Greeting,
FYI, we noticed a 20.7% improvement of reaim.jobs_per_min due to commit:
commit: 7b04b5c2d33be36638b78d5584a2b3b1ff1fd3d5 ("btrfs: switch to iomap_dio_rw()
for dio")
https://github.com/kdave/btrfs-devel.git next/goldwyn/dio-iomap-20200707
in testcase: reaim
on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory
with following parameters:
runtime: 300s
nr_task: 100
disk: 1HDD
fs: btrfs
test: disk
cpufreq_governor: performance
ucode: 0x5002f01
test-description: REAIM is an updated and improved version of AIM 7 benchmark.
test-url:
https://sourceforge.net/projects/re-aim-7/
In addition to that, the commit also has significant impact on the following tests:
+------------------+----------------------------------------------------------------------+
| testcase: change | reaim: reaim.jobs_per_min 19.9% improvement
|
| test machine | 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 192G memory
|
| test parameters | cpufreq_governor=performance
|
| | disk=1HDD
|
| | fs=btrfs
|
| | nr_task=100
|
| | runtime=300s
|
| | test=disk
|
| | ucode=0x5002f01
|
+------------------+----------------------------------------------------------------------+
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/nr_task/rootfs/runtime/tbox_group/test/testcase/ucode:
gcc-9/performance/1HDD/btrfs/x86_64-rhel-8.3/100/debian-10.4-x86_64-20200603.cgz/300s/lkp-csl-2sp7/disk/reaim/0x5002f01
commit:
45d4c2f3f3 ("iomap: IOMAP_DIO_RWF_NO_STALE_PAGECACHE return if page invalidation
fails")
7b04b5c2d3 ("btrfs: switch to iomap_dio_rw() for dio")
45d4c2f3f32fa3d5 7b04b5c2d33be36638b78d5584a
---------------- ---------------------------
fail:runs %reproduction fail:runs
| | |
0:4 0% 0:4 perf-profile.children.cycles-pp.error_entry
0:4 -0% 0:4 perf-profile.self.cycles-pp.error_entry
%stddev %change %stddev
\ | \
6894 +20.7% 8324 ± 2% reaim.jobs_per_min
68.94 +20.7% 83.25 ± 2% reaim.jobs_per_min_child
6946 ± 2% +21.7% 8451 ± 3% reaim.max_jobs_per_min
87.06 -17.1% 72.14 ± 3% reaim.parent_time
0.98 ± 4% -10.6% 0.88 ± 4% reaim.std_dev_time
276860 -85.5% 40122 reaim.time.file_system_inputs
7802166 +25.2% 9764624 ± 8% reaim.time.file_system_outputs
53951 -45.5% 29388 ± 7% reaim.time.involuntary_context_switches
2829 +1.1% 2861 reaim.time.maximum_resident_set_size
6914037 +18.7% 8205371 ± 9% reaim.time.minor_page_faults
86.25 ± 2% +19.4% 103.00 ± 4% reaim.time.percent_of_cpu_this_job_got
19.35 +23.4% 23.88 ± 11% reaim.time.user_time
2142020 +22.2% 2618010 ± 9% reaim.time.voluntary_context_switches
6.68 -1.9 4.82 mpstat.cpu.all.iowait%
2.12 ± 11% -0.3 1.81 ± 14% mpstat.cpu.all.irq%
0.94 ± 4% +0.2 1.13 ± 6% mpstat.cpu.all.sys%
0.09 +0.0 0.10 ± 7% mpstat.cpu.all.usr%
801944 ± 2% +14.0% 914287 ± 3% meminfo.Active
500305 ± 3% +22.3% 611753 ± 6% meminfo.Active(file)
295216 ± 3% -20.9% 233478 ± 7% meminfo.Inactive
284864 ± 3% -21.7% 223123 ± 7% meminfo.Inactive(file)
581.75 ±119% +204.2% 1769 ± 2% meminfo.Mlocked
152278 ± 10% -17.0% 126450 ± 3% softirqs.CPU20.TIMER
142912 ± 10% -15.9% 120252 ± 5% softirqs.CPU27.TIMER
141314 ± 9% -14.7% 120479 ± 5% softirqs.CPU45.TIMER
140111 ± 8% -13.0% 121876 ± 4% softirqs.CPU86.TIMER
142540 ± 9% -14.4% 121953 ± 4% softirqs.CPU92.TIMER
89.50 +2.5% 91.75 vmstat.cpu.id
383.75 -85.3% 56.25 ± 7% vmstat.io.bi
17323 +27.3% 22048 ± 2% vmstat.io.bo
6.25 ± 6% -32.0% 4.25 ± 10% vmstat.procs.b
19571 ± 2% +19.2% 23321 ± 3% vmstat.system.cs
4284 ± 4% -9.7% 3869 ± 2% slabinfo.khugepaged_mm_slot.active_objs
4284 ± 4% -9.7% 3869 ± 2% slabinfo.khugepaged_mm_slot.num_objs
10535 ± 3% +14.1% 12017 ± 4% slabinfo.mnt_cache.active_objs
10705 ± 2% +13.8% 12181 ± 4% slabinfo.mnt_cache.num_objs
40768 +10.9% 45200 ± 2% slabinfo.numa_policy.active_objs
40781 +10.9% 45245 ± 2% slabinfo.numa_policy.num_objs
259658 ± 3% +24.7% 323837 ± 5% numa-meminfo.node0.Active(file)
157871 ± 5% -23.0% 121485 ± 8% numa-meminfo.node0.Inactive
9604 ± 5% -47.3% 5061 ± 81% numa-meminfo.node0.Inactive(anon)
148267 ± 5% -21.5% 116423 ± 9% numa-meminfo.node0.Inactive(file)
253.75 ±115% +249.5% 886.75 ± 13% numa-meminfo.node0.Mlocked
241009 ± 6% +19.4% 287843 ± 7% numa-meminfo.node1.Active(file)
137032 ± 3% -18.3% 111923 ± 7% numa-meminfo.node1.Inactive
747.75 ± 68% +609.1% 5302 ± 77% numa-meminfo.node1.Inactive(anon)
136284 ± 3% -21.8% 106620 ± 5% numa-meminfo.node1.Inactive(file)
125132 ± 2% +11.5% 139551 ± 7% numa-meminfo.node1.SUnreclaim
180488 ± 2% +11.0% 200375 ± 4% numa-meminfo.node1.Slab
64867 ± 3% +24.8% 80970 ± 5% numa-vmstat.node0.nr_active_file
285623 ± 2% +24.2% 354680 ± 8% numa-vmstat.node0.nr_dirtied
2400 ± 5% -47.4% 1263 ± 81% numa-vmstat.node0.nr_inactive_anon
37052 ± 5% -21.6% 29061 ± 9% numa-vmstat.node0.nr_inactive_file
62.75 ±117% +251.8% 220.75 ± 13% numa-vmstat.node0.nr_mlock
275897 ± 2% +24.7% 344100 ± 8% numa-vmstat.node0.nr_written
64867 ± 3% +24.8% 80970 ± 5% numa-vmstat.node0.nr_zone_active_file
2400 ± 5% -47.4% 1263 ± 81% numa-vmstat.node0.nr_zone_inactive_anon
37052 ± 5% -21.6% 29061 ± 9% numa-vmstat.node0.nr_zone_inactive_file
60206 ± 6% +19.5% 71969 ± 7% numa-vmstat.node1.nr_active_file
184.75 ± 69% +616.2% 1323 ± 77% numa-vmstat.node1.nr_inactive_anon
34061 ± 4% -21.9% 26616 ± 5% numa-vmstat.node1.nr_inactive_file
31282 ± 2% +11.5% 34888 ± 7% numa-vmstat.node1.nr_slab_unreclaimable
258090 ± 4% +23.2% 317890 ± 9% numa-vmstat.node1.nr_written
60206 ± 6% +19.5% 71969 ± 7% numa-vmstat.node1.nr_zone_active_file
184.75 ± 69% +616.2% 1323 ± 77% numa-vmstat.node1.nr_zone_inactive_anon
34061 ± 4% -21.9% 26616 ± 5% numa-vmstat.node1.nr_zone_inactive_file
125069 ± 3% +22.2% 152889 ± 6% proc-vmstat.nr_active_file
1100565 +23.9% 1363138 ± 9% proc-vmstat.nr_dirtied
420388 +2.9% 432774 proc-vmstat.nr_file_pages
71152 ± 3% -21.6% 55762 ± 7% proc-vmstat.nr_inactive_file
145.25 ±119% +204.1% 441.75 ± 2% proc-vmstat.nr_mlock
1723 +2.8% 1772 proc-vmstat.nr_page_table_pages
66169 +1.6% 67255 proc-vmstat.nr_slab_unreclaimable
1061674 +24.4% 1320470 ± 9% proc-vmstat.nr_written
125069 ± 3% +22.2% 152889 ± 6% proc-vmstat.nr_zone_active_file
71152 ± 3% -21.6% 55762 ± 7% proc-vmstat.nr_zone_inactive_file
15577 ± 12% -87.5% 1953 ±163% proc-vmstat.numa_hint_faults
5560 ± 58% -71.5% 1585 ±173% proc-vmstat.numa_hint_faults_local
19074 ± 27% -98.6% 272.75 ±112% proc-vmstat.numa_pages_migrated
74402 ± 27% -83.6% 12219 ±152% proc-vmstat.numa_pte_updates
306390 +13.6% 348143 ± 5% proc-vmstat.pgactivate
1538 ± 4% +806.8% 13946 ± 10% proc-vmstat.pgdeactivate
19074 ± 27% -98.6% 272.75 ±112% proc-vmstat.pgmigrate_success
138430 -85.5% 20061 proc-vmstat.pgpgin
6239561 +25.6% 7839433 ± 8% proc-vmstat.pgpgout
25825 ± 2% +50.1% 38757 ± 10% proc-vmstat.pgrotated
20.58 ± 64% +307.9% 83.94 ± 51% sched_debug.cfs_rq:/.MIN_vruntime.avg
194.53 ± 64% +254.6% 689.73 ± 60% sched_debug.cfs_rq:/.MIN_vruntime.stddev
1865 ± 7% +26.1% 2351 ± 10% sched_debug.cfs_rq:/.exec_clock.avg
1473 ± 9% +34.0% 1974 ± 12% sched_debug.cfs_rq:/.exec_clock.min
20.58 ± 64% +307.9% 83.94 ± 51% sched_debug.cfs_rq:/.max_vruntime.avg
194.53 ± 64% +254.6% 689.73 ± 60% sched_debug.cfs_rq:/.max_vruntime.stddev
178769 ± 7% +8.6% 194101 ± 6% sched_debug.cpu.clock.avg
178775 ± 7% +8.6% 194108 ± 6% sched_debug.cpu.clock.max
178762 ± 7% +8.6% 194095 ± 6% sched_debug.cpu.clock.min
33855 ± 6% +29.3% 43766 ± 9% sched_debug.cpu.nr_switches.avg
27786 ± 7% +30.0% 36127 ± 10% sched_debug.cpu.nr_switches.min
34702 ± 7% +30.1% 45156 ± 10% sched_debug.cpu.sched_count.avg
29195 ± 8% +29.0% 37660 ± 11% sched_debug.cpu.sched_count.min
16968 ± 7% +29.9% 22045 ± 10% sched_debug.cpu.sched_goidle.avg
14362 ± 8% +28.1% 18398 ± 10% sched_debug.cpu.sched_goidle.min
16256 ± 6% +30.6% 21234 ± 10% sched_debug.cpu.ttwu_count.avg
149829 ± 7% +19.9% 179651 ± 9% sched_debug.cpu.ttwu_count.max
10851 ± 7% +32.2% 14348 ± 12% sched_debug.cpu.ttwu_count.min
178762 ± 7% +8.6% 194095 ± 6% sched_debug.cpu_clk
178265 ± 7% +8.6% 193574 ± 6% sched_debug.ktime
179094 ± 7% +8.6% 194442 ± 6% sched_debug.sched_clk
3.922e+08 ± 6% +14.7% 4.498e+08 perf-stat.i.branch-instructions
8.46 ± 47% +4.7 13.14 ± 29% perf-stat.i.cache-miss-rate%
4499814 +8.0% 4859352 perf-stat.i.cache-misses
19748 ± 2% +19.0% 23502 ± 3% perf-stat.i.context-switches
3.97 ± 10% -14.3% 3.40 ± 10% perf-stat.i.cpi
783.30 ± 3% +19.5% 935.75 ± 3% perf-stat.i.cpu-migrations
4.708e+08 ± 6% +14.2% 5.378e+08 perf-stat.i.dTLB-loads
2.263e+08 ± 6% +13.9% 2.579e+08 perf-stat.i.dTLB-stores
1857042 ± 13% +18.1% 2193720 ± 7% perf-stat.i.iTLB-load-misses
1607486 ± 34% +44.2% 2318543 ± 12% perf-stat.i.iTLB-loads
1.864e+09 ± 6% +14.5% 2.134e+09 perf-stat.i.instructions
0.27 ± 10% +14.8% 0.31 ± 8% perf-stat.i.ipc
12.04 ± 5% +11.9% 13.47 perf-stat.i.metric.M/sec
21789 +17.3% 25557 ± 2% perf-stat.i.minor-faults
972884 ± 5% +21.2% 1178651 ± 5% perf-stat.i.node-load-misses
137661 ± 2% +13.6% 156382 perf-stat.i.node-loads
394783 ± 3% +17.9% 465416 ± 3% perf-stat.i.node-store-misses
21790 +17.3% 25557 ± 2% perf-stat.i.page-faults
8.40 ± 47% +4.7 13.06 ± 29% perf-stat.overall.cache-miss-rate%
3.70 ± 9% -12.7% 3.23 ± 9% perf-stat.overall.cpi
0.27 ± 10% +14.3% 0.31 ± 8% perf-stat.overall.ipc
16592102 ± 4% -4.5% 15841049 perf-stat.overall.path-length
3.912e+08 ± 6% +14.7% 4.486e+08 perf-stat.ps.branch-instructions
4487285 +8.0% 4845546 perf-stat.ps.cache-misses
19692 ± 2% +19.0% 23433 ± 3% perf-stat.ps.context-switches
781.03 ± 3% +19.5% 932.99 ± 3% perf-stat.ps.cpu-migrations
4.695e+08 ± 6% +14.2% 5.364e+08 perf-stat.ps.dTLB-loads
2.257e+08 ± 6% +13.9% 2.572e+08 perf-stat.ps.dTLB-stores
1851881 ± 13% +18.1% 2187520 ± 7% perf-stat.ps.iTLB-load-misses
1602951 ± 34% +44.2% 2311921 ± 12% perf-stat.ps.iTLB-loads
1.86e+09 ± 6% +14.5% 2.128e+09 perf-stat.ps.instructions
21727 +17.3% 25482 ± 2% perf-stat.ps.minor-faults
970125 ± 5% +21.1% 1175244 ± 5% perf-stat.ps.node-load-misses
137277 ± 2% +13.6% 155939 perf-stat.ps.node-loads
393652 ± 3% +17.9% 464060 ± 3% perf-stat.ps.node-store-misses
21727 +17.3% 25482 ± 2% perf-stat.ps.page-faults
290.75 ± 4% +8.9% 316.75 ± 4% interrupts.CPU0.RES:Rescheduling_interrupts
3276 ± 22% +38.5% 4535 ± 18%
interrupts.CPU1.CAL:Function_call_interrupts
261.50 ± 7% +20.1% 314.00 ± 7% interrupts.CPU1.RES:Rescheduling_interrupts
280.75 ± 4% +16.1% 326.00 ± 7%
interrupts.CPU10.RES:Rescheduling_interrupts
257.50 ± 10% -32.2% 174.50 ± 28%
interrupts.CPU11.NMI:Non-maskable_interrupts
257.50 ± 10% -32.2% 174.50 ± 28%
interrupts.CPU11.PMI:Performance_monitoring_interrupts
3162 ± 14% +19.3% 3773 ± 13%
interrupts.CPU12.CAL:Function_call_interrupts
272.75 ± 4% +22.5% 334.25 ± 4%
interrupts.CPU12.RES:Rescheduling_interrupts
62.25 ± 37% +78.3% 111.00 ± 29% interrupts.CPU12.TLB:TLB_shootdowns
281.75 ± 6% +15.7% 326.00 ± 6%
interrupts.CPU14.RES:Rescheduling_interrupts
288.50 ± 4% +15.2% 332.25 ± 4%
interrupts.CPU16.RES:Rescheduling_interrupts
3213 ± 17% +23.0% 3952 ± 16%
interrupts.CPU2.CAL:Function_call_interrupts
291.50 ± 3% +13.2% 330.00 ± 4% interrupts.CPU2.RES:Rescheduling_interrupts
70.00 ± 16% +68.9% 118.25 ± 24% interrupts.CPU26.TLB:TLB_shootdowns
251.00 ± 6% -10.2% 225.50 ± 5%
interrupts.CPU28.NMI:Non-maskable_interrupts
251.00 ± 6% -10.2% 225.50 ± 5%
interrupts.CPU28.PMI:Performance_monitoring_interrupts
3019 ± 14% +28.4% 3875 ± 9%
interrupts.CPU3.CAL:Function_call_interrupts
260.75 ± 6% +30.8% 341.00 ± 9%
interrupts.CPU30.RES:Rescheduling_interrupts
3029 ± 11% +24.1% 3760 ± 9%
interrupts.CPU35.CAL:Function_call_interrupts
78.75 ± 23% +50.8% 118.75 ± 24% interrupts.CPU37.TLB:TLB_shootdowns
270.50 ± 5% +23.9% 335.25 ± 13%
interrupts.CPU38.RES:Rescheduling_interrupts
71.00 ± 18% +75.7% 124.75 ± 21% interrupts.CPU41.TLB:TLB_shootdowns
243.25 ± 12% -25.8% 180.50 ± 31%
interrupts.CPU43.NMI:Non-maskable_interrupts
243.25 ± 12% -25.8% 180.50 ± 31%
interrupts.CPU43.PMI:Performance_monitoring_interrupts
273.50 ± 6% +30.4% 356.75 ± 23%
interrupts.CPU43.RES:Rescheduling_interrupts
276.50 ± 7% +28.2% 354.50 ± 14%
interrupts.CPU45.RES:Rescheduling_interrupts
269.75 ± 9% -19.9% 216.00 ± 23%
interrupts.CPU48.NMI:Non-maskable_interrupts
269.75 ± 9% -19.9% 216.00 ± 23%
interrupts.CPU48.PMI:Performance_monitoring_interrupts
282.50 ± 8% +17.7% 332.50 ± 6% interrupts.CPU5.RES:Rescheduling_interrupts
292.50 ± 3% +16.6% 341.00 ± 4%
interrupts.CPU55.RES:Rescheduling_interrupts
267.75 ± 13% -15.8% 225.50 ± 8%
interrupts.CPU57.NMI:Non-maskable_interrupts
267.75 ± 13% -15.8% 225.50 ± 8%
interrupts.CPU57.PMI:Performance_monitoring_interrupts
267.00 ± 7% +14.0% 304.50 ± 3%
interrupts.CPU65.RES:Rescheduling_interrupts
261.75 ± 4% +13.8% 297.75 ± 4%
interrupts.CPU67.RES:Rescheduling_interrupts
83.75 ± 20% +32.2% 110.75 ± 16% interrupts.CPU67.TLB:TLB_shootdowns
260.75 ± 7% -33.7% 173.00 ± 29% interrupts.CPU7.NMI:Non-maskable_interrupts
260.75 ± 7% -33.7% 173.00 ± 29%
interrupts.CPU7.PMI:Performance_monitoring_interrupts
252.25 ± 4% +20.2% 303.25 ± 4%
interrupts.CPU70.RES:Rescheduling_interrupts
68.25 ± 29% +44.7% 98.75 ± 14% interrupts.CPU71.TLB:TLB_shootdowns
257.25 ± 11% -41.3% 151.00 ± 34%
interrupts.CPU73.NMI:Non-maskable_interrupts
257.25 ± 11% -41.3% 151.00 ± 34%
interrupts.CPU73.PMI:Performance_monitoring_interrupts
261.50 ± 5% +46.1% 382.00 ± 27%
interrupts.CPU73.RES:Rescheduling_interrupts
257.25 ± 8% +27.4% 327.75 ± 9%
interrupts.CPU75.RES:Rescheduling_interrupts
270.00 ± 5% +12.0% 302.50 ± 5%
interrupts.CPU76.RES:Rescheduling_interrupts
258.75 ± 5% -8.4% 237.00 ± 2%
interrupts.CPU79.NMI:Non-maskable_interrupts
258.75 ± 5% -8.4% 237.00 ± 2%
interrupts.CPU79.PMI:Performance_monitoring_interrupts
266.00 ± 8% -20.6% 211.25 ± 21% interrupts.CPU8.NMI:Non-maskable_interrupts
266.00 ± 8% -20.6% 211.25 ± 21%
interrupts.CPU8.PMI:Performance_monitoring_interrupts
263.50 ± 7% +17.1% 308.50 ± 10%
interrupts.CPU83.RES:Rescheduling_interrupts
2953 ± 15% +28.3% 3790 ± 16%
interrupts.CPU84.CAL:Function_call_interrupts
259.25 ± 6% +14.5% 296.75 ± 3%
interrupts.CPU84.RES:Rescheduling_interrupts
3050 ± 12% +22.6% 3739 ± 12%
interrupts.CPU86.CAL:Function_call_interrupts
275.75 ± 11% +26.6% 349.00 ± 8%
interrupts.CPU86.RES:Rescheduling_interrupts
81.75 ± 20% +66.1% 135.75 ± 24% interrupts.CPU86.TLB:TLB_shootdowns
270.50 ± 9% -25.9% 200.50 ± 22% interrupts.CPU9.NMI:Non-maskable_interrupts
270.50 ± 9% -25.9% 200.50 ± 22%
interrupts.CPU9.PMI:Performance_monitoring_interrupts
265.25 ± 14% +24.8% 331.00 ± 11%
interrupts.CPU90.RES:Rescheduling_interrupts
274.00 ± 8% +41.8% 388.50 ± 35%
interrupts.CPU91.RES:Rescheduling_interrupts
262.25 ± 6% +18.1% 309.75 ± 8%
interrupts.CPU94.RES:Rescheduling_interrupts
29144 ± 5% +9.3% 31857 ± 3% interrupts.RES:Rescheduling_interrupts
2.12 ± 35% -1.1 1.00 ± 69%
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
1.18 ± 4% -0.5 0.66 ± 61%
perf-profile.calltrace.cycles-pp.btrfs_tree_read_lock.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode
1.18 ± 4% -0.5 0.66 ± 61%
perf-profile.calltrace.cycles-pp.btrfs_read_lock_root_node.btrfs_search_slot.btrfs_insert_empty_items.btrfs_log_inode.btrfs_log_inode_parent
1.50 ± 12% -0.4 1.09 ± 32%
perf-profile.calltrace.cycles-pp.__btrfs_drop_extents.log_one_extent.btrfs_log_changed_extents.btrfs_log_inode.btrfs_log_inode_parent
1.38 ± 13% -0.4 1.00 ± 31%
perf-profile.calltrace.cycles-pp.btrfs_lookup_file_extent.__btrfs_drop_extents.log_one_extent.btrfs_log_changed_extents.btrfs_log_inode
1.37 ± 13% -0.4 1.00 ± 31%
perf-profile.calltrace.cycles-pp.btrfs_search_slot.btrfs_lookup_file_extent.__btrfs_drop_extents.log_one_extent.btrfs_log_changed_extents
0.26 ±100% +0.3 0.59 ± 11%
perf-profile.calltrace.cycles-pp.rcu_core.__softirqentry_text_start.asm_call_on_stack.do_softirq_own_stack.irq_exit_rcu
0.39 ± 30% -0.2 0.21 ± 66%
perf-profile.children.cycles-pp.__remove_hrtimer
0.43 ± 19% -0.1 0.30 ± 13%
perf-profile.children.cycles-pp.start_ordered_ops
0.13 ± 38% -0.1 0.03 ±100%
perf-profile.children.cycles-pp.prepare_uptodate_page
0.15 ± 27% -0.1 0.06 ± 67%
perf-profile.children.cycles-pp.prepare_pages
0.16 ± 7% -0.1 0.09 ± 23%
perf-profile.children.cycles-pp.btrfs_submit_bio_hook
0.11 ± 16% -0.1 0.04 ±103%
perf-profile.children.cycles-pp.blk_mq_sched_insert_requests
0.19 ± 3% -0.1 0.12 ± 27%
perf-profile.children.cycles-pp.btrfs_map_bio
0.14 ± 10% -0.1 0.07 ± 62%
perf-profile.children.cycles-pp.blk_mq_make_request
0.10 ± 14% -0.1 0.04 ± 57%
perf-profile.children.cycles-pp.btrfs_alloc_tree_block
0.11 ± 19% -0.1 0.05 ± 64%
perf-profile.children.cycles-pp.blk_mq_flush_plug_list
0.10 ± 12% -0.1 0.04 ± 57%
perf-profile.children.cycles-pp.alloc_tree_block_no_bg_flush
0.11 ± 19% -0.1 0.05 ± 67%
perf-profile.children.cycles-pp.blk_flush_plug_list
0.11 ± 23% -0.1 0.05 ± 67%
perf-profile.children.cycles-pp.blk_finish_plug
0.09 ± 13% -0.1 0.03 ±105%
perf-profile.children.cycles-pp.__blk_mq_delay_run_hw_queue
0.15 ± 10% -0.1 0.10 ± 27%
perf-profile.children.cycles-pp.generic_make_request
0.15 ± 11% -0.0 0.11 ± 25% perf-profile.children.cycles-pp.submit_bio
0.12 ± 16% -0.0 0.07 ± 17%
perf-profile.children.cycles-pp.__blk_mq_sched_dispatch_requests
0.49 -0.0 0.45 ± 7%
perf-profile.children.cycles-pp.flush_smp_call_function_from_idle
0.12 ± 13% -0.0 0.08 ± 19%
perf-profile.children.cycles-pp.__blk_mq_run_hw_queue
0.12 ± 13% -0.0 0.08 ± 19%
perf-profile.children.cycles-pp.blk_mq_sched_dispatch_requests
0.12 ± 13% -0.0 0.08 ± 15%
perf-profile.children.cycles-pp.read_block_for_search
0.10 ± 17% -0.0 0.07 ± 17%
perf-profile.children.cycles-pp.blk_mq_do_dispatch_sched
0.11 ± 15% -0.0 0.08 ± 19%
perf-profile.children.cycles-pp.__queue_work
0.10 ± 8% +0.0 0.12 ± 3%
perf-profile.children.cycles-pp.sync_inodes_sb
0.04 ± 58% +0.0 0.07 ± 10%
perf-profile.children.cycles-pp.memcg_kmem_get_cache
0.18 ± 7% +0.0 0.21 ± 12%
perf-profile.children.cycles-pp.btree_submit_bio_hook
0.17 ± 4% +0.0 0.21 ± 3%
perf-profile.children.cycles-pp.rcu_idle_exit
0.07 ± 10% +0.0 0.11 ± 19%
perf-profile.children.cycles-pp.alloc_pages_vma
0.11 ± 3% +0.0 0.15 ± 12%
perf-profile.children.cycles-pp.unlink_anon_vmas
0.15 ± 12% +0.0 0.19 ± 6%
perf-profile.children.cycles-pp.insert_with_overflow
0.04 ±102% +0.0 0.08 ± 12%
perf-profile.children.cycles-pp.copy_extent_buffer_full
0.07 ± 11% +0.0 0.12 ± 27%
perf-profile.children.cycles-pp.___might_sleep
0.17 ± 13% +0.1 0.22 ± 12%
perf-profile.children.cycles-pp.btrfs_add_link
0.16 ± 14% +0.1 0.21 ± 10%
perf-profile.children.cycles-pp.btrfs_insert_dir_item
0.11 ± 8% +0.1 0.16 ± 21%
perf-profile.children.cycles-pp.__d_lookup_rcu
0.13 ± 15% +0.1 0.19 ± 18%
perf-profile.children.cycles-pp.hrtimer_get_next_event
0.11 ± 9% +0.1 0.18 ± 10%
perf-profile.children.cycles-pp.page_counter_try_charge
0.00 +0.1 0.06 ± 26% perf-profile.children.cycles-pp.__do_fault
0.09 ± 19% +0.1 0.15 ± 27%
perf-profile.children.cycles-pp.terminate_walk
0.30 ± 6% +0.1 0.36 ± 9%
perf-profile.children.cycles-pp.btree_write_cache_pages
0.15 ± 5% +0.1 0.21 ± 13%
perf-profile.children.cycles-pp.__memcg_kmem_charge
0.18 ± 8% +0.1 0.25 ± 11%
perf-profile.children.cycles-pp.__memcg_kmem_charge_page
0.13 ± 32% +0.1 0.20 ± 18% perf-profile.children.cycles-pp.d_alloc
0.30 ± 2% +0.1 0.40 ± 12% perf-profile.children.cycles-pp.wb_workfn
0.29 ± 5% +0.1 0.38 ± 15%
perf-profile.children.cycles-pp.wb_writeback
0.28 ± 3% +0.1 0.38 ± 14%
perf-profile.children.cycles-pp.writeback_sb_inodes
0.28 ± 3% +0.1 0.37 ± 13%
perf-profile.children.cycles-pp.__writeback_single_inode
0.39 ± 20% +0.1 0.50 ± 19% perf-profile.children.cycles-pp.vfs_statx
0.39 ± 19% +0.1 0.51 ± 19%
perf-profile.children.cycles-pp.__do_sys_newstat
0.37 ± 24% +0.1 0.50 ± 21%
perf-profile.children.cycles-pp.__lookup_slow
0.14 ± 29% -0.1 0.06 ± 80% perf-profile.self.cycles-pp.timerqueue_del
0.12 ± 24% -0.1 0.05 ± 74%
perf-profile.self.cycles-pp.asm_call_on_stack
0.17 ± 19% -0.0 0.12 ± 13% perf-profile.self.cycles-pp.load_balance
0.04 ± 58% +0.0 0.07 ± 6%
perf-profile.self.cycles-pp.memcg_kmem_get_cache
0.07 ± 16% +0.0 0.12 ± 25% perf-profile.self.cycles-pp.___might_sleep
0.11 ± 10% +0.1 0.16 ± 11%
perf-profile.self.cycles-pp.page_counter_try_charge
0.10 ± 11% +0.1 0.15 ± 19% perf-profile.self.cycles-pp.__d_lookup_rcu
reaim.time.involuntary_context_switches
60000 +-------------------------------------------------------------------+
| ++.++.+.+ ++.++. .++.+.++.++ ++.++.+.+ +.++.+.++ +.++.|
50000 |-: : : + : : : : : : |
| : : : : : : : : : |
| : : : : : : : : : |
40000 |:+ : : : : : : : : |
|: : : : : : : : : |
30000 |:+O O O : :OO O O O O O O:O: O O O :O : : : |
|:O O : O: O O O O : :O O : : : : |
20000 |:+ : : : : : : : : |
|: : : : : : : : : |
| : : : : : : : |
10000 |-+ : : : : : : : |
| : : : : : : : |
0 +-------------------------------------------------------------------+
reaim.time.file_system_inputs
300000 +------------------------------------------------------------------+
| ++.++.+.+ +.+.++.++.+.++.++.+ +.++.++.+ +.+.++.++ +.++.|
250000 |-: : : : : : : : : |
| : : : : : : : : : |
| : : : : : : : : : |
200000 |:+ : : : : : : : : |
|: : : : : : : : : |
150000 |:+ : : : : : : : : |
|: : : :: : : : : |
100000 |:+ : : :: : : : : |
|: : : :: : : : : |
| : : : : : : : |
50000 |-OO OO O O: :O O OO OO O OO OO O :O OO OO O : : : : |
| : : : : : : : |
0 +------------------------------------------------------------------+
reaim.parent_time
90 +----------------------------------------------------------------------+
| ++.+.++.+ + ++.+.++.+.++.+.+ +.+.++.+.+ +.+.++.+.+ : ++ |
80 |-: O : O : O O O O : : O : : : : |
70 |-:O O O : O: O O O O O O : O: O O O :O : : : |
| : : : : : : : : : |
60 |:+ : : : : : : : : |
50 |:+ : : : : : : : : |
|: : : : : : : : : |
40 |:+ : : :: : : : : |
30 |:+ : : :: : : : : |
|: : : :: : : : : |
20 |-+ : : : : : :: |
10 |-+ : : : : : :: |
| : : : : : :: |
0 +----------------------------------------------------------------------+
reaim.jobs_per_min
9000 +--------------------------------------------------------------------+
| O O O O O OO OO O O O O O OO OO O |
8000 |-O O O O O OO O O |
7000 |-++.+.++.+ ++.+.++.+.++.+.++.+ +.++.+.++ +.++.+.++ .++.|
| : : : : : : : : + |
6000 |-: : : : : : : : : |
5000 |:+ : : : : : : : : |
|: : : : : : : : : |
4000 |:+ : : : : : : : : |
3000 |:+ : : :: : : : : |
|: : : :: : : : : |
2000 |:+ : : :: : : : : |
1000 |-+ :: : : : :: |
| :: : : : :: |
0 +--------------------------------------------------------------------+
reaim.jobs_per_min_child
90 +----------------------------------------------------------------------+
| O O O O OO O O O O O O O O O O O OO |
80 |-O O O O O O O O O |
70 |-++.+.++.+ +.+.++.+.++.+.++.+.+ +.+.++.+.+ +.+.++.+.+ .++.|
| : : : : : : : : + |
60 |-: : : : : : : : : |
50 |:+ : : : : : : : : |
|: : : : : : : : : |
40 |:+ : : : : : : : : |
30 |:+ : : :: : : : : |
|: : : :: : : : : |
20 |:+ : : :: : : : : |
10 |-+ : : : : : :: |
| : : : : : :: |
0 +----------------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
***************************************************************************************************
lkp-csl-2sp5: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 192G memory
=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase/ucode:
gcc-9/performance/1HDD/btrfs/x86_64-rhel-8.3/100/debian-10.4-x86_64-20200603.cgz/300s/lkp-csl-2sp5/disk/reaim/0x5002f01
commit:
45d4c2f3f3 ("iomap: IOMAP_DIO_RWF_NO_STALE_PAGECACHE return if page invalidation
fails")
7b04b5c2d3 ("btrfs: switch to iomap_dio_rw() for dio")
45d4c2f3f32fa3d5 7b04b5c2d33be36638b78d5584a
---------------- ---------------------------
fail:runs %reproduction fail:runs
| | |
0:4 1% 0:4 perf-profile.children.cycles-pp.error_entry
0:4 1% 0:4 perf-profile.self.cycles-pp.error_entry
%stddev %change %stddev
\ | \
74.80 -6.3% 70.10 ± 6% reaim.child_systime
4.62 ± 2% +6.8% 4.94 ± 4% reaim.child_utime
6140 +19.9% 7360 reaim.jobs_per_min
61.41 +19.9% 73.60 reaim.jobs_per_min_child
6198 +20.9% 7495 reaim.max_jobs_per_min
97.72 -16.5% 81.55 reaim.parent_time
1.11 ± 2% -17.6% 0.91 ± 2% reaim.std_dev_time
256900 ± 11% -87.0% 33406 ± 9% reaim.time.file_system_inputs
6965790 ± 11% +18.5% 8257858 reaim.time.file_system_outputs
50320 ± 11% -51.4% 24455 ± 2% reaim.time.involuntary_context_switches
17.34 ± 10% +14.1% 19.79 ± 4% reaim.time.user_time
1965686 ± 11% +12.5% 2212262 reaim.time.voluntary_context_switches
7.46 -2.4 5.06 mpstat.cpu.all.iowait%
0.08 ± 7% +0.0 0.10 mpstat.cpu.all.usr%
724766 ± 5% +16.9% 847457 meminfo.Active
422504 ± 10% +28.8% 544362 meminfo.Active(file)
309606 ± 2% -14.1% 265867 ± 2% meminfo.Inactive
299239 ± 2% -14.6% 255534 ± 2% meminfo.Inactive(file)
123811 ± 5% -10.3% 111055 softirqs.CPU25.TIMER
125021 ± 6% -11.5% 110648 softirqs.CPU73.TIMER
124567 ± 6% -11.8% 109849 softirqs.CPU84.TIMER
124114 ± 5% -11.2% 110151 softirqs.CPU90.TIMER
89.00 +2.2% 91.00 vmstat.cpu.id
340.00 -85.6% 49.00 ± 7% vmstat.io.bi
14598 +34.8% 19681 ± 2% vmstat.io.bo
7.75 ± 5% -38.7% 4.75 ± 9% vmstat.procs.b
17276 +20.9% 20887 vmstat.system.cs
221049 ± 8% +28.6% 284239 numa-meminfo.node0.Active(file)
161887 -15.1% 137515 ± 3% numa-meminfo.node0.Inactive
155092 ± 3% -15.9% 130433 ± 2% numa-meminfo.node0.Inactive(file)
201003 ± 12% +29.5% 260381 ± 2% numa-meminfo.node1.Active(file)
147620 ± 4% -13.0% 128429 ± 2% numa-meminfo.node1.Inactive
144046 ± 3% -13.1% 125170 ± 2% numa-meminfo.node1.Inactive(file)
55283 ± 8% +28.4% 70993 numa-vmstat.node0.nr_active_file
38760 ± 3% -15.7% 32661 ± 2% numa-vmstat.node0.nr_inactive_file
249114 ± 8% +16.2% 289370 numa-vmstat.node0.nr_written
55283 ± 8% +28.4% 70993 numa-vmstat.node0.nr_zone_active_file
38760 ± 3% -15.7% 32661 ± 2% numa-vmstat.node0.nr_zone_inactive_file
50271 ± 12% +29.4% 65030 ± 2% numa-vmstat.node1.nr_active_file
237724 ± 13% +18.6% 282026 numa-vmstat.node1.nr_dirtied
36006 ± 3% -13.0% 31339 ± 2% numa-vmstat.node1.nr_inactive_file
228996 ± 13% +19.4% 273476 numa-vmstat.node1.nr_written
50271 ± 12% +29.4% 65030 ± 2% numa-vmstat.node1.nr_zone_active_file
36006 ± 3% -13.0% 31339 ± 2% numa-vmstat.node1.nr_zone_inactive_file
4678 ± 10% +24.5% 5824 ± 8% slabinfo.eventpoll_pwq.active_objs
4678 ± 10% +24.5% 5824 ± 8% slabinfo.eventpoll_pwq.num_objs
5082 ± 4% -23.6% 3880 slabinfo.khugepaged_mm_slot.active_objs
5082 ± 4% -23.6% 3880 slabinfo.khugepaged_mm_slot.num_objs
12149 ± 3% +10.0% 13363 ± 3% slabinfo.kmalloc-192.active_objs
12301 ± 3% +10.2% 13550 ± 3% slabinfo.kmalloc-192.num_objs
9363 ± 3% +23.9% 11598 ± 4% slabinfo.mnt_cache.active_objs
9502 ± 2% +23.8% 11764 ± 4% slabinfo.mnt_cache.num_objs
36151 ± 5% +20.6% 43613 slabinfo.numa_policy.active_objs
582.50 ± 5% +20.8% 703.50 slabinfo.numa_policy.active_slabs
36151 ± 5% +20.8% 43658 slabinfo.numa_policy.num_objs
582.50 ± 5% +20.8% 703.50 slabinfo.numa_policy.num_slabs
22997 ± 10% +25.0% 28749 ± 9% sched_debug.cfs_rq:/.load_avg.max
2518 ± 7% +22.9% 3095 ± 8% sched_debug.cfs_rq:/.load_avg.stddev
32890 ± 4% +12.8% 37106 ± 7% sched_debug.cfs_rq:/.min_vruntime.avg
80782 ± 8% +32.4% 106932 ± 18% sched_debug.cfs_rq:/.min_vruntime.max
8085 ± 5% +26.8% 10250 ± 15% sched_debug.cfs_rq:/.min_vruntime.stddev
8085 ± 5% +26.8% 10251 ± 15% sched_debug.cfs_rq:/.spread0.stddev
185449 ± 7% -16.2% 155487 ± 8% sched_debug.cpu.clock_task.min
7354 ± 7% -20.9% 5813 ± 10% sched_debug.cpu.nr_switches.stddev
7167 ± 7% -22.3% 5565 ± 11% sched_debug.cpu.sched_count.stddev
3366 ± 8% -21.8% 2633 ± 10% sched_debug.cpu.sched_goidle.stddev
24691 ± 6% -28.2% 17730 ± 12% sched_debug.cpu.ttwu_local.max
841.23 ± 8% -21.2% 662.82 ± 6% sched_debug.cpu.ttwu_local.min
2409 ± 6% -27.0% 1758 ± 11% sched_debug.cpu.ttwu_local.stddev
105540 ± 10% +29.0% 136178 proc-vmstat.nr_active_file
991334 ± 11% +16.5% 1154680 proc-vmstat.nr_dirtied
404435 ± 2% +4.9% 424141 proc-vmstat.nr_file_pages
74763 ± 2% -14.5% 63909 ± 2% proc-vmstat.nr_inactive_file
65602 +1.9% 66852 proc-vmstat.nr_slab_unreclaimable
954730 ± 11% +17.2% 1118546 proc-vmstat.nr_written
105540 ± 10% +29.0% 136178 proc-vmstat.nr_zone_active_file
74763 ± 2% -14.5% 63909 ± 2% proc-vmstat.nr_zone_inactive_file
3591 ± 96% -98.5% 54.25 ±172% proc-vmstat.numa_hint_faults_local
263531 ± 13% +21.5% 320128 proc-vmstat.pgactivate
1344 ± 5% +776.0% 11775 proc-vmstat.pgdeactivate
128514 ± 11% -87.0% 16703 ± 9% proc-vmstat.pgpgin
5506196 ± 10% +20.8% 6650665 proc-vmstat.pgpgout
25999 ± 11% +26.6% 32921 proc-vmstat.pgrotated
11391556 ± 27% +41.0% 16064076 ± 29% perf-stat.i.branch-misses
32370533 ± 33% +63.4% 52900716 ± 41% perf-stat.i.cache-references
17380 +21.4% 21100 ± 2% perf-stat.i.context-switches
664.30 +19.6% 794.80 ± 2% perf-stat.i.cpu-migrations
789973 ± 74% +84.0% 1453256 ± 18% perf-stat.i.dTLB-load-misses
125609 ± 58% +68.2% 211335 ± 17% perf-stat.i.dTLB-store-misses
1.59 ± 17% -22.9% 1.23 ± 12% perf-stat.i.metric.K/sec
19721 +16.8% 23027 perf-stat.i.minor-faults
920648 ± 3% +12.7% 1037566 ± 4% perf-stat.i.node-load-misses
125578 +15.5% 145096 ± 4% perf-stat.i.node-loads
361343 +13.6% 410507 ± 3% perf-stat.i.node-store-misses
73336 ± 12% +28.7% 94357 ± 8% perf-stat.i.node-stores
19721 +16.8% 23027 perf-stat.i.page-faults
18930660 ± 3% -10.9% 16873746 ± 4% perf-stat.overall.path-length
11362541 ± 27% +41.0% 16020633 ± 29% perf-stat.ps.branch-misses
32278829 ± 33% +63.4% 52741241 ± 41% perf-stat.ps.cache-references
17332 +21.4% 21035 ± 2% perf-stat.ps.context-switches
662.47 +19.6% 792.35 ± 2% perf-stat.ps.cpu-migrations
787634 ± 74% +83.9% 1448823 ± 18% perf-stat.ps.dTLB-load-misses
125246 ± 58% +68.2% 210693 ± 17% perf-stat.ps.dTLB-store-misses
19667 +16.7% 22957 perf-stat.ps.minor-faults
918147 ± 3% +12.7% 1034409 ± 4% perf-stat.ps.node-load-misses
125245 +15.5% 144663 ± 4% perf-stat.ps.node-loads
360348 +13.6% 409255 ± 3% perf-stat.ps.node-store-misses
73140 ± 11% +28.6% 94078 ± 8% perf-stat.ps.node-stores
19667 +16.7% 22957 perf-stat.ps.page-faults
252.75 ± 9% +15.0% 290.75 ± 6%
interrupts.CPU10.RES:Rescheduling_interrupts
224.75 ± 4% +19.2% 268.00 ± 8%
interrupts.CPU12.NMI:Non-maskable_interrupts
224.75 ± 4% +19.2% 268.00 ± 8%
interrupts.CPU12.PMI:Performance_monitoring_interrupts
168.50 ± 29% +41.7% 238.75 ± 9%
interrupts.CPU13.NMI:Non-maskable_interrupts
168.50 ± 29% +41.7% 238.75 ± 9%
interrupts.CPU13.PMI:Performance_monitoring_interrupts
228.25 ± 5% +14.6% 261.50 ± 8%
interrupts.CPU16.NMI:Non-maskable_interrupts
228.25 ± 5% +14.6% 261.50 ± 8%
interrupts.CPU16.PMI:Performance_monitoring_interrupts
249.25 ± 6% +23.5% 307.75 ± 14%
interrupts.CPU16.RES:Rescheduling_interrupts
257.25 ± 12% +17.7% 302.75 ± 8%
interrupts.CPU19.RES:Rescheduling_interrupts
84.75 ± 27% -37.2% 53.25 ± 16% interrupts.CPU2.TLB:TLB_shootdowns
156.00 ± 19% -36.1% 99.75 ± 12% interrupts.CPU22.TLB:TLB_shootdowns
97.00 ± 25% -41.2% 57.00 ± 18% interrupts.CPU33.TLB:TLB_shootdowns
218.50 ± 8% +25.9% 275.00 ± 10%
interrupts.CPU34.NMI:Non-maskable_interrupts
218.50 ± 8% +25.9% 275.00 ± 10%
interrupts.CPU34.PMI:Performance_monitoring_interrupts
227.00 ± 5% +18.8% 269.75 ± 8%
interrupts.CPU36.RES:Rescheduling_interrupts
240.50 ± 3% +35.6% 326.00 ± 24%
interrupts.CPU37.RES:Rescheduling_interrupts
236.25 ± 12% +19.0% 281.25 ± 7%
interrupts.CPU39.RES:Rescheduling_interrupts
235.75 ± 9% +22.8% 289.50 ± 7%
interrupts.CPU46.RES:Rescheduling_interrupts
230.50 ± 7% -34.8% 150.25 ± 31%
interrupts.CPU47.NMI:Non-maskable_interrupts
230.50 ± 7% -34.8% 150.25 ± 31%
interrupts.CPU47.PMI:Performance_monitoring_interrupts
304.75 ± 7% +16.3% 354.50 ± 2%
interrupts.CPU49.RES:Rescheduling_interrupts
92.50 ± 25% -34.3% 60.75 ± 21% interrupts.CPU60.TLB:TLB_shootdowns
86.00 ± 22% -32.3% 58.25 ± 9% interrupts.CPU61.TLB:TLB_shootdowns
226.00 ± 5% +12.4% 254.00 ± 2%
interrupts.CPU65.NMI:Non-maskable_interrupts
226.00 ± 5% +12.4% 254.00 ± 2%
interrupts.CPU65.PMI:Performance_monitoring_interrupts
191.50 ± 29% +31.5% 251.75 ± 8%
interrupts.CPU66.NMI:Non-maskable_interrupts
191.50 ± 29% +31.5% 251.75 ± 8%
interrupts.CPU66.PMI:Performance_monitoring_interrupts
254.75 ± 5% +31.6% 335.25 ± 15%
interrupts.CPU67.RES:Rescheduling_interrupts
225.50 ± 10% +18.3% 266.75 ± 7%
interrupts.CPU68.RES:Rescheduling_interrupts
225.75 ± 5% +17.2% 264.50 ± 5%
interrupts.CPU69.RES:Rescheduling_interrupts
88.50 ± 17% -33.6% 58.75 ± 6% interrupts.CPU69.TLB:TLB_shootdowns
233.50 ± 9% +20.7% 281.75 ± 8%
interrupts.CPU75.RES:Rescheduling_interrupts
234.25 ± 5% +22.6% 287.25 ± 2%
interrupts.CPU79.RES:Rescheduling_interrupts
217.25 ± 3% +25.5% 272.75 ± 12%
interrupts.CPU86.RES:Rescheduling_interrupts
93.00 ± 19% -28.8% 66.25 ± 15% interrupts.CPU89.TLB:TLB_shootdowns
18.94 ± 6% -1.9 17.00
perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
0.83 ± 22% -0.5 0.34 ±101%
perf-profile.calltrace.cycles-pp.release_pages.tlb_flush_mmu.tlb_finish_mmu.exit_mmap.mmput
3.17 ± 6% -0.4 2.76 ± 11%
perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry.start_secondary
0.92 ± 20% -0.2 0.67 ± 15%
perf-profile.calltrace.cycles-pp.tlb_finish_mmu.exit_mmap.mmput.do_exit.do_group_exit
0.92 ± 21% -0.2 0.67 ± 15%
perf-profile.calltrace.cycles-pp.tlb_flush_mmu.tlb_finish_mmu.exit_mmap.mmput.do_exit
0.94 ± 19% -0.3 0.67 ± 19%
perf-profile.children.cycles-pp.release_pages
0.61 ± 8% -0.1 0.51 ± 8%
perf-profile.children.cycles-pp.__lock_text_start
0.17 ± 25% -0.1 0.10 ± 18%
perf-profile.children.cycles-pp.generic_make_request
0.17 ± 25% -0.1 0.10 ± 18% perf-profile.children.cycles-pp.submit_bio
0.32 ± 4% -0.1 0.25 ± 14% perf-profile.children.cycles-pp.ksys_read
0.15 ± 30% -0.1 0.10 ± 11%
perf-profile.children.cycles-pp.blk_mq_make_request
0.13 ± 8% -0.0 0.10 ± 12% perf-profile.children.cycles-pp.io_schedule
0.09 ± 13% -0.0 0.06 ± 16% perf-profile.children.cycles-pp.read
0.14 ± 7% -0.0 0.12 ± 12%
perf-profile.children.cycles-pp.call_cpuidle
0.10 ± 15% -0.0 0.07 ± 15% perf-profile.children.cycles-pp.__pte_alloc
0.09 ± 7% +0.0 0.11 ± 3%
perf-profile.children.cycles-pp.___might_sleep
0.05 +0.0 0.08 ± 26% perf-profile.children.cycles-pp.unlock_page
0.09 ± 19% +0.0 0.12 ± 8%
perf-profile.children.cycles-pp.write_one_eb
0.15 ± 7% +0.0 0.19 ± 7%
perf-profile.children.cycles-pp._raw_spin_lock_irq
0.12 ± 12% +0.0 0.16 ± 5% perf-profile.children.cycles-pp.check_leaf
0.13 ± 8% +0.0 0.17 ± 8%
perf-profile.children.cycles-pp.btree_csum_one_bio
0.17 ± 18% +0.0 0.21 ± 10%
perf-profile.children.cycles-pp.btrfs_cow_block
0.14 ± 13% +0.0 0.19 ± 9%
perf-profile.children.cycles-pp.btree_submit_bio_hook
0.21 ± 17% +0.1 0.27 ± 4%
perf-profile.children.cycles-pp.kmem_cache_alloc
0.18 ± 19% +0.1 0.23 ± 10%
perf-profile.children.cycles-pp.unmap_region
0.17 ± 16% +0.1 0.23 ± 13% perf-profile.children.cycles-pp.step_into
0.23 ± 13% +0.1 0.31 ± 11%
perf-profile.children.cycles-pp.btree_write_cache_pages
0.46 ± 16% +0.1 0.58 ± 6% perf-profile.children.cycles-pp.dput
0.66 ± 20% -0.2 0.45 ± 23% perf-profile.self.cycles-pp.release_pages
0.18 ± 4% -0.1 0.11 ± 28%
perf-profile.self.cycles-pp.tick_sched_timer
0.14 ± 7% -0.0 0.12 ± 12% perf-profile.self.cycles-pp.call_cpuidle
0.09 ± 9% +0.0 0.11 ± 4% perf-profile.self.cycles-pp.___might_sleep
0.15 ± 10% +0.0 0.18 ± 8%
perf-profile.self.cycles-pp._raw_spin_lock_irq
0.04 ± 57% +0.0 0.08 ± 26% perf-profile.self.cycles-pp.unlock_page
0.09 ± 15% +0.0 0.14 ± 15%
perf-profile.self.cycles-pp.__sched_text_start
0.07 ± 62% +0.1 0.12 ± 5%
perf-profile.self.cycles-pp.kmem_cache_alloc
0.74 ± 6% +0.1 0.81 ± 3% perf-profile.self.cycles-pp._raw_spin_lock
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