| 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
| ||
|
Message-ID: <202407301600.a03deb58-oliver.sang@intel.com>
Date: Wed, 31 Jul 2024 12:55:59 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Jan Kara <jack@...e.cz>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>, <linux-kernel@...r.kernel.org>,
Theodore Ts'o <tytso@....edu>, Zhang Yi <yi.zhang@...wei.com>,
<linux-ext4@...r.kernel.org>, <ying.huang@...el.com>, <feng.tang@...el.com>,
<fengwei.yin@...el.com>, <oliver.sang@...el.com>
Subject: [linus:master] [jbd2] a794c9ad02:
fxmark.ssd_ext4_MWCL_18_bufferedio.works/sec 10.9% improvement
Hello,
kernel test robot noticed a 10.9% improvement of fxmark.ssd_ext4_MWCL_18_bufferedio.works/sec on:
commit: a794c9ad026f0a28044347f31929fcdb0270eadc ("jbd2: increase maximum transaction size")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
testcase: fxmark
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz (Ice Lake) with 128G memory
parameters:
disk: 1SSD
media: ssd
test: MWCL
fstype: ext4
directio: bufferedio
thread_nr: 18
cpufreq_governor: performance
In addition to that, the commit also has significant impact on the following tests:
+------------------+-----------------------------------------------------------------------------------------------+
| testcase: change | fxmark: fxmark.ssd_ext4_MWCL_18_directio.works/sec 10.9% improvement |
| test machine | 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz (Cascade Lake) with 512G memory |
| test parameters | cpufreq_governor=performance |
| | directio=directio |
| | disk=1SSD |
| | fstype=ext4 |
| | media=ssd |
| | test=MWCL |
| | thread_nr=18 |
+------------------+-----------------------------------------------------------------------------------------------+
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240730/202407301600.a03deb58-oliver.sang@intel.com
=========================================================================================
compiler/cpufreq_governor/directio/disk/fstype/kconfig/media/rootfs/tbox_group/test/testcase/thread_nr:
gcc-13/performance/bufferedio/1SSD/ext4/x86_64-rhel-8.3/ssd/debian-11.1-x86_64-20220510.cgz/lkp-icl-2sp5/MWCL/fxmark/18
commit:
1cf5b024a3 ("jbd2: drop pointless shrinker batch initialization")
a794c9ad02 ("jbd2: increase maximum transaction size")
1cf5b024a3ffa479 a794c9ad026f0a28044347f3192
---------------- ---------------------------
%stddev %change %stddev
\ | \
10.27 +5.0% 10.78 ± 2% iostat.cpu.system
54.92 ± 8% +30.7% 71.75 ± 7% mpstat.max_utilization_pct
25.35 ± 14% -27.2% 18.46 ± 14% sched_debug.cfs_rq:/.util_est.avg
169479 ± 3% -7.0% 157666 ± 4% vmstat.io.bo
1278745 ± 2% +13.0% 1445139 ± 4% vmstat.memory.buff
0.18 ± 54% -0.1 0.10 ± 30% perf-profile.children.cycles-pp.sched_balance_softirq
0.09 ± 19% -0.0 0.05 ± 46% perf-profile.children.cycles-pp.__x64_sys_exit_group
0.10 ± 17% -0.0 0.06 ± 11% perf-profile.children.cycles-pp.do_group_exit
0.11 ± 14% -0.0 0.08 ± 16% perf-profile.children.cycles-pp.do_exit
2408170 -8.3% 2207695 ± 9% perf-stat.i.branch-misses
6871267 -4.3% 6578038 ± 2% perf-stat.i.cache-references
2404936 -8.3% 2204831 ± 9% perf-stat.ps.branch-misses
6890735 -4.3% 6594005 ± 2% perf-stat.ps.cache-references
1295677 ± 2% +14.0% 1477204 ± 4% numa-meminfo.node0.Active
1280375 ± 2% +13.9% 1458502 ± 4% numa-meminfo.node0.Active(file)
5276009 ± 2% +12.7% 5945616 ± 3% numa-meminfo.node0.KReclaimable
5276009 ± 2% +12.7% 5945616 ± 3% numa-meminfo.node0.SReclaimable
677395 ± 3% +13.1% 766117 ± 5% numa-meminfo.node0.SUnreclaim
5953404 ± 2% +12.7% 6711734 ± 3% numa-meminfo.node0.Slab
320063 ± 2% +13.9% 364570 ± 4% numa-vmstat.node0.nr_active_file
748619 +15.4% 863566 numa-vmstat.node0.nr_dirtied
1318890 ± 2% +12.7% 1486316 ± 3% numa-vmstat.node0.nr_slab_reclaimable
169339 ± 3% +13.1% 191517 ± 5% numa-vmstat.node0.nr_slab_unreclaimable
748621 +15.4% 863569 numa-vmstat.node0.nr_written
320063 ± 2% +13.9% 364570 ± 4% numa-vmstat.node0.nr_zone_active_file
1296975 ± 2% +14.2% 1480589 ± 4% meminfo.Active
1281245 ± 2% +14.1% 1461473 ± 4% meminfo.Active(file)
1283104 ± 2% +14.0% 1462913 ± 4% meminfo.Buffers
5305939 ± 2% +12.5% 5970380 ± 4% meminfo.KReclaimable
5305939 ± 2% +12.5% 5970380 ± 4% meminfo.SReclaimable
775354 +9.6% 849840 ± 3% meminfo.SUnreclaim
6081293 ± 2% +12.2% 6820221 ± 3% meminfo.Slab
420.02 ± 3% -6.9% 391.11 fxmark.ssd_ext4_MWCL_18_bufferedio.idle_sec
46.36 ± 3% -7.3% 42.95 fxmark.ssd_ext4_MWCL_18_bufferedio.idle_util
133.80 +9.9% 147.07 fxmark.ssd_ext4_MWCL_18_bufferedio.sys_sec
14.77 +9.4% 16.15 ± 2% fxmark.ssd_ext4_MWCL_18_bufferedio.sys_util
3.40 ± 3% +12.3% 3.81 ± 2% fxmark.ssd_ext4_MWCL_18_bufferedio.user_sec
0.37 ± 3% +11.8% 0.42 ± 2% fxmark.ssd_ext4_MWCL_18_bufferedio.user_util
9455194 +11.4% 10532038 fxmark.ssd_ext4_MWCL_18_bufferedio.works
187654 +10.9% 208067 fxmark.ssd_ext4_MWCL_18_bufferedio.works/sec
320194 ± 2% +14.0% 364991 ± 4% proc-vmstat.nr_active_file
748619 +15.4% 863566 proc-vmstat.nr_dirtied
1049747 +4.3% 1095271 proc-vmstat.nr_file_pages
1326715 ± 2% +12.5% 1492704 ± 4% proc-vmstat.nr_slab_reclaimable
193876 +9.6% 212469 ± 3% proc-vmstat.nr_slab_unreclaimable
748621 +15.4% 863569 proc-vmstat.nr_written
320194 ± 2% +14.0% 364991 ± 4% proc-vmstat.nr_zone_active_file
2458878 +7.3% 2639428 proc-vmstat.numa_hit
2325681 +7.8% 2506229 proc-vmstat.numa_local
5333733 +9.0% 5812775 proc-vmstat.pgalloc_normal
5244126 +9.3% 5730805 proc-vmstat.pgfree
18378357 ± 2% -4.6% 17536147 ± 2% proc-vmstat.pgpgout
***************************************************************************************************
lkp-csl-2sp7: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz (Cascade Lake) with 512G memory
=========================================================================================
compiler/cpufreq_governor/directio/disk/fstype/kconfig/media/rootfs/tbox_group/test/testcase/thread_nr:
gcc-13/performance/directio/1SSD/ext4/x86_64-rhel-8.3/ssd/debian-11.1-x86_64-20220510.cgz/lkp-csl-2sp7/MWCL/fxmark/18
commit:
1cf5b024a3 ("jbd2: drop pointless shrinker batch initialization")
a794c9ad02 ("jbd2: increase maximum transaction size")
1cf5b024a3ffa479 a794c9ad026f0a28044347f3192
---------------- ---------------------------
%stddev %change %stddev
\ | \
82.99 ± 12% +20.2% 99.71 mpstat.max_utilization_pct
329.38 -5.0% 313.04 ± 2% perf-stat.i.instructions-per-iTLB-miss
153741 ± 4% +14.4% 175847 ± 2% turbostat.C1
102.10 +1.1% 103.26 turbostat.PkgWatt
76.73 -1.7% 75.39 iostat.cpu.idle
13.30 +2.2% 13.60 iostat.cpu.iowait
9.52 ± 2% +8.5% 10.33 ± 2% iostat.cpu.system
115484 -7.5% 106777 vmstat.io.bo
911997 +13.2% 1032821 vmstat.memory.buff
26825 +1.2% 27151 vmstat.system.in
45.31 ± 2% -10.1% 40.72 ± 3% fxmark.ssd_ext4_MWCL_18_directio.idle_util
172.12 ± 3% +15.7% 199.13 ± 3% fxmark.ssd_ext4_MWCL_18_directio.sys_sec
19.08 ± 3% +15.1% 21.95 ± 3% fxmark.ssd_ext4_MWCL_18_directio.sys_util
9211191 +11.5% 10268392 fxmark.ssd_ext4_MWCL_18_directio.works
183642 +10.9% 203658 fxmark.ssd_ext4_MWCL_18_directio.works/sec
15.67 ± 3% +10.6% 17.33 ± 2% fxmark.time.percent_of_cpu_this_job_got
919451 +13.3% 1041606 meminfo.Active
913989 +13.3% 1035788 meminfo.Active(file)
915350 +13.3% 1036928 meminfo.Buffers
3702431 +12.3% 4157764 meminfo.KReclaimable
3702431 +12.3% 4157764 meminfo.SReclaimable
4266197 +11.9% 4773429 meminfo.Slab
919001 +13.3% 1041492 numa-meminfo.node0.Active
913908 +13.4% 1036089 numa-meminfo.node0.Active(file)
3680931 +12.3% 4135083 numa-meminfo.node0.KReclaimable
3680931 +12.3% 4135083 numa-meminfo.node0.SReclaimable
499103 ± 3% +12.2% 560196 ± 2% numa-meminfo.node0.SUnreclaim
4180035 +12.3% 4695280 numa-meminfo.node0.Slab
228435 +13.4% 258980 numa-vmstat.node0.nr_active_file
741634 +9.7% 813930 ± 4% numa-vmstat.node0.nr_dirtied
920204 +12.3% 1033566 numa-vmstat.node0.nr_slab_reclaimable
124764 ± 3% +12.2% 140030 ± 2% numa-vmstat.node0.nr_slab_unreclaimable
741636 +9.7% 813931 ± 4% numa-vmstat.node0.nr_written
228435 +13.4% 258980 numa-vmstat.node0.nr_zone_active_file
44474 ± 8% +27.7% 56792 ± 3% sched_debug.cfs_rq:/.avg_vruntime.avg
61425 ± 14% +28.1% 78705 ± 10% sched_debug.cfs_rq:/.avg_vruntime.max
38449 ± 9% +28.4% 49369 ± 3% sched_debug.cfs_rq:/.avg_vruntime.min
44474 ± 8% +27.7% 56792 ± 3% sched_debug.cfs_rq:/.min_vruntime.avg
61425 ± 14% +28.1% 78705 ± 10% sched_debug.cfs_rq:/.min_vruntime.max
38449 ± 9% +28.4% 49369 ± 3% sched_debug.cfs_rq:/.min_vruntime.min
1368 +6.3% 1453 ± 2% proc-vmstat.nr_active_anon
228583 +13.4% 259248 proc-vmstat.nr_active_file
741634 +9.7% 813930 ± 4% proc-vmstat.nr_dirtied
960887 +3.2% 991722 proc-vmstat.nr_file_pages
926829 +12.3% 1040665 proc-vmstat.nr_slab_reclaimable
141078 +9.2% 154034 proc-vmstat.nr_slab_unreclaimable
741636 +9.7% 813931 ± 4% proc-vmstat.nr_written
1368 +6.3% 1453 ± 2% proc-vmstat.nr_zone_active_anon
228583 +13.4% 259248 proc-vmstat.nr_zone_active_file
2377668 +7.2% 2548605 proc-vmstat.numa_hit
2277581 +7.3% 2444791 proc-vmstat.numa_local
27510 +9.6% 30163 proc-vmstat.pgactivate
5155991 +9.2% 5629540 proc-vmstat.pgalloc_normal
5134429 +9.2% 5608738 proc-vmstat.pgfree
18015387 -5.4% 17048860 proc-vmstat.pgpgout
6.85 ± 6% -2.2 4.68 ± 12% perf-profile.calltrace.cycles-pp.kthread.ret_from_fork.ret_from_fork_asm
6.85 ± 6% -2.2 4.68 ± 12% perf-profile.calltrace.cycles-pp.ret_from_fork.ret_from_fork_asm
6.85 ± 6% -2.2 4.68 ± 12% perf-profile.calltrace.cycles-pp.ret_from_fork_asm
5.63 ± 5% -1.9 3.74 ± 14% perf-profile.calltrace.cycles-pp.kjournald2.kthread.ret_from_fork.ret_from_fork_asm
5.61 ± 5% -1.9 3.74 ± 14% perf-profile.calltrace.cycles-pp.jbd2_journal_commit_transaction.kjournald2.kthread.ret_from_fork.ret_from_fork_asm
2.53 ± 10% -0.7 1.83 ± 8% perf-profile.calltrace.cycles-pp.jbd2_journal_get_write_access.__ext4_journal_get_write_access.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir
2.55 ± 9% -0.7 1.86 ± 8% perf-profile.calltrace.cycles-pp.__ext4_journal_get_write_access.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir.ext4_create
1.79 ± 12% -0.6 1.17 ± 8% perf-profile.calltrace.cycles-pp.jbd2_journal_dirty_metadata.__ext4_handle_dirty_metadata.add_dirent_to_buf.ext4_dx_add_entry.ext4_add_entry
1.88 ± 11% -0.6 1.29 ± 8% perf-profile.calltrace.cycles-pp.__ext4_handle_dirty_metadata.add_dirent_to_buf.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir
1.68 ± 12% -0.6 1.13 ± 10% perf-profile.calltrace.cycles-pp.do_get_write_access.jbd2_journal_get_write_access.__ext4_journal_get_write_access.ext4_dx_add_entry.ext4_add_entry
0.95 ± 19% -0.5 0.41 ± 72% perf-profile.calltrace.cycles-pp._raw_spin_lock.do_get_write_access.jbd2_journal_get_write_access.__ext4_journal_get_write_access.ext4_dx_add_entry
1.42 ± 11% -0.5 0.94 ± 14% perf-profile.calltrace.cycles-pp.crc32c_pcl_intel_update.jbd2_journal_commit_transaction.kjournald2.kthread.ret_from_fork
1.40 ± 11% -0.5 0.92 ± 14% perf-profile.calltrace.cycles-pp.crc_pcl.crc32c_pcl_intel_update.jbd2_journal_commit_transaction.kjournald2.kthread
1.08 ± 17% -0.4 0.65 ± 9% perf-profile.calltrace.cycles-pp._raw_spin_lock.jbd2_journal_dirty_metadata.__ext4_handle_dirty_metadata.add_dirent_to_buf.ext4_dx_add_entry
1.60 ± 7% -0.3 1.31 ± 11% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
0.63 ± 6% -0.3 0.38 ± 71% perf-profile.calltrace.cycles-pp.asm_common_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
0.63 ± 6% -0.2 0.38 ± 71% perf-profile.calltrace.cycles-pp.common_interrupt.asm_common_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
0.95 ± 11% -0.2 0.72 ± 5% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
0.84 ± 12% -0.2 0.64 ± 6% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
0.76 ± 5% -0.1 0.66 ± 8% perf-profile.calltrace.cycles-pp.jbd2_journal_get_write_access.__ext4_journal_get_write_access.__ext4_new_inode.ext4_create.lookup_open
1.52 ± 6% +0.1 1.62 ± 2% perf-profile.calltrace.cycles-pp.do_open.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat
0.67 ± 13% +0.1 0.81 ± 9% perf-profile.calltrace.cycles-pp.__ext4_read_dirblock.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir.ext4_create
0.84 ± 9% +0.2 1.00 ± 13% perf-profile.calltrace.cycles-pp.dput.__fput.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.27 ± 6% +0.2 1.44 ± 5% perf-profile.calltrace.cycles-pp.ext4_bread.__ext4_read_dirblock.dx_probe.ext4_dx_add_entry.ext4_add_entry
1.26 ± 6% +0.2 1.43 ± 4% perf-profile.calltrace.cycles-pp.ext4_getblk.ext4_bread.__ext4_read_dirblock.dx_probe.ext4_dx_add_entry
1.46 ± 7% +0.2 1.66 ± 4% perf-profile.calltrace.cycles-pp.do_split.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir.ext4_create
1.42 ± 7% +0.2 1.66 ± 6% perf-profile.calltrace.cycles-pp.__ext4_read_dirblock.dx_probe.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir
2.34 ± 4% +0.3 2.59 ± 3% perf-profile.calltrace.cycles-pp.dx_probe.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir.ext4_create
1.98 ± 3% +0.3 2.24 ± 6% perf-profile.calltrace.cycles-pp.__fput.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
2.54 ± 4% +0.3 2.83 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
2.57 ± 4% +0.3 2.87 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__close
2.42 ± 4% +0.3 2.74 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
2.39 ± 5% +0.4 2.74 ± 5% perf-profile.calltrace.cycles-pp.ext4_bread.__ext4_read_dirblock.dx_probe.ext4_dx_find_entry.__ext4_find_entry
2.38 ± 5% +0.4 2.73 ± 5% perf-profile.calltrace.cycles-pp.ext4_getblk.ext4_bread.__ext4_read_dirblock.dx_probe.ext4_dx_find_entry
2.62 ± 6% +0.5 3.07 ± 4% perf-profile.calltrace.cycles-pp.__ext4_read_dirblock.dx_probe.ext4_dx_find_entry.__ext4_find_entry.ext4_lookup
3.64 ± 4% +0.5 4.13 ± 4% perf-profile.calltrace.cycles-pp.dx_probe.ext4_dx_find_entry.__ext4_find_entry.ext4_lookup.lookup_open
18.30 ± 2% +0.9 19.16 perf-profile.calltrace.cycles-pp.__ext4_find_entry.ext4_lookup.lookup_open.open_last_lookups.path_openat
18.92 ± 2% +0.9 19.81 perf-profile.calltrace.cycles-pp.ext4_lookup.lookup_open.open_last_lookups.path_openat.do_filp_open
4.84 +1.0 5.82 ± 10% perf-profile.calltrace.cycles-pp.__ext4_check_dir_entry.ext4_find_dest_de.add_dirent_to_buf.ext4_dx_add_entry.ext4_add_entry
15.33 +1.2 16.48 ± 2% perf-profile.calltrace.cycles-pp.ext4_find_dest_de.add_dirent_to_buf.ext4_dx_add_entry.ext4_add_entry.ext4_add_nondir
51.37 +1.7 53.03 ± 2% perf-profile.calltrace.cycles-pp.ext4_create.lookup_open.open_last_lookups.path_openat.do_filp_open
72.49 +2.6 75.05 perf-profile.calltrace.cycles-pp.lookup_open.open_last_lookups.path_openat.do_filp_open.do_sys_openat2
73.47 +2.7 76.12 perf-profile.calltrace.cycles-pp.open_last_lookups.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat
80.62 +2.7 83.30 perf-profile.calltrace.cycles-pp.open64
78.14 +2.7 80.83 perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64
79.10 +2.7 81.80 perf-profile.calltrace.cycles-pp.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
78.22 +2.7 80.92 perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe
79.14 +2.7 81.85 perf-profile.calltrace.cycles-pp.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
79.56 +2.7 82.29 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64
79.60 +2.7 82.33 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.open64
6.86 ± 6% -2.2 4.68 ± 12% perf-profile.children.cycles-pp.ret_from_fork
6.86 ± 6% -2.2 4.68 ± 12% perf-profile.children.cycles-pp.ret_from_fork_asm
6.85 ± 6% -2.2 4.68 ± 12% perf-profile.children.cycles-pp.kthread
5.63 ± 5% -1.9 3.74 ± 14% perf-profile.children.cycles-pp.jbd2_journal_commit_transaction
5.63 ± 5% -1.9 3.74 ± 14% perf-profile.children.cycles-pp.kjournald2
6.26 ± 7% -1.0 5.24 ± 4% perf-profile.children.cycles-pp.jbd2_journal_get_write_access
6.46 ± 7% -1.0 5.45 ± 4% perf-profile.children.cycles-pp.__ext4_journal_get_write_access
2.15 ± 11% -0.7 1.46 ± 7% perf-profile.children.cycles-pp.jbd2_journal_dirty_metadata
3.07 ± 8% -0.7 2.38 ± 6% perf-profile.children.cycles-pp.__ext4_handle_dirty_metadata
1.96 ± 12% -0.6 1.32 ± 9% perf-profile.children.cycles-pp.do_get_write_access
2.74 ± 16% -0.5 2.20 ± 11% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
2.62 ± 4% -0.4 2.20 ± 5% perf-profile.children.cycles-pp.crc_pcl
3.91 ± 4% -0.4 3.49 ± 4% perf-profile.children.cycles-pp.crc32c_pcl_intel_update
1.18 ± 4% -0.3 0.89 ± 10% perf-profile.children.cycles-pp.__jbd2_journal_file_buffer
1.67 ± 6% -0.3 1.38 ± 11% perf-profile.children.cycles-pp.intel_idle
0.66 ± 8% -0.2 0.44 ± 20% perf-profile.children.cycles-pp.jbd2_journal_write_metadata_buffer
1.28 ± 7% -0.2 1.07 ± 6% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
0.58 ± 8% -0.2 0.40 ± 14% perf-profile.children.cycles-pp.__jbd2_journal_refile_buffer
1.13 ± 9% -0.2 0.95 ± 7% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
0.56 ± 9% -0.2 0.40 ± 11% perf-profile.children.cycles-pp.__jbd2_journal_temp_unlink_buffer
1.20 ± 2% -0.2 1.05 ± 4% perf-profile.children.cycles-pp.kmem_cache_alloc_noprof
0.40 ± 8% -0.1 0.27 ± 18% perf-profile.children.cycles-pp.jbd2_journal_put_journal_head
0.33 ± 9% -0.1 0.21 ± 21% perf-profile.children.cycles-pp.__jbd2_journal_remove_checkpoint
0.34 ± 15% -0.1 0.24 ± 14% perf-profile.children.cycles-pp.mark_buffer_dirty
0.36 ± 10% -0.1 0.26 ± 10% perf-profile.children.cycles-pp.submit_bh_wbc
0.26 ± 14% -0.1 0.17 ± 13% perf-profile.children.cycles-pp.__slab_free
0.35 ± 10% -0.1 0.26 ± 12% perf-profile.children.cycles-pp.end_bio_bh_io_sync
0.28 ± 12% -0.1 0.20 ± 13% perf-profile.children.cycles-pp.jbd2_journal_add_journal_head
0.41 ± 13% -0.1 0.33 ± 15% perf-profile.children.cycles-pp.submit_bio_noacct_nocheck
0.38 ± 16% -0.1 0.30 ± 15% perf-profile.children.cycles-pp.__submit_bio
0.16 ± 17% -0.1 0.09 ± 17% perf-profile.children.cycles-pp.free_buffer_head
0.22 ± 6% -0.1 0.14 ± 28% perf-profile.children.cycles-pp.jbd2_journal_file_buffer
0.59 ± 7% -0.1 0.53 ± 7% perf-profile.children.cycles-pp.__hrtimer_run_queues
0.34 ± 13% -0.1 0.27 ± 12% perf-profile.children.cycles-pp.blk_mq_submit_bio
0.16 ± 16% -0.1 0.10 ± 15% perf-profile.children.cycles-pp.bio_alloc_bioset
0.23 ± 8% -0.0 0.18 ± 14% perf-profile.children.cycles-pp.ktime_get
0.11 ± 6% -0.0 0.07 ± 12% perf-profile.children.cycles-pp.mempool_alloc_noprof
0.12 ± 14% +0.0 0.15 ± 4% perf-profile.children.cycles-pp.ext4_get_group_info
0.10 ± 18% +0.0 0.15 ± 16% perf-profile.children.cycles-pp.__irqentry_text_start
0.09 ± 32% +0.1 0.16 ± 24% perf-profile.children.cycles-pp.mnt_want_write
0.22 ± 9% +0.1 0.29 ± 16% perf-profile.children.cycles-pp.memcg_list_lru_alloc
0.13 ± 53% +0.1 0.22 ± 30% perf-profile.children.cycles-pp.__dquot_initialize
2.40 ± 3% +0.2 2.59 ± 5% perf-profile.children.cycles-pp.ext4_fill_raw_inode
1.47 ± 7% +0.2 1.67 ± 4% perf-profile.children.cycles-pp.do_split
2.00 ± 3% +0.3 2.26 ± 6% perf-profile.children.cycles-pp.__fput
2.42 ± 4% +0.3 2.74 ± 5% perf-profile.children.cycles-pp.__x64_sys_close
5.98 ± 4% +0.8 6.74 ± 2% perf-profile.children.cycles-pp.dx_probe
18.30 ± 2% +0.9 19.16 perf-profile.children.cycles-pp.__ext4_find_entry
18.92 ± 2% +0.9 19.82 perf-profile.children.cycles-pp.ext4_lookup
4.94 +1.0 5.94 ± 10% perf-profile.children.cycles-pp.__ext4_check_dir_entry
8.26 ± 5% +1.0 9.29 ± 3% perf-profile.children.cycles-pp.__ext4_read_dirblock
15.44 +1.1 16.58 ± 2% perf-profile.children.cycles-pp.ext4_find_dest_de
51.38 +1.7 53.03 ± 2% perf-profile.children.cycles-pp.ext4_create
72.50 +2.6 75.06 perf-profile.children.cycles-pp.lookup_open
73.48 +2.7 76.13 perf-profile.children.cycles-pp.open_last_lookups
80.70 +2.7 83.36 perf-profile.children.cycles-pp.open64
78.19 +2.7 80.87 perf-profile.children.cycles-pp.path_openat
79.15 +2.7 81.84 perf-profile.children.cycles-pp.do_sys_openat2
78.26 +2.7 80.96 perf-profile.children.cycles-pp.do_filp_open
79.19 +2.7 81.89 perf-profile.children.cycles-pp.__x64_sys_openat
82.66 +2.9 85.59 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
82.58 +2.9 85.51 perf-profile.children.cycles-pp.do_syscall_64
2.72 ± 16% -0.5 2.19 ± 11% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
2.61 ± 4% -0.4 2.18 ± 5% perf-profile.self.cycles-pp.crc_pcl
1.18 ± 5% -0.4 0.77 ± 16% perf-profile.self.cycles-pp.jbd2_journal_commit_transaction
2.27 ± 8% -0.3 1.97 ± 9% perf-profile.self.cycles-pp.jbd2_journal_get_write_access
1.67 ± 6% -0.3 1.38 ± 11% perf-profile.self.cycles-pp.intel_idle
0.78 ± 3% -0.2 0.57 ± 9% perf-profile.self.cycles-pp.__jbd2_journal_file_buffer
0.56 ± 9% -0.2 0.40 ± 11% perf-profile.self.cycles-pp.__jbd2_journal_temp_unlink_buffer
0.35 ± 5% -0.1 0.22 ± 28% perf-profile.self.cycles-pp.jbd2_journal_write_metadata_buffer
0.37 ± 7% -0.1 0.25 ± 20% perf-profile.self.cycles-pp.jbd2_journal_put_journal_head
0.28 ± 13% -0.1 0.18 ± 14% perf-profile.self.cycles-pp.do_get_write_access
0.26 ± 13% -0.1 0.16 ± 13% perf-profile.self.cycles-pp.__slab_free
0.26 ± 13% -0.1 0.18 ± 14% perf-profile.self.cycles-pp.jbd2_journal_add_journal_head
0.49 ± 6% -0.1 0.44 ± 6% perf-profile.self.cycles-pp.kmem_cache_alloc_noprof
0.18 ± 10% -0.0 0.13 ± 23% perf-profile.self.cycles-pp.cpuidle_enter_state
0.17 ± 7% -0.0 0.13 ± 9% perf-profile.self.cycles-pp.jbd2__journal_start
0.16 ± 8% -0.0 0.13 ± 13% perf-profile.self.cycles-pp.ktime_get
0.12 ± 14% +0.0 0.15 ± 3% perf-profile.self.cycles-pp.ext4_get_group_info
0.03 ±100% +0.1 0.08 ± 27% perf-profile.self.cycles-pp.ext4_group_desc_csum_set
1.06 ± 6% +0.1 1.17 ± 5% perf-profile.self.cycles-pp.filemap_get_entry
4.89 +1.0 5.88 ± 10% perf-profile.self.cycles-pp.__ext4_check_dir_entry
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
Powered by blists - more mailing lists