| 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: <20181019012828.GJ16117@shao2-debian>
Date: Fri, 19 Oct 2018 09:28:28 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Daniel Rosenberg <drosen@...gle.com>
Cc: Jaegeuk Kim <jaegeuk@...nel.org>,
LKML <linux-kernel@...r.kernel.org>,
linux-f2fs-devel@...ts.sourceforge.net, lkp@...org
Subject: [LKP] [f2fs] 4d8253119c: aim7.jobs-per-min -11.0% regression
Greeting,
FYI, we noticed a -11.0% regression of aim7.jobs-per-min due to commit:
commit: 4d8253119c91ee549db724adac9ff3f7c1b6f318 ("f2fs: checkpoint disabling")
https://git.kernel.org/cgit/linux/kernel/git/jaegeuk/f2fs.git dev
in testcase: aim7
on test machine: 40 threads Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz with 384G memory
with following parameters:
disk: 1BRD_48G
fs: f2fs
test: disk_rw
load: 3000
cpufreq_governor: performance
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/rootfs/tbox_group/test/testcase:
gcc-7/performance/1BRD_48G/f2fs/x86_64-rhel-7.2/3000/debian-x86_64-2018-04-03.cgz/lkp-ivb-ep01/disk_rw/aim7
commit:
fb7d70db30 ("f2fs: clear PageError on the read path")
4d8253119c ("f2fs: checkpoint disabling")
fb7d70db305a1446 4d8253119c91ee549db724adac
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
1:4 -25% :4 dmesg.WARNING:at_ip__slab_free/0x
%stddev %change %stddev
\ | \
107974 ± 2% -11.0% 96114 aim7.jobs-per-min
167.22 ± 3% +12.2% 187.65 aim7.time.elapsed_time
167.22 ± 3% +12.2% 187.65 aim7.time.elapsed_time.max
795131 +26.6% 1006572 ± 4% aim7.time.involuntary_context_switches
6079 ± 3% +13.6% 6904 aim7.time.system_time
288452 ± 64% -61.4% 111309 ±134% cpuidle.C3.usage
69671 +25.6% 87542 ± 13% interrupts.CAL:Function_call_interrupts
1165 -100.0% 0.00 meminfo.Mlocked
1.94 ± 4% -0.3 1.68 ± 2% mpstat.cpu.usr%
870227 ± 2% +20.6% 1049363 ± 9% softirqs.RCU
2754729 ± 6% +13.9% 3137384 softirqs.TIMER
7056 ± 3% -12.0% 6208 vmstat.io.bo
202.00 ± 7% +33.0% 268.75 ± 10% vmstat.procs.r
50764 ± 16% -27.5% 36813 ± 14% numa-meminfo.node0.SReclaimable
153567 ± 26% -36.0% 98338 ± 42% numa-meminfo.node0.Slab
45293 ± 18% +32.7% 60114 ± 9% numa-meminfo.node1.SReclaimable
8716 ± 3% +19.6% 10428 ± 2% slabinfo.ext4_io_end.active_objs
8716 ± 3% +19.6% 10428 ± 2% slabinfo.ext4_io_end.num_objs
9434 ± 3% +14.9% 10842 slabinfo.f2fs_extent_tree.active_objs
9434 ± 3% +14.9% 10842 slabinfo.f2fs_extent_tree.num_objs
18819 ± 12% -26.8% 13776 ± 22% numa-vmstat.node0
156.25 ± 14% -100.0% 0.00 numa-vmstat.node0.nr_mlock
12688 ± 16% -27.5% 9202 ± 14% numa-vmstat.node0.nr_slab_reclaimable
14753 ± 16% +34.5% 19839 ± 15% numa-vmstat.node1
133.00 ± 14% -100.0% 0.00 numa-vmstat.node1.nr_mlock
11327 ± 18% +32.7% 15036 ± 9% numa-vmstat.node1.nr_slab_reclaimable
410794 +4.6% 429491 proc-vmstat.nr_dirty
652264 +2.8% 670355 proc-vmstat.nr_file_pages
409361 +4.5% 427950 proc-vmstat.nr_inactive_file
289.75 ± 2% -100.0% 0.00 proc-vmstat.nr_mlock
409361 +4.5% 427950 proc-vmstat.nr_zone_inactive_file
410651 +4.6% 429423 proc-vmstat.nr_zone_write_pending
590098 ± 2% +8.1% 638010 proc-vmstat.pgfault
1745 -4.3% 1669 proc-vmstat.unevictable_pgs_culled
2898 +1.9% 2954 turbostat.Avg_MHz
288234 ± 64% -61.4% 111193 ±134% turbostat.C3
4.03 ± 22% -26.4% 2.97 ± 14% turbostat.CPU%c1
156.41 +4.4% 163.25 turbostat.CorWatt
14079224 ± 3% +13.9% 16040215 turbostat.IRQ
184.51 +3.5% 190.99 turbostat.PkgWatt
40.65 ± 2% -5.8% 38.28 turbostat.RAMWatt
7981 ± 3% +13.5% 9060 ± 2% turbostat.SMI
1.139e+12 +16.9% 1.332e+12 perf-stat.branch-instructions
0.75 ± 3% -0.1 0.65 ± 3% perf-stat.branch-miss-rate%
36.50 ± 4% +3.5 40.04 perf-stat.cache-miss-rate%
1735749 ± 2% +12.3% 1949439 ± 3% perf-stat.context-switches
1.951e+13 ± 3% +15.7% 2.257e+13 perf-stat.cpu-cycles
493731 ± 4% +10.4% 545082 ± 2% perf-stat.cpu-migrations
1.393e+12 +13.9% 1.587e+12 perf-stat.dTLB-loads
5.084e+12 +15.2% 5.857e+12 perf-stat.instructions
578938 ± 2% +7.5% 622537 perf-stat.minor-faults
42.61 ± 2% -1.7 40.91 perf-stat.node-load-miss-rate%
42.96 -0.8 42.18 perf-stat.node-store-miss-rate%
6.905e+09 +6.5% 7.353e+09 perf-stat.node-stores
578951 ± 2% +7.5% 622540 perf-stat.page-faults
52097 +55.9% 81203 sched_debug.cfs_rq:/.exec_clock.avg
56166 +51.7% 85220 sched_debug.cfs_rq:/.exec_clock.max
51857 +56.0% 80884 sched_debug.cfs_rq:/.exec_clock.min
485.17 ± 35% -33.0% 325.25 ± 5% sched_debug.cfs_rq:/.load_avg.max
2235072 +59.4% 3562439 sched_debug.cfs_rq:/.min_vruntime.avg
2401666 +58.0% 3795568 sched_debug.cfs_rq:/.min_vruntime.max
2147122 +58.4% 3401299 sched_debug.cfs_rq:/.min_vruntime.min
56208 ± 27% +65.1% 92820 ± 30% sched_debug.cfs_rq:/.min_vruntime.stddev
9.62 ± 7% +114.2% 20.60 ± 80% sched_debug.cfs_rq:/.runnable_load_avg.stddev
56172 ± 27% +65.1% 92751 ± 30% sched_debug.cfs_rq:/.spread0.stddev
89807 +34.6% 120913 sched_debug.cpu.clock.avg
89833 +34.6% 120952 sched_debug.cpu.clock.max
89776 +34.6% 120860 sched_debug.cpu.clock.min
16.53 ± 23% +88.8% 31.21 ± 37% sched_debug.cpu.clock.stddev
89807 +34.6% 120913 sched_debug.cpu.clock_task.avg
89833 +34.6% 120952 sched_debug.cpu.clock_task.max
89776 +34.6% 120860 sched_debug.cpu.clock_task.min
16.53 ± 23% +88.8% 31.21 ± 37% sched_debug.cpu.clock_task.stddev
43.50 +10.6% 48.12 ± 5% sched_debug.cpu.cpu_load[0].max
9.78 ± 7% +18.1% 11.55 ± 6% sched_debug.cpu.cpu_load[0].stddev
4471 ± 8% +25.1% 5594 ± 5% sched_debug.cpu.curr->pid.max
872.98 ± 6% +19.2% 1040 ± 6% sched_debug.cpu.curr->pid.stddev
65019 +46.6% 95328 sched_debug.cpu.nr_load_updates.avg
73610 +42.2% 104667 sched_debug.cpu.nr_load_updates.max
62894 +48.5% 93410 sched_debug.cpu.nr_load_updates.min
16278 ± 5% +48.9% 24238 sched_debug.cpu.nr_switches.avg
22788 ± 7% +31.3% 29923 ± 5% sched_debug.cpu.nr_switches.max
14444 ± 5% +53.2% 22129 sched_debug.cpu.nr_switches.min
216.67 ± 2% +41.4% 306.31 ± 22% sched_debug.cpu.nr_uninterruptible.max
91.09 ± 10% +34.7% 122.70 ± 6% sched_debug.cpu.nr_uninterruptible.stddev
15319 ± 6% +52.1% 23302 sched_debug.cpu.sched_count.avg
17371 ± 6% +51.4% 26294 ± 4% sched_debug.cpu.sched_count.max
14141 ± 5% +55.2% 21948 sched_debug.cpu.sched_count.min
729.23 ± 7% +30.0% 948.12 ± 15% sched_debug.cpu.sched_count.stddev
6468 ± 7% +42.8% 9234 sched_debug.cpu.ttwu_count.avg
8790 ± 8% +41.8% 12466 ± 6% sched_debug.cpu.ttwu_count.max
5087 ± 5% +43.3% 7288 ± 2% sched_debug.cpu.ttwu_count.min
810.76 ± 12% +33.8% 1084 ± 12% sched_debug.cpu.ttwu_count.stddev
1794 ± 4% +59.2% 2857 ± 2% sched_debug.cpu.ttwu_local.avg
2499 ± 10% +51.1% 3777 ± 10% sched_debug.cpu.ttwu_local.max
1405 ± 4% +58.2% 2223 ± 2% sched_debug.cpu.ttwu_local.min
231.51 ± 13% +47.9% 342.52 ± 11% sched_debug.cpu.ttwu_local.stddev
89776 +34.6% 120860 sched_debug.cpu_clk
88952 +34.9% 120037 sched_debug.ktime
0.00 ± 16% -100.0% 0.00 sched_debug.rt_rq:/.rt_time.avg
0.02 ± 16% -100.0% 0.00 sched_debug.rt_rq:/.rt_time.max
0.00 ± 16% -100.0% 0.00 sched_debug.rt_rq:/.rt_time.stddev
90219 +34.5% 121306 sched_debug.sched_clk
1.63 ± 15% -0.5 1.12 ± 12% perf-profile.calltrace.cycles-pp.f2fs_lookup_extent_cache.f2fs_write_begin.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter
0.74 ± 25% -0.5 0.27 ±100% perf-profile.calltrace.cycles-pp.balance_dirty_pages_ratelimited.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter.__vfs_write
1.30 -0.2 1.10 ± 4% perf-profile.calltrace.cycles-pp.syscall_return_via_sysret
0.78 ± 9% -0.2 0.59 ± 3% perf-profile.calltrace.cycles-pp.f2fs_preallocate_blocks.f2fs_file_write_iter.__vfs_write.vfs_write.ksys_write
0.58 ± 4% -0.2 0.39 ± 57% perf-profile.calltrace.cycles-pp.security_file_permission.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.60 -0.2 1.42 perf-profile.calltrace.cycles-pp.pagecache_get_page.f2fs_write_begin.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter
1.37 ± 2% -0.2 1.20 ± 6% perf-profile.calltrace.cycles-pp.__entry_SYSCALL_64_trampoline
1.31 ± 4% -0.1 1.18 perf-profile.calltrace.cycles-pp.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter.__vfs_write
1.13 ± 4% -0.1 1.02 perf-profile.calltrace.cycles-pp.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter
0.72 ± 6% -0.1 0.62 ± 3% perf-profile.calltrace.cycles-pp.pagecache_get_page.__get_node_page.f2fs_write_begin.generic_perform_write.__generic_file_write_iter
1.07 ± 5% -0.1 0.98 ± 2% perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter
0.61 ± 3% -0.1 0.53 perf-profile.calltrace.cycles-pp.find_get_entry.pagecache_get_page.f2fs_write_begin.generic_perform_write.__generic_file_write_iter
96.44 +0.6 97.02 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
96.32 +0.6 96.89 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
12.03 ± 3% +0.8 12.81 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_reserve_new_blocks
12.11 ± 3% +0.8 12.90 perf-profile.calltrace.cycles-pp.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_reserve_new_blocks.f2fs_reserve_block.f2fs_get_block
12.11 ± 3% +0.8 12.90 perf-profile.calltrace.cycles-pp.f2fs_mark_inode_dirty_sync.f2fs_reserve_new_blocks.f2fs_reserve_block.f2fs_get_block.f2fs_write_begin
12.09 ± 3% +0.8 12.89 perf-profile.calltrace.cycles-pp._raw_spin_lock.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_reserve_new_blocks.f2fs_reserve_block
93.07 +1.0 94.07 perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
92.77 +1.0 93.82 perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
25.85 ± 3% +1.1 26.98 perf-profile.calltrace.cycles-pp.f2fs_get_block.f2fs_write_begin.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter
25.65 ± 3% +1.2 26.82 perf-profile.calltrace.cycles-pp.f2fs_reserve_block.f2fs_get_block.f2fs_write_begin.generic_perform_write.__generic_file_write_iter
25.61 ± 3% +1.2 26.80 perf-profile.calltrace.cycles-pp.f2fs_reserve_new_blocks.f2fs_reserve_block.f2fs_get_block.f2fs_write_begin.generic_perform_write
91.35 +1.3 92.69 perf-profile.calltrace.cycles-pp.__vfs_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
90.88 +1.7 92.56 perf-profile.calltrace.cycles-pp.f2fs_file_write_iter.__vfs_write.vfs_write.ksys_write.do_syscall_64
88.26 +2.7 90.92 perf-profile.calltrace.cycles-pp.__generic_file_write_iter.f2fs_file_write_iter.__vfs_write.vfs_write.ksys_write
86.91 ± 2% +3.2 90.10 perf-profile.calltrace.cycles-pp.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter.__vfs_write.vfs_write
52.04 ± 3% +3.3 55.37 perf-profile.calltrace.cycles-pp.f2fs_write_end.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter.__vfs_write
49.56 ± 3% +3.6 53.17 perf-profile.calltrace.cycles-pp.f2fs_mark_inode_dirty_sync.f2fs_write_end.generic_perform_write.__generic_file_write_iter.f2fs_file_write_iter
49.56 ± 3% +3.6 53.17 perf-profile.calltrace.cycles-pp.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_write_end.generic_perform_write.__generic_file_write_iter
48.87 ± 4% +3.6 52.49 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_write_end
49.49 ± 3% +3.6 53.14 perf-profile.calltrace.cycles-pp._raw_spin_lock.f2fs_inode_dirtied.f2fs_mark_inode_dirty_sync.f2fs_write_end.generic_perform_write
1.82 ± 14% -0.6 1.26 ± 12% perf-profile.children.cycles-pp.f2fs_lookup_extent_cache
0.58 ± 63% -0.4 0.18 ± 11% perf-profile.children.cycles-pp.file_update_time
2.37 ± 2% -0.3 2.08 perf-profile.children.cycles-pp.pagecache_get_page
0.53 ± 16% -0.2 0.28 ± 34% perf-profile.children.cycles-pp._raw_read_lock
1.48 ± 2% -0.2 1.24 ± 4% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.74 ± 25% -0.2 0.52 ± 6% perf-profile.children.cycles-pp.balance_dirty_pages_ratelimited
0.46 ± 38% -0.2 0.25 ± 3% perf-profile.children.cycles-pp.ksys_lseek
0.80 ± 9% -0.2 0.60 ± 4% perf-profile.children.cycles-pp.f2fs_preallocate_blocks
1.49 ± 2% -0.2 1.30 ± 6% perf-profile.children.cycles-pp.__entry_SYSCALL_64_trampoline
0.31 ± 54% -0.2 0.12 ± 10% perf-profile.children.cycles-pp.f2fs_llseek
0.23 ± 54% -0.2 0.07 ± 12% perf-profile.children.cycles-pp.f2fs_map_blocks
1.09 ± 3% -0.1 0.94 perf-profile.children.cycles-pp.find_get_entry
1.33 ± 4% -0.1 1.18 perf-profile.children.cycles-pp.iov_iter_copy_from_user_atomic
0.45 ± 11% -0.1 0.32 ± 7% perf-profile.children.cycles-pp.cpuidle_enter_state
0.46 ± 11% -0.1 0.33 ± 6% perf-profile.children.cycles-pp.secondary_startup_64
0.46 ± 11% -0.1 0.33 ± 6% perf-profile.children.cycles-pp.cpu_startup_entry
0.46 ± 11% -0.1 0.33 ± 6% perf-profile.children.cycles-pp.do_idle
0.44 ± 11% -0.1 0.32 ± 6% perf-profile.children.cycles-pp.intel_idle
0.45 ± 9% -0.1 0.33 ± 6% perf-profile.children.cycles-pp.start_secondary
0.25 ± 38% -0.1 0.13 ± 9% perf-profile.children.cycles-pp.read_node_page
1.14 ± 4% -0.1 1.03 ± 2% perf-profile.children.cycles-pp.copyin
1.08 ± 5% -0.1 0.99 ± 2% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
0.54 ± 7% -0.1 0.47 ± 4% perf-profile.children.cycles-pp.radix_tree_lookup_slot
0.58 ± 5% -0.1 0.52 ± 5% perf-profile.children.cycles-pp.security_file_permission
0.49 ± 8% -0.1 0.43 ± 6% perf-profile.children.cycles-pp.__radix_tree_lookup
0.48 ± 2% -0.1 0.43 ± 4% perf-profile.children.cycles-pp.add_to_page_cache_lru
0.16 ± 11% -0.1 0.11 ± 4% perf-profile.children.cycles-pp.iov_iter_advance
0.15 ± 12% -0.1 0.10 perf-profile.children.cycles-pp.fsnotify
0.18 ± 13% -0.0 0.14 ± 6% perf-profile.children.cycles-pp.delete_from_page_cache_batch
0.25 ± 9% -0.0 0.21 ± 5% perf-profile.children.cycles-pp.__set_page_dirty_nobuffers
0.12 ± 13% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.__cancel_dirty_page
0.11 ± 7% -0.0 0.07 ± 10% perf-profile.children.cycles-pp.percpu_counter_add_batch
0.25 ± 4% -0.0 0.21 ± 8% perf-profile.children.cycles-pp.__pagevec_release
0.30 ± 3% -0.0 0.28 ± 5% perf-profile.children.cycles-pp.__add_to_page_cache_locked
0.27 ± 6% -0.0 0.24 perf-profile.children.cycles-pp.___might_sleep
0.15 ± 4% -0.0 0.12 ± 3% perf-profile.children.cycles-pp.__lru_cache_add
0.12 ± 17% -0.0 0.09 ± 7% perf-profile.children.cycles-pp.account_page_dirtied
0.14 ± 6% -0.0 0.11 ± 6% perf-profile.children.cycles-pp.pagevec_lru_move_fn
0.16 ± 2% -0.0 0.14 ± 8% perf-profile.children.cycles-pp.down_read
0.19 ± 5% -0.0 0.17 ± 2% perf-profile.children.cycles-pp._cond_resched
0.08 ± 5% -0.0 0.07 ± 7% perf-profile.children.cycles-pp.down_write_trylock
0.15 ± 3% -0.0 0.14 ± 5% perf-profile.children.cycles-pp.page_mapping
0.10 ± 5% -0.0 0.08 ± 5% perf-profile.children.cycles-pp.__x64_sys_write
0.17 ± 15% +0.0 0.20 ± 15% perf-profile.children.cycles-pp.down_write
0.17 ± 13% +0.0 0.20 ± 14% perf-profile.children.cycles-pp.call_rwsem_down_write_failed
0.17 ± 13% +0.0 0.20 ± 14% perf-profile.children.cycles-pp.rwsem_down_write_failed
0.08 ± 29% +0.0 0.12 ± 11% perf-profile.children.cycles-pp.console_unlock
0.08 ± 29% +0.0 0.12 ± 10% perf-profile.children.cycles-pp.irq_work_run_list
96.50 +0.6 97.06 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
96.37 +0.6 96.94 perf-profile.children.cycles-pp.do_syscall_64
93.09 +1.0 94.09 perf-profile.children.cycles-pp.ksys_write
92.81 +1.0 93.84 perf-profile.children.cycles-pp.vfs_write
25.85 ± 3% +1.1 26.98 perf-profile.children.cycles-pp.f2fs_get_block
25.76 ± 3% +1.2 26.94 perf-profile.children.cycles-pp.f2fs_reserve_block
25.71 ± 3% +1.2 26.90 perf-profile.children.cycles-pp.f2fs_reserve_new_blocks
91.38 +1.3 92.71 perf-profile.children.cycles-pp.__vfs_write
90.89 +1.7 92.58 perf-profile.children.cycles-pp.f2fs_file_write_iter
88.30 +2.6 90.94 perf-profile.children.cycles-pp.__generic_file_write_iter
87.36 +3.2 90.53 perf-profile.children.cycles-pp.generic_perform_write
52.06 ± 3% +3.3 55.39 perf-profile.children.cycles-pp.f2fs_write_end
62.34 ± 3% +4.4 66.77 perf-profile.children.cycles-pp.f2fs_mark_inode_dirty_sync
74.47 ± 4% +5.0 79.47 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
75.70 ± 3% +5.0 80.72 perf-profile.children.cycles-pp._raw_spin_lock
75.17 ± 3% +5.0 80.20 perf-profile.children.cycles-pp.f2fs_inode_dirtied
1.26 ± 24% -0.5 0.74 ± 11% perf-profile.self.cycles-pp.f2fs_file_write_iter
0.44 ± 72% -0.3 0.10 ± 18% perf-profile.self.cycles-pp.__vfs_write
1.24 ± 14% -0.3 0.92 ± 7% perf-profile.self.cycles-pp.f2fs_lookup_extent_cache
0.53 ± 15% -0.3 0.28 ± 37% perf-profile.self.cycles-pp._raw_read_lock
1.48 ± 2% -0.2 1.24 ± 5% perf-profile.self.cycles-pp.syscall_return_via_sysret
0.32 ± 52% -0.2 0.11 ± 4% perf-profile.self.cycles-pp.balance_dirty_pages_ratelimited
1.47 ± 2% -0.2 1.28 ± 6% perf-profile.self.cycles-pp.__entry_SYSCALL_64_trampoline
0.23 ± 55% -0.2 0.06 ± 17% perf-profile.self.cycles-pp.f2fs_map_blocks
0.48 ± 27% -0.2 0.33 ± 2% perf-profile.self.cycles-pp.f2fs_write_end
0.44 ± 11% -0.1 0.32 ± 6% perf-profile.self.cycles-pp.intel_idle
0.24 ± 41% -0.1 0.12 ± 6% perf-profile.self.cycles-pp.read_node_page
0.77 ± 3% -0.1 0.67 ± 3% perf-profile.self.cycles-pp.generic_perform_write
1.07 ± 5% -0.1 0.98 ± 2% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string
0.60 ± 3% -0.1 0.51 ± 5% perf-profile.self.cycles-pp.do_syscall_64
0.54 ± 4% -0.1 0.47 ± 4% perf-profile.self.cycles-pp.find_get_entry
0.48 ± 8% -0.1 0.42 ± 6% perf-profile.self.cycles-pp.__radix_tree_lookup
0.30 ± 10% -0.1 0.24 ± 5% perf-profile.self.cycles-pp.pagecache_get_page
0.14 ± 15% -0.0 0.10 ± 4% perf-profile.self.cycles-pp.fsnotify
0.15 ± 12% -0.0 0.11 ± 4% perf-profile.self.cycles-pp.iov_iter_advance
0.10 ± 10% -0.0 0.06 ± 17% perf-profile.self.cycles-pp.percpu_counter_add_batch
0.30 ± 4% -0.0 0.26 ± 7% perf-profile.self.cycles-pp.f2fs_set_data_page_dirty
0.19 ± 6% -0.0 0.16 ± 7% perf-profile.self.cycles-pp.iov_iter_copy_from_user_atomic
0.25 ± 7% -0.0 0.23 ± 3% perf-profile.self.cycles-pp.___might_sleep
0.12 ± 17% -0.0 0.09 ± 19% perf-profile.self.cycles-pp.f2fs_convert_inline_inode
0.08 ± 5% -0.0 0.07 ± 7% perf-profile.self.cycles-pp.down_write_trylock
0.15 ± 6% -0.0 0.13 ± 8% perf-profile.self.cycles-pp.page_mapping
0.52 ± 12% +0.3 0.84 ± 3% perf-profile.self.cycles-pp.__get_node_page
73.96 ± 4% +5.0 79.00 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
aim7.jobs-per-min
115000 +-+----------------------------------------------------------------+
| .+ .+.. .+.. |
|. : + +..+ +.+..+..+.+..+. .+.+.. .+ + |
110000 +-+ : + + + +. +..+ + : |
| :+ + + + : |
| + + +. : |
105000 +-+ + |
| |
100000 +-+ |
| O |
O O O |
95000 +-+ O O O O O O O O O O O O O O O O
| O O O O O |
| O O |
90000 +-+----------------------------------------------------------------+
[*] 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-4.19.0-rc2-00204-g4d82531" of type "text/plain" (167661 bytes)
View attachment "job-script" of type "text/plain" (7586 bytes)
View attachment "job.yaml" of type "text/plain" (5232 bytes)
View attachment "reproduce" of type "text/plain" (692 bytes)
Powered by blists - more mailing lists