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]
Date:   Fri, 11 Oct 2019 23:00:15 +0800
From:   kernel test robot <rong.a.chen@...el.com>
To:     David Sterba <dsterba@...e.com>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        lkp@...ts.01.org
Subject: [btrfs]  cb49511328:  aim7.jobs-per-min 3.1% improvement

Greeting,

FYI, we noticed a 3.1% improvement of aim7.jobs-per-min due to commit:


commit: cb49511328dcce73840a54661622950d7fa6384e ("btrfs: define separate btrfs_set/get_XX helpers")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

in testcase: aim7
on test machine: 72 threads Intel(R) Xeon(R) Gold 6139 CPU @ 2.30GHz with 128G memory
with following parameters:

	disk: 4BRD_12G
	md: RAID1
	fs: btrfs
	test: sync_disk_rw
	load: 20
	cpufreq_governor: performance
	ucode: 0x2000064

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 run     job.yaml

=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/load/md/rootfs/tbox_group/test/testcase/ucode:
  gcc-7/performance/4BRD_12G/btrfs/x86_64-rhel-7.6/20/RAID1/debian-x86_64-2019-09-23.cgz/lkp-skl-2sp7/sync_disk_rw/aim7/0x2000064

commit: 
  6ff49c6ad2 ("btrfs: Make btrfs_find_name_in_ext_backref return struct btrfs_inode_extref")
  cb49511328 ("btrfs: define separate btrfs_set/get_XX helpers")

6ff49c6ad285160b cb49511328dcce73840a5466162 
---------------- --------------------------- 
       fail:runs  %reproduction    fail:runs
           |             |             |    
          1:4          -25%            :4     dmesg.WARNING:at#for_ip_interrupt_entry/0x
         %stddev     %change         %stddev
             \          |                \  
    623.25            +3.1%     642.59        aim7.jobs-per-min
    192.83            -3.1%     186.94        aim7.time.elapsed_time
    192.83            -3.1%     186.94        aim7.time.elapsed_time.max
  19175958            -1.8%   18833102        aim7.time.voluntary_context_switches
    108009 ± 39%     -45.4%      59005 ± 68%  numa-meminfo.node1.AnonHugePages
    102.75 ± 29%     +34.5%     138.25 ±  9%  numa-vmstat.node1.nr_dirty
     29277 ±  4%     -10.0%      26347        softirqs.CPU26.SCHED
     28981 ±  8%      -9.3%      26293 ±  2%  softirqs.CPU33.SCHED
    178853            +2.9%     184022        vmstat.io.bo
    254789            +2.2%     260366        vmstat.system.cs
      7.07            +3.1%       7.29        iostat.cpu.system
      9482            +2.7%       9737        iostat.md0.w/s
    179158            +2.9%     184350        iostat.md0.wkB/s
    268.00 ±  2%      +4.3%     279.50        turbostat.Avg_MHz
    154.10            +1.6%     156.65        turbostat.PkgWatt
     39.43            +2.5%      40.43        turbostat.RAMWatt
    191.25 ± 19%     +31.5%     251.50 ±  7%  proc-vmstat.nr_dirty
      6086            +1.1%       6154        proc-vmstat.nr_mapped
     36370            +1.5%      36926        proc-vmstat.nr_slab_unreclaimable
    517903            -2.8%     503160        proc-vmstat.pgfault
     37863 ±  3%     +12.6%      42624 ±  3%  slabinfo.Acpi-State.active_objs
    744.75 ±  3%     +12.6%     838.50 ±  3%  slabinfo.Acpi-State.active_slabs
     38018 ±  3%     +12.5%      42784 ±  3%  slabinfo.Acpi-State.num_objs
    744.75 ±  3%     +12.6%     838.50 ±  3%  slabinfo.Acpi-State.num_slabs
      2003 ±  4%     +11.5%       2234 ±  2%  slabinfo.btrfs_ordered_extent.active_objs
      2003 ±  4%     +11.5%       2234 ±  2%  slabinfo.btrfs_ordered_extent.num_objs
      6864 ±  4%     +10.1%       7554 ±  6%  slabinfo.kmalloc-512.active_objs
      6879 ±  4%     +10.2%       7578 ±  6%  slabinfo.kmalloc-512.num_objs
      7.29 ± 59%    +108.2%      15.18 ± 39%  sched_debug.cfs_rq:/.removed.load_avg.avg
     41.23 ± 59%     +65.7%      68.32 ± 29%  sched_debug.cfs_rq:/.removed.load_avg.stddev
    335.80 ± 59%    +108.5%     700.23 ± 39%  sched_debug.cfs_rq:/.removed.runnable_sum.avg
      2.52 ± 58%    +149.8%       6.30 ± 42%  sched_debug.cfs_rq:/.removed.util_avg.avg
     14.85 ± 63%     +97.5%      29.32 ± 33%  sched_debug.cfs_rq:/.removed.util_avg.stddev
     20.66 ±  4%      -9.6%      18.68 ±  7%  sched_debug.cfs_rq:/.runnable_load_avg.stddev
    211012 ±  5%     -19.2%     170486 ± 19%  sched_debug.cpu.nr_switches.stddev
      6.35           +15.5%       7.34 ±  5%  sched_debug.cpu.nr_uninterruptible.stddev
    210721 ±  5%     -19.1%     170396 ± 19%  sched_debug.cpu.sched_count.stddev
    104847 ±  5%     -19.2%      84687 ± 19%  sched_debug.cpu.sched_goidle.stddev
    100269 ±  6%     -22.7%      77483 ± 18%  sched_debug.cpu.ttwu_count.stddev
      4412 ± 18%     -23.7%       3368 ± 23%  interrupts.CPU11.RES:Rescheduling_interrupts
    841.25 ± 59%    +113.1%       1793 ± 29%  interrupts.CPU18.NMI:Non-maskable_interrupts
    841.25 ± 59%    +113.1%       1793 ± 29%  interrupts.CPU18.PMI:Performance_monitoring_interrupts
    583.25 ±125%    +189.8%       1690 ± 45%  interrupts.CPU22.NMI:Non-maskable_interrupts
    583.25 ±125%    +189.8%       1690 ± 45%  interrupts.CPU22.PMI:Performance_monitoring_interrupts
      4646 ± 24%     -24.2%       3519 ±  9%  interrupts.CPU30.RES:Rescheduling_interrupts
    812.75 ± 63%    +101.7%       1639 ± 31%  interrupts.CPU54.NMI:Non-maskable_interrupts
    812.75 ± 63%    +101.7%       1639 ± 31%  interrupts.CPU54.PMI:Performance_monitoring_interrupts
    535.50 ±125%    +215.6%       1690 ± 47%  interrupts.CPU58.NMI:Non-maskable_interrupts
    535.50 ±125%    +215.6%       1690 ± 47%  interrupts.CPU58.PMI:Performance_monitoring_interrupts
      2161 ± 38%     +89.6%       4096 ± 32%  interrupts.CPU61.RES:Rescheduling_interrupts
      2247 ± 31%     +74.6%       3924 ± 10%  interrupts.CPU68.RES:Rescheduling_interrupts
      1841 ± 12%     -46.9%     977.25 ± 49%  interrupts.CPU7.RES:Rescheduling_interrupts
 1.549e+09            -2.7%  1.507e+09        perf-stat.i.branch-instructions
     23.10 ±  5%      +3.9       27.02        perf-stat.i.cache-miss-rate%
  19276786 ±  4%     +16.5%   22461951 ±  2%  perf-stat.i.cache-misses
    258175            +2.3%     264230        perf-stat.i.context-switches
 1.876e+10 ±  2%      +4.4%  1.958e+10        perf-stat.i.cpu-cycles
      8.91 ±  7%     -21.0%       7.04 ±  8%  perf-stat.i.cpu-migrations
      1398 ±  5%     -21.7%       1094 ± 11%  perf-stat.i.cycles-between-cache-misses
      0.45            -4.8%       0.43 ±  2%  perf-stat.i.ipc
     84.36 ±  2%      +4.6       89.00        perf-stat.i.node-load-miss-rate%
   4683731 ±  7%     +22.2%    5725019        perf-stat.i.node-load-misses
     55.59 ±  6%     +10.7       66.27        perf-stat.i.node-store-miss-rate%
   2165178 ±  6%     +27.1%    2752883        perf-stat.i.node-store-misses
   1474872 ±  4%     -12.6%    1288534 ±  2%  perf-stat.i.node-stores
     22.77 ±  7%      +4.5       27.26        perf-stat.overall.cache-miss-rate%
      2.23            +4.8%       2.33        perf-stat.overall.cpi
    975.43 ±  4%     -10.6%     872.26        perf-stat.overall.cycles-between-cache-misses
      0.45            -4.6%       0.43        perf-stat.overall.ipc
     89.83            +1.1       90.94        perf-stat.overall.node-load-miss-rate%
     59.44 ±  4%      +8.7       68.11        perf-stat.overall.node-store-miss-rate%
 1.541e+09            -2.7%  1.499e+09        perf-stat.ps.branch-instructions
  19172392 ±  4%     +16.5%   22337735 ±  2%  perf-stat.ps.cache-misses
    256781            +2.3%     262765        perf-stat.ps.context-switches
 1.866e+10 ±  2%      +4.4%  1.948e+10        perf-stat.ps.cpu-cycles
      8.86 ±  7%     -21.0%       7.00 ±  8%  perf-stat.ps.cpu-migrations
   4658275 ±  7%     +22.2%    5693292        perf-stat.ps.node-load-misses
   2153399 ±  6%     +27.1%    2737622        perf-stat.ps.node-store-misses
   1466929 ±  4%     -12.6%    1281396 ±  2%  perf-stat.ps.node-stores
 1.629e+12            -3.3%  1.576e+12        perf-stat.total.instructions
     44.97            -2.8       42.19        perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
     44.96            -2.8       42.19        perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
     44.38            -2.7       41.66        perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
     44.37            -2.7       41.65        perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
     44.33            -2.7       41.62        perf-profile.calltrace.cycles-pp.new_sync_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
     44.32            -2.7       41.61        perf-profile.calltrace.cycles-pp.btrfs_file_write_iter.new_sync_write.vfs_write.ksys_write.do_syscall_64
     43.06            -2.7       40.39        perf-profile.calltrace.cycles-pp.btrfs_sync_file.btrfs_file_write_iter.new_sync_write.vfs_write.ksys_write
     32.16            -1.8       30.36        perf-profile.calltrace.cycles-pp.btrfs_log_dentry_safe.btrfs_sync_file.btrfs_file_write_iter.new_sync_write.vfs_write
     32.14            -1.8       30.35        perf-profile.calltrace.cycles-pp.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file.btrfs_file_write_iter.new_sync_write
     31.93            -1.7       30.21        perf-profile.calltrace.cycles-pp.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file.btrfs_file_write_iter
     11.06            -1.4        9.71 ±  2%  perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.prepare_to_wait_event.btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot
     10.96            -1.4        9.60 ±  2%  perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.prepare_to_wait_event.btrfs_tree_read_lock.btrfs_read_lock_root_node
     18.91            -1.0       17.89        perf-profile.calltrace.cycles-pp.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file
      8.11 ±  4%      -0.9        7.19 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_sync_log.btrfs_sync_file.btrfs_file_write_iter.new_sync_write.vfs_write
     10.32 ±  4%      -0.7        9.64 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe
     10.32 ±  4%      -0.7        9.65 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_insert_empty_items.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe.btrfs_sync_file
      6.99            -0.6        6.36 ±  3%  perf-profile.calltrace.cycles-pp.__btrfs_drop_extents.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe
      4.98 ±  5%      -0.5        4.44 ±  2%  perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.prepare_to_wait_event.btrfs_tree_lock.btrfs_lock_root_node
      5.39 ±  2%      -0.5        4.87 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.__btrfs_drop_extents.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent
      5.38 ±  2%      -0.5        4.86 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.btrfs_log_changed_extents.btrfs_log_inode
      4.41 ±  5%      -0.5        3.89 ±  5%  perf-profile.calltrace.cycles-pp.prepare_to_wait_event.btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items
      3.14 ±  3%      -0.5        2.63 ±  2%  perf-profile.calltrace.cycles-pp.check_leaf.btree_csum_one_bio.btree_submit_bio_hook.submit_one_bio.btree_write_cache_pages
      1.47 ±  3%      -0.5        0.96 ± 28%  perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock
      1.46 ±  2%      -0.5        0.96 ± 28%  perf-profile.calltrace.cycles-pp.activate_task.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common
      3.44 ±  3%      -0.5        2.93 ±  2%  perf-profile.calltrace.cycles-pp.btree_write_cache_pages.do_writepages.__filemap_fdatawrite_range.btrfs_write_marked_extents.btrfs_sync_log
      1.46 ±  3%      -0.5        0.96 ± 28%  perf-profile.calltrace.cycles-pp.enqueue_task_fair.activate_task.ttwu_do_activate.try_to_wake_up.autoremove_wake_function
      3.65            -0.5        3.15 ±  2%  perf-profile.calltrace.cycles-pp.prepare_to_wait_event.btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items
      3.44 ±  3%      -0.5        2.94 ±  2%  perf-profile.calltrace.cycles-pp.__filemap_fdatawrite_range.btrfs_write_marked_extents.btrfs_sync_log.btrfs_sync_file.btrfs_file_write_iter
      3.44 ±  3%      -0.5        2.94 ±  2%  perf-profile.calltrace.cycles-pp.do_writepages.__filemap_fdatawrite_range.btrfs_write_marked_extents.btrfs_sync_log.btrfs_sync_file
      1.43 ±  3%      -0.5        0.93 ± 28%  perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.activate_task.ttwu_do_activate.try_to_wake_up
      3.44 ±  3%      -0.5        2.95 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_write_marked_extents.btrfs_sync_log.btrfs_sync_file.btrfs_file_write_iter.new_sync_write
      3.23 ±  3%      -0.5        2.74 ±  2%  perf-profile.calltrace.cycles-pp.btree_submit_bio_hook.submit_one_bio.btree_write_cache_pages.do_writepages.__filemap_fdatawrite_range
      3.23 ±  3%      -0.5        2.74 ±  2%  perf-profile.calltrace.cycles-pp.submit_one_bio.btree_write_cache_pages.do_writepages.__filemap_fdatawrite_range.btrfs_write_marked_extents
      3.21 ±  3%      -0.5        2.72 ±  2%  perf-profile.calltrace.cycles-pp.btree_csum_one_bio.btree_submit_bio_hook.submit_one_bio.btree_write_cache_pages.do_writepages
      5.04 ±  5%      -0.4        4.62 ±  2%  perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.prepare_to_wait_event.btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot
     11.68            -0.4       11.31        perf-profile.calltrace.cycles-pp.btrfs_csum_file_blocks.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent.btrfs_log_dentry_safe
      2.95 ±  8%      -0.3        2.61 ±  3%  perf-profile.calltrace.cycles-pp.wait_log_commit.btrfs_sync_log.btrfs_sync_file.btrfs_file_write_iter.new_sync_write
      2.62 ±  8%      -0.3        2.29 ±  3%  perf-profile.calltrace.cycles-pp.__mutex_lock.wait_log_commit.btrfs_sync_log.btrfs_sync_file.btrfs_file_write_iter
      0.57 ±  2%      -0.3        0.26 ±100%  perf-profile.calltrace.cycles-pp.prepare_to_wait_event.btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_csum_file_blocks
      2.35 ±  8%      -0.3        2.05 ±  3%  perf-profile.calltrace.cycles-pp.osq_lock.__mutex_lock.wait_log_commit.btrfs_sync_log.btrfs_sync_file
      2.97 ±  2%      -0.3        2.69 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.btrfs_log_changed_extents
      3.63 ±  2%      -0.3        3.36 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode.btrfs_log_inode_parent
      3.62 ±  2%      -0.3        3.36 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode
      1.37 ±  2%      -0.3        1.11 ± 24%  perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.btrfs_unlock_up_safe.setup_items_for_insert.__btrfs_drop_extents
      1.34 ±  2%      -0.3        1.09 ± 24%  perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.btrfs_unlock_up_safe.setup_items_for_insert
      2.17 ±  4%      -0.2        1.94 ±  4%  perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.btrfs_log_changed_extents
      4.50 ±  2%      -0.2        4.29        perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_insert_empty_items.btrfs_csum_file_blocks.btrfs_log_changed_extents.btrfs_log_inode
      4.57 ±  2%      -0.2        4.36        perf-profile.calltrace.cycles-pp.btrfs_insert_empty_items.btrfs_csum_file_blocks.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent
      1.40 ±  2%      -0.2        1.20 ±  5%  perf-profile.calltrace.cycles-pp.__wake_up_common_lock.unlock_up.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode
      2.66 ±  2%      -0.2        2.47 ±  5%  perf-profile.calltrace.cycles-pp.prepare_to_wait_event.btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_csum
      1.41 ±  2%      -0.2        1.21 ±  5%  perf-profile.calltrace.cycles-pp.unlock_up.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode.btrfs_log_inode_parent
      1.05 ±  4%      -0.2        0.88 ±  6%  perf-profile.calltrace.cycles-pp.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.unlock_up
      1.07 ±  4%      -0.2        0.91 ±  5%  perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.unlock_up.btrfs_search_slot
      1.08 ±  4%      -0.2        0.93 ±  5%  perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.unlock_up.btrfs_search_slot.btrfs_insert_empty_items
      2.26 ±  3%      -0.1        2.11 ±  2%  perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_csum_file_blocks.btrfs_log_changed_extents
      2.25 ±  3%      -0.1        2.10 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_tree_lock.btrfs_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_csum_file_blocks
      1.31 ±  2%      -0.1        1.19 ±  5%  perf-profile.calltrace.cycles-pp.setup_items_for_insert.__btrfs_drop_extents.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent
      1.15 ±  2%      -0.1        1.04 ±  6%  perf-profile.calltrace.cycles-pp.__wake_up_common_lock.btrfs_unlock_up_safe.setup_items_for_insert.__btrfs_drop_extents.btrfs_log_changed_extents
      1.16 ±  2%      -0.1        1.05 ±  6%  perf-profile.calltrace.cycles-pp.btrfs_unlock_up_safe.setup_items_for_insert.__btrfs_drop_extents.btrfs_log_changed_extents.btrfs_log_inode
      0.77 ±  4%      -0.1        0.67 ±  5%  perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
      0.75 ±  3%      -0.1        0.65 ±  5%  perf-profile.calltrace.cycles-pp.__sched_text_start.schedule_idle.do_idle.cpu_startup_entry.start_secondary
      0.54 ±  6%      +0.1        0.61 ±  5%  perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry
      0.67 ±  7%      +0.1        0.74 ±  3%  perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry.start_secondary
      0.94 ±  7%      +0.1        1.05 ±  2%  perf-profile.calltrace.cycles-pp.extent_write_cache_pages.extent_writepages.do_writepages.__filemap_fdatawrite_range.btrfs_fdatawrite_range
      0.80 ±  7%      +0.1        0.92 ±  2%  perf-profile.calltrace.cycles-pp.__extent_writepage.extent_write_cache_pages.extent_writepages.do_writepages.__filemap_fdatawrite_range
      0.66 ±  8%      +0.1        0.78 ±  3%  perf-profile.calltrace.cycles-pp.cow_file_range.btrfs_run_delalloc_range.writepage_delalloc.__extent_writepage.extent_write_cache_pages
      0.69 ±  8%      +0.1        0.81 ±  3%  perf-profile.calltrace.cycles-pp.writepage_delalloc.__extent_writepage.extent_write_cache_pages.extent_writepages.do_writepages
      0.66 ±  9%      +0.1        0.79 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_run_delalloc_range.writepage_delalloc.__extent_writepage.extent_write_cache_pages.extent_writepages
      0.83 ±  8%      +0.2        1.00 ±  7%  perf-profile.calltrace.cycles-pp.btrfs_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.insert_reserved_file_extent
      0.64 ± 12%      +0.2        0.85 ± 13%  perf-profile.calltrace.cycles-pp.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
      0.41 ± 57%      +0.2        0.63 ± 13%  perf-profile.calltrace.cycles-pp.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt
      1.47 ±  6%      +0.3        1.78 ±  9%  perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.insert_reserved_file_extent
      0.27 ±100%      +0.4        0.62 ± 13%  perf-profile.calltrace.cycles-pp.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt
      6.07            +0.4        6.50 ±  4%  perf-profile.calltrace.cycles-pp.worker_thread.kthread.ret_from_fork
      5.97            +0.4        6.41 ±  4%  perf-profile.calltrace.cycles-pp.process_one_work.worker_thread.kthread.ret_from_fork
      6.16            +0.4        6.61 ±  4%  perf-profile.calltrace.cycles-pp.ret_from_fork
      6.16            +0.4        6.61 ±  4%  perf-profile.calltrace.cycles-pp.kthread.ret_from_fork
      4.98 ±  3%      +0.5        5.46 ±  4%  perf-profile.calltrace.cycles-pp.btrfs_finish_ordered_io.normal_work_helper.process_one_work.worker_thread.kthread
      4.04 ±  4%      +0.5        4.53 ±  6%  perf-profile.calltrace.cycles-pp.insert_reserved_file_extent.btrfs_finish_ordered_io.normal_work_helper.process_one_work.worker_thread
      3.83 ±  5%      +0.5        4.32 ±  6%  perf-profile.calltrace.cycles-pp.__btrfs_drop_extents.insert_reserved_file_extent.btrfs_finish_ordered_io.normal_work_helper.process_one_work
      4.98 ±  3%      +0.5        5.47 ±  4%  perf-profile.calltrace.cycles-pp.normal_work_helper.process_one_work.worker_thread.kthread.ret_from_fork
      2.41 ±  6%      +0.5        2.91 ±  8%  perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.insert_reserved_file_extent.btrfs_finish_ordered_io
      2.41 ±  6%      +0.5        2.91 ±  8%  perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.__btrfs_drop_extents.insert_reserved_file_extent.btrfs_finish_ordered_io.normal_work_helper
      1.96 ±  5%      +0.5        2.46 ± 11%  perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter
      0.51 ± 58%      +0.5        1.02 ± 14%  perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state
      3.37 ±  6%      +0.5        3.90 ± 10%  perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle
      3.67 ±  6%      +0.6        4.25 ± 10%  perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
      0.00            +0.8        0.77 ± 18%  perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
      0.00            +0.8        0.80 ±  5%  perf-profile.calltrace.cycles-pp.btrfs_get_32.check_leaf.btree_csum_one_bio.btree_submit_bio_hook.submit_one_bio
      0.00            +0.9        0.93 ±  3%  perf-profile.calltrace.cycles-pp.btrfs_get_64.check_leaf.btree_csum_one_bio.btree_submit_bio_hook.submit_one_bio
     40.31            +1.5       41.77        perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
     43.98            +1.7       45.73 ±  2%  perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary
     44.28            +1.8       46.06 ±  2%  perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
     47.44            +2.2       49.66 ±  2%  perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64
     47.43            +2.2       49.66 ±  2%  perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64
     47.41            +2.2       49.65 ±  2%  perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
     48.03            +2.3       50.35        perf-profile.calltrace.cycles-pp.secondary_startup_64
     45.07            -2.8       42.30        perf-profile.children.cycles-pp.do_syscall_64
     45.07            -2.8       42.30        perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
     44.38            -2.7       41.66        perf-profile.children.cycles-pp.vfs_write
     44.38            -2.7       41.67        perf-profile.children.cycles-pp.ksys_write
     44.33            -2.7       41.63        perf-profile.children.cycles-pp.new_sync_write
     44.32            -2.7       41.61        perf-profile.children.cycles-pp.btrfs_file_write_iter
     43.06            -2.7       40.39        perf-profile.children.cycles-pp.btrfs_sync_file
     32.16            -1.8       30.36        perf-profile.children.cycles-pp.btrfs_log_dentry_safe
     32.14            -1.8       30.35        perf-profile.children.cycles-pp.btrfs_log_inode_parent
     31.93            -1.7       30.21        perf-profile.children.cycles-pp.btrfs_log_inode
     18.61            -1.6       16.96        perf-profile.children.cycles-pp.prepare_to_wait_event
      1.50 ±  2%      -1.1        0.41 ±  2%  perf-profile.children.cycles-pp.btrfs_get_token_32
     26.14            -1.1       25.08        perf-profile.children.cycles-pp._raw_spin_lock_irqsave
     28.51            -1.1       27.45        perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
     32.83            -1.1       31.78        perf-profile.children.cycles-pp.btrfs_search_slot
     18.91            -1.0       17.89        perf-profile.children.cycles-pp.btrfs_log_changed_extents
      8.11 ±  4%      -0.9        7.19 ±  2%  perf-profile.children.cycles-pp.btrfs_sync_log
     15.15 ±  3%      -0.9       14.26 ±  2%  perf-profile.children.cycles-pp.btrfs_insert_empty_items
     10.16            -0.5        9.64 ±  2%  perf-profile.children.cycles-pp.btrfs_lock_root_node
     10.17            -0.5        9.66 ±  2%  perf-profile.children.cycles-pp.btrfs_tree_lock
      3.44 ±  3%      -0.5        2.94 ±  2%  perf-profile.children.cycles-pp.btree_write_cache_pages
      3.76            -0.5        3.26 ±  4%  perf-profile.children.cycles-pp.try_to_wake_up
      3.44 ±  3%      -0.5        2.95 ±  2%  perf-profile.children.cycles-pp.btrfs_write_marked_extents
      3.22 ±  3%      -0.5        2.72 ±  2%  perf-profile.children.cycles-pp.btree_csum_one_bio
      3.60 ±  3%      -0.5        3.12 ±  2%  perf-profile.children.cycles-pp.submit_one_bio
      3.23 ±  3%      -0.5        2.75 ±  2%  perf-profile.children.cycles-pp.btree_submit_bio_hook
      3.18 ±  3%      -0.5        2.70 ±  3%  perf-profile.children.cycles-pp.check_leaf
      3.62            -0.4        3.18 ±  4%  perf-profile.children.cycles-pp.autoremove_wake_function
      4.86            -0.4        4.42 ±  3%  perf-profile.children.cycles-pp.__wake_up_common_lock
      3.68            -0.4        3.25 ±  4%  perf-profile.children.cycles-pp.__wake_up_common
      2.81 ±  8%      -0.4        2.41 ±  2%  perf-profile.children.cycles-pp.__mutex_lock
      4.78 ±  4%      -0.4        4.39 ±  2%  perf-profile.children.cycles-pp.__filemap_fdatawrite_range
      4.77 ±  4%      -0.4        4.38 ±  2%  perf-profile.children.cycles-pp.do_writepages
      2.48 ±  8%      -0.4        2.11 ±  3%  perf-profile.children.cycles-pp.osq_lock
     12.05            -0.4       11.69        perf-profile.children.cycles-pp.btrfs_csum_file_blocks
      2.96 ±  8%      -0.3        2.61 ±  3%  perf-profile.children.cycles-pp.wait_log_commit
      1.60 ±  2%      -0.2        1.37 ±  5%  perf-profile.children.cycles-pp.unlock_up
      1.83 ±  2%      -0.2        1.65 ±  6%  perf-profile.children.cycles-pp.__sched_text_start
      0.78 ±  3%      -0.1        0.67 ±  5%  perf-profile.children.cycles-pp.schedule_idle
      1.45 ±  2%      -0.1        1.36 ±  2%  perf-profile.children.cycles-pp.map_private_extent_buffer
      0.53 ±  4%      -0.1        0.45 ±  8%  perf-profile.children.cycles-pp.pick_next_task_fair
      0.22 ± 15%      -0.1        0.15 ± 21%  perf-profile.children.cycles-pp.console_unlock
      0.21 ± 16%      -0.1        0.14 ± 20%  perf-profile.children.cycles-pp.wait_for_xmitr
      0.23 ± 16%      -0.1        0.15 ± 23%  perf-profile.children.cycles-pp.irq_work_run_list
      0.21 ± 16%      -0.1        0.14 ± 23%  perf-profile.children.cycles-pp.uart_console_write
      0.21 ± 14%      -0.1        0.14 ± 20%  perf-profile.children.cycles-pp.serial8250_console_putchar
      0.21 ± 16%      -0.1        0.14 ± 22%  perf-profile.children.cycles-pp.serial8250_console_write
      0.26 ±  5%      -0.1        0.20 ±  9%  perf-profile.children.cycles-pp.__queue_work
      0.26 ±  5%      -0.1        0.20 ±  9%  perf-profile.children.cycles-pp.queue_work_on
      0.27 ±  8%      -0.0        0.23 ±  5%  perf-profile.children.cycles-pp.end_bio_extent_writepage
      0.34 ±  4%      -0.0        0.30 ±  4%  perf-profile.children.cycles-pp.btrfs_end_bio
      0.23 ±  3%      -0.0        0.20 ±  5%  perf-profile.children.cycles-pp.stack_trace_consume_entry_nosched
      0.19 ±  7%      -0.0        0.16 ±  9%  perf-profile.children.cycles-pp.update_rq_clock
      0.13 ±  3%      -0.0        0.10 ± 18%  perf-profile.children.cycles-pp.__x86_indirect_thunk_rax
      0.08 ±  6%      -0.0        0.06 ± 14%  perf-profile.children.cycles-pp.__btrfs_map_block
      0.10 ±  7%      -0.0        0.08 ±  5%  perf-profile.children.cycles-pp.lock_extent_bits
      0.06 ± 11%      +0.0        0.08 ±  5%  perf-profile.children.cycles-pp.can_overcommit
      0.04 ± 58%      +0.0        0.07 ± 14%  perf-profile.children.cycles-pp.btrfs_tree_unlock
      0.20 ±  7%      +0.0        0.24 ±  8%  perf-profile.children.cycles-pp.block_group_cache_tree_search
      0.16 ±  5%      +0.1        0.21 ±  5%  perf-profile.children.cycles-pp.__list_del_entry_valid
      0.19 ±  8%      +0.1        0.25 ±  5%  perf-profile.children.cycles-pp._raw_read_lock
      0.56 ±  6%      +0.1        0.63 ±  6%  perf-profile.children.cycles-pp.tick_nohz_next_event
      0.69 ±  7%      +0.1        0.76 ±  4%  perf-profile.children.cycles-pp.tick_nohz_get_sleep_length
      0.05 ± 58%      +0.1        0.12 ± 33%  perf-profile.children.cycles-pp.run_local_timers
      0.34 ±  4%      +0.1        0.42 ±  3%  perf-profile.children.cycles-pp.find_free_extent
      0.36 ±  4%      +0.1        0.45 ±  2%  perf-profile.children.cycles-pp.btrfs_reserve_extent
      0.06 ± 62%      +0.1        0.15 ± 23%  perf-profile.children.cycles-pp.calc_global_load_tick
      0.06 ± 65%      +0.1        0.16 ± 13%  perf-profile.children.cycles-pp.timekeeping_max_deferment
      0.95 ±  7%      +0.1        1.07 ±  2%  perf-profile.children.cycles-pp.extent_write_cache_pages
      0.80 ±  7%      +0.1        0.92 ±  2%  perf-profile.children.cycles-pp.__extent_writepage
      0.66 ±  8%      +0.1        0.78 ±  3%  perf-profile.children.cycles-pp.cow_file_range
      0.69 ±  8%      +0.1        0.81 ±  3%  perf-profile.children.cycles-pp.writepage_delalloc
      0.66 ±  9%      +0.1        0.79 ±  3%  perf-profile.children.cycles-pp.btrfs_run_delalloc_range
      0.26 ± 20%      +0.1        0.39 ± 11%  perf-profile.children.cycles-pp.tick_nohz_irq_exit
      0.77 ± 11%      +0.2        0.96 ± 13%  perf-profile.children.cycles-pp.tick_sched_timer
      0.69 ± 14%      +0.4        1.07 ± 14%  perf-profile.children.cycles-pp.clockevents_program_event
      6.07            +0.4        6.50 ±  4%  perf-profile.children.cycles-pp.worker_thread
      5.97            +0.4        6.41 ±  4%  perf-profile.children.cycles-pp.process_one_work
      6.17            +0.4        6.61 ±  4%  perf-profile.children.cycles-pp.ret_from_fork
      0.00            +0.4        0.45 ±  9%  perf-profile.children.cycles-pp.btrfs_get_8
      6.16            +0.4        6.61 ±  4%  perf-profile.children.cycles-pp.kthread
      4.98 ±  3%      +0.5        5.46 ±  4%  perf-profile.children.cycles-pp.btrfs_finish_ordered_io
      4.04 ±  4%      +0.5        4.53 ±  6%  perf-profile.children.cycles-pp.insert_reserved_file_extent
      4.98 ±  3%      +0.5        5.47 ±  4%  perf-profile.children.cycles-pp.normal_work_helper
      6.42 ±  2%      +0.5        6.92 ±  3%  perf-profile.children.cycles-pp.finish_wait
      2.20 ±  5%      +0.5        2.70 ± 11%  perf-profile.children.cycles-pp.hrtimer_interrupt
      0.97 ± 15%      +0.5        1.47 ± 14%  perf-profile.children.cycles-pp.ktime_get
      3.68 ±  7%      +0.5        4.22 ± 11%  perf-profile.children.cycles-pp.smp_apic_timer_interrupt
      0.10 ± 72%      +0.6        0.67 ± 29%  perf-profile.children.cycles-pp.sched_ttwu_pending
      4.02 ±  6%      +0.6        4.59 ± 10%  perf-profile.children.cycles-pp.apic_timer_interrupt
      0.00            +0.9        0.92 ±  4%  perf-profile.children.cycles-pp.btrfs_get_32
      0.00            +1.0        1.04 ±  3%  perf-profile.children.cycles-pp.btrfs_get_64
     40.44            +1.4       41.80        perf-profile.children.cycles-pp.intel_idle
     44.84            +1.8       46.69        perf-profile.children.cycles-pp.cpuidle_enter_state
     44.85            +1.9       46.70        perf-profile.children.cycles-pp.cpuidle_enter
     47.44            +2.2       49.66 ±  2%  perf-profile.children.cycles-pp.start_secondary
     48.05            +2.3       50.37        perf-profile.children.cycles-pp.do_idle
     48.03            +2.3       50.35        perf-profile.children.cycles-pp.secondary_startup_64
     48.03            +2.3       50.35        perf-profile.children.cycles-pp.cpu_startup_entry
     28.48            -1.0       27.44        perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
      0.94 ±  2%      -0.6        0.37 ±  2%  perf-profile.self.cycles-pp.btrfs_get_token_32
      2.47 ±  8%      -0.4        2.10 ±  2%  perf-profile.self.cycles-pp.osq_lock
      1.36 ±  2%      -0.1        1.25 ±  2%  perf-profile.self.cycles-pp.map_private_extent_buffer
      0.39 ±  6%      -0.1        0.31 ±  6%  perf-profile.self.cycles-pp.check_leaf
      0.44 ±  2%      -0.1        0.38 ±  9%  perf-profile.self.cycles-pp.__sched_text_start
      0.20 ±  9%      -0.0        0.16 ± 11%  perf-profile.self.cycles-pp.set_next_entity
      0.12 ±  5%      -0.0        0.08 ± 17%  perf-profile.self.cycles-pp.__x86_indirect_thunk_rax
      0.16 ±  4%      -0.0        0.13 ±  9%  perf-profile.self.cycles-pp.stack_trace_consume_entry_nosched
      0.16 ± 10%      -0.0        0.13 ±  5%  perf-profile.self.cycles-pp.update_load_avg
      0.12 ±  4%      -0.0        0.11 ±  3%  perf-profile.self.cycles-pp.stack_trace_save_tsk
      0.08 ± 10%      +0.0        0.10 ± 10%  perf-profile.self.cycles-pp.enqueue_task_fair
      0.04 ± 58%      +0.0        0.07 ± 14%  perf-profile.self.cycles-pp.btrfs_tree_unlock
      0.10 ± 10%      +0.0        0.14 ± 10%  perf-profile.self.cycles-pp.btrfs_tree_lock
      0.14 ± 18%      +0.0        0.18 ±  7%  perf-profile.self.cycles-pp.rcu_sched_clock_irq
      0.22 ±  5%      +0.0        0.26 ±  9%  perf-profile.self.cycles-pp.queued_read_lock_slowpath
      0.16 ±  5%      +0.0        0.21 ±  3%  perf-profile.self.cycles-pp.__list_del_entry_valid
      0.14 ±  9%      +0.0        0.19 ±  2%  perf-profile.self.cycles-pp.try_to_wake_up
      0.19 ±  8%      +0.1        0.25 ±  5%  perf-profile.self.cycles-pp._raw_read_lock
      0.05 ± 59%      +0.1        0.11 ± 28%  perf-profile.self.cycles-pp.tick_sched_timer
      0.04 ± 59%      +0.1        0.12 ± 33%  perf-profile.self.cycles-pp.run_local_timers
      0.06 ± 65%      +0.1        0.16 ± 13%  perf-profile.self.cycles-pp.timekeeping_max_deferment
      0.68 ±  5%      +0.1        0.81 ±  6%  perf-profile.self.cycles-pp._raw_spin_lock_irqsave
      0.00            +0.2        0.20 ±  4%  perf-profile.self.cycles-pp.btrfs_get_8
      0.00            +0.5        0.47 ±  4%  perf-profile.self.cycles-pp.btrfs_get_64
      0.00            +0.5        0.47        perf-profile.self.cycles-pp.btrfs_get_32
      0.70 ± 21%      +0.5        1.21 ± 16%  perf-profile.self.cycles-pp.ktime_get
     40.44            +1.4       41.79        perf-profile.self.cycles-pp.intel_idle


                                                                                
                                 aim7.jobs-per-min                              
                                                                                
  655 +-+-------------------------------------------------------------------+   
  650 +-+             O    O  O                                             |   
      |            O     O         O         OO  O                          |   
  645 O-+O  O       O  O     O  O   O   O  O        O                       |   
  640 +-+ O    OO         O                    O  O                         |   
  635 +O+    O   O               O   O O  O                                 |   
  630 +-+                                                +        +         |   
      |+.+   +             +.++.  .+++.                  :+    +  :        +|   
  625 +-+ +.+ +   .++. +.++     ++     ++.+   +   +.+   +  ++  :+: :.+  + + |   
  620 +-+      + +    +                    :.+ :.+  :   :    +:  + +  :+ +  |   
  615 +-+       +                          +   +    :  +      +       +     |   
  610 +-+                                            ::                     |   
      |                                              ::                     |   
  605 +-+                                            +                      |   
  600 +-+-------------------------------------------------------------------+   
                                                                                
                                                                                
[*] 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-5.3.0-rc8-00115-gcb49511328dcc" of type "text/plain" (199452 bytes)

View attachment "job-script" of type "text/plain" (7724 bytes)

View attachment "job.yaml" of type "text/plain" (5317 bytes)

View attachment "reproduce" of type "text/plain" (1009 bytes)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ