Re: [PATCH] vfs: Delete the associated dentry when deleting a file

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hello,

kernel test robot noticed a 6.7% improvement of stress-ng.touch.ops_per_sec on:


commit: 3681ce364442ce2ec7c7fbe90ad0aca651db475b ("[PATCH] vfs: Delete the associated dentry when deleting a file")
url: https://github.com/intel-lab-lkp/linux/commits/Yafang-Shao/vfs-Delete-the-associated-dentry-when-deleting-a-file/20240516-144340
base: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git 3c999d1ae3c75991902a1a7dad0cb62c2a3008b4
patch link: https://lore.kernel.org/all/20240515091727.22034-1-laoar.shao@xxxxxxxxx/
patch subject: [PATCH] vfs: Delete the associated dentry when deleting a file

testcase: stress-ng
test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
parameters:

	nr_threads: 100%
	disk: 1HDD
	testtime: 60s
	fs: ext4
	test: touch
	cpufreq_governor: performance



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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240522/202405221518.ecea2810-oliver.sang@xxxxxxxxx

=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
  gcc-13/performance/1HDD/ext4/x86_64-rhel-8.3/100%/debian-12-x86_64-20240206.cgz/lkp-icl-2sp8/touch/stress-ng/60s

commit: 
  3c999d1ae3 ("Merge tag 'wq-for-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq")
  3681ce3644 ("vfs: Delete the associated dentry when deleting a file")

3c999d1ae3c75991 3681ce364442ce2ec7c7fbe90ad 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
 9.884e+08           -49.1%  5.027e+08 ±  4%  cpuidle..time
     23.46 ±  2%     -38.3%      14.47 ±  5%  iostat.cpu.idle
     75.71           +11.7%      84.60        iostat.cpu.system
    620100 ±  5%     -24.0%     471157 ±  6%  numa-numastat.node0.local_node
    650333 ±  3%     -22.3%     505122 ±  5%  numa-numastat.node0.numa_hit
    736690 ±  3%     -21.7%     577182 ±  4%  numa-numastat.node1.local_node
    772759 ±  3%     -21.1%     609537 ±  3%  numa-numastat.node1.numa_hit
     23.42           -38.1%      14.50 ±  5%  vmstat.cpu.id
     54.39 ±  3%     +13.4%      61.67 ±  2%  vmstat.procs.r
     75507 ±  6%     +24.6%      94113 ±  5%  vmstat.system.cs
    177863           +14.2%     203176        vmstat.system.in
     21.30 ±  2%      -9.5       11.76 ±  7%  mpstat.cpu.all.idle%
      0.37 ±  2%      +0.1        0.42 ±  2%  mpstat.cpu.all.irq%
      0.14            -0.0        0.11 ±  2%  mpstat.cpu.all.soft%
     77.37            +9.4       86.79        mpstat.cpu.all.sys%
      0.81            +0.1        0.92 ±  2%  mpstat.cpu.all.usr%
     68.24           -11.5%      60.40        stress-ng.time.elapsed_time
     68.24           -11.5%      60.40        stress-ng.time.elapsed_time.max
    175478            +5.3%     184765        stress-ng.time.involuntary_context_switches
      5038           +12.4%       5663        stress-ng.time.percent_of_cpu_this_job_got
    259551 ±  2%      +6.7%     277010        stress-ng.touch.ops_per_sec
    454143 ±  2%      -9.2%     412504 ±  2%  meminfo.Active
    445748 ±  2%      -9.3%     404154 ±  2%  meminfo.Active(anon)
   1714332 ±  2%     -92.8%     123761 ±  2%  meminfo.KReclaimable
   7111721           -23.7%    5423125        meminfo.Memused
   1714332 ±  2%     -92.8%     123761 ±  2%  meminfo.SReclaimable
    291963           -35.6%     188122        meminfo.SUnreclaim
   2006296           -84.5%     311883        meminfo.Slab
   7289014           -24.0%    5539852        meminfo.max_used_kB
    875347 ±  3%     -91.3%      75880 ± 30%  numa-meminfo.node0.KReclaimable
    875347 ±  3%     -91.3%      75880 ± 30%  numa-meminfo.node0.SReclaimable
    161663 ±  7%     -31.3%     111087 ± 12%  numa-meminfo.node0.SUnreclaim
   1037010 ±  3%     -82.0%     186968 ± 16%  numa-meminfo.node0.Slab
    838678 ±  3%     -94.3%      48016 ± 50%  numa-meminfo.node1.KReclaimable
    838678 ±  3%     -94.3%      48016 ± 50%  numa-meminfo.node1.SReclaimable
    130259 ±  8%     -40.8%      77055 ± 18%  numa-meminfo.node1.SUnreclaim
    968937 ±  3%     -87.1%     125072 ± 25%  numa-meminfo.node1.Slab
    218872 ±  3%     -91.3%      18961 ± 31%  numa-vmstat.node0.nr_slab_reclaimable
     40425 ±  7%     -31.3%      27772 ± 12%  numa-vmstat.node0.nr_slab_unreclaimable
    649973 ±  3%     -22.3%     504715 ±  5%  numa-vmstat.node0.numa_hit
    619740 ±  5%     -24.0%     470750 ±  6%  numa-vmstat.node0.numa_local
    209697 ±  3%     -94.3%      12019 ± 50%  numa-vmstat.node1.nr_slab_reclaimable
     32567 ±  8%     -40.8%      19264 ± 18%  numa-vmstat.node1.nr_slab_unreclaimable
    771696 ±  3%     -21.1%     608506 ±  3%  numa-vmstat.node1.numa_hit
    735626 ±  3%     -21.7%     576154 ±  4%  numa-vmstat.node1.numa_local
    111469 ±  2%      -9.3%     101103 ±  2%  proc-vmstat.nr_active_anon
    446.10           -36.6%     283.05        proc-vmstat.nr_dirtied
     18812            +2.5%      19287        proc-vmstat.nr_kernel_stack
    428165 ±  2%     -92.8%      30970 ±  2%  proc-vmstat.nr_slab_reclaimable
     72954           -35.5%      47032        proc-vmstat.nr_slab_unreclaimable
    111469 ±  2%      -9.3%     101103 ±  2%  proc-vmstat.nr_zone_active_anon
   1424982           -21.7%    1116423        proc-vmstat.numa_hit
   1358679           -22.7%    1050103 ±  2%  proc-vmstat.numa_local
   4261989 ±  3%     -14.9%    3625822 ±  3%  proc-vmstat.pgalloc_normal
    399826            -4.6%     381396        proc-vmstat.pgfault
   3996977 ±  3%     -15.9%    3359964 ±  3%  proc-vmstat.pgfree
     13500            -5.9%      12708        proc-vmstat.pgpgout
      0.13 ±  3%      -0.0        0.08 ±  4%  perf-profile.children.cycles-pp.d_lookup
      0.12 ±  4%      -0.0        0.08        perf-profile.children.cycles-pp.__d_lookup
      0.11 ±  2%      +0.0        0.13 ±  3%  perf-profile.children.cycles-pp.irq_exit_rcu
      0.06 ±  7%      +0.0        0.09 ±  2%  perf-profile.children.cycles-pp.__slab_free
      0.02 ±100%      +0.0        0.06 ±  8%  perf-profile.children.cycles-pp.__memcg_slab_free_hook
      0.07 ±  7%      +0.0        0.12 ±  4%  perf-profile.children.cycles-pp.run_ksoftirqd
      0.09 ±  5%      +0.0        0.14 ±  4%  perf-profile.children.cycles-pp.smpboot_thread_fn
      0.18 ±  3%      +0.1        0.24 ±  3%  perf-profile.children.cycles-pp.kmem_cache_free
      0.10 ±  7%      +0.1        0.16 ±  7%  perf-profile.children.cycles-pp.kthread
      0.10 ±  7%      +0.1        0.16 ±  7%  perf-profile.children.cycles-pp.ret_from_fork
      0.10 ±  7%      +0.1        0.16 ±  7%  perf-profile.children.cycles-pp.ret_from_fork_asm
      0.14 ±  4%      +0.1        0.20 ±  3%  perf-profile.children.cycles-pp.rcu_do_batch
      0.15 ±  3%      +0.1        0.21 ±  2%  perf-profile.children.cycles-pp.rcu_core
      0.18 ±  3%      +0.1        0.24 ±  2%  perf-profile.children.cycles-pp.handle_softirqs
      0.00            +0.1        0.06 ±  7%  perf-profile.children.cycles-pp.list_lru_del
      0.82 ±  2%      +0.1        0.89 ±  3%  perf-profile.children.cycles-pp._raw_spin_lock
      0.01 ±238%      +0.1        0.08 ±  4%  perf-profile.children.cycles-pp.__call_rcu_common
      0.00            +0.1        0.08 ±  3%  perf-profile.children.cycles-pp.d_lru_del
      0.00            +0.2        0.17 ±  3%  perf-profile.children.cycles-pp.__dentry_kill
      0.33 ± 11%      +0.2        0.50 ±  6%  perf-profile.children.cycles-pp.dput
      0.09 ±  4%      -0.0        0.05 ± 22%  perf-profile.self.cycles-pp.__d_lookup
      0.06 ±  5%      +0.0        0.09 ±  5%  perf-profile.self.cycles-pp.__slab_free
      0.74 ±  2%      +0.1        0.79        perf-profile.self.cycles-pp._raw_spin_lock
      2.55 ±  4%     -40.6%       1.51 ±  5%  perf-stat.i.MPKI
 1.219e+10           +12.8%  1.376e+10        perf-stat.i.branch-instructions
      0.27 ±  2%      -0.1        0.21 ±  2%  perf-stat.i.branch-miss-rate%
  22693772           +14.3%   25941855        perf-stat.i.branch-misses
     39.43            -4.6       34.83        perf-stat.i.cache-miss-rate%
  95834044 ±  3%     +10.9%  1.063e+08 ±  4%  perf-stat.i.cache-misses
 2.658e+08 ±  2%     +14.8%  3.051e+08 ±  4%  perf-stat.i.cache-references
     77622 ±  6%     +25.5%      97395 ±  5%  perf-stat.i.context-switches
      2.82            +3.3%       2.91        perf-stat.i.cpi
 1.821e+11           +12.5%  2.049e+11        perf-stat.i.cpu-cycles
      9159 ±  3%     +22.9%      11257 ±  3%  perf-stat.i.cpu-migrations
 6.223e+10           +12.8%  7.019e+10        perf-stat.i.instructions
      0.36            -4.8%       0.34        perf-stat.i.ipc
      1.19 ±  9%     +27.6%       1.51 ±  5%  perf-stat.i.metric.K/sec
      4716            +6.3%       5011        perf-stat.i.minor-faults
      4716            +6.3%       5011        perf-stat.i.page-faults
     35.93            -1.2       34.77        perf-stat.overall.cache-miss-rate%
 1.214e+10           +11.5%  1.353e+10        perf-stat.ps.branch-instructions
  22276184           +13.3%   25240906        perf-stat.ps.branch-misses
  95133798 ±  3%      +9.8%  1.045e+08 ±  4%  perf-stat.ps.cache-misses
 2.648e+08 ±  2%     +13.5%  3.004e+08 ±  4%  perf-stat.ps.cache-references
     77612 ±  6%     +23.8%      96101 ±  5%  perf-stat.ps.context-switches
 1.813e+11           +11.1%  2.015e+11        perf-stat.ps.cpu-cycles
      9093 ±  3%     +21.5%      11047 ±  2%  perf-stat.ps.cpu-migrations
 6.192e+10           +11.5%  6.901e+10        perf-stat.ps.instructions
      4639            +5.6%       4899        perf-stat.ps.minor-faults
      4640            +5.6%       4899        perf-stat.ps.page-faults




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://github.com/intel/lkp-tests/wiki





[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux