[btrfs] 483a265a17: aim7.jobs-per-min 2.8% improvement

Greeting,

FYI, we noticed a 2.8% improvement of aim7.jobs-per-min due to commit:


commit: 483a265a1702a918bf38b7a54d4aa5a575879583 ("btrfs: Fix multiple out-of-bounds warnings")
https://git.kernel.org/cgit/linux/kernel/git/gustavoars/linux.git for-next/testing


in testcase: aim7
on test machine: 88 threads 2 sockets Intel(R) Xeon(R) Gold 6238M CPU @ 2.10GHz with 128G memory
with following parameters:

	disk: 4BRD_12G
	md: RAID0
	fs: btrfs
	test: disk_src
	load: 500
	cpufreq_governor: performance
	ucode: 0x5003006

test-description: AIM7 is a traditional UNIX system level benchmark suite which is used to test and measure the performance of multiuser system.
test-url: https://sourceforge.net/projects/aimbench/files/aim-suite7/





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 split-job --compatible job.yaml  # generate the yaml file for lkp run
        bin/lkp run                    generated-yaml-file

=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/load/md/rootfs/tbox_group/test/testcase/ucode:
  gcc-9/performance/4BRD_12G/btrfs/x86_64-rhel-8.3/500/RAID0/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp9/disk_src/aim7/0x5003006

commit: 
  v5.13-rc2
  483a265a17 ("btrfs: Fix multiple out-of-bounds warnings")

       v5.13-rc2 483a265a1702a918bf38b7a54d4 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
     37218            +2.8%      38248        aim7.jobs-per-min
    705.29            -3.0%     684.35        aim7.time.system_time
      3733 ±  5%      +8.0%       4032 ±  5%  numa-vmstat.node0.numa_interleave
  11317887 ± 26%     -22.4%    8782788        turbostat.C1
 1.121e+09 ± 38%     -36.9%  7.073e+08        cpuidle.C1.time
  11320152 ± 26%     -22.4%    8785577        cpuidle.C1.usage
    416367            -1.9%     408635        proc-vmstat.numa_hit
    336857            -2.3%     329123        proc-vmstat.numa_local
    280627            -3.0%     272107        proc-vmstat.pgfault
     16725 ±  2%      -4.5%      15978 ±  2%  proc-vmstat.pgreuse
    156.83 ±  7%     +42.2%     223.00 ± 15%  interrupts.CPU13.RES:Rescheduling_interrupts
    183.33 ±  7%     +25.3%     229.67 ± 12%  interrupts.CPU22.RES:Rescheduling_interrupts
    172.50 ±  5%     +33.7%     230.67 ± 18%  interrupts.CPU25.RES:Rescheduling_interrupts
    180.67 ± 12%     +27.3%     230.00 ± 15%  interrupts.CPU36.RES:Rescheduling_interrupts
    151.00 ± 12%     +27.6%     192.67 ± 14%  interrupts.CPU47.RES:Rescheduling_interrupts
    151.83 ±  6%     +24.3%     188.67 ± 13%  interrupts.CPU53.RES:Rescheduling_interrupts
     15377 ±  4%     +15.5%      17755 ± 10%  interrupts.RES:Rescheduling_interrupts
    215.00 ± 41%     +58.1%     340.00 ± 12%  interrupts.TLB:TLB_shootdowns
     26.92            -0.7       26.20        perf-profile.calltrace.cycles-pp.osq_lock.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot
     13.36 ±  2%      -0.4       12.92        perf-profile.calltrace.cycles-pp.rwsem_down_write_slowpath.__btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items
     13.06 ±  2%      -0.4       12.69        perf-profile.calltrace.cycles-pp.btrfs_create.path_openat.do_filp_open.do_sys_openat2.do_sys_open
      5.06            -0.1        4.91        perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_inode.__btrfs_update_delayed_inode.btrfs_commit_inode_delayed_inode.btrfs_evict_inode
      5.06            -0.1        4.92        perf-profile.calltrace.cycles-pp.btrfs_lookup_inode.__btrfs_update_delayed_inode.btrfs_commit_inode_delayed_inode.btrfs_evict_inode.evict
      1.03 ±  4%      +0.1        1.10 ±  4%  perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state
      1.04 ±  4%      +0.1        1.11 ±  4%  perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter
      1.70 ±  4%      +0.1        1.83 ±  3%  perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle
     46.12            +0.9       47.03        perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
     46.12            +0.9       47.03        perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
     46.11            +0.9       47.01        perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
     44.29            +0.9       45.20        perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
     44.15            +0.9       45.06        perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary
     46.65            +1.0       47.61        perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
     42.02            +1.1       43.12        perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
     36.97            -1.2       35.80        perf-profile.children.cycles-pp.btrfs_search_slot
     39.78            -1.0       38.83        perf-profile.children.cycles-pp.rwsem_down_write_slowpath
     32.59            -0.9       31.68        perf-profile.children.cycles-pp.__btrfs_tree_lock
     32.48            -0.9       31.56        perf-profile.children.cycles-pp.btrfs_lock_root_node
     28.44            -0.7       27.71        perf-profile.children.cycles-pp.osq_lock
     16.67            -0.5       16.20        perf-profile.children.cycles-pp.btrfs_insert_empty_items
     13.06 ±  2%      -0.4       12.69        perf-profile.children.cycles-pp.btrfs_create
      5.21            -0.2        5.03        perf-profile.children.cycles-pp.btrfs_lookup_inode
      0.42 ±  4%      -0.1        0.37 ±  2%  perf-profile.children.cycles-pp.generic_bin_search
      0.20 ±  4%      -0.0        0.16 ±  6%  perf-profile.children.cycles-pp.native_sched_clock
      0.17 ±  2%      -0.0        0.14 ±  4%  perf-profile.children.cycles-pp.sched_clock_cpu
      0.08 ±  5%      +0.0        0.10 ±  4%  perf-profile.children.cycles-pp.refill_obj_stock
      0.19 ±  5%      +0.0        0.22 ±  4%  perf-profile.children.cycles-pp.rcu_do_batch
      0.22 ±  6%      +0.0        0.26 ±  3%  perf-profile.children.cycles-pp.kmem_cache_free
      0.08 ± 10%      +0.0        0.12 ± 16%  perf-profile.children.cycles-pp.tick_nohz_irq_exit
      0.26 ±  7%      +0.1        0.31 ±  3%  perf-profile.children.cycles-pp.poll_idle
      0.66 ±  3%      +0.1        0.73 ±  3%  perf-profile.children.cycles-pp.setup_items_for_insert
      1.26 ±  4%      +0.1        1.35 ±  4%  perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
      1.24 ±  5%      +0.1        1.33 ±  4%  perf-profile.children.cycles-pp.hrtimer_interrupt
      0.42 ±  6%      +0.1        0.54 ±  2%  perf-profile.children.cycles-pp.btrfs_get_token_32
      2.00 ±  4%      +0.2        2.17 ±  3%  perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
     42.32            +0.8       43.13        perf-profile.children.cycles-pp.intel_idle
     46.12            +0.9       47.03        perf-profile.children.cycles-pp.start_secondary
     46.65            +1.0       47.61        perf-profile.children.cycles-pp.secondary_startup_64_no_verify
     46.65            +1.0       47.61        perf-profile.children.cycles-pp.cpu_startup_entry
     46.64            +1.0       47.60        perf-profile.children.cycles-pp.do_idle
     44.80            +1.0       45.76        perf-profile.children.cycles-pp.cpuidle_enter
     44.80            +1.0       45.76        perf-profile.children.cycles-pp.cpuidle_enter_state
     28.26            -0.7       27.51        perf-profile.self.cycles-pp.osq_lock
      0.48 ±  3%      -0.1        0.34 ±  3%  perf-profile.self.cycles-pp.btrfs_search_slot
      0.15 ±  7%      -0.1        0.10 ±  4%  perf-profile.self.cycles-pp.generic_bin_search
      0.20 ±  4%      -0.0        0.16 ±  4%  perf-profile.self.cycles-pp.native_sched_clock
      0.25 ±  8%      +0.0        0.30 ±  5%  perf-profile.self.cycles-pp.poll_idle
      0.38 ±  5%      +0.1        0.49 ±  3%  perf-profile.self.cycles-pp.btrfs_get_token_32
     42.32            +0.8       43.13        perf-profile.self.cycles-pp.intel_idle


                                                                                
                                  aim7.jobs-per-min                             
                                                                                
  40000 +-------------------------------------------------------------------+   
        |.+.+.++.+.+.+.+.++.+.+.+.+.+O +.+.+.+.++.+.+.+.+.++ O O O O OO O O |   
  35000 |-+                         :  :                                    |   
  30000 |-+                         :  :                                    |   
        |                           :  :                                    |   
  25000 |-+                         : :                                     |   
        |                           : :                                     |   
  20000 |-+                         : :                                     |   
        |                            ::                                     |   
  15000 |-+                          ::                                     |   
  10000 |-+                          ::                                     |   
        |                            :                                      |   
   5000 |-+                          :                                      |   
        |                            :                                      |   
      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.


---
0DAY/LKP+ Test Infrastructure                   Open Source Technology Center
https://lists.01.org/hyperkitty/list/lkp@lists.01.org       Intel Corporation

Thanks,
Oliver Sang