[LKP] [mm/swap] d884021f52: will-it-scale.per_process_ops -2.4% regression
From: kernel test robot <hidden>
Date: 2018-09-30 03:16:33
Also in:
oe-lkp
Greeting,
FYI, we noticed a -2.4% regression of will-it-scale.per_process_ops due to commit:
commit: d884021f52609407c7943705b3e54b1642fa10cb ("[PATCH 1/2] mm/swap: Add pagevec locking")
url: https://github.com/0day-ci/linux/commits/Sebastian-Andrzej-Siewior/mm-swap-Add-pagevec-locking/20180915-030618
in testcase: will-it-scale
on test machine: 88 threads Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz with 64G memory
with following parameters:
nr_task: 50%
mode: process
test: brk1
cpufreq_governor: performance
test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
test-url: https://github.com/antonblanchard/will-it-scale
In addition to that, the commit also has significant impact on the following tests:
+------------------+-----------------------------------------------------------------------+
| testcase: change | fio-basic: |
| test machine | 48 threads Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 64G memory |
| test parameters | bs=4k |
| | cpufreq_governor=performance |
| | disk=1HDD |
| | fs2=nfsv4 |
| | fs=ext4 |
| | ioengine=sync |
| | nr_task=100% |
| | runtime=300s |
| | rw=write |
| | test_size=128G |
| | ucode=0x42d |
+------------------+-----------------------------------------------------------------------+
| testcase: change | fio-basic: fio.latency_100us% 1.6% improvement |
| test machine | 72 threads Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz with 128G memory |
| test parameters | bs=4k |
| | cpufreq_governor=performance |
| | disk=1SSD |
| | fs=ext4 |
| | ioengine=sync |
| | nr_task=64 |
| | runtime=300s |
| | rw=randwrite |
| | test_size=512g |
| | ucode=0x3d |
+------------------+-----------------------------------------------------------------------+
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/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase:
gcc-7/performance/x86_64-rhel-7.2/process/50%/debian-x86_64-2018-04-03.cgz/lkp-bdw-ep3d/brk1/will-it-scale
commit:
f3c0b8ce48 (" dmaengine fix for dmaengine-fix-4.19-rc4")
d884021f52 ("mm/swap: Add pagevec locking")
f3c0b8ce48408b74 d884021f52609407c7943705b3
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
:4 25% 1:4 dmesg.WARNING:at#for_ip_interrupt_entry/0x
:4 75% 3:4 dmesg.WARNING:at_ip_perf_event_mmap_output/0x
%stddev %change %stddev
\ | \
743536 -2.4% 725610 will-it-scale.per_process_ops
32715630 -2.4% 31926873 will-it-scale.workload
0.00 A+- 71% +0.0 0.01 A+- 34% mpstat.cpu.soft%
2457 A+- 5% +12.2% 2757 A+- 5% slabinfo.kmalloc-512.active_objs
67.33 A+- 9% -17.3% 55.67 A+- 4% sched_debug.cpu.cpu_load[0].max
10817 A+- 11% -16.7% 9008 A+- 5% sched_debug.cpu.load.stddev
1.26 -0.0 1.23 perf-stat.branch-miss-rate%
4.635e+10 -3.0% 4.496e+10 perf-stat.branch-misses
3.046e+12 +1.7% 3.097e+12 perf-stat.dTLB-stores
11.55 A+- 2% +11.5 23.10 A+- 6% perf-stat.iTLB-load-miss-rate%
1.57e+09 +125.1% 3.534e+09 A+- 7% perf-stat.iTLB-load-misses
11183 -55.4% 4991 A+- 7% perf-stat.instructions-per-iTLB-miss
55.41 A+- 19% +21.4 76.78 A+- 15% perf-stat.node-store-miss-rate%
3387268 A+- 21% -36.2% 2161442 A+- 7% perf-stat.node-stores
536500 +2.4% 549279 perf-stat.path-length
31.36 -1.1 30.24 perf-profile.calltrace.cycles-pp.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
8.85 -0.6 8.21 perf-profile.calltrace.cycles-pp.unmap_vmas.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64
7.70 -0.4 7.33 perf-profile.calltrace.cycles-pp.unmap_page_range.unmap_vmas.unmap_region.do_munmap.__x64_sys_brk
11.19 -0.2 10.96 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret
5.01 -0.2 4.79 perf-profile.calltrace.cycles-pp.security_vm_enough_memory_mm.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
3.41 -0.2 3.21 perf-profile.calltrace.cycles-pp.down_write_killable.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
5.23 -0.2 5.05 perf-profile.calltrace.cycles-pp.find_vma.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
4.62 -0.2 4.44 perf-profile.calltrace.cycles-pp.get_unmapped_area.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.67 -0.2 1.48 perf-profile.calltrace.cycles-pp.find_vma.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
3.59 -0.2 3.42 perf-profile.calltrace.cycles-pp.vma_link.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
3.23 -0.1 3.08 perf-profile.calltrace.cycles-pp.selinux_vm_enough_memory.security_vm_enough_memory_mm.do_brk_flags.__x64_sys_brk.do_syscall_64
2.05 -0.1 1.91 perf-profile.calltrace.cycles-pp.vmacache_find.find_vma.do_munmap.__x64_sys_brk.do_syscall_64
3.94 -0.1 3.79 perf-profile.calltrace.cycles-pp.vm_area_alloc.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
7.96 -0.1 7.84 perf-profile.calltrace.cycles-pp.perf_event_mmap.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.42 -0.1 2.30 perf-profile.calltrace.cycles-pp.cred_has_capability.selinux_vm_enough_memory.security_vm_enough_memory_mm.do_brk_flags.__x64_sys_brk
2.50 -0.1 2.38 perf-profile.calltrace.cycles-pp.remove_vma.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.33 -0.1 2.23 A+- 2% perf-profile.calltrace.cycles-pp.kmem_cache_alloc.vm_area_alloc.do_brk_flags.__x64_sys_brk.do_syscall_64
1.16 -0.1 1.07 A+- 2% perf-profile.calltrace.cycles-pp.vma_compute_subtree_gap.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.25 -0.1 2.15 perf-profile.calltrace.cycles-pp.__vma_link_rb.vma_link.do_brk_flags.__x64_sys_brk.do_syscall_64
1.49 -0.1 1.40 perf-profile.calltrace.cycles-pp.vma_compute_subtree_gap.__vma_link_rb.vma_link.do_brk_flags.__x64_sys_brk
1.06 -0.1 0.97 perf-profile.calltrace.cycles-pp.__vm_enough_memory.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.63 -0.1 1.55 perf-profile.calltrace.cycles-pp.avc_has_perm_noaudit.cred_has_capability.selinux_vm_enough_memory.security_vm_enough_memory_mm.do_brk_flags
1.15 -0.1 1.07 A+- 2% perf-profile.calltrace.cycles-pp.up_write.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.91 -0.1 0.84 A+- 2% perf-profile.calltrace.cycles-pp.tlb_gather_mmu.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64
0.88 A+- 3% -0.1 0.81 perf-profile.calltrace.cycles-pp.___might_sleep.down_write_killable.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.74 A+- 2% -0.1 0.68 perf-profile.calltrace.cycles-pp.free_pgd_range.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64
1.16 -0.1 1.10 perf-profile.calltrace.cycles-pp.vma_merge.do_brk_flags.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.27 -0.1 1.22 A+- 2% perf-profile.calltrace.cycles-pp.tlb_finish_mmu.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64
1.13 -0.1 1.08 perf-profile.calltrace.cycles-pp.__vma_rb_erase.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.37 A+- 2% -0.0 1.32 perf-profile.calltrace.cycles-pp.cap_vm_enough_memory.security_vm_enough_memory_mm.do_brk_flags.__x64_sys_brk.do_syscall_64
1.58 -0.0 1.54 perf-profile.calltrace.cycles-pp.arch_get_unmapped_area_topdown.get_unmapped_area.do_brk_flags.__x64_sys_brk.do_syscall_64
0.94 -0.0 0.90 perf-profile.calltrace.cycles-pp.kmem_cache_free.remove_vma.do_munmap.__x64_sys_brk.do_syscall_64
1.14 -0.0 1.10 perf-profile.calltrace.cycles-pp.perf_event_mmap_output.perf_iterate_sb.perf_event_mmap.do_brk_flags.__x64_sys_brk
0.73 -0.0 0.69 A+- 2% perf-profile.calltrace.cycles-pp.cap_mmap_addr.security_mmap_addr.get_unmapped_area.do_brk_flags.__x64_sys_brk
0.96 -0.0 0.93 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_stage2
74.01 +0.1 74.13 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe
72.69 +0.2 72.89 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe
69.82 +0.3 70.16 perf-profile.calltrace.cycles-pp.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +0.7 0.73 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.lru_add_drain_cpu.unmap_region.do_munmap.__x64_sys_brk
0.00 +0.8 0.83 A+- 2% perf-profile.calltrace.cycles-pp._raw_spin_unlock_irqrestore.lru_add_drain_cpu.unmap_region.do_munmap.__x64_sys_brk
0.00 +2.2 2.23 perf-profile.calltrace.cycles-pp._raw_spin_lock.lru_add_drain_cpu.unmap_region.do_munmap.__x64_sys_brk
27.94 +2.4 30.30 perf-profile.calltrace.cycles-pp.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
14.50 +2.9 17.43 perf-profile.calltrace.cycles-pp.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +4.4 4.43 perf-profile.calltrace.cycles-pp.lru_add_drain_cpu.unmap_region.do_munmap.__x64_sys_brk.do_syscall_64
31.57 -1.1 30.43 perf-profile.children.cycles-pp.do_brk_flags
0.82 A+- 3% -0.8 0.07 perf-profile.children.cycles-pp.lru_add_drain
8.91 -0.7 8.26 perf-profile.children.cycles-pp.unmap_vmas
7.98 -0.4 7.59 perf-profile.children.cycles-pp.unmap_page_range
7.18 -0.4 6.81 perf-profile.children.cycles-pp.find_vma
12.90 -0.2 12.65 perf-profile.children.cycles-pp.syscall_return_via_sysret
3.27 -0.2 3.03 perf-profile.children.cycles-pp.vma_compute_subtree_gap
0.60 A+- 3% -0.2 0.37 A+- 3% perf-profile.children.cycles-pp.unmap_single_vma
3.62 A+- 2% -0.2 3.40 perf-profile.children.cycles-pp.down_write_killable
5.06 -0.2 4.84 perf-profile.children.cycles-pp.security_vm_enough_memory_mm
1.71 -0.2 1.52 perf-profile.children.cycles-pp._cond_resched
4.74 -0.2 4.55 perf-profile.children.cycles-pp.get_unmapped_area
2.41 -0.2 2.25 A+- 2% perf-profile.children.cycles-pp.vmacache_find
3.74 -0.2 3.58 perf-profile.children.cycles-pp.vma_link
3.27 -0.1 3.12 perf-profile.children.cycles-pp.selinux_vm_enough_memory
3.95 -0.1 3.80 A+- 2% perf-profile.children.cycles-pp.vm_area_alloc
8.28 -0.1 8.14 perf-profile.children.cycles-pp.perf_event_mmap
2.94 -0.1 2.81 perf-profile.children.cycles-pp.___might_sleep
2.47 -0.1 2.35 perf-profile.children.cycles-pp.__vma_link_rb
2.43 -0.1 2.31 perf-profile.children.cycles-pp.cred_has_capability
0.34 A+- 2% -0.1 0.22 A+- 5% perf-profile.children.cycles-pp.arch_tlb_gather_mmu
2.64 -0.1 2.53 perf-profile.children.cycles-pp.remove_vma
0.62 A+- 3% -0.1 0.53 A+- 4% perf-profile.children.cycles-pp.vmacache_update
1.14 -0.1 1.04 perf-profile.children.cycles-pp.__vm_enough_memory
0.87 A+- 2% -0.1 0.79 A+- 3% perf-profile.children.cycles-pp.rcu_all_qs
2.46 -0.1 2.37 A+- 2% perf-profile.children.cycles-pp.kmem_cache_alloc
1.22 -0.1 1.14 A+- 2% perf-profile.children.cycles-pp.up_write
0.92 -0.1 0.84 A+- 2% perf-profile.children.cycles-pp.tlb_gather_mmu
1.63 -0.1 1.55 perf-profile.children.cycles-pp.avc_has_perm_noaudit
1.26 A+- 2% -0.1 1.19 perf-profile.children.cycles-pp.__vma_rb_erase
0.78 A+- 2% -0.1 0.72 perf-profile.children.cycles-pp.free_pgd_range
1.19 -0.1 1.12 perf-profile.children.cycles-pp.vma_merge
1.41 A+- 2% -0.1 1.35 perf-profile.children.cycles-pp.cap_vm_enough_memory
0.82 -0.1 0.77 perf-profile.children.cycles-pp.percpu_counter_add_batch
1.30 -0.0 1.25 A+- 2% perf-profile.children.cycles-pp.tlb_finish_mmu
1.64 -0.0 1.59 perf-profile.children.cycles-pp.arch_get_unmapped_area_topdown
0.95 -0.0 0.90 perf-profile.children.cycles-pp.kmem_cache_free
0.44 -0.0 0.40 perf-profile.children.cycles-pp.strlen
1.22 -0.0 1.18 perf-profile.children.cycles-pp.perf_event_mmap_output
0.53 A+- 3% -0.0 0.49 A+- 3% perf-profile.children.cycles-pp.cap_capable
0.96 A+- 2% -0.0 0.93 perf-profile.children.cycles-pp.entry_SYSCALL_64_stage2
0.37 A+- 2% -0.0 0.35 A+- 4% perf-profile.children.cycles-pp.tlb_flush_mmu_free
74.20 +0.1 74.31 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
72.84 +0.2 73.04 perf-profile.children.cycles-pp.do_syscall_64
70.18 +0.3 70.48 perf-profile.children.cycles-pp.__x64_sys_brk
0.00 +0.8 0.84 A+- 3% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
0.00 +1.0 0.97 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.72 +2.3 3.02 perf-profile.children.cycles-pp._raw_spin_lock
28.33 +2.3 30.68 perf-profile.children.cycles-pp.do_munmap
14.65 +2.9 17.56 perf-profile.children.cycles-pp.unmap_region
0.66 A+- 4% +3.9 4.55 perf-profile.children.cycles-pp.lru_add_drain_cpu
3.19 -0.4 2.78 A+- 2% perf-profile.self.cycles-pp.__x64_sys_brk
5.09 -0.4 4.71 perf-profile.self.cycles-pp.unmap_page_range
12.87 -0.2 12.62 perf-profile.self.cycles-pp.syscall_return_via_sysret
0.55 A+- 4% -0.2 0.34 A+- 4% perf-profile.self.cycles-pp.unmap_single_vma
2.81 -0.2 2.64 perf-profile.self.cycles-pp.vma_compute_subtree_gap
2.28 -0.2 2.12 perf-profile.self.cycles-pp.vmacache_find
2.84 -0.1 2.70 perf-profile.self.cycles-pp.___might_sleep
0.80 -0.1 0.69 A+- 2% perf-profile.self.cycles-pp._cond_resched
3.24 -0.1 3.12 perf-profile.self.cycles-pp.do_brk_flags
0.33 A+- 3% -0.1 0.22 A+- 5% perf-profile.self.cycles-pp.arch_tlb_gather_mmu
4.25 -0.1 4.14 perf-profile.self.cycles-pp.find_vma
2.52 -0.1 2.41 perf-profile.self.cycles-pp.do_munmap
2.43 A+- 2% -0.1 2.33 perf-profile.self.cycles-pp.do_syscall_64
1.42 -0.1 1.32 perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.56 A+- 3% -0.1 0.47 A+- 5% perf-profile.self.cycles-pp.vmacache_update
1.62 -0.1 1.54 perf-profile.self.cycles-pp.avc_has_perm_noaudit
1.14 -0.1 1.07 perf-profile.self.cycles-pp.up_write
1.14 -0.1 1.07 perf-profile.self.cycles-pp.vma_merge
0.77 A+- 2% -0.1 0.71 A+- 2% perf-profile.self.cycles-pp.free_pgd_range
0.78 -0.1 0.73 A+- 2% perf-profile.self.cycles-pp.security_mmap_addr
0.77 -0.1 0.72 A+- 3% perf-profile.self.cycles-pp.get_unmapped_area
0.77 -0.1 0.72 A+- 4% perf-profile.self.cycles-pp.cred_has_capability
0.39 A+- 2% -0.0 0.34 A+- 3% perf-profile.self.cycles-pp.unmap_vmas
1.44 A+- 2% -0.0 1.39 perf-profile.self.cycles-pp.vm_area_alloc
0.89 -0.0 0.84 perf-profile.self.cycles-pp.__vma_rb_erase
0.78 -0.0 0.73 perf-profile.self.cycles-pp.__vm_enough_memory
1.12 A+- 2% -0.0 1.07 perf-profile.self.cycles-pp.__might_sleep
0.78 -0.0 0.73 perf-profile.self.cycles-pp.percpu_counter_add_batch
1.16 -0.0 1.12 perf-profile.self.cycles-pp.perf_event_mmap_output
0.94 -0.0 0.90 perf-profile.self.cycles-pp.kmem_cache_free
0.66 -0.0 0.62 perf-profile.self.cycles-pp.rcu_all_qs
0.49 A+- 3% -0.0 0.46 A+- 2% perf-profile.self.cycles-pp.cap_capable
0.40 A+- 2% -0.0 0.36 A+- 2% perf-profile.self.cycles-pp.strlen
0.65 -0.0 0.63 A+- 2% perf-profile.self.cycles-pp.cap_mmap_addr
0.63 A+- 4% +0.1 0.75 perf-profile.self.cycles-pp.lru_add_drain_cpu
0.00 +0.8 0.81 A+- 2% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore
0.00 +0.9 0.94 perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.68 A+- 2% +2.2 2.92 perf-profile.self.cycles-pp._raw_spin_lock
will-it-scale.per_process_ops
760000 +-+----------------------------------------------------------------+
| .+. + +. : |
755000 +-+ +. .+.+.+ : |
750000 +-+ : +. : |
|.+. : +. .+.. .+.+. |
745000 +-+ +..+.+ + + +..+. .+.|
| +.+.+..+ |
740000 +-+ |
| |
735000 +-+ |
730000 +-+ O |
| O O O |
725000 O-O O O O O O O O O O O O |
| O O O O O O O O |
720000 +-+----------------------------------------------------------------+
will-it-scale.workload
3.36e+07 +-+--------------------------------------------------------------+
3.34e+07 +-+ .+. .+. .+.+ |
| +.+..+.+ + +. : |
3.32e+07 +-+ +. + : |
3.3e+07 +-+ + + : |
|.+.+..+.+ +.+.+.+..+.+. |
3.28e+07 +-+ +.+.+.+..+.+.+.|
3.26e+07 +-+ |
3.24e+07 +-+ |
| |
3.22e+07 +-+ O O |
3.2e+07 +-O O O O O O O |
O O O O O O O O O O O O O O |
3.18e+07 +-+ O O |
3.16e+07 +-+--------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
***************************************************************************************************
ivb44: 48 threads Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 64G memory
=========================================================================================
bs/compiler/cpufreq_governor/disk/fs2/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/ucode:
4k/gcc-7/performance/1HDD/nfsv4/ext4/sync/x86_64-rhel-7.2/100%/debian-x86_64-2018-04-03.cgz/300s/write/ivb44/128G/fio-basic/0x42d
commit:
f3c0b8ce48 (" dmaengine fix for dmaengine-fix-4.19-rc4")
d884021f52 ("mm/swap: Add pagevec locking")
f3c0b8ce48408b74 d884021f52609407c7943705b3
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
:2 50% 1:4 kmsg.usb#-#:device_descriptor_read,error
:2 150% 3:4 dmesg.WARNING:at#for_ip_swapgs_restore_regs_and_return_to_usermode/0x
:2 150% 3:4 dmesg.WARNING:stack_recursion
0:2 15% 0:4 perf-profile.children.cycles-pp.io_schedule_timeout
0:2 17% 0:4 perf-profile.children.cycles-pp.schedule_timeout
%stddev %change %stddev
\ | \
4.1e+09 A+- 76% -50.6% 2.025e+09 A+-134% cpuidle.C3.time
7382534 A+- 46% -61.3% 2854923 A+- 99% cpuidle.C3.usage
29610 -1.1% 29281 proc-vmstat.nr_slab_unreclaimable
797236 +6.3% 847312 A+- 4% proc-vmstat.pgfree
7382736 A+- 46% -61.3% 2854836 A+- 99% turbostat.C3
28.31 A+- 76% -14.3 13.97 A+-134% turbostat.C3%
2520 A+- 2% -20.2% 2010 A+- 14% slabinfo.eventpoll_pwq.active_objs
2520 A+- 2% -20.2% 2010 A+- 14% slabinfo.eventpoll_pwq.num_objs
350.00 A+- 9% -27.1% 255.00 A+- 17% slabinfo.secpath_cache.active_objs
350.00 A+- 9% -27.1% 255.00 A+- 17% slabinfo.secpath_cache.num_objs
1972 A+- 2% -27.8% 1425 A+- 24% slabinfo.task_group.active_objs
1972 A+- 2% -27.8% 1425 A+- 24% slabinfo.task_group.num_objs
86415 +65.8% 143246 A+- 2% numa-meminfo.node0.Active
80095 A+- 7% +69.3% 135603 A+- 3% numa-meminfo.node0.Active(anon)
78653 A+- 9% +69.4% 133251 A+- 3% numa-meminfo.node0.AnonPages
8516 A+- 75% +1396.8% 127471 A+- 65% numa-meminfo.node0.Inactive(anon)
9990 A+- 53% +1200.9% 129966 A+- 63% numa-meminfo.node0.Shmem
198827 -27.4% 144403 A+- 2% numa-meminfo.node1.Active
190365 A+- 3% -27.9% 137259 A+- 2% numa-meminfo.node1.Active(anon)
187188 A+- 4% -28.1% 134639 A+- 2% numa-meminfo.node1.AnonPages
231370 A+- 2% -51.6% 112031 A+- 74% numa-meminfo.node1.Inactive(anon)
240802 -48.7% 123588 A+- 66% numa-meminfo.node1.Mapped
234636 A+- 2% -51.3% 114274 A+- 72% numa-meminfo.node1.Shmem
165.66 A+- 44% -55.4% 73.84 A+- 33% sched_debug.cfs_rq:/.load_avg.avg
304.80 A+- 34% -37.0% 191.89 A+- 6% sched_debug.cfs_rq:/.removed.load_avg.max
14073 A+- 33% -36.8% 8887 A+- 6% sched_debug.cfs_rq:/.removed.runnable_sum.max
125.80 A+- 39% -60.3% 49.99 A+- 26% sched_debug.cfs_rq:/.removed.util_avg.max
21.17 A+- 48% -50.6% 10.45 A+- 57% sched_debug.cfs_rq:/.removed.util_avg.stddev
506292 A+- 2% -33.1% 338712 A+- 18% sched_debug.cpu.avg_idle.min
103884 A+- 5% +368.2% 486437 A+- 71% sched_debug.cpu.avg_idle.stddev
7.96 +14.2% 9.10 A+- 5% sched_debug.cpu.cpu_load[3].avg
246.40 A+- 19% +37.1% 337.89 A+- 9% sched_debug.cpu.cpu_load[3].max
37.79 A+- 12% +29.3% 48.86 A+- 9% sched_debug.cpu.cpu_load[3].stddev
160.10 A+- 4% +43.3% 229.43 A+- 13% sched_debug.cpu.cpu_load[4].max
24.69 +34.6% 33.25 A+- 13% sched_debug.cpu.cpu_load[4].stddev
0.00 A+- 6% +32.1% 0.00 A+- 11% sched_debug.cpu.next_balance.stddev
20024 A+- 7% +69.3% 33898 A+- 3% numa-vmstat.node0.nr_active_anon
19661 A+- 9% +69.4% 33311 A+- 3% numa-vmstat.node0.nr_anon_pages
2128 A+- 75% +1395.3% 31827 A+- 65% numa-vmstat.node0.nr_inactive_anon
2499 A+- 52% +1198.6% 32451 A+- 63% numa-vmstat.node0.nr_shmem
20024 A+- 7% +69.3% 33898 A+- 3% numa-vmstat.node0.nr_zone_active_anon
2128 A+- 75% +1395.3% 31827 A+- 65% numa-vmstat.node0.nr_zone_inactive_anon
16608 A+- 4% -26.0% 12293 A+- 28% numa-vmstat.node1
47590 A+- 3% -27.9% 34315 A+- 2% numa-vmstat.node1.nr_active_anon
46795 A+- 4% -28.1% 33660 A+- 2% numa-vmstat.node1.nr_anon_pages
57747 A+- 2% -51.5% 27994 A+- 74% numa-vmstat.node1.nr_inactive_anon
60219 -48.6% 30929 A+- 66% numa-vmstat.node1.nr_mapped
58564 A+- 2% -51.2% 28556 A+- 72% numa-vmstat.node1.nr_shmem
47590 A+- 3% -27.9% 34315 A+- 2% numa-vmstat.node1.nr_zone_active_anon
57747 A+- 2% -51.5% 27994 A+- 74% numa-vmstat.node1.nr_zone_inactive_anon
75.04 A+- 6% -3.9 71.14 A+- 4% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
87.77 -2.6 85.21 perf-profile.calltrace.cycles-pp.secondary_startup_64
1.31 A+- 3% -0.2 1.11 A+- 12% perf-profile.calltrace.cycles-pp.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.ext4_file_write_iter.__vfs_write
1.24 A+- 4% -0.2 1.08 A+- 13% perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter
1.24 A+- 4% -0.1 1.09 A+- 12% perf-profile.calltrace.cycles-pp.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.ext4_file_write_iter
1.25 +0.1 1.33 A+- 3% perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
78.72 -3.3 75.42 A+- 3% perf-profile.children.cycles-pp.cpuidle_enter_state
87.77 -2.6 85.21 perf-profile.children.cycles-pp.secondary_startup_64
87.77 -2.6 85.21 perf-profile.children.cycles-pp.cpu_startup_entry
87.82 -2.5 85.29 perf-profile.children.cycles-pp.do_idle
1.37 A+- 49% -0.7 0.62 A+- 19% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
1.31 A+- 3% -0.2 1.11 A+- 12% perf-profile.children.cycles-pp.iov_iter_copy_from_user_atomic
0.30 A+- 9% -0.2 0.14 A+- 30% perf-profile.children.cycles-pp.__hrtimer_get_next_event
1.25 A+- 4% -0.1 1.10 A+- 12% perf-profile.children.cycles-pp.copyin
1.25 A+- 3% -0.1 1.11 A+- 14% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
0.34 A+- 18% -0.1 0.25 A+- 28% perf-profile.children.cycles-pp.timerqueue_del
0.18 A+- 13% -0.1 0.10 A+- 58% perf-profile.children.cycles-pp.nr_iowait_cpu
0.24 A+- 19% -0.1 0.15 A+- 28% perf-profile.children.cycles-pp.interrupt_entry
0.26 A+- 17% -0.1 0.19 A+- 16% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
0.10 A+- 40% -0.1 0.03 A+-105% perf-profile.children.cycles-pp.__list_del_entry_valid
0.10 A+- 40% -0.1 0.03 A+-105% perf-profile.children.cycles-pp.pick_next_task_fair
0.07 A+- 20% -0.0 0.04 A+- 57% perf-profile.children.cycles-pp.mem_cgroup_try_charge
0.10 A+- 14% -0.0 0.07 A+- 26% perf-profile.children.cycles-pp.can_stop_idle_tick
0.20 A+- 2% +0.0 0.24 A+- 3% perf-profile.children.cycles-pp.radix_tree_next_chunk
0.00 +0.1 0.06 A+- 9% perf-profile.children.cycles-pp.alloc_pages_current
0.00 +0.1 0.07 A+- 23% perf-profile.children.cycles-pp.sys_imageblit
0.00 +0.1 0.07 A+- 23% perf-profile.children.cycles-pp.drm_fb_helper_sys_imageblit
0.00 +0.1 0.07 A+- 23% perf-profile.children.cycles-pp.mga_imageblit
0.10 A+- 30% +0.1 0.17 A+- 4% perf-profile.children.cycles-pp.rcu_needs_cpu
0.06 A+- 16% +0.1 0.13 A+- 42% perf-profile.children.cycles-pp.__wake_up_common_lock
0.08 A+- 5% +0.1 0.17 A+- 28% perf-profile.children.cycles-pp.__x64_sys_execve
0.08 A+- 5% +0.1 0.17 A+- 25% perf-profile.children.cycles-pp.execve
0.08 A+- 6% +0.1 0.16 A+- 26% perf-profile.children.cycles-pp.__do_execve_file
0.00 +0.1 0.09 A+- 40% perf-profile.children.cycles-pp.proc_reg_read
0.00 +0.1 0.11 A+- 37% perf-profile.children.cycles-pp.seq_read
0.00 +0.1 0.13 A+- 42% perf-profile.children.cycles-pp.__mutex_lock
0.30 A+- 6% +0.2 0.46 A+- 28% perf-profile.children.cycles-pp._raw_spin_lock
0.26 +0.2 0.45 A+- 23% perf-profile.children.cycles-pp._raw_spin_lock_irq
0.21 A+- 23% -0.1 0.08 A+- 15% perf-profile.self.cycles-pp.__hrtimer_get_next_event
0.18 A+- 13% -0.1 0.09 A+- 59% perf-profile.self.cycles-pp.nr_iowait_cpu
0.24 A+- 19% -0.1 0.14 A+- 30% perf-profile.self.cycles-pp.interrupt_entry
0.12 A+- 28% -0.1 0.04 A+-110% perf-profile.self.cycles-pp.timerqueue_del
0.24 A+- 16% -0.1 0.16 A+- 16% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
0.22 A+- 4% -0.1 0.15 A+- 18% perf-profile.self.cycles-pp.get_next_timer_interrupt
0.22 A+- 4% -0.0 0.18 A+- 12% perf-profile.self.cycles-pp.timerqueue_add
0.10 A+- 14% -0.0 0.07 A+- 26% perf-profile.self.cycles-pp.can_stop_idle_tick
0.20 A+- 2% +0.0 0.24 A+- 3% perf-profile.self.cycles-pp.radix_tree_next_chunk
0.10 A+- 14% +0.1 0.17 A+- 15% perf-profile.self.cycles-pp.do_syscall_64
0.09 +0.1 0.15 A+- 24% perf-profile.self.cycles-pp.__update_load_avg_se
0.00 +0.1 0.07 A+- 23% perf-profile.self.cycles-pp.sys_imageblit
0.00 +0.1 0.07 A+- 31% perf-profile.self.cycles-pp.ext4_block_write_begin
0.10 A+- 26% +0.1 0.17 A+- 4% perf-profile.self.cycles-pp.rcu_needs_cpu
0.00 +0.1 0.07 A+- 38% perf-profile.self.cycles-pp.hrtimer_get_next_event
0.00 +0.1 0.08 A+- 19% perf-profile.self.cycles-pp.__mutex_lock
0.23 A+- 2% +0.2 0.39 A+- 23% perf-profile.self.cycles-pp._raw_spin_lock_irq
0.29 +0.2 0.44 A+- 28% perf-profile.self.cycles-pp._raw_spin_lock
0.50 A+- 2% +0.2 0.68 A+- 16% perf-profile.self.cycles-pp.__next_timer_interrupt
***************************************************************************************************
lkp-hsw-ep2: 72 threads Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz with 128G memory
=========================================================================================
bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/ucode:
4k/gcc-7/performance/1SSD/ext4/sync/x86_64-rhel-7.2/64/debian-x86_64-2018-04-03.cgz/300s/randwrite/lkp-hsw-ep2/512g/fio-basic/0x3d
commit:
f3c0b8ce48 (" dmaengine fix for dmaengine-fix-4.19-rc4")
d884021f52 ("mm/swap: Add pagevec locking")
f3c0b8ce48408b74 d884021f52609407c7943705b3
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
:2 50% 1:4 dmesg.WARNING:at#for_ip_interrupt_entry/0x
:2 50% 1:4 dmesg.WARNING:at_ip_native_sched_clock/0x
0:2 22% 1:4 perf-profile.children.cycles-pp.schedule_timeout
1:2 60% 2:4 perf-profile.children.cycles-pp.io_schedule_timeout
%stddev %change %stddev
\ | \
5.06 +1.6 6.65 A+- 11% fio.latency_100us%
0.86 A+- 3% +0.1 0.99 A+- 3% fio.latency_250us%
256.63 +7.7% 276.50 fio.time.system_time
45.00 +7.8% 48.50 A+- 3% fio.write_clat_90%_us
58.00 +7.8% 62.50 A+- 3% fio.write_clat_95%_us
14118389 A+- 51% +79.1% 25292065 A+- 9% cpuidle.C6.usage
2571 -1.1% 2543 proc-vmstat.nr_page_table_pages
19228 A+- 79% -80.4% 3774 A+- 3% proc-vmstat.numa_pte_updates
14115889 A+- 51% +79.2% 25289182 A+- 9% turbostat.C6
0.21 A+- 17% -64.6% 0.07 A+- 40% turbostat.Pkg%pc3
7321922 A+- 2% -8.3% 6717403 A+- 6% numa-numastat.node0.local_node
436778 A+- 29% -67.9% 140332 A+-173% numa-numastat.node0.numa_foreign
7336061 A+- 2% -8.4% 6721069 A+- 6% numa-numastat.node0.numa_hit
436778 A+- 29% -67.9% 140332 A+-173% numa-numastat.node1.numa_miss
865.00 A+- 13% -20.7% 686.00 A+- 26% slabinfo.nfs_commit_data.active_objs
865.00 A+- 13% -20.7% 686.00 A+- 26% slabinfo.nfs_commit_data.num_objs
2627 A+- 24% -22.1% 2045 A+- 34% slabinfo.scsi_sense_cache.active_objs
2628 A+- 24% -21.4% 2065 A+- 32% slabinfo.scsi_sense_cache.num_objs
51178 A+- 4% -7.7% 47251 A+- 4% slabinfo.vm_area_struct.active_objs
1287 A+- 4% -7.8% 1186 A+- 4% slabinfo.vm_area_struct.active_slabs
51507 A+- 4% -7.8% 47465 A+- 4% slabinfo.vm_area_struct.num_objs
1287 A+- 4% -7.8% 1186 A+- 4% slabinfo.vm_area_struct.num_slabs
2194 A+- 3% -119.1% -419.80 sched_debug.cfs_rq:/.spread0.avg
5.71 A+- 3% -14.8% 4.87 A+- 12% sched_debug.cfs_rq:/.util_est_enqueued.avg
324306 A+- 10% -9.0% 295152 A+- 4% sched_debug.cpu.nr_load_updates.max
5621 A+- 68% -69.7% 1702 A+- 12% sched_debug.cpu.nr_load_updates.stddev
11.00 A+- 13% -18.6% 8.95 A+- 20% sched_debug.cpu.nr_uninterruptible.max
1027 A+- 7% +45.0% 1490 A+- 19% sched_debug.cpu.ttwu_count.min
546.55 -30.2% 381.53 A+- 28% sched_debug.cpu.ttwu_local.min
0.00 A+- 49% +122.3% 0.00 A+- 30% sched_debug.rt_rq:/.rt_time.avg
0.02 A+- 49% +122.3% 0.03 A+- 30% sched_debug.rt_rq:/.rt_time.max
0.00 A+- 49% +122.3% 0.00 A+- 30% sched_debug.rt_rq:/.rt_time.stddev
289208 A+- 15% -26.5% 212596 A+- 23% numa-meminfo.node0.Active
190569 -33.4% 126938 A+- 23% numa-meminfo.node0.Active(anon)
157915 A+- 2% -36.2% 100710 A+- 26% numa-meminfo.node0.AnonHugePages
190832 -35.5% 123030 A+- 22% numa-meminfo.node0.AnonPages
7548 -16.5% 6301 A+- 4% numa-meminfo.node0.KernelStack
8824 A+- 2% -64.8% 3105 A+- 78% numa-meminfo.node0.PageTables
69548 -11.1% 61798 A+- 8% numa-meminfo.node0.SUnreclaim
87222 +74.1% 151868 A+- 18% numa-meminfo.node1.Active(anon)
62739 A+- 2% +93.2% 121230 A+- 22% numa-meminfo.node1.AnonHugePages
79918 A+- 2% +85.9% 148605 A+- 18% numa-meminfo.node1.AnonPages
15315 +531.7% 96745 A+- 49% numa-meminfo.node1.Inactive(anon)
4801 A+- 4% +23.8% 5941 A+- 5% numa-meminfo.node1.KernelStack
16370 +510.7% 99979 A+- 48% numa-meminfo.node1.Mapped
1468 A+- 12% +381.8% 7073 A+- 34% numa-meminfo.node1.PageTables
47642 -33.4% 31737 A+- 23% numa-vmstat.node0.nr_active_anon
47710 -35.5% 30760 A+- 22% numa-vmstat.node0.nr_anon_pages
7549 -16.5% 6301 A+- 4% numa-vmstat.node0.nr_kernel_stack
2206 A+- 2% -64.8% 776.75 A+- 78% numa-vmstat.node0.nr_page_table_pages
17386 -11.1% 15449 A+- 8% numa-vmstat.node0.nr_slab_unreclaimable
3677874 -11.3% 3261486 A+- 3% numa-vmstat.node0.nr_written
47642 -33.4% 31737 A+- 23% numa-vmstat.node0.nr_zone_active_anon
432470 A+- 29% -67.9% 138936 A+-173% numa-vmstat.node0.numa_foreign
6791323 -12.1% 5968091 A+- 4% numa-vmstat.node0.numa_hit
6776182 -12.0% 5962755 A+- 4% numa-vmstat.node0.numa_local
21807 +74.1% 37971 A+- 18% numa-vmstat.node1.nr_active_anon
19981 A+- 2% +86.0% 37155 A+- 18% numa-vmstat.node1.nr_anon_pages
3829 +532.5% 24221 A+- 49% numa-vmstat.node1.nr_inactive_anon
4804 A+- 4% +23.6% 5939 A+- 5% numa-vmstat.node1.nr_kernel_stack
4094 +513.7% 25127 A+- 48% numa-vmstat.node1.nr_mapped
367.50 A+- 12% +381.1% 1768 A+- 34% numa-vmstat.node1.nr_page_table_pages
3117498 A+- 3% +14.3% 3562760 A+- 4% numa-vmstat.node1.nr_written
21807 +74.1% 37971 A+- 18% numa-vmstat.node1.nr_zone_active_anon
3829 +532.5% 24221 A+- 49% numa-vmstat.node1.nr_zone_inactive_anon
5695266 +15.9% 6602176 A+- 6% numa-vmstat.node1.numa_hit
5557113 +16.1% 6453474 A+- 6% numa-vmstat.node1.numa_local
432474 A+- 29% -67.9% 138938 A+-173% numa-vmstat.node1.numa_miss
19.04 -4.1 14.96 A+- 16% perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary
16.23 A+- 4% -3.6 12.66 A+- 18% perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.do_idle.cpu_startup_entry
6.30 A+- 11% -2.2 4.15 A+- 34% perf-profile.calltrace.cycles-pp.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.do_idle
4.96 A+- 14% -1.7 3.30 A+- 39% perf-profile.calltrace.cycles-pp.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state
3.58 A+- 3% -1.0 2.55 A+- 19% perf-profile.calltrace.cycles-pp.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
5.03 A+- 5% -0.8 4.21 A+- 12% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state
3.06 A+- 2% -0.8 2.26 A+- 18% perf-profile.calltrace.cycles-pp.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt
2.86 A+- 3% -0.8 2.09 A+- 18% perf-profile.calltrace.cycles-pp.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt
1.50 A+- 23% -0.7 0.76 A+- 80% perf-profile.calltrace.cycles-pp.rcu_process_callbacks.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt
2.65 A+- 22% -0.7 1.92 A+- 38% perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state
1.66 A+- 34% -0.7 0.96 A+- 75% perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
3.17 -0.6 2.54 A+- 15% perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry.start_secondary
2.56 -0.6 2.00 A+- 16% perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry
1.58 -0.4 1.15 A+- 24% perf-profile.calltrace.cycles-pp.scheduler_tick.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues
0.77 A+- 9% -0.4 0.33 A+-104% perf-profile.calltrace.cycles-pp.load_balance.rebalance_domains.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt
0.78 A+- 3% -0.3 0.46 A+- 58% perf-profile.calltrace.cycles-pp.run_timer_softirq.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt
18.20 A+- 4% -3.9 14.30 A+- 16% perf-profile.children.cycles-pp.apic_timer_interrupt
16.71 A+- 6% -3.7 13.05 A+- 18% perf-profile.children.cycles-pp.smp_apic_timer_interrupt
8.34 A+- 14% -1.6 6.73 A+- 21% perf-profile.children.cycles-pp.irq_exit
8.96 A+- 4% -1.5 7.42 A+- 14% perf-profile.children.cycles-pp.hrtimer_interrupt
3.20 A+- 19% -1.2 2.01 A+- 36% perf-profile.children.cycles-pp.ktime_get
3.79 -1.1 2.68 A+- 19% perf-profile.children.cycles-pp.tick_sched_timer
3.26 A+- 2% -0.9 2.38 A+- 18% perf-profile.children.cycles-pp.tick_sched_handle
3.05 A+- 2% -0.8 2.21 A+- 18% perf-profile.children.cycles-pp.update_process_times
5.28 -0.8 4.47 A+- 11% perf-profile.children.cycles-pp.__hrtimer_run_queues
5.86 A+- 2% -0.8 5.08 A+- 13% perf-profile.children.cycles-pp.menu_select
2.71 A+- 23% -0.7 1.97 A+- 37% perf-profile.children.cycles-pp.clockevents_program_event
3.24 -0.7 2.57 A+- 15% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length
1.54 A+- 24% -0.6 0.90 A+- 55% perf-profile.children.cycles-pp.rcu_process_callbacks
2.62 -0.6 2.03 A+- 16% perf-profile.children.cycles-pp.tick_nohz_next_event
0.86 A+- 11% -0.5 0.40 A+- 31% perf-profile.children.cycles-pp.tick_nohz_irq_exit
0.53 A+- 34% -0.4 0.09 A+- 39% perf-profile.children.cycles-pp.timekeeping_max_deferment
0.71 A+- 14% -0.3 0.42 A+- 51% perf-profile.children.cycles-pp.note_gp_changes
0.80 -0.2 0.58 A+- 19% perf-profile.children.cycles-pp.run_timer_softirq
0.23 A+- 53% -0.2 0.06 A+- 64% perf-profile.children.cycles-pp.page_fault
0.34 A+- 49% -0.2 0.16 A+-111% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
0.23 A+- 52% -0.2 0.05 A+- 62% perf-profile.children.cycles-pp.do_page_fault
0.22 A+- 55% -0.2 0.05 A+- 62% perf-profile.children.cycles-pp.__do_page_fault
0.57 A+- 12% -0.1 0.43 A+- 31% perf-profile.children.cycles-pp.schedule
0.67 A+- 5% -0.1 0.53 A+- 23% perf-profile.children.cycles-pp.rcu_check_callbacks
0.68 A+- 4% -0.1 0.54 A+- 7% perf-profile.children.cycles-pp._raw_spin_lock
0.52 A+- 6% -0.1 0.42 A+- 15% perf-profile.children.cycles-pp.unwind_next_frame
0.19 A+- 21% -0.1 0.10 A+- 24% perf-profile.children.cycles-pp.raise_softirq
0.16 A+- 9% -0.1 0.08 A+- 15% perf-profile.children.cycles-pp.cpu_load_update
0.56 -0.1 0.49 A+- 10% perf-profile.children.cycles-pp.__entry_SYSCALL_64_trampoline
0.17 A+- 23% -0.1 0.10 A+- 29% perf-profile.children.cycles-pp.irq_entries_start
0.11 A+- 4% -0.1 0.05 A+- 67% perf-profile.children.cycles-pp.orc_find
0.23 A+- 6% -0.1 0.18 A+- 8% perf-profile.children.cycles-pp.rcu_eqs_enter
0.17 A+- 3% -0.0 0.12 A+- 25% perf-profile.children.cycles-pp.calc_global_load_tick
0.09 A+- 17% -0.0 0.04 A+-103% perf-profile.children.cycles-pp.blk_queue_start_tag
0.15 A+- 6% -0.0 0.12 A+- 23% perf-profile.children.cycles-pp.rcu_nmi_exit
0.09 -0.0 0.06 A+- 59% perf-profile.children.cycles-pp.percpu_counter_add_batch
0.09 A+- 22% -0.0 0.06 A+- 22% perf-profile.children.cycles-pp.update_rt_rq_load_avg
0.10 A+- 5% -0.0 0.08 A+- 5% perf-profile.children.cycles-pp.__alloc_pages_nodemask
0.08 A+- 12% -0.0 0.06 A+- 17% perf-profile.children.cycles-pp.task_tick_idle
0.10 A+- 5% -0.0 0.08 A+- 5% perf-profile.children.cycles-pp.get_iowait_load
0.10 A+- 5% +0.0 0.14 A+- 15% perf-profile.children.cycles-pp.nr_iowait_cpu
0.00 +0.1 0.06 A+- 20% perf-profile.children.cycles-pp.blk_account_io_done
0.09 A+- 17% +0.1 0.16 A+- 21% perf-profile.children.cycles-pp.blk_finish_request
0.10 A+- 26% +0.1 0.22 A+- 45% perf-profile.children.cycles-pp.kmem_cache_free
0.30 A+- 6% +0.2 0.48 A+- 39% perf-profile.children.cycles-pp.ext4_end_bio
0.00 +0.2 0.18 A+- 27% perf-profile.children.cycles-pp.pipe_read
0.75 A+- 6% +0.2 0.93 A+- 8% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler
0.07 A+- 7% +0.2 0.29 A+- 26% perf-profile.children.cycles-pp.__vfs_read
0.07 A+- 20% +0.2 0.32 A+- 24% perf-profile.children.cycles-pp.vfs_read
0.07 A+- 20% +0.3 0.34 A+- 24% perf-profile.children.cycles-pp.ksys_read
0.03 A+-100% +0.3 0.34 A+- 23% perf-profile.children.cycles-pp.read
2.52 A+- 25% -1.2 1.35 A+- 56% perf-profile.self.cycles-pp.ktime_get
0.53 A+- 35% -0.4 0.08 A+- 42% perf-profile.self.cycles-pp.timekeeping_max_deferment
2.04 A+- 9% -0.3 1.72 A+- 6% perf-profile.self.cycles-pp.cpuidle_enter_state
0.42 A+- 12% -0.2 0.23 A+- 46% perf-profile.self.cycles-pp.__softirqentry_text_start
0.44 A+- 21% -0.2 0.25 A+- 50% perf-profile.self.cycles-pp.note_gp_changes
0.34 A+- 49% -0.2 0.16 A+-111% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
0.41 -0.2 0.24 A+- 22% perf-profile.self.cycles-pp.run_timer_softirq
0.29 -0.2 0.13 A+- 34% perf-profile.self.cycles-pp.tick_sched_timer
0.67 A+- 3% -0.1 0.53 A+- 8% perf-profile.self.cycles-pp._raw_spin_lock
0.38 A+- 6% -0.1 0.25 A+- 35% perf-profile.self.cycles-pp.update_blocked_averages
0.18 A+- 18% -0.1 0.09 A+- 27% perf-profile.self.cycles-pp.raise_softirq
0.21 A+- 2% -0.1 0.12 A+- 21% perf-profile.self.cycles-pp.load_balance
0.16 A+- 9% -0.1 0.08 A+- 15% perf-profile.self.cycles-pp.cpu_load_update
0.28 A+- 14% -0.1 0.21 A+- 24% perf-profile.self.cycles-pp.rcu_process_callbacks
0.26 A+- 21% -0.1 0.18 A+- 10% perf-profile.self.cycles-pp.idle_cpu
0.54 -0.1 0.46 A+- 12% perf-profile.self.cycles-pp.__entry_SYSCALL_64_trampoline
0.18 A+- 8% -0.1 0.12 A+- 20% perf-profile.self.cycles-pp.scheduler_tick
0.23 A+- 6% -0.1 0.17 A+- 4% perf-profile.self.cycles-pp.rcu_eqs_enter
0.11 -0.1 0.05 A+- 70% perf-profile.self.cycles-pp.orc_find
0.09 A+- 17% -0.1 0.03 A+-102% perf-profile.self.cycles-pp.update_rt_rq_load_avg
0.09 A+- 22% -0.1 0.04 A+-102% perf-profile.self.cycles-pp.tick_nohz_get_sleep_length
0.15 A+- 17% -0.1 0.09 A+- 24% perf-profile.self.cycles-pp.rcu_needs_cpu
0.35 A+- 9% -0.1 0.30 A+- 9% perf-profile.self.cycles-pp.tick_nohz_next_event
0.15 A+- 6% -0.0 0.12 A+- 23% perf-profile.self.cycles-pp.rcu_nmi_exit
0.07 A+- 20% -0.0 0.04 A+- 63% perf-profile.self.cycles-pp.ext4_bio_write_page
0.10 A+- 5% -0.0 0.08 A+- 8% perf-profile.self.cycles-pp.get_iowait_load
0.09 A+- 11% +0.0 0.14 A+- 15% perf-profile.self.cycles-pp.nr_iowait_cpu
0.15 A+- 33% +0.1 0.24 A+- 17% perf-profile.self.cycles-pp.perf_mux_hrtimer_handler
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 Attachments
- config-4.19.0-rc3-00248-gd884021 [text/plain] 167701 bytes · preview
- job-script [text/plain] 6930 bytes · preview
- job.yaml [text/plain] 4586 bytes · preview
- reproduce [text/plain] 307 bytes · preview