file_remove_privs() fix for v6.0-rc3
Subsystems (2)
Christian Brauner
maintainerHey Linus,
/* Summary */
As part of Stefan's and Jens' work to add async buffered write support to xfs we refactored file_remove_privs() and added __file_remove_privs() to avoid calling __remove_privs() when IOCB_NOWAIT is passed.
While debugging a recent performance regression report I found that during review we missed that faf99b563558 ("fs: add __remove_file_privs() with flags parameter") accidently changed behavior when dentry_needs_remove_privs() returns zero. Before the commit it would still call inode_has_no_xattr() setting the S_NOSEC bit and thereby avoiding even calling into dentry_needs_remove_privs() the next time this function is called. After that commit inode_has_no_xattr() would only be called if __remove_privs() had to be called. Restore the old behavior. This is likely the cause of the performance regression.
/* Testing */
All patches are based on v6.0-rc1 and have been sitting in linux-next. No build failures or warnings were observed and fstests, selftests, and LTP have seen no regressions.
/* Conflicts */
At the time of creating this PR no merge conflicts were reported from linux-next and no merge conflicts showed up doing a test-merge with current mainline.
The following changes since commit 568035b01cfb107af8d2e4bd2fb9aea22cf5b868:
Linux 6.0-rc1 (2022-08-14 15:50:18 -0700)
are available in the Git repository at:
ssh://[email protected]/pub/scm/linux/kernel/git/vfs/idmapping.git tags/fs.fixes.v6.0-rc3
for you to fetch changes up to 41191cf6bf565f4139046d7be68ec30c290af92d:
fs: __file_remove_privs(): restore call to inode_has_no_xattr() (2022-08-18 09:39:33 +0200)
Please consider pulling these changes from the signed fs.fixes.v6.0-rc3 tag.
Thanks!
Christian
----------------------------------------------------------------
fs.fixes.v6.0-rc3
----------------------------------------------------------------
Stefan Roesch (1):
fs: __file_remove_privs(): restore call to inode_has_no_xattr()
fs/inode.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
The pull request you sent on Tue, 23 Aug 2022 13:10:56 +0200:
The pull request you sent on Tue, 23 Aug 2022 13:10:56 +0200:
Quoted 1 line
ssh://[email protected]/pub/scm/linux/kernel/git/vfs/idmapping.git tags/fs.fixes.v6.0-rc3
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/062d26ad0b36829c0142e5b96a694f3cdb6eaa43
Thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/prtracker.html
Christian Brauner
maintainerQuoted 7 lines · Christian Brauner
Hey Linus,
/* Summary */
As part of Stefan's and Jens' work to add async buffered write support to xfs we refactoredfile_remove_privs()and added__file_remove_privs()to avoid calling__remove_privs()whenIOCB_NOWAITis passed.
Quoted 9 lines
While debugging a recent performance regression report I found that during review we missed that
faf99b563558("fs: add__remove_file_privs()with flags parameter") accidently changed behavior whendentry_needs_remove_privs()returns zero. Before the commit it would still callinode_has_no_xattr()setting theS_NOSECbit and thereby avoiding even calling intodentry_needs_remove_privs()the next time this function is called. After that commitinode_has_no_xattr()would only be called if__remove_privs()had to be called. Restore the old behavior. This is likely the cause of the performance regression.
Just fyi, so it seems this really was the cause of the perf regression we've seen:
Quoted 7,384 lines · kernel test robot
Greeting,
FYI, we noticed a 20.1% improvement of aim7.jobs-per-min due to commit:
commit:
41191cf6bf565f4139046d7be68ec30c290af92d("fs:__file_remove_privs(): restore call toinode_has_no_xattr()")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git masterin testcase: aim7
on test machine: 88 threads 2 sockets Intel(R) Xeon(R) Gold 6238M CPU @ 2.10GHz (Cascade Lake) with 128G memory with following parameters:disk: 4BRD_12G md: RAID1 fs: btrfs test: disk_cp load: 1500 cpufreq_governor: performance ucode: 0x5003302test-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/=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/load/md/rootfs/tbox_group/test/testcase/ucode:
gcc-11/performance/4BRD_12G/btrfs/x86_64-rhel-8.3/1500/RAID1/debian-11.1-x86_64-20220510.cgz/lkp-csl-2sp9/disk_cp/aim7/0x5003302commit:
v6.0-rc1
41191cf6bf("fs:__file_remove_privs(): restore call toinode_has_no_xattr()")v6.0-rc1 41191cf6bf565f4139046d7be68 ---------------- --------------------------- %stddev %change %stddev \ | \ 29181 +20.1% 35055 aim7.jobs-per-min 308.64 ± 2% -16.8% 256.94 aim7.time.elapsed_time 308.64 ± 2% -16.8% 256.94 aim7.time.elapsed_time.max 1178060 ± 3% -71.1% 340028 aim7.time.involuntary_context_switches 17054 ± 2% +9.3% 18632 ± 2% aim7.time.system_time 45.32 ± 4% -47.3% 23.89 aim7.time.user_time 1.057e+08 -78.5% 22735675 aim7.time.voluntary_context_switches 8.918e+09 -58.9% 3.668e+09 cpuidle..time 1.078e+08 -73.6% 28502398 cpuidle..usage 34.11 -50.9% 16.76 ± 2% iostat.cpu.idle 65.54 +26.6% 83.00 iostat.cpu.system 349.55 -14.8% 297.68 uptime.boot 11947 -44.2% 6668 uptime.idle 33.71 -17.6 16.13 ± 2% mpstat.cpu.all.idle% 0.06 ± 12% -0.0 0.02 ± 8% mpstat.cpu.all.iowait% 0.12 -0.0 0.10 mpstat.cpu.all.soft% 64.71 +17.8 82.48 mpstat.cpu.all.sys% 0.29 ± 2% -0.1 0.21 mpstat.cpu.all.usr% 33.67 -51.5% 16.33 ± 2% vmstat.cpu.id 2774 ± 2% -12.3% 2433 ± 3% vmstat.io.bo 62.00 ± 4% +17.2% 72.67 vmstat.procs.r 632940 -72.9% 171766 ± 2% vmstat.system.cs 203603 -9.5% 184186 vmstat.system.in 182789 ± 4% -12.3% 160289 ± 5% meminfo.Active 122477 ± 5% -12.4% 107343 ± 8% meminfo.Active(anon) 60311 ± 2% -12.2% 52946 meminfo.Active(file) 59054 ± 2% -20.1% 47182 meminfo.Dirty 484001 -18.5% 394230 meminfo.Inactive 475556 -17.5% 392469 meminfo.Inactive(anon) 8444 ± 22% -79.1% 1761 ± 23% meminfo.Inactive(file) 138108 ± 2% -36.6% 87492 ± 2% meminfo.Mapped 276760 ± 2% -36.0% 177130 ± 5% meminfo.Shmem 6917037 -14.3% 5929840 meminfo.max_used_kB 47358 ± 6% -27.2% 34461 ± 4% numa-meminfo.node0.Active 17218 ± 16% -56.4% 7502 ± 17% numa-meminfo.node0.Active(anon) 30139 ± 2% -10.6% 26959 ± 2% numa-meminfo.node0.Active(file) 29506 -18.7% 23986 numa-meminfo.node0.Dirty 4405 ± 28% -76.1% 1052 ± 30% numa-meminfo.node0.Inactive(file) 72755 ± 13% -56.6% 31582 ± 41% numa-meminfo.node0.Shmem 30126 -10.7% 26903 ± 2% numa-meminfo.node1.Active(file) 29465 -18.6% 23994 numa-meminfo.node1.Dirty 4045 ± 18% -82.5% 708.50 ± 17% numa-meminfo.node1.Inactive(file) 78269 ± 17% -54.7% 35419 ± 18% numa-meminfo.node1.Mapped 204806 ± 4% -28.7% 146055 ± 12% numa-meminfo.node1.Shmem 1873 +25.2% 2345 turbostat.Avg_MHz 68.13 +16.0 84.16 turbostat.Busy% 2756 +1.3% 2793 turbostat.Bzy_MHz 9610265 ± 27% -85.9% 1351164 turbostat.C1 1.57 ± 19% -1.3 0.25 ± 3% turbostat.C1% 97365101 ± 3% -72.5% 26815902 turbostat.C1E 29.84 ± 5% -14.5 15.32 ± 6% turbostat.C1E% 31.67 -50.1% 15.81 ± 2% turbostat.CPU%c1 63734044 ± 2% -24.5% 48100272 turbostat.IRQ 444391 ± 3% -73.6% 117306 turbostat.POLL 0.03 ± 11% -0.0 0.01 turbostat.POLL% 208.28 +3.7% 216.00 turbostat.PkgWatt 14.65 -5.1% 13.91 turbostat.RAMWatt 4311 ± 16% -56.4% 1880 ± 17% numa-vmstat.node0.nr_active_anon 7518 ± 2% -9.6% 6799 ± 2% numa-vmstat.node0.nr_active_file 7369 -17.6% 6070 numa-vmstat.node0.nr_dirty 1105 ± 28% -76.2% 262.67 ± 30% numa-vmstat.node0.nr_inactive_file 18223 ± 13% -56.5% 7919 ± 41% numa-vmstat.node0.nr_shmem 109157 ± 3% -27.3% 79325 ± 5% numa-vmstat.node0.nr_written 4311 ± 16% -56.4% 1880 ± 17% numa-vmstat.node0.nr_zone_active_anon 7518 ± 2% -9.5% 6800 ± 2% numa-vmstat.node0.nr_zone_active_file 1105 ± 28% -76.2% 262.67 ± 30% numa-vmstat.node0.nr_zone_inactive_file 7375 -17.6% 6079 numa-vmstat.node0.nr_zone_write_pending 7378 -17.8% 6062 numa-vmstat.node1.nr_dirty 1002 ± 21% -82.4% 176.83 ± 17% numa-vmstat.node1.nr_inactive_file 19623 ± 17% -55.0% 8838 ± 19% numa-vmstat.node1.nr_mapped 51264 ± 4% -28.7% 36571 ± 12% numa-vmstat.node1.nr_shmem 108077 ± 4% -26.2% 79733 ± 5% numa-vmstat.node1.nr_written 1002 ± 21% -82.4% 176.83 ± 17% numa-vmstat.node1.nr_zone_inactive_file 7385 -17.8% 6067 numa-vmstat.node1.nr_zone_write_pending 30625 ± 5% -12.4% 26839 ± 8% proc-vmstat.nr_active_anon 15084 -11.3% 13372 proc-vmstat.nr_active_file 14759 ± 2% -19.2% 11922 proc-vmstat.nr_dirty 772798 -3.6% 744684 proc-vmstat.nr_file_pages 118908 -17.4% 98166 proc-vmstat.nr_inactive_anon 2109 ± 22% -79.1% 440.00 ± 23% proc-vmstat.nr_inactive_file 34555 ± 2% -36.5% 21927 ± 2% proc-vmstat.nr_mapped 69216 ± 2% -36.0% 44320 ± 5% proc-vmstat.nr_shmem 31948 -1.3% 31519 proc-vmstat.nr_slab_reclaimable 217232 ± 3% -26.8% 159058 ± 5% proc-vmstat.nr_written 30625 ± 5% -12.4% 26839 ± 8% proc-vmstat.nr_zone_active_anon 15084 -11.3% 13372 proc-vmstat.nr_zone_active_file 118908 -17.4% 98166 proc-vmstat.nr_zone_inactive_anon 2109 ± 22% -79.1% 440.00 ± 23% proc-vmstat.nr_zone_inactive_file 14793 ± 2% -19.3% 11932 proc-vmstat.nr_zone_write_pending 254847 -37.2% 160158 ± 5% proc-vmstat.numa_hint_faults 129185 ± 3% -44.0% 72336 ± 6% proc-vmstat.numa_hint_faults_local 40301718 -1.0% 39889525 proc-vmstat.numa_hit 40214984 -1.0% 39807793 proc-vmstat.numa_local 86751 -7.1% 80628 proc-vmstat.numa_other 408870 ± 4% -24.9% 307066 ± 9% proc-vmstat.numa_pte_updates 3567612 -21.6% 2798606 proc-vmstat.pgactivate 40300101 -1.0% 39887792 proc-vmstat.pgalloc_normal 1265033 -17.1% 1048307 proc-vmstat.pgfault 869060 ± 3% -26.8% 636245 ± 5% proc-vmstat.pgpgout 40841 ± 2% -12.5% 35735 proc-vmstat.pgreuse 0.59 ± 6% +24.7% 0.74 ± 2% sched_debug.cfs_rq:/.h_nr_running.avg 2.42 ± 15% -21.4% 1.90 ± 13% sched_debug.cfs_rq:/.h_nr_running.max 0.59 ± 5% -31.8% 0.40 ± 7% sched_debug.cfs_rq:/.h_nr_running.stddev 311.67 ± 4% +17.5% 366.06 ± 6% sched_debug.cfs_rq:/.load_avg.avg 1913 ± 6% +16.9% 2236 ± 8% sched_debug.cfs_rq:/.load_avg.max 4769342 +34.4% 6411917 sched_debug.cfs_rq:/.min_vruntime.avg 4844578 +34.6% 6521960 sched_debug.cfs_rq:/.min_vruntime.max 4710875 +33.6% 6295049 sched_debug.cfs_rq:/.min_vruntime.min 19514 ± 11% +120.8% 43097 ± 21% sched_debug.cfs_rq:/.min_vruntime.stddev 0.52 ± 4% +36.6% 0.71 ± 2% sched_debug.cfs_rq:/.nr_running.avg 0.46 -24.1% 0.35 ± 6% sched_debug.cfs_rq:/.nr_running.stddev 170.72 +20.0% 204.80 sched_debug.cfs_rq:/.removed.load_avg.max 602.38 ± 2% +18.6% 714.71 sched_debug.cfs_rq:/.runnable_avg.avg 1567 ± 7% +23.8% 1941 ± 7% sched_debug.cfs_rq:/.runnable_avg.max 302.68 ± 5% +20.8% 365.78 ± 4% sched_debug.cfs_rq:/.runnable_avg.stddev 84955 ± 33% +97.5% 167755 ± 31% sched_debug.cfs_rq:/.spread0.max 19554 ± 11% +120.2% 43065 ± 21% sched_debug.cfs_rq:/.spread0.stddev 548.71 ± 2% +27.7% 700.46 sched_debug.cfs_rq:/.util_avg.avg 1457 ± 8% +31.2% 1911 ± 7% sched_debug.cfs_rq:/.util_avg.max 282.03 ± 5% +28.0% 361.09 ± 4% sched_debug.cfs_rq:/.util_avg.stddev 187.15 ± 8% +97.0% 368.62 ± 6% sched_debug.cfs_rq:/.util_est_enqueued.avg 855.47 ± 9% +32.9% 1136 ± 5% sched_debug.cfs_rq:/.util_est_enqueued.max 207.21 ± 5% +18.6% 245.80 ± 4% sched_debug.cfs_rq:/.util_est_enqueued.stddev 211668 +22.7% 259752 sched_debug.cpu.avg_idle.avg 371532 ± 7% +94.7% 723450 ± 11% sched_debug.cpu.avg_idle.max 49675 ± 5% +18.8% 59037 ± 2% sched_debug.cpu.avg_idle.min 61942 ± 6% +72.2% 106692 ± 8% sched_debug.cpu.avg_idle.stddev 188403 -16.0% 158334 sched_debug.cpu.clock.avg 188416 -16.0% 158348 sched_debug.cpu.clock.max 188389 -16.0% 158319 sched_debug.cpu.clock.min 186467 -15.9% 156816 sched_debug.cpu.clock_task.avg 186657 -15.9% 156971 sched_debug.cpu.clock_task.max 180956 -16.6% 150977 sched_debug.cpu.clock_task.min 3380 ± 2% +26.4% 4273 ± 2% sched_debug.cpu.curr->pid.avg 2697 ± 2% -25.4% 2013 ± 3% sched_debug.cpu.curr->pid.stddev 0.00 ± 7% +56.5% 0.00 ± 6% sched_debug.cpu.next_balance.stddev 0.61 ± 4% +20.4% 0.73 ± 2% sched_debug.cpu.nr_running.avg 2.39 ± 14% -21.9% 1.87 ± 10% sched_debug.cpu.nr_running.max 0.58 ± 5% -31.1% 0.40 ± 5% sched_debug.cpu.nr_running.stddev 1055217 -78.0% 232183 ± 2% sched_debug.cpu.nr_switches.avg 1088698 -76.2% 258664 ± 3% sched_debug.cpu.nr_switches.max 1035183 -78.3% 225001 ± 2% sched_debug.cpu.nr_switches.min 9105 ± 19% -48.2% 4714 ± 20% sched_debug.cpu.nr_switches.stddev 195.69 ±103% -90.8% 18.07 ± 86% sched_debug.cpu.nr_uninterruptible.min 188388 -16.0% 158319 sched_debug.cpu_clk 187815 -16.0% 157746 sched_debug.ktime 188743 -15.9% 158672 sched_debug.sched_clk 14.79 ± 4% -44.4% 8.23 ± 5% perf-stat.i.MPKI 5.478e+09 +5.8% 5.794e+09 perf-stat.i.branch-instructions 1.37 ± 4% -0.7 0.66 ± 3% perf-stat.i.branch-miss-rate% 71612844 -51.7% 34555585 ± 4% perf-stat.i.branch-misses 21.39 +6.2 27.62 ± 3% perf-stat.i.cache-miss-rate% 80562382 -26.1% 59517832 ± 8% perf-stat.i.cache-misses 3.754e+08 -43.5% 2.121e+08 ± 6% perf-stat.i.cache-references 639535 -72.8% 173702 ± 2% perf-stat.i.context-switches 6.40 +24.6% 7.98 perf-stat.i.cpi 1.651e+11 +25.1% 2.065e+11 perf-stat.i.cpu-cycles 79147 ± 4% -81.5% 14611 perf-stat.i.cpu-migrations 2131 +68.3% 3588 ± 6% perf-stat.i.cycles-between-cache-misses 0.05 ± 16% -0.0 0.03 ± 18% perf-stat.i.dTLB-load-miss-rate% 3419430 ± 3% -53.0% 1608520 ± 5% perf-stat.i.dTLB-load-misses 7.076e+09 -4.7% 6.741e+09 perf-stat.i.dTLB-loads 0.02 ± 8% -0.0 0.01 ± 12% perf-stat.i.dTLB-store-miss-rate% 340689 ± 4% -57.9% 143364 ± 6% perf-stat.i.dTLB-store-misses 2.266e+09 -29.3% 1.602e+09 ± 2% perf-stat.i.dTLB-stores 16.62 ± 4% +12.5 29.15 ± 4% perf-stat.i.iTLB-load-miss-rate% 5513121 ± 5% -29.3% 3896352 ± 2% perf-stat.i.iTLB-load-misses 29179123 -67.2% 9562945 ± 6% perf-stat.i.iTLB-loads 4636 ± 4% +39.4% 6461 perf-stat.i.instructions-per-iTLB-miss 0.17 -15.9% 0.14 perf-stat.i.ipc 1.31 ± 32% +117.2% 2.84 ± 32% perf-stat.i.major-faults 1.88 +25.1% 2.35 perf-stat.i.metric.GHz 819.21 -51.2% 399.49 ± 3% perf-stat.i.metric.K/sec 172.67 -5.6% 163.05 perf-stat.i.metric.M/sec 3698 -2.7% 3599 perf-stat.i.minor-faults 91.37 -1.9 89.52 perf-stat.i.node-load-miss-rate% 26914730 -42.4% 15505847 ± 4% perf-stat.i.node-load-misses 2373822 -27.7% 1716647 ± 4% perf-stat.i.node-loads 93.62 -3.7 89.94 perf-stat.i.node-store-miss-rate% 11005913 -40.4% 6563466 ± 2% perf-stat.i.node-store-misses 633520 +6.0% 671332 perf-stat.i.node-stores 3699 -2.6% 3602 perf-stat.i.page-faults 14.72 -43.2% 8.37 ± 5% perf-stat.overall.MPKI 1.31 -0.7 0.60 ± 4% perf-stat.overall.branch-miss-rate% 21.46 +6.6 28.03 ± 3% perf-stat.overall.cache-miss-rate% 6.47 +25.8% 8.15 perf-stat.overall.cpi 2049 +70.5% 3492 ± 7% perf-stat.overall.cycles-between-cache-misses 0.05 ± 3% -0.0 0.02 ± 5% perf-stat.overall.dTLB-load-miss-rate% 0.02 ± 4% -0.0 0.01 ± 7% perf-stat.overall.dTLB-store-miss-rate% 15.89 ± 5% +13.1 29.00 ± 4% perf-stat.overall.iTLB-load-miss-rate% 4636 ± 5% +40.4% 6509 perf-stat.overall.instructions-per-iTLB-miss 0.15 -20.5% 0.12 perf-stat.overall.ipc 91.89 -1.9 90.03 perf-stat.overall.node-load-miss-rate% 94.56 -3.8 90.72 perf-stat.overall.node-store-miss-rate% 5.46e+09 +5.7% 5.772e+09 perf-stat.ps.branch-instructions 71379717 -51.8% 34420765 ± 4% perf-stat.ps.branch-misses 80303371 -26.2% 59297913 ± 8% perf-stat.ps.cache-misses 3.742e+08 -43.5% 2.114e+08 ± 6% perf-stat.ps.cache-references 637458 -72.9% 173056 ± 2% perf-stat.ps.context-switches 1.645e+11 +25.1% 2.058e+11 perf-stat.ps.cpu-cycles 78890 ± 4% -81.5% 14559 perf-stat.ps.cpu-migrations 3408249 ± 3% -53.0% 1601788 ± 5% perf-stat.ps.dTLB-load-misses 7.054e+09 -4.8% 6.716e+09 perf-stat.ps.dTLB-loads 339601 ± 4% -57.9% 142822 ± 6% perf-stat.ps.dTLB-store-misses 2.259e+09 -29.3% 1.596e+09 ± 2% perf-stat.ps.dTLB-stores 5495330 ± 5% -29.4% 3881689 ± 2% perf-stat.ps.iTLB-load-misses 29084404 -67.2% 9526991 ± 6% perf-stat.ps.iTLB-loads 1.30 ± 32% +115.9% 2.81 ± 32% perf-stat.ps.major-faults 3684 -2.8% 3583 perf-stat.ps.minor-faults 26828067 -42.4% 15448951 ± 4% perf-stat.ps.node-load-misses 2366457 -27.7% 1710324 ± 4% perf-stat.ps.node-loads 10970333 -40.4% 6539195 ± 2% perf-stat.ps.node-store-misses 631508 +5.9% 668792 perf-stat.ps.node-stores 3686 -2.7% 3586 perf-stat.ps.page-faults 7.9e+12 -17.1% 6.546e+12 perf-stat.total.instructions 10.20 ± 5% -10.2 0.00 perf-profile.calltrace.cycles-pp.btrfs_write_check.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write 10.12 ± 5% -10.1 0.00 perf-profile.calltrace.cycles-pp.__file_remove_privs.btrfs_write_check.btrfs_buffered_write.btrfs_do_write_iter.vfs_write 10.10 ± 5% -10.1 0.00 perf-profile.calltrace.cycles-pp.security_inode_need_killpriv.__file_remove_privs.btrfs_write_check.btrfs_buffered_write.btrfs_do_write_iter 10.09 ± 5% -10.1 0.00 perf-profile.calltrace.cycles-pp.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.btrfs_write_check.btrfs_buffered_write 10.08 ± 5% -10.1 0.00 perf-profile.calltrace.cycles-pp.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.btrfs_write_check 10.01 ± 5% -10.0 0.00 perf-profile.calltrace.cycles-pp.btrfs_getxattr.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs 9.35 ± 5% -9.3 0.00 perf-profile.calltrace.cycles-pp.btrfs_lookup_xattr.btrfs_getxattr.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv 9.29 ± 5% -9.3 0.00 perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_xattr.btrfs_getxattr.__vfs_getxattr.cap_inode_need_killpriv 13.73 -7.3 6.43 perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify 13.58 -7.2 6.36 perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify 13.58 -7.2 6.36 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 13.58 -7.2 6.36 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 12.74 -6.6 6.16 perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify6.49 ± 5% -6.5 0.00 perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_xattr.btrfs_getxattr.__vfs_getxattr
12.45 -6.4 6.08 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
12.44 -6.4 6.08 perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
6.18 ± 5% -6.2 0.00 perf-profile.calltrace.cycles-pp.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_xattr.btrfs_getxattr
5.96 ± 5% -6.0 0.00 perf-profile.calltrace.cycles-pp.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_xattr
11.50 -5.7 5.84 perf-profile.calltrace.cycles-pp.mwait_idle_with_hints.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
11.50 -5.7 5.84 perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
4.06 ± 9% -3.3 0.78 ± 44% perf-profile.calltrace.cycles-pp.schedule.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot
4.04 ± 9% -3.3 0.77 ± 44% perf-profile.calltrace.cycles-pp.__schedule.schedule.rwsem_down_read_slowpath.__btrfs_tree_read_lock.btrfs_read_lock_root_node
3.33 ± 11% -2.7 0.64 ± 44% perf-profile.calltrace.cycles-pp.pick_next_task_fair.__schedule.schedule.rwsem_down_read_slowpath.__btrfs_tree_read_lock
3.31 ± 11% -2.7 0.64 ± 44% perf-profile.calltrace.cycles-pp.newidle_balance.pick_next_task_fair.__schedule.schedule.rwsem_down_read_slowpath
3.01 ± 17% -2.4 0.60 ± 44% perf-profile.calltrace.cycles-pp.load_balance.newidle_balance.pick_next_task_fair.__schedule.schedule
2.35 ± 19% -1.8 0.50 ± 44% perf-profile.calltrace.cycles-pp.find_busiest_group.load_balance.newidle_balance.pick_next_task_fair.__schedule
2.32 ± 19% -1.8 0.50 ± 44% perf-profile.calltrace.cycles-pp.update_sd_lb_stats.find_busiest_group.load_balance.newidle_balance.pick_next_task_fair
2.02 ± 19% -1.6 0.46 ± 44% perf-profile.calltrace.cycles-pp.update_sg_lb_stats.update_sd_lb_stats.find_busiest_group.load_balance.newidle_balance
3.01 ± 4% -0.5 2.50 ± 10% perf-profile.calltrace.cycles-pp.btrfs_set_extent_delalloc.btrfs_dirty_pages.btrfs_buffered_write.btrfs_do_write_iter.vfs_write
2.76 ± 5% -0.5 2.25 ± 10% perf-profile.calltrace.cycles-pp.btrfs_get_extent.btrfs_set_extent_delalloc.btrfs_dirty_pages.btrfs_buffered_write.btrfs_do_write_iter
2.30 ± 5% -0.4 1.93 ± 12% perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_set_extent_delalloc.btrfs_dirty_pages
2.31 ± 5% -0.4 1.93 ± 11% perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_set_extent_delalloc.btrfs_dirty_pages.btrfs_buffered_write
0.56 ± 3% -0.3 0.26 ±100% perf-profile.calltrace.cycles-pp.read
1.60 ± 5% -0.2 1.36 ± 14% perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_lookup_file_extent.btrfs_get_extent.btrfs_set_extent_delalloc
0.70 ± 3% -0.1 0.63 ± 4% perf-profile.calltrace.cycles-pp.prepare_pages.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write
22.63 +3.9 26.54 perf-profile.calltrace.cycles-pp.btrfs_dirty_pages.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write
19.10 +4.3 23.44 perf-profile.calltrace.cycles-pp.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_clear_delalloc_extent.clear_state_bit.__clear_extent_bit
19.12 +4.3 23.45 perf-profile.calltrace.cycles-pp.btrfs_inode_rsv_release.btrfs_clear_delalloc_extent.clear_state_bit.__clear_extent_bit.clear_extent_bit
19.04 +4.3 23.37 perf-profile.calltrace.cycles-pp._raw_spin_lock.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_clear_delalloc_extent.clear_state_bit
18.92 +4.3 23.26 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_clear_delalloc_extent
19.48 +4.4 23.92 perf-profile.calltrace.cycles-pp.clear_extent_bit.btrfs_dirty_pages.btrfs_buffered_write.btrfs_do_write_iter.vfs_write
19.47 +4.5 23.92 perf-profile.calltrace.cycles-pp.__clear_extent_bit.clear_extent_bit.btrfs_dirty_pages.btrfs_buffered_write.btrfs_do_write_iter
19.39 +4.5 23.85 perf-profile.calltrace.cycles-pp.clear_state_bit.__clear_extent_bit.clear_extent_bit.btrfs_dirty_pages.btrfs_buffered_write
19.38 +4.5 23.85 perf-profile.calltrace.cycles-pp.btrfs_clear_delalloc_extent.clear_state_bit.__clear_extent_bit.clear_extent_bit.btrfs_dirty_pages
23.42 +6.6 30.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_buffered_write
23.58 +6.6 30.16 perf-profile.calltrace.cycles-pp._raw_spin_lock.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_buffered_write.btrfs_do_write_iter
23.68 +6.6 30.28 perf-profile.calltrace.cycles-pp.btrfs_inode_rsv_release.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write
23.67 +6.6 30.26 perf-profile.calltrace.cycles-pp.btrfs_block_rsv_release.btrfs_inode_rsv_release.btrfs_buffered_write.btrfs_do_write_iter.vfs_write
24.98 +7.6 32.61 perf-profile.calltrace.cycles-pp.btrfs_reserve_metadata_bytes.btrfs_delalloc_reserve_metadata.btrfs_buffered_write.btrfs_do_write_iter.vfs_write
25.25 +7.6 32.89 perf-profile.calltrace.cycles-pp.btrfs_delalloc_reserve_metadata.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write
24.97 +7.6 32.61 perf-profile.calltrace.cycles-pp.__reserve_bytes.btrfs_reserve_metadata_bytes.btrfs_delalloc_reserve_metadata.btrfs_buffered_write.btrfs_do_write_iter
24.26 +7.6 31.91 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.__reserve_bytes.btrfs_reserve_metadata_bytes.btrfs_delalloc_reserve_metadata
24.42 +7.6 32.07 perf-profile.calltrace.cycles-pp._raw_spin_lock.__reserve_bytes.btrfs_reserve_metadata_bytes.btrfs_delalloc_reserve_metadata.btrfs_buffered_write
84.14 +7.8 91.90 perf-profile.calltrace.cycles-pp.write
84.00 +7.8 91.82 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.write
83.98 +7.8 91.81 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
83.90 +7.9 91.78 perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
83.88 +7.9 91.76 perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.write
83.81 +7.9 91.71 perf-profile.calltrace.cycles-pp.btrfs_do_write_iter.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
83.76 +7.9 91.66 perf-profile.calltrace.cycles-pp.btrfs_buffered_write.btrfs_do_write_iter.vfs_write.ksys_write.do_syscall_64
10.20 ± 5% -10.1 0.06 ± 8% perf-profile.children.cycles-pp.btrfs_write_check
10.12 ± 5% -10.1 0.00 perf-profile.children.cycles-pp.__file_remove_privs
10.10 ± 5% -10.1 0.00 perf-profile.children.cycles-pp.security_inode_need_killpriv
10.09 ± 5% -10.1 0.00 perf-profile.children.cycles-pp.cap_inode_need_killpriv
10.08 ± 5% -10.1 0.00 perf-profile.children.cycles-pp.__vfs_getxattr
12.13 ± 4% -10.1 2.06 ± 11% perf-profile.children.cycles-pp.btrfs_search_slot
10.01 ± 5% -10.0 0.00 perf-profile.children.cycles-pp.btrfs_getxattr
9.35 ± 5% -9.3 0.00 perf-profile.children.cycles-pp.btrfs_lookup_xattr
13.73 -7.3 6.43 perf-profile.children.cycles-pp.secondary_startup_64_no_verify
13.73 -7.3 6.43 perf-profile.children.cycles-pp.cpu_startup_entry
13.73 -7.3 6.43 perf-profile.children.cycles-pp.do_idle
13.58 -7.2 6.36 perf-profile.children.cycles-pp.start_secondary
8.14 ± 5% -6.8 1.38 ± 14% perf-profile.children.cycles-pp.btrfs_read_lock_root_node
12.88 -6.7 6.23 perf-profile.children.cycles-pp.cpuidle_idle_call
7.92 ± 5% -6.5 1.38 ± 14% perf-profile.children.cycles-pp.__btrfs_tree_read_lock
12.59 -6.4 6.15 perf-profile.children.cycles-pp.cpuidle_enter
12.58 -6.4 6.15 perf-profile.children.cycles-pp.cpuidle_enter_state
12.30 -6.3 6.03 perf-profile.children.cycles-pp.mwait_idle_with_hints
7.52 ± 5% -6.2 1.31 ± 14% perf-profile.children.cycles-pp.rwsem_down_read_slowpath
11.63 -5.7 5.90 perf-profile.children.cycles-pp.intel_idle
4.38 ± 9% -3.4 0.96 ± 21% perf-profile.children.cycles-pp.__schedule
4.16 ± 9% -3.2 0.91 ± 21% perf-profile.children.cycles-pp.schedule
3.48 ± 10% -2.7 0.76 ± 24% perf-profile.children.cycles-pp.pick_next_task_fair
3.39 ± 11% -2.6 0.74 ± 25% perf-profile.children.cycles-pp.newidle_balance
3.00 ± 7% -2.6 0.38 ± 6% perf-profile.children.cycles-pp._raw_spin_lock_irq
3.18 ± 11% -2.5 0.70 ± 26% perf-profile.children.cycles-pp.load_balance
2.58 ± 10% -2.0 0.60 ± 26% perf-profile.children.cycles-pp.find_busiest_group
2.55 ± 10% -2.0 0.59 ± 25% perf-profile.children.cycles-pp.update_sd_lb_stats
2.40 ± 10% -1.9 0.55 ± 26% perf-profile.children.cycles-pp.update_sg_lb_stats
1.23 ± 11% -1.1 0.17 ± 9% perf-profile.children.cycles-pp.generic_bin_search
1.13 ± 8% -0.9 0.20 ± 6% perf-profile.children.cycles-pp.read_block_for_search
1.10 ± 8% -0.9 0.18 ± 8% perf-profile.children.cycles-pp.btrfs_release_path
0.68 -0.6 0.11 ± 3% perf-profile.children.cycles-pp.rwsem_wake
0.67 ± 10% -0.6 0.12 ± 5% perf-profile.children.cycles-pp.intel_idle_irq
0.63 ± 14% -0.5 0.10 ± 14% perf-profile.children.cycles-pp.free_extent_buffer
3.01 ± 4% -0.5 2.50 ± 10% perf-profile.children.cycles-pp.btrfs_set_extent_delalloc
2.76 ± 5% -0.5 2.26 ± 11% perf-profile.children.cycles-pp.btrfs_get_extent
0.60 ± 2% -0.5 0.10 ± 4% perf-profile.children.cycles-pp.wake_up_q
0.59 ± 2% -0.5 0.10 ± 4% perf-profile.children.cycles-pp.try_to_wake_up
0.48 ± 12% -0.4 0.06 ± 11% perf-profile.children.cycles-pp.btrfs_get_64
0.49 ± 2% -0.4 0.12 ± 4% perf-profile.children.cycles-pp.flush_smp_call_function_queue
2.31 ± 5% -0.4 1.93 ± 11% perf-profile.children.cycles-pp.btrfs_lookup_file_extent
0.44 ± 4% -0.3 0.10 ± 6% perf-profile.children.cycles-pp.dequeue_task_fair
0.40 ± 2% -0.3 0.08 ± 6% perf-profile.children.cycles-pp.btrfs_insert_empty_items
0.40 ± 11% -0.3 0.08 ± 45% perf-profile.children.cycles-pp.idle_cpu
0.41 -0.3 0.09 ± 6% perf-profile.children.cycles-pp.sched_ttwu_pending
0.38 ± 7% -0.3 0.07 ± 7% perf-profile.children.cycles-pp.down_read
0.37 ± 11% -0.3 0.06 ± 7% perf-profile.children.cycles-pp.btrfs_root_node
0.36 ± 3% -0.3 0.08 ± 5% perf-profile.children.cycles-pp.dequeue_entity
0.33 -0.3 0.07 ± 7% perf-profile.children.cycles-pp.enqueue_task_fair
0.32 ± 2% -0.3 0.06 ± 7% perf-profile.children.cycles-pp.ttwu_do_activate
0.31 ± 8% -0.3 0.05 ± 8% perf-profile.children.cycles-pp.up_read
0.32 ± 2% -0.2 0.09 ± 5% perf-profile.children.cycles-pp.btrfs_create_new_inode
0.30 ± 6% -0.2 0.06 ± 7% perf-profile.children.cycles-pp.find_extent_buffer
0.38 -0.2 0.16 ± 4% perf-profile.children.cycles-pp.lookup_open
0.37 -0.2 0.15 ± 3% perf-profile.children.cycles-pp.btrfs_create_common
0.35 ± 2% -0.2 0.13 ± 19% perf-profile.children.cycles-pp.update_load_avg
0.32 ± 3% -0.2 0.12 ± 3% perf-profile.children.cycles-pp.vfs_unlink
0.32 ± 3% -0.2 0.12 ± 3% perf-profile.children.cycles-pp.btrfs_unlink
0.25 -0.2 0.05 ± 8% perf-profile.children.cycles-pp.enqueue_entity
0.24 ± 2% -0.2 0.06 ± 6% perf-profile.children.cycles-pp.schedule_idle
0.23 ± 4% -0.2 0.05 ± 8% perf-profile.children.cycles-pp.find_extent_buffer_nolock
0.24 ± 4% -0.2 0.06 ± 6% perf-profile.children.cycles-pp.menu_select
0.21 ± 8% -0.2 0.06 ± 45% perf-profile.children.cycles-pp._find_next_bit
0.57 ± 2% -0.2 0.41 ± 3% perf-profile.children.cycles-pp.syscall_exit_to_user_mode
0.56 ± 2% -0.2 0.40 ± 3% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
0.19 ± 3% -0.1 0.06 ± 14% perf-profile.children.cycles-pp.update_curr
0.18 ± 4% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.btrfs_add_link
0.18 ± 3% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.btrfs_insert_dir_item
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.__close
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.exit_to_user_mode_loop
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.evict
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.btrfs_evict_inode
0.49 ± 3% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.task_work_run
0.49 ± 3% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.__fput
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.dput
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.dentry_kill
0.49 ± 2% -0.1 0.38 ± 3% perf-profile.children.cycles-pp.__dentry_kill
0.36 ± 2% -0.1 0.26 ± 2% perf-profile.children.cycles-pp.unlink
0.36 ± 2% -0.1 0.26 ± 2% perf-profile.children.cycles-pp.__x64_sys_unlink
0.36 ± 2% -0.1 0.26 ± 2% perf-profile.children.cycles-pp.do_unlinkat
0.15 ± 12% -0.1 0.05 ± 73% perf-profile.children.cycles-pp.start_kernel
0.15 ± 12% -0.1 0.05 ± 73% perf-profile.children.cycles-pp.arch_call_rest_init
0.15 ± 12% -0.1 0.05 ± 73% perf-profile.children.cycles-pp.rest_init
0.15 ± 4% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.btrfs_lock_root_node
0.15 ± 5% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.__btrfs_tree_lock
0.12 ± 4% -0.1 0.03 ±100% perf-profile.children.cycles-pp.update_blocked_averages
0.10 -0.1 0.02 ± 99% perf-profile.children.cycles-pp.__lookup_extent_mapping
0.70 ± 2% -0.1 0.63 ± 4% perf-profile.children.cycles-pp.prepare_pages
0.13 ± 5% -0.1 0.06 perf-profile.children.cycles-pp.ret_from_fork
0.13 ± 5% -0.1 0.06 perf-profile.children.cycles-pp.kthread
0.12 ± 5% -0.1 0.05 ± 7% perf-profile.children.cycles-pp.process_one_work
0.12 ± 5% -0.1 0.06 ± 9% perf-profile.children.cycles-pp.worker_thread
0.11 ± 6% -0.1 0.05 perf-profile.children.cycles-pp.btrfs_work_helper
0.11 ± 6% -0.1 0.05 perf-profile.children.cycles-pp.btrfs_async_run_delayed_root
0.13 ± 8% -0.1 0.07 ± 11% perf-profile.children.cycles-pp.ktime_get
0.45 ± 2% -0.1 0.39 ± 9% perf-profile.children.cycles-pp.do_sys_openat2
0.45 -0.1 0.39 ± 9% perf-profile.children.cycles-pp.do_filp_open
0.45 -0.1 0.39 ± 9% perf-profile.children.cycles-pp.path_openat
0.45 -0.1 0.39 ± 9% perf-profile.children.cycles-pp.creat64
0.45 -0.1 0.39 ± 9% perf-profile.children.cycles-pp.__x64_sys_creat
0.45 -0.1 0.39 ± 9% perf-profile.children.cycles-pp.open_last_lookups
0.11 ± 4% -0.1 0.05 perf-profile.children.cycles-pp.__btrfs_update_delayed_inode
0.57 ± 2% -0.1 0.51 ± 2% perf-profile.children.cycles-pp.read
0.38 ± 3% -0.1 0.33 ± 4% perf-profile.children.cycles-pp.pagecache_get_page
0.26 ± 2% -0.1 0.20 ± 4% perf-profile.children.cycles-pp.kmem_cache_alloc
0.38 ± 2% -0.0 0.33 ± 4% perf-profile.children.cycles-pp.__filemap_get_folio
0.47 ± 2% -0.0 0.42 ± 3% perf-profile.children.cycles-pp.set_extent_bit
0.46 ± 2% -0.0 0.42 ± 3% perf-profile.children.cycles-pp.ksys_read
0.18 ± 2% -0.0 0.14 ± 11% perf-profile.children.cycles-pp.__irq_exit_rcu
0.17 ± 2% -0.0 0.12 ± 5% perf-profile.children.cycles-pp.lock_and_cleanup_extent_if_need
0.16 ± 4% -0.0 0.12 ± 6% perf-profile.children.cycles-pp.lock_extent_bits
0.10 -0.0 0.06 ± 11% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.12 ± 8% -0.0 0.08 ± 9% perf-profile.children.cycles-pp.clockevents_program_event
0.43 ± 2% -0.0 0.39 ± 2% perf-profile.children.cycles-pp.vfs_read
0.07 ± 5% -0.0 0.03 ± 70% perf-profile.children.cycles-pp.xas_load
0.09 ± 5% -0.0 0.07 ± 8% perf-profile.children.cycles-pp.btrfs_copy_from_user
0.23 ± 2% -0.0 0.21 ± 4% perf-profile.children.cycles-pp.need_preemptive_reclaim
0.08 ± 4% -0.0 0.06 perf-profile.children.cycles-pp.merge_state
0.08 ± 5% -0.0 0.06 ± 6% perf-profile.children.cycles-pp.folio_mark_accessed
0.07 ± 6% -0.0 0.05 ± 8% perf-profile.children.cycles-pp.copyin
0.13 ± 6% -0.0 0.11 ± 4% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
0.08 ± 5% -0.0 0.07 ± 7% perf-profile.children.cycles-pp.copy_page_from_iter_atomic
0.07 ± 5% -0.0 0.05 ± 8% perf-profile.children.cycles-pp.btrfs_add_extent_mapping
0.08 ± 6% -0.0 0.06 ± 6% perf-profile.children.cycles-pp.__might_resched
0.07 ± 7% -0.0 0.05 ± 8% perf-profile.children.cycles-pp.add_extent_mapping
0.09 ± 5% +0.0 0.11 ± 7% perf-profile.children.cycles-pp.btrfs_drop_pages
0.04 ± 44% +0.0 0.06 perf-profile.children.cycles-pp.btrfs_block_rsv_add
0.08 +0.0 0.11 ± 3% perf-profile.children.cycles-pp.__btrfs_end_transaction
0.08 +0.0 0.11 ± 3% perf-profile.children.cycles-pp.btrfs_trans_release_metadata
0.00 +0.1 0.06 ± 9% perf-profile.children.cycles-pp.evict_refill_and_join
0.00 +0.1 0.06 ± 9% perf-profile.children.cycles-pp.btrfs_block_rsv_refill
0.14 ± 3% +0.1 0.20 ± 27% perf-profile.children.cycles-pp.task_tick_fair
0.20 +0.1 0.26 ± 33% perf-profile.children.cycles-pp.scheduler_tick
0.29 +0.1 0.37 ± 32% perf-profile.children.cycles-pp.update_process_times
0.30 ± 9% +0.1 0.41 ± 15% perf-profile.children.cycles-pp.btrfs_check_data_free_space
0.16 ± 6% +0.1 0.28 ± 14% perf-profile.children.cycles-pp.btrfs_free_reserved_data_space_noquota
0.25 ± 10% +0.1 0.38 ± 16% perf-profile.children.cycles-pp.btrfs_reserve_data_bytes
0.25 ± 3% +0.2 0.42 ± 8% perf-profile.children.cycles-pp.rwsem_down_write_slowpath
0.18 ± 5% +0.2 0.37 ± 10% perf-profile.children.cycles-pp.rwsem_optimistic_spin
0.00 +0.2 0.20 ± 17% perf-profile.children.cycles-pp.osq_lock
22.63 +3.9 26.54 perf-profile.children.cycles-pp.btrfs_dirty_pages
19.68 +4.4 24.12 perf-profile.children.cycles-pp.__clear_extent_bit
19.52 +4.5 23.98 perf-profile.children.cycles-pp.clear_state_bit
19.50 +4.5 23.96 perf-profile.children.cycles-pp.clear_extent_bit
19.41 +4.5 23.90 perf-profile.children.cycles-pp.btrfs_clear_delalloc_extent
85.82 +7.5 93.33 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
85.80 +7.5 93.31 perf-profile.children.cycles-pp.do_syscall_64
25.25 +7.6 32.89 perf-profile.children.cycles-pp.btrfs_delalloc_reserve_metadata
25.06 +7.7 32.73 perf-profile.children.cycles-pp.btrfs_reserve_metadata_bytes
84.17 +7.7 91.91 perf-profile.children.cycles-pp.write
25.28 +7.8 33.08 perf-profile.children.cycles-pp.__reserve_bytes
83.89 +7.9 91.78 perf-profile.children.cycles-pp.vfs_write
83.90 +7.9 91.79 perf-profile.children.cycles-pp.ksys_write
83.81 +7.9 91.71 perf-profile.children.cycles-pp.btrfs_do_write_iter
83.76 +7.9 91.67 perf-profile.children.cycles-pp.btrfs_buffered_write
42.83 +10.9 53.76 perf-profile.children.cycles-pp.btrfs_inode_rsv_release
42.92 +11.0 53.92 perf-profile.children.cycles-pp.btrfs_block_rsv_release
70.09 +16.2 86.26 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
68.44 +18.5 86.96 perf-profile.children.cycles-pp._raw_spin_lock
12.23 -6.2 6.01 perf-profile.self.cycles-pp.mwait_idle_with_hints
1.85 ± 10% -1.4 0.42 ± 26% perf-profile.self.cycles-pp.update_sg_lb_stats
1.22 ± 11% -1.0 0.17 ± 9% perf-profile.self.cycles-pp.generic_bin_search
0.73 ± 9% -0.6 0.11 ± 10% perf-profile.self.cycles-pp.btrfs_search_slot
0.60 ± 15% -0.5 0.09 ± 12% perf-profile.self.cycles-pp.free_extent_buffer
0.47 ± 11% -0.4 0.06 ± 11% perf-profile.self.cycles-pp.btrfs_get_64
0.40 ± 11% -0.3 0.08 ± 44% perf-profile.self.cycles-pp.idle_cpu
0.37 ± 12% -0.3 0.06 ± 11% perf-profile.self.cycles-pp.btrfs_root_node
0.36 ± 7% -0.3 0.06 ± 7% perf-profile.self.cycles-pp.down_read
0.30 ± 7% -0.2 0.05 ± 7% perf-profile.self.cycles-pp.up_read
1.24 ± 2% -0.2 1.06 perf-profile.self.cycles-pp._raw_spin_lock
0.20 ± 4% -0.2 0.02 ± 99% perf-profile.self.cycles-pp.find_extent_buffer_nolock
0.20 ± 8% -0.1 0.06 ± 45% perf-profile.self.cycles-pp._find_next_bit
0.17 ± 3% -0.1 0.06 ± 18% perf-profile.self.cycles-pp.update_load_avg
0.10 ± 10% -0.1 0.05 ± 46% perf-profile.self.cycles-pp.ktime_get
0.07 ± 6% -0.0 0.03 ± 70% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.14 ± 5% -0.0 0.11 ± 6% perf-profile.self.cycles-pp.kmem_cache_alloc
0.13 ± 4% -0.0 0.11 ± 7% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string
0.08 ± 6% -0.0 0.06 ± 6% perf-profile.self.cycles-pp.kmem_cache_free
0.08 ± 4% -0.0 0.06 ± 7% perf-profile.self.cycles-pp.set_extent_bit
0.08 ± 6% -0.0 0.06 perf-profile.self.cycles-pp.__might_resched
0.07 -0.0 0.06 ± 8% perf-profile.self.cycles-pp.btrfs_buffered_write
0.04 ± 45% +0.0 0.07 ± 7% perf-profile.self.cycles-pp.rwsem_optimistic_spin
0.00 +0.2 0.20 ± 17% perf-profile.self.cycles-pp.osq_lock
69.56 +16.1 85.62 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpathTo reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
sudo bin/lkp installjob.yaml# job file is attached in this email
bin/lkp split-job --compatiblejob.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.
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.6,866 lines not shown · raw message
Part of this message is not shown here. View the raw message.