 71%      +0.0        0.08 ±  9%  perf-profile.self.cycles-pp.btrfs_drop_extents
      0.13 ±  8%      +0.0        0.17 ±  2%  perf-profile.self.cycles-pp.wake_up_q
      0.13 ± 11%      +0.0        0.17 ±  7%  perf-profile.self.cycles-pp.kmem_cache_free
      0.06 ±  8%      +0.0        0.10 ±  5%  perf-profile.self.cycles-pp.btrfs_block_rsv_release
      0.22 ±  2%      +0.1        0.27 ±  7%  perf-profile.self.cycles-pp.kmem_cache_alloc
      0.00            +0.1        0.05 ±  8%  perf-profile.self.cycles-pp.btrfs_del_items
      0.51 ±  4%      +0.1        0.57 ±  3%  perf-profile.self.cycles-pp.cpuidle_enter_state
      0.18 ±  5%      +0.1        0.25 ±  3%  perf-profile.self.cycles-pp.btrfs_set_token_32
      0.37 ±  4%      +0.1        0.44 ±  3%  perf-profile.self.cycles-pp.down_write
      0.33 ±  3%      +0.1        0.40 ±  6%  perf-profile.self.cycles-pp._raw_spin_lock_irqsave
      0.08 ±  8%      +0.1        0.16 ±  7%  perf-profile.self.cycles-pp.btrfs_update_inode
      0.06 ± 11%      +0.1        0.14 ±  7%  perf-profile.self.cycles-pp.btrfs_put_transaction
      0.18 ±  4%      +0.1        0.26 ±  2%  perf-profile.self.cycles-pp.start_transaction
      0.14 ±  3%      +0.1        0.23 ±  9%  perf-profile.self.cycles-pp.mutex_lock
      0.25 ±  7%      +0.1        0.33 ±  3%  perf-profile.self.cycles-pp.wake_q_add
      0.97            +0.1        1.07 ±  2%  perf-profile.self.cycles-pp.rwsem_spin_on_owner
      0.19 ±  9%      +0.1        0.30 ±  5%  perf-profile.self.cycles-pp.join_transaction
      0.17 ±  7%      +0.1        0.29 ±  5%  perf-profile.self.cycles-pp.__btrfs_end_transaction
      0.62 ±  4%      +0.1        0.76 ±  3%  perf-profile.self.cycles-pp.btrfs_get_token_32
      0.31 ±  7%      +0.2        0.52 ±  9%  perf-profile.self.cycles-pp.mutex_unlock
      1.17 ±  6%      +0.3        1.51 ±  3%  perf-profile.self.cycles-pp.memmove
      1.74 ±  2%      +0.5        2.22        perf-profile.self.cycles-pp._raw_spin_lock
     16.62 ±  4%      +2.0       18.57 ±  6%  perf-profile.self.cycles-pp.osq_lock


***************************************************************************************************
lkp-icl-2sp1: 96 threads 2 sockets Ice Lake with 256G memory
=========================================================================================
bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/ucode:
  4k/gcc-11/performance/1HDD/btrfs/ftruncate/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/300s/write/lkp-icl-2sp1/128G/fio-basic/0xb000280

commit: 
  bbac58698a ("btrfs: remove device item and update super block in the same transaction")
  05fd9564e9 ("btrfs: fix fallocate to use file_modified to update permissions consistently")

bbac58698a55cc0a 05fd9564e9faf0f23b4676385e2 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      1.56 ±  8%      -0.6        0.97 ± 20%  fio.latency_1000us%
      0.48 ± 25%      -0.2        0.28 ±  9%  fio.latency_100us%
      0.19 ± 12%      +0.0        0.24 ±  6%  fio.latency_20us%
      7.28 ± 21%      -2.9        4.43 ± 14%  fio.latency_250us%
      0.26 ± 41%      -0.1        0.12 ±  8%  fio.latency_2ms%
     80.43 ±  3%     +12.1       92.51        fio.latency_500us%
      9.38 ± 10%      -8.3        1.12 ±  5%  fio.latency_750us%
    115.96            -7.4%     107.38        fio.time.elapsed_time
    115.96            -7.4%     107.38        fio.time.elapsed_time.max
     44582 ±  2%     +16.6%      51987        fio.time.involuntary_context_switches
      7196 ±  2%     +10.0%       7913        fio.time.percent_of_cpu_this_job_got
  27777258 ±  9%     -41.4%   16286771 ±  6%  fio.time.voluntary_context_switches
      1134            +7.9%       1225        fio.write_bw_MBps
    510976 ±  3%     -22.4%     396629        fio.write_clat_90%_us
    563882 ±  2%     -21.4%     443050 ±  2%  fio.write_clat_95%_us
    882005 ±  2%     -13.5%     763221 ±  3%  fio.write_clat_99%_us
    325641            -7.0%     302910        fio.write_clat_mean_us
    545861 ±164%     -79.8%     110211 ±  4%  fio.write_clat_stddev
    290547            +7.9%     313626        fio.write_iops
      7071 ±  5%     -17.5%       5834 ±  3%  uptime.idle
 2.841e+09 ±  9%     -34.3%  1.866e+09 ±  5%  cpuidle..time
  33160554 ±  9%     -40.2%   19838701 ±  5%  cpuidle..usage
     26.22 ±  7%     -27.6%      18.99 ±  4%  iostat.cpu.idle
     73.41 ±  2%      +9.8%      80.61        iostat.cpu.system
     25.00 ±  8%      -7.5       17.54 ±  5%  mpstat.cpu.all.idle%
      0.05 ±  3%      -0.0        0.03 ±  4%  mpstat.cpu.all.soft%
    538527 ±  2%      +9.5%     589753        meminfo.Dirty
      8527 ±  6%     -33.2%       5699 ± 19%  meminfo.Inactive(file)
      3746 ±  6%     +29.1%       4835 ±  3%  meminfo.Writeback
     25.67 ±  8%     -27.9%      18.50 ±  5%  vmstat.cpu.id
     27708 ±  5%     +25.3%      34723        vmstat.io.bo
     68.00 ±  3%     +11.3%      75.67        vmstat.procs.r
    467455 ±  8%     -36.6%     296241 ±  5%  vmstat.system.cs
    269989 ±  2%      +9.4%     295282 ±  2%  numa-meminfo.node0.Dirty
     11862 ±  4%      -9.8%      10696 ±  9%  numa-meminfo.node0.KernelStack
      1964 ± 11%     +23.6%       2427 ±  4%  numa-meminfo.node0.Writeback
    269209 ±  2%      +9.7%     295385 ±  2%  numa-meminfo.node1.Dirty
      4916 ± 18%     -39.9%       2954 ± 18%  numa-meminfo.node1.Inactive(file)
      1950 ± 12%     +23.5%       2409 ±  5%  numa-meminfo.node1.Writeback
    256453 ±  8%     -34.2%     168719 ±  6%  turbostat.C1
  32750582 ±  9%     -40.4%   19532310 ±  6%  turbostat.C1E
     24.28 ± 10%      -7.3       16.97 ±  6%  turbostat.C1E%
     24.20 ±  9%     -29.6%      17.05 ±  5%  turbostat.CPU%c1
     63618 ±  9%     -44.5%      35335 ±  6%  turbostat.POLL
      0.03 ± 14%      -0.0        0.02        turbostat.POLL%
     67508 ±  2%      +9.4%      73864 ±  2%  numa-vmstat.node0.nr_dirty
     11863 ±  4%      -9.8%      10696 ±  9%  numa-vmstat.node0.nr_kernel_stack
    492.67 ±  8%     +21.5%     598.50 ±  3%  numa-vmstat.node0.nr_writeback
    209023 ±  4%     +14.7%     239805        numa-vmstat.node0.nr_written
     68001 ±  2%      +9.5%      74461 ±  2%  numa-vmstat.node0.nr_zone_write_pending
     67307 ±  2%      +9.8%      73910 ±  2%  numa-vmstat.node1.nr_dirty
      1227 ± 18%     -39.9%     737.83 ± 18%  numa-vmstat.node1.nr_inactive_file
    489.17 ±  8%     +22.4%     598.83 ±  3%  numa-vmstat.node1.nr_writeback
    203605 ±  3%     +17.4%     238967        numa-vmstat.node1.nr_written
      1227 ± 18%     -39.9%     737.83 ± 18%  numa-vmstat.node1.nr_zone_inactive_file
     67796 ±  2%      +9.9%      74509 ±  2%  numa-vmstat.node1.nr_zone_write_pending
    303700            +2.7%     311750        proc-vmstat.nr_active_file
    134751 ±  2%      +9.6%     147708        proc-vmstat.nr_dirty
      2132 ±  6%     -33.2%       1425 ± 19%  proc-vmstat.nr_inactive_file
    629472            +2.3%     643898        proc-vmstat.nr_slab_unreclaimable
    961.83 ± 10%     +27.5%       1226 ±  5%  proc-vmstat.nr_writeback
    412628 ±  3%     +15.8%     477937        proc-vmstat.nr_written
    303700            +2.7%     311750        proc-vmstat.nr_zone_active_file
      2132 ±  6%     -33.2%       1425 ± 19%  proc-vmstat.nr_zone_inactive_file
    135713 ±  2%      +9.7%     148929        proc-vmstat.nr_zone_write_pending
   1723450            -1.0%    1705980        proc-vmstat.numa_local
    115078            -1.6%     113250        proc-vmstat.pgactivate
    509367            -4.9%     484437        proc-vmstat.pgfault
   3299005 ±  3%     +16.1%    3829684        proc-vmstat.pgpgout
     30854            -7.3%      28591        proc-vmstat.pgreuse
     13.08 ± 55%      -9.9        3.13 ±144%  perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe
     13.08 ± 55%      -9.9        3.13 ±144%  perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64
     14.09 ± 44%      -9.5        4.59 ±183%  perf-profile.calltrace.cycles-pp._dl_catch_error
     10.57 ± 77%      -8.9        1.65 ±170%  perf-profile.calltrace.cycles-pp.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe._dl_catch_error
     10.57 ± 77%      -8.9        1.65 ±170%  perf-profile.calltrace.cycles-pp.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe._dl_catch_error
     12.33 ± 51%      -7.7        4.59 ±183%  perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe._dl_catch_error
     12.33 ± 51%      -7.7        4.59 ±183%  perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe._dl_catch_error
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyin.copy_page_from_iter_atomic.generic_perform_write.__generic_file_write_iter
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.calltrace.cycles-pp.copy_page_from_iter_atomic.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.new_sync_write
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.calltrace.cycles-pp.copyin.copy_page_from_iter_atomic.generic_perform_write.__generic_file_write_iter.generic_file_write_iter
      7.74 ±118%      -6.4        1.30 ±223%  perf-profile.calltrace.cycles-pp.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open
      7.74 ±118%      -6.4        1.30 ±223%  perf-profile.calltrace.cycles-pp.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open
      8.17 ±113%      -3.5        4.63 ±160%  perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.open
      7.96 ±115%      -3.3        4.63 ±160%  perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.open
      7.96 ±115%      -3.3        4.63 ±160%  perf-profile.calltrace.cycles-pp.open
     19.54 ± 79%     -16.4        3.13 ±144%  perf-profile.children.cycles-pp.__x64_sys_openat
     19.33 ± 80%     -16.2        3.13 ±144%  perf-profile.children.cycles-pp.do_sys_openat2
     13.08 ± 55%      -9.9        3.13 ±144%  perf-profile.children.cycles-pp.do_filp_open
     13.08 ± 55%      -9.9        3.13 ±144%  perf-profile.children.cycles-pp.path_openat
     14.09 ± 44%      -7.8        6.24 ±180%  perf-profile.children.cycles-pp._dl_catch_error
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.children.cycles-pp.copy_page_from_iter_atomic
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.children.cycles-pp.copyin
      8.17 ±113%      -3.5        4.63 ±160%  perf-profile.children.cycles-pp.open
      4.09 ±118%      -3.2        0.92 ±223%  perf-profile.children.cycles-pp.sched_setaffinity
      9.02 ±108%      -7.7        1.35 ±144%  perf-profile.self.cycles-pp.copy_user_enhanced_fast_string
     14723 ± 92%    +115.5%      31730 ± 10%  sched_debug.cfs_rq:/.MIN_vruntime.max
      0.22 ± 15%    +160.3%       0.58        sched_debug.cfs_rq:/.h_nr_running.avg
      1.00           +50.0%       1.50        sched_debug.cfs_rq:/.h_nr_running.max
      0.40 ±  2%     -42.0%       0.23 ±  5%  sched_debug.cfs_rq:/.h_nr_running.stddev
    142515 ± 30%    +271.5%     529398        sched_debug.cfs_rq:/.load.avg
    542210           +56.4%     848239 ± 11%  sched_debug.cfs_rq:/.load.max
    225138 ±  7%     -82.3%      39815 ± 21%  sched_debug.cfs_rq:/.load.stddev
    198.39 ± 20%    +185.9%     567.13 ±  6%  sched_debug.cfs_rq:/.load_avg.avg
    998.08 ±  2%    +233.2%       3326 ± 85%  sched_debug.cfs_rq:/.load_avg.max
     26.17 ± 42%   +1711.1%     473.92 ± 17%  sched_debug.cfs_rq:/.load_avg.min
     14723 ± 92%    +115.5%      31730 ± 10%  sched_debug.cfs_rq:/.max_vruntime.max
     29056 ±  6%     +18.6%      34460 ±  8%  sched_debug.cfs_rq:/.min_vruntime.avg
     45989 ±  3%     +13.6%      52249 ±  5%  sched_debug.cfs_rq:/.min_vruntime.max
     24793 ±  7%     +18.1%      29271 ±  7%  sched_debug.cfs_rq:/.min_vruntime.min
      0.22 ± 15%    +160.3%       0.58        sched_debug.cfs_rq:/.nr_running.avg
      1.00           +50.0%       1.50        sched_debug.cfs_rq:/.nr_running.max
      0.40 ±  2%     -42.0%       0.23 ±  5%  sched_debug.cfs_rq:/.nr_running.stddev
    336.61 ± 13%    +102.5%     681.61        sched_debug.cfs_rq:/.runnable_avg.avg
      1031 ± 18%     +35.1%       1393 ±  4%  sched_debug.cfs_rq:/.runnable_avg.max
     61.67 ± 44%    +696.5%     491.17 ±  9%  sched_debug.cfs_rq:/.runnable_avg.min
    336.37 ± 13%    +102.1%     679.89        sched_debug.cfs_rq:/.util_avg.avg
     61.58 ± 44%    +647.0%     460.00 ± 21%  sched_debug.cfs_rq:/.util_avg.min
    224.62 ± 12%     -16.7%     187.05 ±  4%  sched_debug.cfs_rq:/.util_avg.stddev
     59.04 ± 45%    +780.7%     519.91        sched_debug.cfs_rq:/.util_est_enqueued.avg
    587.83 ±  4%     +54.9%     910.42 ±  2%  sched_debug.cfs_rq:/.util_est_enqueued.max
    129.31 ± 16%     -45.2%      70.81 ± 22%  sched_debug.cfs_rq:/.util_est_enqueued.stddev
     24128 ±  7%     -68.2%       7669 ± 76%  sched_debug.cpu.avg_idle.min
      2.74 ± 14%    +137.7%       6.50 ±  6%  sched_debug.cpu.clock.stddev
      1218 ± 19%    +174.0%       3339        sched_debug.cpu.curr->pid.avg
      2161 ±  3%     -61.4%     834.73 ±  5%  sched_debug.cpu.curr->pid.stddev
      0.00 ± 11%    +174.9%       0.00 ± 93%  sched_debug.cpu.next_balance.stddev
      0.23 ± 15%    +152.5%       0.58        sched_debug.cpu.nr_running.avg
      1.00           +50.0%       1.50        sched_debug.cpu.nr_running.max
      0.41 ±  3%     -41.9%       0.24 ±  4%  sched_debug.cpu.nr_running.stddev
    251747 ±  4%     -31.0%     173815 ±  6%  sched_debug.cpu.nr_switches.avg
    286899 ±  4%     -28.5%     205164 ±  5%  sched_debug.cpu.nr_switches.max
    239382 ±  8%     -31.4%     164226 ±  6%  sched_debug.cpu.nr_switches.min
     15.38            -9.1%      13.97        perf-stat.i.MPKI
      0.94 ±  3%      -0.2        0.78        perf-stat.i.branch-miss-rate%
  36133609 ±  2%     -14.8%   30793722        perf-stat.i.branch-misses
     35.61            +3.0       38.64        perf-stat.i.cache-miss-rate%
  2.97e+08 ±  2%      -8.7%  2.711e+08        perf-stat.i.cache-references
    481070 ±  8%     -36.6%     305142 ±  5%  perf-stat.i.context-switches
     11.52 ±  2%     +10.7%      12.75        perf-stat.i.cpi
 2.341e+11 ±  2%      +9.3%  2.559e+11        perf-stat.i.cpu-cycles
      1937 ± 45%     -39.2%       1177 ±  4%  perf-stat.i.cpu-migrations
 2.179e+09            -5.6%  2.057e+09        perf-stat.i.dTLB-stores
      0.10 ±  2%      -7.4%       0.09        perf-stat.i.ipc
     42.85            +7.9%      46.25        perf-stat.i.major-faults
      2.44 ±  2%      +9.3%       2.67        perf-stat.i.metric.GHz
    494.68            -3.3%     478.40        perf-stat.i.metric.K/sec
      3453            +2.1%       3524        perf-stat.i.minor-faults
  19325519            -4.2%   18510309        perf-stat.i.node-load-misses
    825433           -11.2%     733152        perf-stat.i.node-loads
     62.55            +3.0       65.51        perf-stat.i.node-store-miss-rate%
  16733759            +1.8%   17040381        perf-stat.i.node-store-misses
   9751714            -9.0%    8875942        perf-stat.i.node-stores
      3496            +2.1%       3570        perf-stat.i.page-faults
     15.22            -8.9%      13.87        perf-stat.overall.MPKI
      0.90 ±  3%      -0.1        0.76        perf-stat.overall.branch-miss-rate%
     35.70            +2.9       38.61        perf-stat.overall.cache-miss-rate%
     12.01            +9.0%      13.09        perf-stat.overall.cpi
      2210 ±  2%     +10.6%       2445        perf-stat.overall.cycles-between-cache-misses
      0.08            -8.3%       0.08        perf-stat.overall.ipc
     63.19            +2.6       65.75        perf-stat.overall.node-store-miss-rate%
     67491            -7.2%      62618        perf-stat.overall.path-length
  35814910 ±  2%     -14.8%   30502558        perf-stat.ps.branch-misses
 2.945e+08 ±  2%      -8.8%  2.686e+08        perf-stat.ps.cache-references
    475498 ±  8%     -36.5%     301875 ±  5%  perf-stat.ps.context-switches
 2.323e+11 ±  2%      +9.2%  2.536e+11        perf-stat.ps.cpu-cycles
      1935 ± 44%     -39.8%       1165 ±  4%  perf-stat.ps.cpu-migrations
  2.16e+09            -5.7%  2.038e+09        perf-stat.ps.dTLB-stores
     42.22            +8.0%      45.58        perf-stat.ps.major-faults
      3423            +1.9%       3488        perf-stat.ps.minor-faults
  19159594            -4.3%   18339834        perf-stat.ps.node-load-misses
    818492           -11.3%     726363        perf-stat.ps.node-loads
  16591344            +1.8%   16883498        perf-stat.ps.node-store-misses
   9666594            -9.0%    8793340        perf-stat.ps.node-stores
      3466            +2.0%       3534        perf-stat.ps.page-faults
 2.265e+12            -7.2%  2.101e+12        perf-stat.total.instructions





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.


-- 
0-DAY CI Kernel Test Service
https://01.org/lkp



View attachment "config-5.17.0-rc8-00103-g05fd9564e9fa" of type "text/plain" (161380 bytes)

View attachment "job-script" of type "text/plain" (8511 bytes)

View attachment "job.yaml" of type "text/plain" (5864 bytes)

View attachment "reproduce" of type "text/plain" (710 bytes)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ