Greeting,
FYI, we noticed a 10.3% improvement of hackbench.throughput due to commit:
commit: 58056f77502f3567b760c9a8fc8d2e9081515b2d ("memcg, kmem: further deprecate kmem.limit_in_bytes")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: hackbench
on test machine: 144 threads 4 sockets Intel(R) Xeon(R) Gold 5318H CPU @ 2.50GHz with 128G memory
with following parameters:
nr_threads: 100%
iterations: 4
mode: process
ipc: socket
cpufreq_governor: performance
ucode: 0x700001e
test-description: Hackbench is both a benchmark and a stress test for the Linux kernel scheduler.
test-url: https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/sched/cfs-scheduler/hackbench.c
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
sudo bin/lkp install job.yaml # job file is attached in this email
bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
sudo bin/lkp run generated-yaml-file
# if come across any failure that blocks the test,
# please remove ~/.lkp and /lkp dir to run from a clean state.
=========================================================================================
compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase/ucode:
gcc-9/performance/socket/4/x86_64-rhel-8.3/process/100%/debian-10.4-x86_64-20200603.cgz/lkp-cpl-4sp1/hackbench/0x700001e
commit:
16f6bf266c ("mm/list_lru.c: prefer struct_size over open coded arithmetic")
58056f7750 ("memcg, kmem: further deprecate kmem.limit_in_bytes")
16f6bf266c94017c 58056f77502f3567b760c9a8fc8
---------------- ---------------------------
%stddev %change %stddev
\ | \
124164 +10.3% 137012 ? 2% hackbench.throughput
553.20 -9.9% 498.51 ? 2% hackbench.time.elapsed_time
553.20 -9.9% 498.51 ? 2% hackbench.time.elapsed_time.max
3.519e+08 ? 4% -56.3% 1.539e+08 ? 2% hackbench.time.involuntary_context_switches
76944 -10.0% 69266 ? 2% hackbench.time.system_time
1046 -15.9% 880.42 ? 2% hackbench.time.user_time
9.209e+08 ? 2% -41.2% 5.414e+08 hackbench.time.voluntary_context_switches
516011 ? 17% -33.5% 343117 ? 32% numa-numastat.node1.numa_hit
260286 ? 8% -16.7% 216841 ? 15% numa-vmstat.node3.nr_shmem
607.74 -8.8% 554.41 uptime.boot
164520 +2.7% 168980 proc-vmstat.nr_slab_unreclaimable
137719 -4.5% 131582 proc-vmstat.pgreuse
0.42 ? 6% +0.1 0.53 ? 6% turbostat.C1%
2.966e+08 -18.8% 2.408e+08 ? 2% turbostat.IRQ
2746 -12.3% 2408 vmstat.procs.r
2336697 ? 3% -38.4% 1439816 vmstat.system.cs
534308 -9.9% 481527 vmstat.system.in
5546 ? 5% -12.6% 4846 ? 6% slabinfo.kmalloc-cg-192.active_objs
5546 ? 5% -12.6% 4846 ? 6% slabinfo.kmalloc-cg-192.num_objs
157208 +9.5% 172170 slabinfo.kmalloc-cg-512.active_objs
3128 +11.3% 3480 slabinfo.kmalloc-cg-512.active_slabs
200236 +11.3% 222802 slabinfo.kmalloc-cg-512.num_objs
3128 +11.3% 3480 slabinfo.kmalloc-cg-512.num_slabs
157390 +9.5% 172289 slabinfo.skbuff_head_cache.active_objs
3134 +11.2% 3485 slabinfo.skbuff_head_cache.active_slabs
200626 +11.2% 223129 slabinfo.skbuff_head_cache.num_objs
3134 +11.2% 3485 slabinfo.skbuff_head_cache.num_slabs
1.669e+10 -5.2% 1.582e+10 perf-stat.i.branch-instructions
0.80 -0.2 0.64 ? 2% perf-stat.i.branch-miss-rate%
1.312e+08 -24.3% 99283197 ? 2% perf-stat.i.branch-misses
27.80 +1.1 28.86 perf-stat.i.cache-miss-rate%
8.619e+08 -1.5% 8.491e+08 perf-stat.i.cache-references
2349252 ? 3% -38.2% 1452325 perf-stat.i.context-switches
143032 ? 2% -14.7% 121977 ? 2% perf-stat.i.cpu-migrations
2001 -3.5% 1931 perf-stat.i.cycles-between-cache-misses
0.07 ? 5% -0.0 0.06 ? 5% perf-stat.i.dTLB-load-miss-rate%
16549027 ? 4% -12.9% 14414299 ? 3% perf-stat.i.dTLB-load-misses
2.392e+10 -1.9% 2.348e+10 perf-stat.i.dTLB-loads
0.03 ? 11% +0.0 0.04 ? 6% perf-stat.i.dTLB-store-miss-rate%
4025883 ? 11% +30.5% 5252098 ? 5% perf-stat.i.dTLB-store-misses
56000903 -35.7% 35989438 ? 8% perf-stat.i.iTLB-load-misses
23047129 ? 3% -35.8% 14787249 perf-stat.i.iTLB-loads
8.356e+10 -3.9% 8.027e+10 perf-stat.i.instructions
1548 +47.8% 2288 ? 7% perf-stat.i.instructions-per-iTLB-miss
0.18 -4.4% 0.17 perf-stat.i.ipc
869.08 +4.5% 908.26 perf-stat.i.metric.K/sec
384.93 -2.7% 374.53 perf-stat.i.metric.M/sec
7130 +3.7% 7398 ? 3% perf-stat.i.minor-faults
66.31 -6.3 60.05 ? 2% perf-stat.i.node-load-miss-rate%
39678105 -3.8% 38161927 perf-stat.i.node-load-misses
20549470 +25.2% 25719712 ? 5% perf-stat.i.node-loads
43.76 -6.0 37.72 ? 5% perf-stat.i.node-store-miss-rate%
15613166 ? 2% +10.0% 17180670 ? 4% perf-stat.i.node-store-misses
20301635 +40.5% 28518438 ? 4% perf-stat.i.node-stores
7172 +3.8% 7443 ? 3% perf-stat.i.page-faults
0.79 -0.2 0.62 ? 2% perf-stat.overall.branch-miss-rate%
28.13 +0.9 29.08 perf-stat.overall.cache-miss-rate%
5.65 +2.5% 5.79 perf-stat.overall.cpi
1942 -2.3% 1899 perf-stat.overall.cycles-between-cache-misses
0.07 ? 5% -0.0 0.06 ? 5% perf-stat.overall.dTLB-load-miss-rate%
0.03 ? 11% +0.0 0.04 ? 6% perf-stat.overall.dTLB-store-miss-rate%
1500 +49.7% 2246 ? 7% perf-stat.overall.instructions-per-iTLB-miss
0.18 -2.4% 0.17 perf-stat.overall.ipc
64.79 -5.9 58.87 perf-stat.overall.node-load-miss-rate%
40.92 -5.0 35.89 ? 3% perf-stat.overall.node-store-miss-rate%
1.641e+10 -3.5% 1.584e+10 perf-stat.ps.branch-instructions
1.288e+08 -23.6% 98487415 ? 2% perf-stat.ps.branch-misses
2337457 ? 3% -38.5% 1437257 perf-stat.ps.context-switches
130209 ? 2% -13.6% 112490 perf-stat.ps.cpu-migrations
16228057 ? 4% -11.2% 14403294 ? 3% perf-stat.ps.dTLB-load-misses
3947999 ? 10% +31.5% 5191308 ? 5% perf-stat.ps.dTLB-store-misses
54846930 -34.4% 35981347 ? 8% perf-stat.ps.iTLB-load-misses
22682918 ? 2% -35.8% 14572556 perf-stat.ps.iTLB-loads
8.23e+10 -2.4% 8.035e+10 perf-stat.ps.instructions
20.85 ? 3% +15.9% 24.16 ? 4% perf-stat.ps.major-faults
5283 +10.5% 5839 perf-stat.ps.minor-faults
39315654 -4.2% 37669399 perf-stat.ps.node-load-misses
21363970 +23.3% 26334557 ? 4% perf-stat.ps.node-loads
14602656 +11.5% 16280558 ? 2% perf-stat.ps.node-store-misses
21089334 +38.0% 29102191 ? 3% perf-stat.ps.node-stores
5304 +10.5% 5863 perf-stat.ps.page-faults
4.56e+13 -12.0% 4.011e+13 perf-stat.total.instructions
0.14 ?149% +6903.8% 10.10 ? 90% perf-sched.sch_delay.avg.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
146.03 ? 20% -59.7% 58.91 ? 32% perf-sched.sch_delay.avg.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
20.00 ? 16% -39.8% 12.05 ? 15% perf-sched.sch_delay.avg.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
45.20 ? 21% -45.1% 24.80 ? 17% perf-sched.sch_delay.avg.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
168.56 ? 19% -77.4% 38.03 ? 34% perf-sched.sch_delay.avg.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
87.74 ? 39% -69.7% 26.57 ? 32% perf-sched.sch_delay.avg.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
142.77 ? 20% -39.2% 86.82 ? 21% perf-sched.sch_delay.avg.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
22.06 ? 12% -51.5% 10.70 ? 19% perf-sched.sch_delay.avg.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
6.08 ?146% +12273.2% 752.85 ? 96% perf-sched.sch_delay.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
22236 ? 14% -62.5% 8341 ? 29% perf-sched.sch_delay.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
26048 ? 9% -52.9% 12272 ? 28% perf-sched.sch_delay.max.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
24687 ? 8% -61.5% 9499 ? 27% perf-sched.sch_delay.max.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
24838 ? 8% -70.9% 7234 ? 34% perf-sched.sch_delay.max.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
21611 ? 13% -65.7% 7403 ? 44% perf-sched.sch_delay.max.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
26017 ? 10% -53.3% 12149 ? 32% perf-sched.sch_delay.max.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
26199 ? 9% -57.5% 11127 ? 28% perf-sched.sch_delay.max.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
26.44 ? 13% -36.5% 16.79 ? 16% perf-sched.total_sch_delay.average.ms
26690 ? 10% -52.4% 12702 ? 29% perf-sched.total_sch_delay.max.ms
92.56 ? 13% -34.8% 60.38 ? 16% perf-sched.total_wait_and_delay.average.ms
53236 ? 9% -51.9% 25601 ? 30% perf-sched.total_wait_and_delay.max.ms
66.12 ? 13% -34.1% 43.58 ? 17% perf-sched.total_wait_time.average.ms
26766 ? 8% -47.8% 13965 ? 29% perf-sched.total_wait_time.max.ms
549.67 ? 18% -64.8% 193.37 ? 28% perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
75.13 ? 14% -41.6% 43.84 ? 14% perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
167.49 ? 17% -45.5% 91.23 ? 16% perf-sched.wait_and_delay.avg.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
594.39 ? 14% -76.9% 137.13 ? 29% perf-sched.wait_and_delay.avg.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
317.87 ? 21% -65.9% 108.34 ? 28% perf-sched.wait_and_delay.avg.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
1953 ?115% -90.1% 193.28 ?107% perf-sched.wait_and_delay.avg.ms.preempt_schedule_common.__cond_resched.rmap_walk_anon.remove_migration_ptes.migrate_pages
154.92 ? 33% -82.5% 27.16 ?152% perf-sched.wait_and_delay.avg.ms.preempt_schedule_common.__cond_resched.wait_for_completion.affine_move_task.__set_cpus_allowed_ptr_locked
7364 ? 51% -83.3% 1228 ?110% perf-sched.wait_and_delay.avg.ms.rwsem_down_read_slowpath.rmap_walk_anon.remove_migration_ptes.migrate_pages
532.84 ? 22% -42.2% 308.22 ? 23% perf-sched.wait_and_delay.avg.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
73.20 ? 12% -48.1% 37.98 ? 19% perf-sched.wait_and_delay.avg.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
131.17 ? 12% +54.1% 202.17 ? 14% perf-sched.wait_and_delay.count.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt.[unknown]
1020 ? 16% +30.8% 1335 ? 15% perf-sched.wait_and_delay.count.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
12199 ? 15% +39.9% 17063 ? 19% perf-sched.wait_and_delay.count.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
1423 ? 12% +44.5% 2056 ? 17% perf-sched.wait_and_delay.count.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
6.00 ? 19% +88.9% 11.33 ? 15% perf-sched.wait_and_delay.count.schedule_timeout.kcompactd.kthread.ret_from_fork
48952 ? 19% +143.5% 119182 ? 12% perf-sched.wait_and_delay.count.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
240.00 ? 17% +52.6% 366.17 ? 18% perf-sched.wait_and_delay.count.smpboot_thread_fn.kthread.ret_from_fork
119.67 ? 28% +60.3% 191.83 ? 17% perf-sched.wait_and_delay.count.worker_thread.kthread.ret_from_fork
45862 ? 11% -63.5% 16731 ? 29% perf-sched.wait_and_delay.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
52359 ? 9% -52.3% 24957 ? 30% perf-sched.wait_and_delay.max.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
49522 ? 8% -61.6% 19021 ? 27% perf-sched.wait_and_delay.max.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
49837 ? 8% -70.5% 14699 ? 33% perf-sched.wait_and_delay.max.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
43808 ? 12% -66.0% 14910 ? 44% perf-sched.wait_and_delay.max.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
36717 ? 23% -82.8% 6317 ?122% perf-sched.wait_and_delay.max.ms.preempt_schedule_common.__cond_resched.rmap_walk_anon.remove_migration_ptes.migrate_pages
31347 ? 40% -75.5% 7689 ?112% perf-sched.wait_and_delay.max.ms.rwsem_down_read_slowpath.rmap_walk_anon.remove_migration_ptes.migrate_pages
52076 ? 10% -52.5% 24745 ? 34% perf-sched.wait_and_delay.max.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
52504 ? 9% -57.3% 22437 ? 28% perf-sched.wait_and_delay.max.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
1.82 ?163% +2252.9% 42.73 ?129% perf-sched.wait_time.avg.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
403.64 ? 24% -66.7% 134.46 ? 28% perf-sched.wait_time.avg.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
55.12 ? 14% -42.3% 31.79 ? 14% perf-sched.wait_time.avg.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.02 ?108% +534.1% 0.13 ? 85% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.__alloc_pages.alloc_pages_vma.do_anonymous_page
122.29 ? 16% -45.7% 66.43 ? 16% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
425.82 ? 16% -76.7% 99.10 ? 28% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
465.09 ?223% -100.0% 0.04 ?117% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.change_p4d_range.change_protection.change_prot_numa
9.43 ?125% +219.2% 30.11 ?104% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.generic_perform_write.__generic_file_write_iter.generic_file_write_iter
230.14 ? 17% -64.5% 81.77 ? 28% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
70.21 ? 31% -56.3% 30.65 ? 43% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.mutex_lock.unix_stream_read_generic.unix_stream_recvmsg
1362 ?123% -88.1% 161.89 ? 95% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.rmap_walk_anon.remove_migration_ptes.migrate_pages
0.17 ?118% +1194.7% 2.26 ? 80% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.stop_one_cpu.sched_exec.bprm_execve
154.92 ? 33% -64.9% 54.45 ? 45% perf-sched.wait_time.avg.ms.preempt_schedule_common.__cond_resched.wait_for_completion.affine_move_task.__set_cpus_allowed_ptr_locked
5277 ? 37% -81.9% 953.75 ?103% perf-sched.wait_time.avg.ms.rwsem_down_read_slowpath.rmap_walk_anon.remove_migration_ptes.migrate_pages
390.06 ? 23% -43.2% 221.40 ? 23% perf-sched.wait_time.avg.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
51.14 ? 12% -46.7% 27.27 ? 19% perf-sched.wait_time.avg.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
42.41 ?143% +7008.4% 3014 ?126% perf-sched.wait_time.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
17958 ? 24% -60.2% 7144 ? 33% perf-sched.wait_time.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt.[unknown]
24588 ? 7% -65.6% 8461 ? 28% perf-sched.wait_time.max.ms.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_reschedule_ipi.[unknown]
26488 ? 8% -51.3% 12906 ? 31% perf-sched.wait_time.max.ms.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
20113 ? 16% -45.9% 10885 ? 38% perf-sched.wait_time.max.ms.pipe_read.new_sync_read.vfs_read.ksys_read
25666 ? 9% -57.7% 10860 ? 33% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
19730 ? 11% -59.6% 7972 ? 23% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg
25151 ? 8% -64.3% 8977 ? 31% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg
1860 ?223% -100.0% 0.06 ?105% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.change_p4d_range.change_protection.change_prot_numa
4.30 ?194% -97.7% 0.10 ?116% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.down_write_killable.vm_mmap_pgoff.elf_map
320.22 ?175% +1509.4% 5153 ? 71% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.generic_perform_write.__generic_file_write_iter.generic_file_write_iter
24087 ? 12% -61.8% 9191 ? 42% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
17911 ? 16% -62.7% 6687 ? 29% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.mutex_lock.unix_stream_read_generic.unix_stream_recvmsg
20724 ? 17% -79.9% 4168 ? 82% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.rmap_walk_anon.remove_migration_ptes.migrate_pages
1.20 ?151% +2217.5% 27.84 ? 75% perf-sched.wait_time.max.ms.preempt_schedule_common.__cond_resched.stop_one_cpu.sched_exec.bprm_execve
19696 ? 23% -77.1% 4500 ? 99% perf-sched.wait_time.max.ms.rwsem_down_read_slowpath.rmap_walk_anon.remove_migration_ptes.migrate_pages
26233 ? 10% -51.2% 12801 ? 36% perf-sched.wait_time.max.ms.schedule_timeout.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
26305 ? 9% -56.7% 11393 ? 28% perf-sched.wait_time.max.ms.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
24961 ? 11% -45.5% 13607 ? 28% perf-sched.wait_time.max.ms.smpboot_thread_fn.kthread.ret_from_fork
25452 ? 10% -47.3% 13401 ? 30% perf-sched.wait_time.max.ms.worker_thread.kthread.ret_from_fork
84420 ? 6% -11.5% 74716 ? 8% softirqs.CPU0.RCU
86481 ? 5% -11.8% 76240 ? 9% softirqs.CPU1.RCU
87185 ? 5% -13.1% 75796 ? 9% softirqs.CPU10.RCU
92504 ? 6% -14.8% 78845 ? 7% softirqs.CPU100.RCU
92105 ? 6% -15.2% 78097 ? 7% softirqs.CPU101.RCU
92008 ? 6% -14.9% 78278 ? 7% softirqs.CPU102.RCU
92262 ? 6% -15.3% 78190 ? 6% softirqs.CPU103.RCU
92609 ? 6% -14.8% 78921 ? 7% softirqs.CPU104.RCU
92568 ? 6% -15.0% 78674 ? 7% softirqs.CPU105.RCU
93113 ? 6% -15.2% 78921 ? 7% softirqs.CPU106.RCU
94050 ? 6% -15.6% 79354 ? 8% softirqs.CPU107.RCU
86336 ? 6% -12.2% 75835 ? 7% softirqs.CPU108.RCU
85713 ? 6% -12.9% 74646 ? 9% softirqs.CPU109.RCU
85964 ? 5% -12.0% 75619 ? 9% softirqs.CPU11.RCU
85393 ? 7% -12.6% 74646 ? 9% softirqs.CPU110.RCU
85002 ? 6% -12.3% 74549 ? 8% softirqs.CPU111.RCU
95689 ? 6% -14.9% 81465 ? 10% softirqs.CPU112.RCU
95426 ? 6% -13.5% 82531 ? 8% softirqs.CPU113.RCU
93843 ? 6% -13.2% 81424 ? 9% softirqs.CPU114.RCU
94782 ? 6% -13.7% 81765 ? 8% softirqs.CPU115.RCU
95329 ? 6% -13.2% 82770 ? 9% softirqs.CPU116.RCU
95098 ? 6% -13.3% 82488 ? 9% softirqs.CPU117.RCU
94061 ? 6% -13.4% 81501 ? 8% softirqs.CPU118.RCU
94978 ? 6% -13.7% 81931 ? 9% softirqs.CPU119.RCU
85245 ? 6% -10.5% 76276 ? 9% softirqs.CPU12.RCU
94735 ? 6% -13.3% 82148 ? 9% softirqs.CPU120.RCU
95239 ? 6% -13.3% 82558 ? 9% softirqs.CPU121.RCU
94890 ? 6% -13.5% 82113 ? 9% softirqs.CPU122.RCU
94265 ? 6% -13.5% 81563 ? 8% softirqs.CPU123.RCU
95082 ? 6% -14.6% 81160 ? 10% softirqs.CPU124.RCU
95351 ? 6% -13.6% 82390 ? 9% softirqs.CPU125.RCU
81884 ? 5% -11.7% 72288 ? 8% softirqs.CPU126.RCU
81461 ? 6% -12.1% 71593 ? 8% softirqs.CPU127.RCU
88358 ? 5% -13.9% 76053 ? 9% softirqs.CPU128.RCU
88086 ? 5% -13.4% 76318 ? 8% softirqs.CPU129.RCU
14400 +9.9% 15821 ? 3% softirqs.CPU13.SCHED
88026 ? 5% -13.4% 76206 ? 8% softirqs.CPU130.RCU
88351 ? 5% -13.7% 76205 ? 9% softirqs.CPU131.RCU
87490 ? 5% -13.3% 75876 ? 9% softirqs.CPU132.RCU
87529 ? 5% -13.6% 75668 ? 9% softirqs.CPU133.RCU
87798 ? 5% -12.5% 76813 ? 9% softirqs.CPU134.RCU
88136 ? 5% -13.5% 76276 ? 9% softirqs.CPU135.RCU
88294 ? 5% -13.6% 76251 ? 9% softirqs.CPU136.RCU
87208 ? 5% -13.5% 75465 ? 9% softirqs.CPU137.RCU
87695 ? 5% -13.3% 75994 ? 9% softirqs.CPU138.RCU
88320 ? 5% -13.6% 76309 ? 9% softirqs.CPU139.RCU
86555 ? 6% -12.3% 75887 ? 8% softirqs.CPU14.RCU
14298 +7.8% 15412 ? 4% softirqs.CPU14.SCHED
88184 ? 5% -13.7% 76139 ? 9% softirqs.CPU140.RCU
87603 ? 5% -13.1% 76136 ? 9% softirqs.CPU141.RCU
87625 ? 5% -13.3% 75972 ? 9% softirqs.CPU142.RCU
88256 ? 5% -13.3% 76557 ? 9% softirqs.CPU143.RCU
87050 ? 5% -12.2% 76430 ? 8% softirqs.CPU15.RCU
81130 ? 6% -12.1% 71332 ? 8% softirqs.CPU16.RCU
82146 ? 6% -12.5% 71850 ? 9% softirqs.CPU17.RCU
14082 +10.2% 15524 ? 3% softirqs.CPU17.SCHED
93814 ? 5% -15.8% 79008 ? 7% softirqs.CPU18.RCU
92946 ? 5% -15.5% 78562 ? 7% softirqs.CPU19.RCU
86506 ? 5% -9.5% 78315 ? 6% softirqs.CPU2.RCU
92407 ? 5% -15.2% 78322 ? 7% softirqs.CPU20.RCU
92212 ? 6% -15.7% 77774 ? 7% softirqs.CPU21.RCU
92309 ? 6% -15.1% 78328 ? 7% softirqs.CPU22.RCU
92929 ? 5% -15.4% 78577 ? 7% softirqs.CPU23.RCU
93052 ? 6% -15.7% 78470 ? 7% softirqs.CPU24.RCU
92080 ? 6% -15.3% 77996 ? 7% softirqs.CPU25.RCU
91828 ? 5% -15.3% 77740 ? 7% softirqs.CPU26.RCU
92903 ? 5% -15.6% 78432 ? 7% softirqs.CPU27.RCU
92628 ? 6% -15.3% 78450 ? 7% softirqs.CPU28.RCU
92249 ? 6% -16.2% 77285 ? 8% softirqs.CPU29.RCU
86877 ? 5% -12.0% 76462 ? 8% softirqs.CPU3.RCU
91350 ? 6% -14.7% 77958 ? 8% softirqs.CPU30.RCU
91443 ? 6% -16.0% 76829 ? 5% softirqs.CPU31.RCU
86014 ? 6% -14.2% 73818 ? 8% softirqs.CPU32.RCU
85380 ? 6% -13.7% 73689 ? 8% softirqs.CPU33.RCU
86155 ? 5% -14.3% 73854 ? 8% softirqs.CPU34.RCU
86462 ? 5% -14.1% 74234 ? 8% softirqs.CPU35.RCU
92387 ? 6% -13.1% 80287 ? 9% softirqs.CPU36.RCU
92117 ? 6% -12.9% 80218 ? 8% softirqs.CPU37.RCU
90761 ? 8% -11.9% 79957 ? 9% softirqs.CPU38.RCU
90705 ? 5% -11.5% 80235 ? 9% softirqs.CPU39.RCU
86170 ? 5% -11.2% 76515 ? 7% softirqs.CPU4.RCU
13627 ? 6% +14.0% 15539 ? 3% softirqs.CPU4.SCHED
92368 ? 6% -13.7% 79721 ? 9% softirqs.CPU40.RCU
92055 ? 6% -13.0% 80123 ? 8% softirqs.CPU41.RCU
91447 ? 6% -13.0% 79565 ? 9% softirqs.CPU42.RCU
91880 ? 6% -13.2% 79751 ? 8% softirqs.CPU43.RCU
92254 ? 6% -12.7% 80501 ? 8% softirqs.CPU44.RCU
91783 ? 6% -12.8% 80015 ? 9% softirqs.CPU45.RCU
91421 ? 6% -12.9% 79645 ? 9% softirqs.CPU46.RCU
91390 ? 6% -12.8% 79722 ? 8% softirqs.CPU47.RCU
88932 ? 6% -12.8% 77543 ? 8% softirqs.CPU48.RCU
88850 ? 6% -12.4% 77848 ? 9% softirqs.CPU49.RCU
86897 ? 4% -12.3% 76176 ? 8% softirqs.CPU5.RCU
88709 ? 6% -12.5% 77631 ? 8% softirqs.CPU50.RCU
88614 ? 6% -12.5% 77564 ? 8% softirqs.CPU51.RCU
88876 ? 6% -13.3% 77084 ? 9% softirqs.CPU52.RCU
88779 ? 6% -12.4% 77752 ? 8% softirqs.CPU53.RCU
89712 ? 5% -13.5% 77589 ? 8% softirqs.CPU54.RCU
88569 ? 5% -13.2% 76854 ? 8% softirqs.CPU55.RCU
88777 ? 5% -13.1% 77130 ? 8% softirqs.CPU56.RCU
89211 ? 5% -13.8% 76929 ? 8% softirqs.CPU57.RCU
88989 ? 5% -13.0% 77400 ? 8% softirqs.CPU58.RCU
88940 ? 5% -13.1% 77250 ? 8% softirqs.CPU59.RCU
86373 ? 5% -12.3% 75749 ? 8% softirqs.CPU6.RCU
88320 ? 5% -13.0% 76839 ? 9% softirqs.CPU60.RCU
88405 ? 5% -13.2% 76706 ? 8% softirqs.CPU61.RCU
88722 ? 5% -12.8% 77340 ? 8% softirqs.CPU62.RCU
88541 ? 5% -12.9% 77089 ? 9% softirqs.CPU63.RCU
88636 ? 5% -13.6% 76600 ? 8% softirqs.CPU64.RCU
88387 ? 5% -13.4% 76579 ? 8% softirqs.CPU65.RCU
88139 ? 5% -13.3% 76411 ? 8% softirqs.CPU66.RCU
88420 ? 5% -13.3% 76702 ? 8% softirqs.CPU67.RCU
88484 ? 5% -13.2% 76794 ? 8% softirqs.CPU68.RCU
88366 ? 5% -12.7% 77154 ? 8% softirqs.CPU69.RCU
86334 ? 5% -12.1% 75872 ? 7% softirqs.CPU7.RCU
88438 ? 5% -13.4% 76599 ? 8% softirqs.CPU70.RCU
88125 ? 5% -13.3% 76369 ? 8% softirqs.CPU71.RCU
87488 ? 6% -12.1% 76899 ? 8% softirqs.CPU72.RCU
13664 ? 6% +12.1% 15314 ? 3% softirqs.CPU73.SCHED
87669 ? 6% -11.6% 77534 ? 7% softirqs.CPU74.RCU
87675 ? 5% -11.5% 77573 ? 8% softirqs.CPU75.RCU
87948 ? 5% -12.0% 77402 ? 8% softirqs.CPU76.RCU
88247 ? 5% -12.2% 77474 ? 7% softirqs.CPU77.RCU
87612 ? 5% -11.7% 77372 ? 8% softirqs.CPU78.RCU
87923 ? 6% -12.4% 77023 ? 8% softirqs.CPU79.RCU
86391 ? 5% -11.4% 76543 ? 8% softirqs.CPU8.RCU
88597 ? 6% -12.0% 78003 ? 8% softirqs.CPU80.RCU
89101 ? 6% -12.5% 77968 ? 8% softirqs.CPU81.RCU
14183 ? 2% +8.3% 15363 ? 3% softirqs.CPU81.SCHED
88545 ? 6% -12.4% 77527 ? 7% softirqs.CPU82.RCU
87757 ? 7% -11.5% 77621 ? 8% softirqs.CPU83.RCU
88307 ? 6% -11.5% 78128 ? 8% softirqs.CPU84.RCU
14211 +9.8% 15605 ? 3% softirqs.CPU84.SCHED
89048 ? 6% -13.0% 77482 ? 8% softirqs.CPU85.RCU
89209 ? 5% -12.3% 78258 ? 7% softirqs.CPU86.RCU
88691 ? 5% -12.3% 77825 ? 8% softirqs.CPU87.RCU
88012 ? 5% -11.8% 77588 ? 8% softirqs.CPU88.RCU
88781 ? 5% -11.9% 78190 ? 8% softirqs.CPU89.RCU
86346 ? 6% -10.6% 77225 ? 8% softirqs.CPU9.RCU
90192 ? 5% -14.8% 76846 ? 7% softirqs.CPU90.RCU
89520 ? 6% -14.7% 76378 ? 7% softirqs.CPU91.RCU
89174 ? 5% -14.4% 76374 ? 7% softirqs.CPU92.RCU
88839 ? 6% -14.4% 76030 ? 7% softirqs.CPU93.RCU
89065 ? 5% -14.4% 76238 ? 7% softirqs.CPU94.RCU
89354 ? 6% -14.3% 76619 ? 7% softirqs.CPU95.RCU
92662 ? 6% -14.8% 78959 ? 7% softirqs.CPU96.RCU
91610 ? 6% -14.8% 78044 ? 7% softirqs.CPU97.RCU
92230 ? 6% -15.0% 78392 ? 7% softirqs.CPU98.RCU
92985 ? 6% -14.9% 79138 ? 7% softirqs.CPU99.RCU
12886523 ? 6% -13.3% 11171782 ? 8% softirqs.RCU
112751 ? 3% -10.3% 101130 ? 7% softirqs.TIMER
6866613 ? 7% -20.9% 5431401 ? 9% interrupts.CAL:Function_call_interrupts
1109865 -13.2% 963752 ? 7% interrupts.CPU0.LOC:Local_timer_interrupts
746403 ? 6% -26.6% 547987 ? 6% interrupts.CPU0.RES:Rescheduling_interrupts
1109844 -11.5% 982545 ? 4% interrupts.CPU1.LOC:Local_timer_interrupts
784948 ? 6% -26.8% 574218 ? 6% interrupts.CPU1.RES:Rescheduling_interrupts
1109908 -11.5% 982586 ? 4% interrupts.CPU10.LOC:Local_timer_interrupts
768936 ? 6% -25.0% 576330 ? 7% interrupts.CPU10.RES:Rescheduling_interrupts
1109673 -11.3% 983929 ? 3% interrupts.CPU100.LOC:Local_timer_interrupts
933365 ? 9% -33.5% 620758 ? 11% interrupts.CPU100.RES:Rescheduling_interrupts
1109648 -11.2% 985868 ? 3% interrupts.CPU101.LOC:Local_timer_interrupts
905179 ? 4% -32.6% 610073 ? 8% interrupts.CPU101.RES:Rescheduling_interrupts
55524 ? 32% -37.9% 34488 ? 22% interrupts.CPU102.CAL:Function_call_interrupts
1109644 -11.3% 983935 ? 3% interrupts.CPU102.LOC:Local_timer_interrupts
919161 ? 4% -33.6% 610117 ? 10% interrupts.CPU102.RES:Rescheduling_interrupts
1109645 -11.3% 983934 ? 3% interrupts.CPU103.LOC:Local_timer_interrupts
913475 ? 5% -33.8% 604948 ? 10% interrupts.CPU103.RES:Rescheduling_interrupts
1109644 -11.4% 983504 ? 3% interrupts.CPU104.LOC:Local_timer_interrupts
891411 ? 4% -30.6% 618904 ? 11% interrupts.CPU104.RES:Rescheduling_interrupts
1109685 -11.3% 983840 ? 3% interrupts.CPU105.LOC:Local_timer_interrupts
916161 ? 6% -33.4% 609904 ? 12% interrupts.CPU105.RES:Rescheduling_interrupts
1109651 -11.4% 983590 ? 3% interrupts.CPU106.LOC:Local_timer_interrupts
940033 ? 4% -36.6% 596222 ? 8% interrupts.CPU106.RES:Rescheduling_interrupts
45963 ? 35% -31.8% 31357 ? 20% interrupts.CPU107.CAL:Function_call_interrupts
1109713 -11.3% 983779 ? 3% interrupts.CPU107.LOC:Local_timer_interrupts
934019 ? 10% -35.0% 606683 ? 9% interrupts.CPU107.RES:Rescheduling_interrupts
1109681 -11.2% 985738 ? 3% interrupts.CPU108.LOC:Local_timer_interrupts
907098 ? 10% -26.3% 668850 ? 4% interrupts.CPU108.RES:Rescheduling_interrupts
1109685 -11.2% 985797 ? 3% interrupts.CPU109.LOC:Local_timer_interrupts
926079 ? 10% -27.0% 675677 ? 2% interrupts.CPU109.RES:Rescheduling_interrupts
1109842 -11.5% 982553 ? 3% interrupts.CPU11.LOC:Local_timer_interrupts
777408 ? 7% -24.9% 584102 ? 6% interrupts.CPU11.RES:Rescheduling_interrupts
1109698 -11.2% 985930 ? 3% interrupts.CPU110.LOC:Local_timer_interrupts
927794 ? 6% -26.1% 685774 ? 3% interrupts.CPU110.RES:Rescheduling_interrupts
1109662 -11.1% 986214 ? 3% interrupts.CPU111.LOC:Local_timer_interrupts
910204 ? 4% -26.3% 670493 ? 3% interrupts.CPU111.RES:Rescheduling_interrupts
1109686 -11.3% 984562 ? 3% interrupts.CPU112.LOC:Local_timer_interrupts
956972 ? 6% -29.5% 674228 ? 3% interrupts.CPU112.RES:Rescheduling_interrupts
1109660 -11.1% 986024 ? 3% interrupts.CPU113.LOC:Local_timer_interrupts
911937 ? 6% -25.3% 680865 ? 3% interrupts.CPU113.RES:Rescheduling_interrupts
1109640 -11.1% 986264 ? 3% interrupts.CPU114.LOC:Local_timer_interrupts
945548 ? 10% -27.3% 687639 ? 2% interrupts.CPU114.RES:Rescheduling_interrupts
1109707 -11.1% 986350 ? 3% interrupts.CPU115.LOC:Local_timer_interrupts
965953 ? 5% -28.4% 692092 ? 4% interrupts.CPU115.RES:Rescheduling_interrupts
1109635 -11.1% 985969 ? 3% interrupts.CPU116.LOC:Local_timer_interrupts
961063 ? 9% -30.4% 669281 ? 3% interrupts.CPU116.RES:Rescheduling_interrupts
1109648 -11.1% 986070 ? 3% interrupts.CPU117.LOC:Local_timer_interrupts
953449 ? 5% -29.3% 674189 ? 4% interrupts.CPU117.RES:Rescheduling_interrupts
1109688 -11.1% 986329 ? 3% interrupts.CPU118.LOC:Local_timer_interrupts
909710 ? 9% -22.2% 707837 ? 2% interrupts.CPU118.RES:Rescheduling_interrupts
1109682 -11.1% 986282 ? 3% interrupts.CPU119.LOC:Local_timer_interrupts
951262 ? 7% -27.6% 688722 ? 4% interrupts.CPU119.RES:Rescheduling_interrupts
1109883 -11.5% 982267 ? 4% interrupts.CPU12.LOC:Local_timer_interrupts
787531 ? 3% -27.2% 573213 ? 7% interrupts.CPU12.RES:Rescheduling_interrupts
1109698 -11.1% 986222 ? 3% interrupts.CPU120.LOC:Local_timer_interrupts
943666 ? 5% -28.5% 674336 ? 4% interrupts.CPU120.RES:Rescheduling_interrupts
1109696 -11.1% 986248 ? 3% interrupts.CPU121.LOC:Local_timer_interrupts
912017 ? 7% -24.5% 688310 interrupts.CPU121.RES:Rescheduling_interrupts
1109688 -11.1% 986359 ? 3% interrupts.CPU122.LOC:Local_timer_interrupts
962703 ? 8% -29.7% 676523 ? 2% interrupts.CPU122.RES:Rescheduling_interrupts
1109653 -11.1% 986405 ? 3% interrupts.CPU123.LOC:Local_timer_interrupts
949945 ? 6% -25.6% 706314 ? 4% interrupts.CPU123.RES:Rescheduling_interrupts
1109693 -11.1% 986142 ? 3% interrupts.CPU124.LOC:Local_timer_interrupts
926407 ? 8% -25.0% 695173 ? 3% interrupts.CPU124.RES:Rescheduling_interrupts
1109690 -11.1% 986479 ? 3% interrupts.CPU125.LOC:Local_timer_interrupts
897337 ? 8% -24.5% 677912 ? 4% interrupts.CPU125.RES:Rescheduling_interrupts
1109701 -11.2% 985053 ? 3% interrupts.CPU126.LOC:Local_timer_interrupts
870200 ? 5% -27.7% 629561 ? 12% interrupts.CPU126.RES:Rescheduling_interrupts
1109638 -11.2% 985218 ? 3% interrupts.CPU127.LOC:Local_timer_interrupts
903216 ? 5% -26.2% 667011 ? 11% interrupts.CPU127.RES:Rescheduling_interrupts
1109678 -11.2% 985554 ? 3% interrupts.CPU128.LOC:Local_timer_interrupts
898010 ? 3% -27.7% 649239 ? 10% interrupts.CPU128.RES:Rescheduling_interrupts
1109640 -11.2% 985393 ? 3% interrupts.CPU129.LOC:Local_timer_interrupts
914045 ? 5% -27.6% 661981 ? 13% interrupts.CPU129.RES:Rescheduling_interrupts
1109756 -11.5% 982011 ? 4% interrupts.CPU13.LOC:Local_timer_interrupts
770920 ? 8% -26.9% 563555 ? 7% interrupts.CPU13.RES:Rescheduling_interrupts
1109642 -11.2% 985483 ? 3% interrupts.CPU130.LOC:Local_timer_interrupts
902719 ? 3% -27.4% 655719 ? 12% interrupts.CPU130.RES:Rescheduling_interrupts
1109678 -11.2% 985411 ? 3% interrupts.CPU131.LOC:Local_timer_interrupts
927667 ? 2% -29.9% 650000 ? 12% interrupts.CPU131.RES:Rescheduling_interrupts
1109655 -11.2% 985585 ? 3% interrupts.CPU132.LOC:Local_timer_interrupts
895668 ? 4% -26.7% 656131 ? 9% interrupts.CPU132.RES:Rescheduling_interrupts
1109644 -11.2% 985607 ? 3% interrupts.CPU133.LOC:Local_timer_interrupts
932719 ? 8% -28.6% 665823 ? 11% interrupts.CPU133.RES:Rescheduling_interrupts
1109654 -11.2% 985756 ? 3% interrupts.CPU134.LOC:Local_timer_interrupts
919080 ? 4% -28.9% 653480 ? 10% interrupts.CPU134.RES:Rescheduling_interrupts
1109612 -11.2% 985559 ? 3% interrupts.CPU135.LOC:Local_timer_interrupts
919061 ? 6% -29.3% 649968 ? 10% interrupts.CPU135.RES:Rescheduling_interrupts
1109671 -11.2% 985352 ? 3% interrupts.CPU136.LOC:Local_timer_interrupts
942893 ? 4% -30.7% 653873 ? 10% interrupts.CPU136.RES:Rescheduling_interrupts
1109638 -11.2% 985586 ? 3% interrupts.CPU137.LOC:Local_timer_interrupts
909483 ? 4% -26.2% 671290 ? 12% interrupts.CPU137.RES:Rescheduling_interrupts
1109667 -11.2% 985336 ? 3% interrupts.CPU138.LOC:Local_timer_interrupts
905979 -24.9% 680152 ? 12% interrupts.CPU138.RES:Rescheduling_interrupts
1109666 -11.2% 985457 ? 3% interrupts.CPU139.LOC:Local_timer_interrupts
914012 ? 2% -30.0% 639753 ? 11% interrupts.CPU139.RES:Rescheduling_interrupts
1109769 -11.5% 982477 ? 4% interrupts.CPU14.LOC:Local_timer_interrupts
786901 ? 6% -26.1% 581705 ? 5% interrupts.CPU14.RES:Rescheduling_interrupts
1109661 -11.2% 985582 ? 3% interrupts.CPU140.LOC:Local_timer_interrupts
891457 ? 4% -25.1% 667637 ? 9% interrupts.CPU140.RES:Rescheduling_interrupts
1109567 -11.2% 985643 ? 3% interrupts.CPU141.LOC:Local_timer_interrupts
920671 ? 4% -29.1% 652448 ? 10% interrupts.CPU141.RES:Rescheduling_interrupts
1109583 -11.2% 985732 ? 3% interrupts.CPU142.LOC:Local_timer_interrupts
901948 ? 3% -25.7% 670496 ? 11% interrupts.CPU142.RES:Rescheduling_interrupts
1109693 -11.2% 985489 ? 3% interrupts.CPU143.LOC:Local_timer_interrupts
897848 ? 3% -29.8% 630227 ? 11% interrupts.CPU143.RES:Rescheduling_interrupts
1109764 -11.5% 982288 ? 4% interrupts.CPU15.LOC:Local_timer_interrupts
769032 ? 4% -24.6% 579800 ? 5% interrupts.CPU15.RES:Rescheduling_interrupts
1109749 -11.5% 981954 ? 4% interrupts.CPU16.LOC:Local_timer_interrupts
753284 ? 7% -24.5% 568931 ? 7% interrupts.CPU16.RES:Rescheduling_interrupts
1109740 -11.5% 982067 ? 4% interrupts.CPU17.LOC:Local_timer_interrupts
762912 ? 3% -24.3% 577864 ? 6% interrupts.CPU17.RES:Rescheduling_interrupts
1109715 -11.3% 983766 ? 3% interrupts.CPU18.LOC:Local_timer_interrupts
862584 ? 9% -31.5% 591294 ? 8% interrupts.CPU18.RES:Rescheduling_interrupts
1109709 -11.4% 983571 ? 3% interrupts.CPU19.LOC:Local_timer_interrupts
914512 ? 5% -33.8% 605096 ? 9% interrupts.CPU19.RES:Rescheduling_interrupts
1109849 -11.5% 982602 ? 4% interrupts.CPU2.LOC:Local_timer_interrupts
763288 ? 2% -24.2% 578849 ? 8% interrupts.CPU2.RES:Rescheduling_interrupts
1109697 -11.3% 983869 ? 3% interrupts.CPU20.LOC:Local_timer_interrupts
935470 ? 7% -33.8% 619417 ? 8% interrupts.CPU20.RES:Rescheduling_interrupts
1109689 -11.3% 983811 ? 3% interrupts.CPU21.LOC:Local_timer_interrupts
953999 ? 5% -35.9% 611854 ? 9% interrupts.CPU21.RES:Rescheduling_interrupts
1109713 -11.3% 983859 ? 3% interrupts.CPU22.LOC:Local_timer_interrupts
949063 ? 4% -34.9% 617867 ? 10% interrupts.CPU22.RES:Rescheduling_interrupts
1109677 -11.3% 983782 ? 3% interrupts.CPU23.LOC:Local_timer_interrupts
916942 ? 2% -31.5% 627663 ? 9% interrupts.CPU23.RES:Rescheduling_interrupts
1109676 -11.3% 983778 ? 3% interrupts.CPU24.LOC:Local_timer_interrupts
946944 ? 7% -34.4% 621109 ? 9% interrupts.CPU24.RES:Rescheduling_interrupts
1109671 -11.3% 983788 ? 3% interrupts.CPU25.LOC:Local_timer_interrupts
927026 ? 3% -32.5% 625454 ? 10% interrupts.CPU25.RES:Rescheduling_interrupts
1109686 -11.3% 983799 ? 3% interrupts.CPU26.LOC:Local_timer_interrupts
925930 ? 4% -31.8% 631366 ? 9% interrupts.CPU26.RES:Rescheduling_interrupts
1109675 -11.3% 983850 ? 3% interrupts.CPU27.LOC:Local_timer_interrupts
930402 ? 7% -32.6% 627189 ? 8% interrupts.CPU27.RES:Rescheduling_interrupts
1109729 -11.4% 983703 ? 3% interrupts.CPU28.LOC:Local_timer_interrupts
928439 ? 4% -32.0% 630948 ? 7% interrupts.CPU28.RES:Rescheduling_interrupts
1109731 -11.9% 977654 ? 4% interrupts.CPU29.LOC:Local_timer_interrupts
917894 ? 3% -31.6% 627431 ? 7% interrupts.CPU29.RES:Rescheduling_interrupts
1109813 -11.5% 982425 ? 4% interrupts.CPU3.LOC:Local_timer_interrupts
763728 ? 4% -25.8% 566752 ? 7% interrupts.CPU3.RES:Rescheduling_interrupts
1109702 -11.4% 983710 ? 3% interrupts.CPU30.LOC:Local_timer_interrupts
959814 ? 6% -34.4% 630064 ? 11% interrupts.CPU30.RES:Rescheduling_interrupts
1109691 -11.3% 983822 ? 3% interrupts.CPU31.LOC:Local_timer_interrupts
953721 ? 7% -34.2% 627837 ? 12% interrupts.CPU31.RES:Rescheduling_interrupts
1109716 -11.4% 983559 ? 3% interrupts.CPU32.LOC:Local_timer_interrupts
929251 ? 5% -32.4% 628141 ? 10% interrupts.CPU32.RES:Rescheduling_interrupts
1109720 -11.4% 983527 ? 3% interrupts.CPU33.LOC:Local_timer_interrupts
955082 ? 8% -34.0% 629974 ? 9% interrupts.CPU33.RES:Rescheduling_interrupts
1109706 -11.4% 983432 ? 3% interrupts.CPU34.LOC:Local_timer_interrupts
933432 ? 6% -33.6% 619604 ? 9% interrupts.CPU34.RES:Rescheduling_interrupts
1109724 -11.4% 983426 ? 3% interrupts.CPU35.LOC:Local_timer_interrupts
904660 ? 3% -31.4% 620967 ? 9% interrupts.CPU35.RES:Rescheduling_interrupts
1109716 -11.1% 986109 ? 3% interrupts.CPU36.LOC:Local_timer_interrupts
908916 ? 7% -25.5% 677428 ? 2% interrupts.CPU36.RES:Rescheduling_interrupts
1109635 -11.1% 986076 ? 3% interrupts.CPU37.LOC:Local_timer_interrupts
926313 ? 8% -24.1% 702863 ? 3% interrupts.CPU37.RES:Rescheduling_interrupts
1109685 -11.1% 986009 ? 3% interrupts.CPU38.LOC:Local_timer_interrupts
951056 ? 6% -27.3% 691529 ? 4% interrupts.CPU38.RES:Rescheduling_interrupts
1109743 -11.1% 986389 ? 3% interrupts.CPU39.LOC:Local_timer_interrupts
927813 ? 7% -24.0% 705228 ? 4% interrupts.CPU39.RES:Rescheduling_interrupts
1109737 -11.5% 982501 ? 3% interrupts.CPU4.LOC:Local_timer_interrupts
766534 ? 8% -24.7% 577507 ? 6% interrupts.CPU4.RES:Rescheduling_interrupts
1109783 -11.1% 986790 ? 3% interrupts.CPU40.LOC:Local_timer_interrupts
929300 ? 3% -24.5% 702028 ? 3% interrupts.CPU40.RES:Rescheduling_interrupts
1109714 -11.2% 985893 ? 3% interrupts.CPU41.LOC:Local_timer_interrupts
952762 ? 9% -26.6% 698904 ? 3% interrupts.CPU41.RES:Rescheduling_interrupts
1109708 -11.1% 986368 ? 3% interrupts.CPU42.LOC:Local_timer_interrupts
961704 ? 6% -26.4% 707713 ? 3% interrupts.CPU42.RES:Rescheduling_interrupts
1109757 -11.1% 986228 ? 3% interrupts.CPU43.LOC:Local_timer_interrupts
952246 ? 6% -26.2% 702405 ? 2% interrupts.CPU43.RES:Rescheduling_interrupts
1109751 -11.1% 986140 ? 3% interrupts.CPU44.LOC:Local_timer_interrupts
980627 ? 2% -29.8% 688585 ? 4% interrupts.CPU44.RES:Rescheduling_interrupts
1109689 -11.1% 985981 ? 3% interrupts.CPU45.LOC:Local_timer_interrupts
976440 ? 3% -29.2% 691802 ? 3% interrupts.CPU45.RES:Rescheduling_interrupts
1109645 -11.1% 986013 ? 3% interrupts.CPU46.LOC:Local_timer_interrupts
952352 ? 2% -26.7% 697811 ? 4% interrupts.CPU46.RES:Rescheduling_interrupts
1109682 -11.1% 986172 ? 3% interrupts.CPU47.LOC:Local_timer_interrupts
957266 ? 4% -28.5% 684262 interrupts.CPU47.RES:Rescheduling_interrupts
49803 ? 13% -18.0% 40844 ? 12% interrupts.CPU48.CAL:Function_call_interrupts
1109702 -11.1% 986471 ? 3% interrupts.CPU48.LOC:Local_timer_interrupts
977427 ? 6% -27.8% 705625 ? 3% interrupts.CPU48.RES:Rescheduling_interrupts
1109658 -11.1% 986172 ? 3% interrupts.CPU49.LOC:Local_timer_interrupts
937091 ? 7% -26.2% 691409 ? 3% interrupts.CPU49.RES:Rescheduling_interrupts
1109735 -11.5% 982317 ? 4% interrupts.CPU5.LOC:Local_timer_interrupts
741049 ? 6% -23.6% 566103 ? 6% interrupts.CPU5.RES:Rescheduling_interrupts
1109692 -11.1% 986149 ? 3% interrupts.CPU50.LOC:Local_timer_interrupts
942242 ? 7% -26.2% 695845 ? 3% interrupts.CPU50.RES:Rescheduling_interrupts
1109688 -11.1% 986153 ? 3% interrupts.CPU51.LOC:Local_timer_interrupts
978237 ? 5% -27.8% 706561 ? 2% interrupts.CPU51.RES:Rescheduling_interrupts
1109680 -11.1% 986101 ? 3% interrupts.CPU52.LOC:Local_timer_interrupts
942523 ? 6% -25.9% 698844 ? 2% interrupts.CPU52.RES:Rescheduling_interrupts
1109709 -11.1% 986142 ? 3% interrupts.CPU53.LOC:Local_timer_interrupts
968770 ? 8% -28.5% 692330 ? 4% interrupts.CPU53.RES:Rescheduling_interrupts
1109706 -11.2% 985372 ? 3% interrupts.CPU54.LOC:Local_timer_interrupts
892744 ? 3% -27.4% 648201 ? 10% interrupts.CPU54.RES:Rescheduling_interrupts
1109711 -11.2% 985410 ? 3% interrupts.CPU55.LOC:Local_timer_interrupts
905314 ? 4% -26.4% 666564 ? 10% interrupts.CPU55.RES:Rescheduling_interrupts
1109760 -11.2% 985583 ? 3% interrupts.CPU56.LOC:Local_timer_interrupts
923287 ? 5% -27.0% 673797 ? 10% interrupts.CPU56.RES:Rescheduling_interrupts
1109750 -11.2% 985363 ? 3% interrupts.CPU57.LOC:Local_timer_interrupts
941749 ? 6% -27.9% 678794 ? 9% interrupts.CPU57.RES:Rescheduling_interrupts
1109711 -11.2% 985560 ? 3% interrupts.CPU58.LOC:Local_timer_interrupts
911298 ? 3% -27.4% 661172 ? 10% interrupts.CPU58.RES:Rescheduling_interrupts
1109694 -11.2% 985480 ? 3% interrupts.CPU59.LOC:Local_timer_interrupts
934580 ? 3% -29.9% 654916 ? 9% interrupts.CPU59.RES:Rescheduling_interrupts
1109735 -11.5% 982399 ? 4% interrupts.CPU6.LOC:Local_timer_interrupts
740135 ? 6% -24.3% 560193 ? 5% interrupts.CPU6.RES:Rescheduling_interrupts
1109690 -11.2% 985677 ? 3% interrupts.CPU60.LOC:Local_timer_interrupts
927684 ? 3% -28.1% 667287 ? 11% interrupts.CPU60.RES:Rescheduling_interrupts
1109694 -11.2% 985524 ? 3% interrupts.CPU61.LOC:Local_timer_interrupts
958054 ? 4% -30.3% 667940 ? 11% interrupts.CPU61.RES:Rescheduling_interrupts
1109679 -11.2% 985364 ? 3% interrupts.CPU62.LOC:Local_timer_interrupts
946262 ? 4% -30.0% 662460 ? 11% interrupts.CPU62.RES:Rescheduling_interrupts
1109678 -11.2% 985301 ? 3% interrupts.CPU63.LOC:Local_timer_interrupts
931012 ? 4% -26.6% 683774 ? 11% interrupts.CPU63.RES:Rescheduling_interrupts
1109691 -11.2% 985194 ? 3% interrupts.CPU64.LOC:Local_timer_interrupts
929091 ? 6% -29.7% 653309 ? 11% interrupts.CPU64.RES:Rescheduling_interrupts
1109744 -11.2% 985320 ? 3% interrupts.CPU65.LOC:Local_timer_interrupts
933881 ? 3% -27.6% 676297 ? 9% interrupts.CPU65.RES:Rescheduling_interrupts
1109710 -11.2% 985673 ? 3% interrupts.CPU66.LOC:Local_timer_interrupts
956361 ? 5% -29.2% 676634 ? 9% interrupts.CPU66.RES:Rescheduling_interrupts
1109687 -11.2% 985315 ? 3% interrupts.CPU67.LOC:Local_timer_interrupts
909257 ? 3% -26.6% 667439 ? 12% interrupts.CPU67.RES:Rescheduling_interrupts
1109693 -11.2% 985287 ? 3% interrupts.CPU68.LOC:Local_timer_interrupts
925288 ? 2% -28.0% 665809 ? 9% interrupts.CPU68.RES:Rescheduling_interrupts
1109675 -11.2% 985486 ? 3% interrupts.CPU69.LOC:Local_timer_interrupts
958528 ? 4% -29.0% 680393 ? 9% interrupts.CPU69.RES:Rescheduling_interrupts
31192 ? 5% -17.8% 25645 ? 15% interrupts.CPU7.CAL:Function_call_interrupts
1109763 -11.4% 982851 ? 3% interrupts.CPU7.LOC:Local_timer_interrupts
766751 ? 7% -25.8% 569219 ? 4% interrupts.CPU7.RES:Rescheduling_interrupts
1109572 -11.2% 985353 ? 3% interrupts.CPU70.LOC:Local_timer_interrupts
934309 ? 2% -28.6% 666929 ? 11% interrupts.CPU70.RES:Rescheduling_interrupts
1109770 -11.2% 985376 ? 3% interrupts.CPU71.LOC:Local_timer_interrupts
923580 ? 5% -26.7% 676802 ? 9% interrupts.CPU71.RES:Rescheduling_interrupts
48586 ? 18% -31.1% 33495 ? 20% interrupts.CPU72.CAL:Function_call_interrupts
1109690 -11.4% 983437 ? 3% interrupts.CPU72.LOC:Local_timer_interrupts
732823 ? 6% -25.1% 548780 ? 6% interrupts.CPU72.RES:Rescheduling_interrupts
1109780 -11.5% 982255 ? 4% interrupts.CPU73.LOC:Local_timer_interrupts
748198 ? 6% -25.7% 555808 ? 2% interrupts.CPU73.RES:Rescheduling_interrupts
1109731 -11.5% 982361 ? 4% interrupts.CPU74.LOC:Local_timer_interrupts
732000 ? 5% -24.4% 553248 ? 8% interrupts.CPU74.RES:Rescheduling_interrupts
1109689 -11.5% 982406 ? 4% interrupts.CPU75.LOC:Local_timer_interrupts
732437 ? 4% -23.9% 557346 ? 5% interrupts.CPU75.RES:Rescheduling_interrupts
1109783 -11.5% 982253 ? 4% interrupts.CPU76.LOC:Local_timer_interrupts
727115 -22.8% 561035 ? 6% interrupts.CPU76.RES:Rescheduling_interrupts
1109749 -11.5% 981909 ? 4% interrupts.CPU77.LOC:Local_timer_interrupts
722320 ? 5% -23.9% 549545 ? 7% interrupts.CPU77.RES:Rescheduling_interrupts
1109776 -11.5% 982201 ? 4% interrupts.CPU78.LOC:Local_timer_interrupts
774003 ? 8% -27.3% 562990 ? 5% interrupts.CPU78.RES:Rescheduling_interrupts
1109771 -11.5% 982534 ? 3% interrupts.CPU79.LOC:Local_timer_interrupts
725034 ? 4% -21.5% 569192 ? 5% interrupts.CPU79.RES:Rescheduling_interrupts
1109745 -11.5% 982390 ? 4% interrupts.CPU8.LOC:Local_timer_interrupts
766391 ? 6% -26.4% 564224 ? 5% interrupts.CPU8.RES:Rescheduling_interrupts
1109765 -11.5% 982241 ? 4% interrupts.CPU80.LOC:Local_timer_interrupts
747959 ? 5% -24.2% 566670 ? 8% interrupts.CPU80.RES:Rescheduling_interrupts
1109814 -11.5% 981873 ? 4% interrupts.CPU81.LOC:Local_timer_interrupts
747605 ? 7% -24.3% 565728 ? 7% interrupts.CPU81.RES:Rescheduling_interrupts
1109714 -11.5% 982405 ? 4% interrupts.CPU82.LOC:Local_timer_interrupts
740632 ? 4% -25.4% 552433 ? 7% interrupts.CPU82.RES:Rescheduling_interrupts
1109762 -11.5% 982189 ? 4% interrupts.CPU83.LOC:Local_timer_interrupts
752433 ? 6% -23.9% 572430 ? 6% interrupts.CPU83.RES:Rescheduling_interrupts
1109801 -11.5% 982438 ? 4% interrupts.CPU84.LOC:Local_timer_interrupts
750543 ? 6% -25.7% 557447 ? 7% interrupts.CPU84.RES:Rescheduling_interrupts
1109757 -11.5% 982181 ? 4% interrupts.CPU85.LOC:Local_timer_interrupts
710008 ? 5% -20.3% 565565 ? 7% interrupts.CPU85.RES:Rescheduling_interrupts
1109819 -11.5% 982651 ? 3% interrupts.CPU86.LOC:Local_timer_interrupts
756402 ? 4% -26.1% 559174 ? 6% interrupts.CPU86.RES:Rescheduling_interrupts
1109763 -11.5% 982634 ? 3% interrupts.CPU87.LOC:Local_timer_interrupts
763567 ? 5% -27.5% 553678 ? 5% interrupts.CPU87.RES:Rescheduling_interrupts
1109795 -11.4% 982983 ? 3% interrupts.CPU88.LOC:Local_timer_interrupts
736222 ? 4% -24.9% 552717 ? 6% interrupts.CPU88.RES:Rescheduling_interrupts
1109788 -11.4% 982800 ? 3% interrupts.CPU89.LOC:Local_timer_interrupts
729712 ? 5% -24.6% 550308 ? 6% interrupts.CPU89.RES:Rescheduling_interrupts
1109951 -11.5% 982025 ? 4% interrupts.CPU9.LOC:Local_timer_interrupts
749632 ? 7% -25.7% 556858 ? 7% interrupts.CPU9.RES:Rescheduling_interrupts
1109721 -11.4% 983595 ? 3% interrupts.CPU90.LOC:Local_timer_interrupts
889032 ? 8% -34.4% 582776 ? 9% interrupts.CPU90.RES:Rescheduling_interrupts
1109668 -11.4% 983263 ? 3% interrupts.CPU91.LOC:Local_timer_interrupts
914855 ? 5% -35.1% 593653 ? 8% interrupts.CPU91.RES:Rescheduling_interrupts
1109647 -11.3% 983819 ? 3% interrupts.CPU92.LOC:Local_timer_interrupts
948214 ? 8% -35.0% 616661 ? 10% interrupts.CPU92.RES:Rescheduling_interrupts
1109694 -11.4% 983708 ? 3% interrupts.CPU93.LOC:Local_timer_interrupts
892302 ? 7% -32.9% 598886 ? 9% interrupts.CPU93.RES:Rescheduling_interrupts
1109699 -11.4% 983475 ? 3% interrupts.CPU94.LOC:Local_timer_interrupts
913830 ? 4% -33.8% 605237 ? 10% interrupts.CPU94.RES:Rescheduling_interrupts
1109687 -11.4% 983654 ? 3% interrupts.CPU95.LOC:Local_timer_interrupts
942816 ? 8% -35.3% 610115 ? 9% interrupts.CPU95.RES:Rescheduling_interrupts
1109662 -11.3% 983930 ? 3% interrupts.CPU96.LOC:Local_timer_interrupts
921056 ? 7% -33.8% 609373 ? 10% interrupts.CPU96.RES:Rescheduling_interrupts
1109663 -11.3% 983971 ? 3% interrupts.CPU97.LOC:Local_timer_interrupts
939132 ? 5% -35.0% 610299 ? 10% interrupts.CPU97.RES:Rescheduling_interrupts
1109659 -11.3% 983854 ? 3% interrupts.CPU98.LOC:Local_timer_interrupts
905810 ? 6% -32.7% 609848 ? 9% interrupts.CPU98.RES:Rescheduling_interrupts
1109697 -11.3% 983762 ? 3% interrupts.CPU99.LOC:Local_timer_interrupts
936646 ? 7% -34.8% 610801 ? 10% interrupts.CPU99.RES:Rescheduling_interrupts
1.598e+08 -11.3% 1.417e+08 ? 3% interrupts.LOC:Local_timer_interrupts
1.274e+08 ? 2% -28.5% 91108791 interrupts.RES:Rescheduling_interrupts
21.07 ? 13% -14.9 6.16 ? 35% perf-profile.calltrace.cycles-pp.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event
20.01 ? 13% -14.3 5.71 ? 38% perf-profile.calltrace.cycles-pp.perf_callchain.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow
19.91 ? 13% -14.2 5.68 ? 38% perf-profile.calltrace.cycles-pp.get_perf_callchain.perf_callchain.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow
11.18 ? 11% -11.2 0.00 perf-profile.calltrace.cycles-pp.page_counter_try_charge.obj_cgroup_charge_pages.obj_cgroup_charge.__kmalloc_node_track_caller.kmalloc_reserve
17.91 ? 12% -11.0 6.86 ? 22% perf-profile.calltrace.cycles-pp.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg.sock_sendmsg.sock_write_iter
17.29 ? 12% -10.9 6.42 ? 23% perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg.sock_sendmsg
17.15 ? 12% -10.8 6.31 ? 23% perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sock_def_readable.unix_stream_sendmsg
17.06 ? 12% -10.8 6.26 ? 23% perf-profile.calltrace.cycles-pp.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sock_def_readable
18.74 ? 11% -10.4 8.30 ? 17% perf-profile.calltrace.cycles-pp.sock_def_readable.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write
12.96 ? 13% -9.5 3.45 ? 49% perf-profile.calltrace.cycles-pp.perf_callchain_kernel.get_perf_callchain.perf_callchain.perf_prepare_sample.perf_event_output_forward
15.35 ? 11% -9.5 5.88 ? 22% perf-profile.calltrace.cycles-pp.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
15.28 ? 11% -9.4 5.84 ? 22% perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
15.16 ? 11% -9.4 5.77 ? 23% perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.unix_stream_read_generic.unix_stream_recvmsg
10.21 ? 12% -7.0 3.21 ? 32% perf-profile.calltrace.cycles-pp.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime.update_curr
10.16 ? 12% -7.0 3.19 ? 32% perf-profile.calltrace.cycles-pp.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime
5.82 ? 26% -5.8 0.00 perf-profile.calltrace.cycles-pp.asm_exc_page_fault.__get_user_nocheck_8.perf_callchain_user.get_perf_callchain.perf_callchain
5.63 ? 11% -5.6 0.00 perf-profile.calltrace.cycles-pp.page_counter_try_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb
6.42 ? 13% -5.6 0.81 ?114% perf-profile.calltrace.cycles-pp.perf_callchain_user.get_perf_callchain.perf_callchain.perf_prepare_sample.perf_event_output_forward
6.28 ? 14% -4.8 1.48 ? 46% perf-profile.calltrace.cycles-pp.perf_swevent_overflow.perf_tp_event.perf_trace_sched_switch.__schedule.schedule
6.27 ? 14% -4.8 1.47 ? 46% perf-profile.calltrace.cycles-pp.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_switch.__schedule
5.06 ? 17% -4.8 0.28 ?223% perf-profile.calltrace.cycles-pp.__unwind_start.perf_callchain_kernel.get_perf_callchain.perf_callchain.perf_prepare_sample
6.24 ? 14% -4.8 1.46 ? 46% perf-profile.calltrace.cycles-pp.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_switch
6.92 ? 13% -4.5 2.40 ? 24% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock
4.80 ? 13% -4.5 0.31 ?223% perf-profile.calltrace.cycles-pp.unwind_next_frame.perf_callchain_kernel.get_perf_callchain.perf_callchain.perf_prepare_sample
6.87 ? 13% -4.5 2.38 ? 24% perf-profile.calltrace.cycles-pp.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common
52.74 -4.5 48.28 perf-profile.calltrace.cycles-pp.__libc_write
52.06 -4.3 47.73 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__libc_write
6.76 ? 11% -4.3 2.44 ? 26% perf-profile.calltrace.cycles-pp.dequeue_task_fair.__schedule.schedule.schedule_timeout.unix_stream_read_generic
51.93 -4.3 47.62 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write
6.17 ? 13% -4.1 2.04 ? 27% perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.autoremove_wake_function
6.08 ? 11% -4.0 2.11 ? 28% perf-profile.calltrace.cycles-pp.dequeue_entity.dequeue_task_fair.__schedule.schedule.schedule_timeout
5.56 ? 13% -3.8 1.73 ? 30% perf-profile.calltrace.cycles-pp.update_curr.enqueue_entity.enqueue_task_fair.ttwu_do_activate.try_to_wake_up
5.78 ? 11% -3.8 1.95 ? 30% perf-profile.calltrace.cycles-pp.update_curr.dequeue_entity.dequeue_task_fair.__schedule.schedule
5.51 ? 11% -3.7 1.83 ? 31% perf-profile.calltrace.cycles-pp.perf_trace_sched_stat_runtime.update_curr.dequeue_entity.dequeue_task_fair.__schedule
5.25 ? 13% -3.7 1.59 ? 32% perf-profile.calltrace.cycles-pp.perf_trace_sched_stat_runtime.update_curr.enqueue_entity.enqueue_task_fair.ttwu_do_activate
5.45 ? 12% -3.6 1.83 ? 30% perf-profile.calltrace.cycles-pp.perf_trace_sched_wakeup_template.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock
5.36 ? 11% -3.6 1.77 ? 32% perf-profile.calltrace.cycles-pp.perf_tp_event.perf_trace_sched_stat_runtime.update_curr.dequeue_entity.dequeue_task_fair
5.08 ? 13% -3.6 1.52 ? 33% perf-profile.calltrace.cycles-pp.perf_tp_event.perf_trace_sched_stat_runtime.update_curr.enqueue_entity.enqueue_task_fair
5.31 ? 12% -3.6 1.76 ? 31% perf-profile.calltrace.cycles-pp.perf_tp_event.perf_trace_sched_wakeup_template.try_to_wake_up.autoremove_wake_function.__wake_up_common
5.25 ? 11% -3.5 1.73 ? 31% perf-profile.calltrace.cycles-pp.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime.update_curr.dequeue_entity
4.98 ? 13% -3.5 1.49 ? 33% perf-profile.calltrace.cycles-pp.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime.update_curr.enqueue_entity
5.10 ? 12% -3.4 1.68 ? 31% perf-profile.calltrace.cycles-pp.perf_swevent_overflow.perf_tp_event.perf_trace_sched_wakeup_template.try_to_wake_up.autoremove_wake_function
5.09 ? 12% -3.4 1.67 ? 31% perf-profile.calltrace.cycles-pp.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_wakeup_template.try_to_wake_up
5.07 ? 12% -3.4 1.66 ? 32% perf-profile.calltrace.cycles-pp.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_wakeup_template
4.63 ? 13% -3.2 1.45 ? 33% perf-profile.calltrace.cycles-pp.perf_trace_sched_switch.__schedule.schedule.schedule_timeout.unix_stream_read_generic
4.45 ? 13% -3.1 1.38 ? 33% perf-profile.calltrace.cycles-pp.perf_tp_event.perf_trace_sched_switch.__schedule.schedule.schedule_timeout
4.07 ? 12% -2.9 1.15 ? 27% perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write
4.01 ? 12% -2.9 1.11 ? 28% perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write
3.78 ? 12% -2.8 0.99 ? 30% perf-profile.calltrace.cycles-pp.schedule.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe
3.74 ? 12% -2.8 0.98 ? 30% perf-profile.calltrace.cycles-pp.__schedule.schedule.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
2.40 ? 12% -1.5 0.90 ? 18% perf-profile.calltrace.cycles-pp._raw_spin_lock.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock
2.09 ? 13% -1.4 0.66 ? 46% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.try_to_wake_up.autoremove_wake_function.__wake_up_common
47.70 -1.3 46.38 perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write
47.45 -1.3 46.14 perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write
46.94 -1.3 45.63 perf-profile.calltrace.cycles-pp.new_sync_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
46.52 -1.2 45.29 perf-profile.calltrace.cycles-pp.sock_write_iter.new_sync_write.vfs_write.ksys_write.do_syscall_64
46.20 -1.1 45.08 perf-profile.calltrace.cycles-pp.sock_sendmsg.sock_write_iter.new_sync_write.vfs_write.ksys_write
45.87 -1.1 44.76 perf-profile.calltrace.cycles-pp.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write.vfs_write
1.33 ? 3% -0.6 0.78 ? 6% perf-profile.calltrace.cycles-pp.switch_mm_irqs_off.__schedule.schedule.schedule_timeout.unix_stream_read_generic
0.62 ? 2% +0.2 0.78 perf-profile.calltrace.cycles-pp.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor
0.65 ? 2% +0.2 0.81 perf-profile.calltrace.cycles-pp.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic
0.75 ? 2% +0.2 0.92 ? 4% perf-profile.calltrace.cycles-pp.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write
0.62 ? 3% +0.3 0.90 ? 3% perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter
0.65 ? 2% +0.3 0.94 ? 3% perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor
0.81 ? 2% +0.3 1.12 ? 3% perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic
0.58 ? 7% +0.4 0.96 ? 4% perf-profile.calltrace.cycles-pp.__slab_free.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg
0.18 ?141% +0.4 0.57 ? 6% perf-profile.calltrace.cycles-pp.mod_objcg_state.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
1.06 ? 6% +0.4 1.47 ? 5% perf-profile.calltrace.cycles-pp._raw_spin_lock.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
0.73 ? 7% +0.4 1.18 ? 7% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.skb_queue_tail.unix_stream_sendmsg.sock_sendmsg.sock_write_iter
0.75 ? 7% +0.4 1.20 ? 7% perf-profile.calltrace.cycles-pp.skb_queue_tail.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write
0.60 ? 12% +0.5 1.06 ? 8% perf-profile.calltrace.cycles-pp.skb_unlink.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
0.36 ? 71% +0.5 0.83 ? 9% perf-profile.calltrace.cycles-pp.get_mem_cgroup_from_objcg.obj_cgroup_charge_pages.obj_cgroup_charge.__kmalloc_node_track_caller.kmalloc_reserve
1.52 ? 2% +0.5 1.99 ? 2% perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
1.50 ? 2% +0.5 1.97 ? 2% perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg
0.37 ? 71% +0.5 0.84 ? 8% perf-profile.calltrace.cycles-pp.get_mem_cgroup_from_objcg.obj_cgroup_uncharge_pages.kfree.skb_release_data.consume_skb
1.53 +0.5 2.01 ? 2% perf-profile.calltrace.cycles-pp.unix_stream_read_actor.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
0.09 ?223% +0.5 0.58 ? 6% perf-profile.calltrace.cycles-pp.mod_objcg_state.kfree.skb_release_data.consume_skb.unix_stream_read_generic
0.65 ? 5% +0.5 1.15 ? 6% perf-profile.calltrace.cycles-pp.skb_set_owner_w.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg.sock_write_iter
0.08 ?223% +0.5 0.59 ? 5% perf-profile.calltrace.cycles-pp.mutex_lock.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
0.41 ? 71% +0.6 1.00 ? 7% perf-profile.calltrace.cycles-pp.mutex_unlock.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
0.41 ? 71% +0.6 1.02 ? 8% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.skb_unlink.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
0.00 +0.7 0.67 ? 4% perf-profile.calltrace.cycles-pp.unix_write_space.sock_wfree.unix_destruct_scm.skb_release_head_state.skb_release_all
1.12 ? 7% +0.7 1.81 ? 5% perf-profile.calltrace.cycles-pp._raw_spin_lock.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write
0.88 ? 10% +0.7 1.57 ? 5% perf-profile.calltrace.cycles-pp.__slab_free.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
0.96 ? 13% +0.7 1.69 ? 7% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_uncharge.obj_cgroup_uncharge_pages.kmem_cache_free.unix_stream_read_generic
1.16 ? 9% +0.8 1.99 ? 4% perf-profile.calltrace.cycles-pp.sock_wfree.unix_destruct_scm.skb_release_head_state.skb_release_all.consume_skb
1.20 ? 8% +0.8 2.03 ? 4% perf-profile.calltrace.cycles-pp.unix_destruct_scm.skb_release_head_state.skb_release_all.consume_skb.unix_stream_read_generic
1.22 ? 8% +0.8 2.06 ? 4% perf-profile.calltrace.cycles-pp.skb_release_head_state.skb_release_all.consume_skb.unix_stream_read_generic.unix_stream_recvmsg
1.23 ? 8% +0.8 2.07 ? 4% perf-profile.calltrace.cycles-pp.skb_release_all.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
1.97 ? 12% +1.4 3.41 ? 7% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_uncharge.obj_cgroup_uncharge_pages.kfree.skb_release_data
0.00 +1.7 1.72 ? 7% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node
3.75 ? 12% +1.8 5.55 ? 6% perf-profile.calltrace.cycles-pp.page_counter_cancel.page_counter_uncharge.obj_cgroup_uncharge_pages.kmem_cache_free.unix_stream_read_generic
6.27 ? 10% +2.2 8.45 ? 5% perf-profile.calltrace.cycles-pp.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags
6.32 ? 10% +2.2 8.50 ? 5% perf-profile.calltrace.cycles-pp.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
7.85 ? 8% +2.4 10.30 ? 4% perf-profile.calltrace.cycles-pp.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg
4.76 ? 12% +2.6 7.32 ? 5% perf-profile.calltrace.cycles-pp.page_counter_uncharge.obj_cgroup_uncharge_pages.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg
5.38 ? 11% +3.0 8.34 ? 5% perf-profile.calltrace.cycles-pp.obj_cgroup_uncharge_pages.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
7.80 ? 11% +3.3 11.14 ? 5% perf-profile.calltrace.cycles-pp.page_counter_cancel.page_counter_uncharge.obj_cgroup_uncharge_pages.kfree.skb_release_data
0.00 +3.4 3.40 ? 6% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_charge.obj_cgroup_charge_pages.obj_cgroup_charge.__kmalloc_node_track_caller
46.87 +3.5 50.41 perf-profile.calltrace.cycles-pp.__libc_read
45.87 +3.7 49.56 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__libc_read
45.74 +3.7 49.46 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read
44.83 +3.9 48.69 perf-profile.calltrace.cycles-pp.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read
45.02 +3.9 48.89 perf-profile.calltrace.cycles-pp.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read
43.59 +3.9 47.47 perf-profile.calltrace.cycles-pp.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read.vfs_read
43.68 +3.9 47.56 perf-profile.calltrace.cycles-pp.unix_stream_recvmsg.sock_read_iter.new_sync_read.vfs_read.ksys_read
44.11 +3.9 48.00 perf-profile.calltrace.cycles-pp.sock_read_iter.new_sync_read.vfs_read.ksys_read.do_syscall_64
44.32 +3.9 48.22 perf-profile.calltrace.cycles-pp.new_sync_read.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe
7.54 ? 9% +4.1 11.64 ? 4% perf-profile.calltrace.cycles-pp.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
12.45 ? 10% +4.3 16.71 ? 5% perf-profile.calltrace.cycles-pp.obj_cgroup_charge_pages.obj_cgroup_charge.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
12.50 ? 10% +4.3 16.77 ? 5% perf-profile.calltrace.cycles-pp.obj_cgroup_charge.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags
14.17 ? 9% +4.5 18.70 ? 4% perf-profile.calltrace.cycles-pp.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
14.23 ? 9% +4.5 18.75 ? 4% perf-profile.calltrace.cycles-pp.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg
9.88 ? 11% +4.8 14.72 ? 5% perf-profile.calltrace.cycles-pp.page_counter_uncharge.obj_cgroup_uncharge_pages.kfree.skb_release_data.consume_skb
11.16 ? 11% +5.6 16.78 ? 4% perf-profile.calltrace.cycles-pp.obj_cgroup_uncharge_pages.kfree.skb_release_data.consume_skb.unix_stream_read_generic
12.06 ? 9% +5.9 17.92 ? 4% perf-profile.calltrace.cycles-pp.kfree.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg
13.11 ? 9% +6.5 19.61 ? 4% perf-profile.calltrace.cycles-pp.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter
22.76 ? 8% +7.1 29.89 ? 4% perf-profile.calltrace.cycles-pp.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg.sock_write_iter
22.70 ? 8% +7.1 29.82 ? 4% perf-profile.calltrace.cycles-pp.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg
0.00 +7.4 7.38 ? 6% perf-profile.calltrace.cycles-pp.page_counter_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb
14.56 ? 9% +7.5 22.04 ? 4% perf-profile.calltrace.cycles-pp.consume_skb.unix_stream_read_generic.unix_stream_recvmsg.sock_read_iter.new_sync_read
23.80 ? 8% +7.9 31.75 ? 4% perf-profile.calltrace.cycles-pp.sock_alloc_send_pskb.unix_stream_sendmsg.sock_sendmsg.sock_write_iter.new_sync_write
0.00 +14.6 14.60 ? 5% perf-profile.calltrace.cycles-pp.page_counter_charge.obj_cgroup_charge_pages.obj_cgroup_charge.__kmalloc_node_track_caller.kmalloc_reserve
17.18 ? 11% -16.6 0.59 ? 7% perf-profile.children.cycles-pp.page_counter_try_charge
23.30 ? 12% -15.5 7.83 ? 31% perf-profile.children.cycles-pp.perf_tp_event
22.67 ? 12% -15.1 7.58 ? 31% perf-profile.children.cycles-pp.perf_swevent_overflow
22.63 ? 12% -15.1 7.56 ? 31% perf-profile.children.cycles-pp.__perf_event_overflow
22.53 ? 12% -15.0 7.52 ? 31% perf-profile.children.cycles-pp.perf_event_output_forward
22.12 ? 12% -14.8 7.34 ? 31% perf-profile.children.cycles-pp.perf_prepare_sample
21.00 ? 12% -14.1 6.88 ? 32% perf-profile.children.cycles-pp.perf_callchain
20.89 ? 12% -14.0 6.85 ? 32% perf-profile.children.cycles-pp.get_perf_callchain
19.54 ? 10% -12.0 7.51 ? 22% perf-profile.children.cycles-pp.schedule
19.55 ? 10% -11.9 7.61 ? 21% perf-profile.children.cycles-pp.__schedule
18.11 ? 12% -10.8 7.26 ? 21% perf-profile.children.cycles-pp.__wake_up_common_lock
17.47 ? 12% -10.7 6.81 ? 21% perf-profile.children.cycles-pp.__wake_up_common
17.34 ? 12% -10.6 6.70 ? 22% perf-profile.children.cycles-pp.autoremove_wake_function
17.24 ? 12% -10.6 6.64 ? 22% perf-profile.children.cycles-pp.try_to_wake_up
18.74 ? 11% -10.4 8.30 ? 17% perf-profile.children.cycles-pp.sock_def_readable
13.76 ? 13% -9.3 4.50 ? 32% perf-profile.children.cycles-pp.perf_callchain_kernel
15.56 ? 10% -9.2 6.32 ? 21% perf-profile.children.cycles-pp.schedule_timeout
12.23 ? 12% -7.8 4.42 ? 28% perf-profile.children.cycles-pp.update_curr
11.26 ? 12% -7.3 3.96 ? 30% perf-profile.children.cycles-pp.perf_trace_sched_stat_runtime
10.42 ? 13% -7.0 3.38 ? 32% perf-profile.children.cycles-pp.unwind_next_frame
6.96 ? 13% -4.8 2.12 ? 34% perf-profile.children.cycles-pp.perf_trace_sched_switch
6.72 ? 13% -4.5 2.22 ? 31% perf-profile.children.cycles-pp.perf_callchain_user
7.06 ? 13% -4.5 2.60 ? 24% perf-profile.children.cycles-pp.ttwu_do_activate
52.87 -4.4 48.42 perf-profile.children.cycles-pp.__libc_write
7.00 ? 13% -4.4 2.58 ? 24% perf-profile.children.cycles-pp.enqueue_task_fair
6.37 ? 12% -4.3 2.11 ? 31% perf-profile.children.cycles-pp.__get_user_nocheck_8
6.86 ? 11% -4.2 2.63 ? 24% perf-profile.children.cycles-pp.dequeue_task_fair
6.30 ? 13% -4.1 2.21 ? 26% perf-profile.children.cycles-pp.enqueue_entity
6.17 ? 11% -3.9 2.28 ? 27% perf-profile.children.cycles-pp.dequeue_entity
5.50 ? 12% -3.7 1.76 ? 32% perf-profile.children.cycles-pp.__unwind_start
5.52 ? 11% -3.6 1.94 ? 29% perf-profile.children.cycles-pp.perf_trace_sched_wakeup_template
4.70 ? 11% -3.1 1.64 ? 19% perf-profile.children.cycles-pp.syscall_exit_to_user_mode
4.61 ? 11% -3.0 1.56 ? 20% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
4.40 ? 13% -2.5 1.87 ? 28% perf-profile.children.cycles-pp.asm_exc_page_fault
2.99 ? 13% -2.0 1.00 ? 31% perf-profile.children.cycles-pp.__orc_find
3.90 ? 10% -1.5 2.38 ? 21% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
47.70 -1.3 46.38 perf-profile.children.cycles-pp.ksys_write
47.46 -1.3 46.14 perf-profile.children.cycles-pp.vfs_write
46.95 -1.3 45.64 perf-profile.children.cycles-pp.new_sync_write
46.55 -1.2 45.36 perf-profile.children.cycles-pp.sock_write_iter
1.67 ? 13% -1.1 0.55 ? 32% perf-profile.children.cycles-pp.orc_find
46.21 -1.1 45.09 perf-profile.children.cycles-pp.sock_sendmsg
45.90 -1.1 44.79 perf-profile.children.cycles-pp.unix_stream_sendmsg
1.66 ? 12% -1.1 0.57 ? 31% perf-profile.children.cycles-pp.unwind_get_return_address
5.94 ? 5% -1.1 4.86 ? 3% perf-profile.children.cycles-pp._raw_spin_lock
2.00 ? 3% -0.9 1.12 ? 6% perf-profile.children.cycles-pp.switch_mm_irqs_off
1.30 ? 12% -0.8 0.46 ? 30% perf-profile.children.cycles-pp.__kernel_text_address
1.20 ? 10% -0.8 0.44 ? 28% perf-profile.children.cycles-pp.native_irq_return_iret
1.09 ? 13% -0.8 0.34 ? 31% perf-profile.children.cycles-pp.kernelmode_fixup_or_oops
1.05 ? 14% -0.7 0.32 ? 34% perf-profile.children.cycles-pp.stack_access_ok
1.01 ? 13% -0.7 0.31 ? 31% perf-profile.children.cycles-pp.fixup_exception
1.00 ? 12% -0.7 0.34 ? 30% perf-profile.children.cycles-pp.kernel_text_address
0.91 ? 13% -0.6 0.28 ? 32% perf-profile.children.cycles-pp.search_exception_tables
0.88 ? 13% -0.6 0.27 ? 32% perf-profile.children.cycles-pp.search_extable
0.84 ? 14% -0.6 0.26 ? 31% perf-profile.children.cycles-pp.bsearch
1.44 ? 14% -0.5 0.90 ? 29% perf-profile.children.cycles-pp.exc_page_fault
97.98 -0.5 97.46 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
0.95 ? 14% -0.5 0.46 ? 13% perf-profile.children.cycles-pp.select_task_rq_fair
97.74 -0.5 97.26 perf-profile.children.cycles-pp.do_syscall_64
0.82 ? 11% -0.4 0.42 ? 8% perf-profile.children.cycles-pp.pick_next_task_fair
0.70 ? 14% -0.4 0.31 ? 15% perf-profile.children.cycles-pp.select_idle_sibling
0.65 ? 9% -0.4 0.27 ? 28% perf-profile.children.cycles-pp.__perf_event_header__init_id
0.87 ? 12% -0.4 0.51 ? 9% perf-profile.children.cycles-pp.update_load_avg
0.51 ? 14% -0.4 0.16 ? 31% perf-profile.children.cycles-pp.cmp_ex_search
0.46 ? 11% -0.3 0.21 ? 13% perf-profile.children.cycles-pp.reweight_entity
0.44 ? 9% -0.3 0.19 ? 10% perf-profile.children.cycles-pp.load_new_mm_cr3
0.41 ? 15% -0.2 0.18 ? 16% perf-profile.children.cycles-pp.select_idle_cpu
0.46 ? 8% -0.2 0.24 ? 7% perf-profile.children.cycles-pp.switch_fpu_return
0.37 ? 8% -0.2 0.15 ? 26% perf-profile.children.cycles-pp.perf_event_pid_type
0.45 ? 3% -0.2 0.25 ? 6% perf-profile.children.cycles-pp.__switch_to
0.31 ? 11% -0.2 0.11 ? 32% perf-profile.children.cycles-pp.ftrace_graph_ret_addr
0.31 ? 12% -0.2 0.12 ? 30% perf-profile.children.cycles-pp.perf_output_begin_forward
0.31 ? 9% -0.2 0.13 ? 17% perf-profile.children.cycles-pp.sched_clock_cpu
0.30 ? 8% -0.2 0.12 ? 28% perf-profile.children.cycles-pp.__task_pid_nr_ns
0.32 ? 16% -0.2 0.15 ? 31% perf-profile.children.cycles-pp.perf_trace_sched_migrate_task
0.37 ? 5% -0.2 0.21 ? 7% perf-profile.children.cycles-pp.ttwu_do_wakeup
0.37 ? 16% -0.2 0.21 ? 24% perf-profile.children.cycles-pp.set_task_cpu
0.27 ? 10% -0.2 0.11 ? 18% perf-profile.children.cycles-pp.native_sched_clock
0.27 ? 17% -0.2 0.11 ? 22% perf-profile.children.cycles-pp.available_idle_cpu
0.30 ? 9% -0.2 0.15 ? 10% perf-profile.children.cycles-pp.set_next_entity
0.35 ? 5% -0.2 0.20 ? 7% perf-profile.children.cycles-pp.check_preempt_curr
0.23 ? 13% -0.2 0.08 ? 48% perf-profile.children.cycles-pp.bad_get_user
0.29 ? 10% -0.1 0.14 ? 9% perf-profile.children.cycles-pp.__switch_to_asm
0.32 ? 9% -0.1 0.18 ? 14% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
0.66 ? 5% -0.1 0.52 ? 6% perf-profile.children.cycles-pp.prepare_to_wait
0.30 ? 4% -0.1 0.16 ? 9% perf-profile.children.cycles-pp.check_preempt_wakeup
0.20 ? 11% -0.1 0.06 ? 47% perf-profile.children.cycles-pp.error_entry
0.26 ? 11% -0.1 0.12 ? 10% perf-profile.children.cycles-pp.update_rq_clock
0.21 ? 16% -0.1 0.08 ? 8% perf-profile.children.cycles-pp.__enqueue_entity
0.30 ? 15% -0.1 0.17 ? 22% perf-profile.children.cycles-pp.finish_task_switch
0.19 ? 14% -0.1 0.07 ? 48% perf-profile.children.cycles-pp.is_bpf_text_address
0.24 ? 11% -0.1 0.11 ? 13% perf-profile.children.cycles-pp.__restore_fpregs_from_fpstate
0.24 ? 12% -0.1 0.12 ? 11% perf-profile.children.cycles-pp.__update_load_avg_se
0.21 ? 16% -0.1 0.09 ? 20% perf-profile.children.cycles-pp.cpuacct_charge
0.22 ? 13% -0.1 0.10 ? 11% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
0.13 ? 15% -0.1 0.03 ?102% perf-profile.children.cycles-pp.perf_tp_event_match
0.16 ? 11% -0.1 0.05 ? 45% perf-profile.children.cycles-pp.perf_trace_buf_alloc
0.16 ? 16% -0.1 0.06 ? 11% perf-profile.children.cycles-pp.put_prev_entity
0.14 ? 14% -0.1 0.04 ? 75% perf-profile.children.cycles-pp.save_fpregs_to_fpstate
0.13 ? 11% -0.1 0.04 ? 73% perf-profile.children.cycles-pp.get_callchain_entry
0.15 ? 11% -0.1 0.06 ? 46% perf-profile.children.cycles-pp.perf_trace_buf_update
0.14 ? 15% -0.1 0.05 ? 51% perf-profile.children.cycles-pp.bpf_ksym_find
0.13 ? 11% -0.1 0.05 ? 47% perf-profile.children.cycles-pp.get_stack_info
0.16 ? 4% -0.1 0.08 ? 8% perf-profile.children.cycles-pp.resched_curr
0.11 ? 11% -0.1 0.04 ? 71% perf-profile.children.cycles-pp.perf_instruction_pointer
0.11 ? 14% -0.1 0.04 ? 47% perf-profile.children.cycles-pp.___perf_sw_event
0.10 ? 14% -0.1 0.04 ? 71% perf-profile.children.cycles-pp.tracing_gen_ctx_irq_test
0.13 ? 15% -0.1 0.07 ? 10% perf-profile.children.cycles-pp.update_min_vruntime
0.14 ? 14% -0.1 0.08 ? 11% perf-profile.children.cycles-pp.__list_del_entry_valid
0.14 ? 11% -0.0 0.09 ? 12% perf-profile.children.cycles-pp.preempt_schedule_common
0.10 ? 9% -0.0 0.05 ? 8% perf-profile.children.cycles-pp.__list_add_valid
0.08 ? 6% -0.0 0.03 ? 70% perf-profile.children.cycles-pp.iov_iter_init
0.10 ? 7% -0.0 0.06 ? 7% perf-profile.children.cycles-pp.__calc_delta
0.17 ? 4% -0.0 0.14 ? 5% perf-profile.children.cycles-pp.asm_sysvec_reschedule_ipi
0.12 ? 6% -0.0 0.09 ? 6% perf-profile.children.cycles-pp.finish_wait
0.14 ? 3% -0.0 0.10 ? 4% perf-profile.children.cycles-pp.rcu_read_unlock_strict
0.06 +0.0 0.07 perf-profile.children.cycles-pp.refill_obj_stock
0.06 +0.0 0.07 ? 5% perf-profile.children.cycles-pp.check_stack_object
0.07 +0.0 0.09 ? 7% perf-profile.children.cycles-pp.rcu_all_qs
0.15 ? 3% +0.0 0.17 ? 4% perf-profile.children.cycles-pp.__ksize
0.04 ? 45% +0.0 0.06 ? 7% perf-profile.children.cycles-pp.irq_exit_rcu
0.10 ? 4% +0.0 0.12 ? 3% perf-profile.children.cycles-pp.wait_for_unix_gc
0.13 ? 5% +0.0 0.16 ? 4% perf-profile.children.cycles-pp.__might_fault
0.19 ? 3% +0.0 0.22 ? 4% perf-profile.children.cycles-pp.__virt_addr_valid
0.18 +0.0 0.21 ? 4% perf-profile.children.cycles-pp.__might_sleep
0.19 ? 2% +0.0 0.22 ? 2% perf-profile.children.cycles-pp.security_socket_recvmsg
0.22 ? 2% +0.0 0.25 perf-profile.children.cycles-pp.sock_recvmsg
0.26 ? 3% +0.0 0.30 ? 2% perf-profile.children.cycles-pp.copyin
0.22 ? 2% +0.1 0.27 ? 3% perf-profile.children.cycles-pp.__check_heap_object
0.00 +0.1 0.05 ? 7% perf-profile.children.cycles-pp.load_balance
0.37 +0.1 0.42 ? 2% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.33 ? 2% +0.1 0.38 ? 2% perf-profile.children.cycles-pp.aa_sk_perm
0.04 ? 73% +0.1 0.09 ? 13% perf-profile.children.cycles-pp.generic_file_write_iter
0.04 ? 73% +0.1 0.09 ? 13% perf-profile.children.cycles-pp.__generic_file_write_iter
0.04 ? 73% +0.1 0.09 ? 13% perf-profile.children.cycles-pp.generic_perform_write
0.00 +0.1 0.06 ? 6% perf-profile.children.cycles-pp.__softirqentry_text_start
0.42 ? 2% +0.1 0.49 ? 4% perf-profile.children.cycles-pp._copy_from_iter
0.38 +0.1 0.45 ? 3% perf-profile.children.cycles-pp.__entry_text_start
0.00 +0.1 0.08 ? 17% perf-profile.children.cycles-pp.schedule_idle
0.26 ? 4% +0.1 0.35 ? 3% perf-profile.children.cycles-pp.__build_skb_around
0.01 ?223% +0.1 0.11 ? 41% perf-profile.children.cycles-pp.try_to_migrate_one
0.49 ? 3% +0.1 0.60 ? 5% perf-profile.children.cycles-pp.mutex_lock
0.90 ? 3% +0.1 1.01 ? 6% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
0.01 ?223% +0.1 0.14 ? 40% perf-profile.children.cycles-pp.try_to_migrate
0.65 +0.2 0.81 perf-profile.children.cycles-pp.simple_copy_to_iter
0.75 ? 2% +0.2 0.92 ? 4% perf-profile.children.cycles-pp.skb_copy_datagram_from_iter
0.02 ?223% +0.2 0.22 ? 48% perf-profile.children.cycles-pp.remove_migration_pte
0.76 ? 7% +0.2 0.99 ? 12% perf-profile.children.cycles-pp.__slab_alloc
0.76 ? 6% +0.2 0.98 ? 11% perf-profile.children.cycles-pp.___slab_alloc
0.92 +0.2 1.15 ? 2% perf-profile.children.cycles-pp.__check_object_size
0.29 ? 15% +0.2 0.53 ? 7% perf-profile.children.cycles-pp.drain_stock
0.49 ? 12% +0.2 0.74 ? 19% perf-profile.children.cycles-pp.__unfreeze_partials
0.03 ?155% +0.2 0.27 ? 47% perf-profile.children.cycles-pp.remove_migration_ptes
0.34 ? 13% +0.3 0.60 ? 6% perf-profile.children.cycles-pp.refill_stock
0.40 ? 9% +0.3 0.67 ? 4% perf-profile.children.cycles-pp.unix_write_space
0.34 ? 15% +0.3 0.62 ? 7% perf-profile.children.cycles-pp.try_charge_memcg
0.03 ?161% +0.3 0.32 ? 45% perf-profile.children.cycles-pp.page_vma_mapped_walk
0.65 ? 2% +0.3 0.94 ? 3% perf-profile.children.cycles-pp.copyout
0.82 ? 2% +0.3 1.12 ? 3% perf-profile.children.cycles-pp._copy_to_iter
0.17 ? 38% +0.3 0.49 ? 39% perf-profile.children.cycles-pp.do_user_addr_fault
0.88 ? 2% +0.3 1.20 ? 3% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
0.06 ?106% +0.4 0.41 ? 44% perf-profile.children.cycles-pp.rmap_walk_anon
1.28 ? 9% +0.4 1.63 ? 7% perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
0.06 ?106% +0.4 0.42 ? 44% perf-profile.children.cycles-pp.migrate_misplaced_page
0.06 ?106% +0.4 0.42 ? 44% perf-profile.children.cycles-pp.migrate_pages
0.06 ?108% +0.4 0.42 ? 45% perf-profile.children.cycles-pp.do_numa_page
0.08 ? 81% +0.4 0.44 ? 43% perf-profile.children.cycles-pp.__handle_mm_fault
0.08 ? 84% +0.4 0.45 ? 42% perf-profile.children.cycles-pp.handle_mm_fault
1.79 ? 8% +0.4 2.22 ? 6% perf-profile.children.cycles-pp.mod_objcg_state
0.00 +0.4 0.43 ? 22% perf-profile.children.cycles-pp.intel_idle
0.58 ? 12% +0.4 1.01 ? 7% perf-profile.children.cycles-pp.mutex_unlock
0.76 ? 7% +0.4 1.21 ? 7% perf-profile.children.cycles-pp.skb_queue_tail
0.01 ?223% +0.5 0.46 ? 22% perf-profile.children.cycles-pp.cpuidle_enter_state
0.01 ?223% +0.5 0.46 ? 22% perf-profile.children.cycles-pp.cpuidle_enter
0.60 ? 12% +0.5 1.06 ? 7% perf-profile.children.cycles-pp.skb_unlink
1.52 +0.5 1.99 ? 2% perf-profile.children.cycles-pp.skb_copy_datagram_iter
1.50 ? 2% +0.5 1.98 ? 2% perf-profile.children.cycles-pp.__skb_datagram_iter
1.53 +0.5 2.01 ? 2% perf-profile.children.cycles-pp.unix_stream_read_actor
0.65 ? 5% +0.5 1.15 ? 6% perf-profile.children.cycles-pp.skb_set_owner_w
0.02 ?144% +0.6 0.58 ? 21% perf-profile.children.cycles-pp.start_secondary
0.02 ?144% +0.6 0.59 ? 21% perf-profile.children.cycles-pp.secondary_startup_64_no_verify
0.02 ?144% +0.6 0.59 ? 21% perf-profile.children.cycles-pp.cpu_startup_entry
0.02 ?144% +0.6 0.59 ? 21% perf-profile.children.cycles-pp.do_idle
1.16 ? 9% +0.8 1.99 ? 4% perf-profile.children.cycles-pp.sock_wfree
1.21 ? 8% +0.8 2.04 ? 4% perf-profile.children.cycles-pp.unix_destruct_scm
1.22 ? 8% +0.8 2.06 ? 4% perf-profile.children.cycles-pp.skb_release_head_state
1.23 ? 8% +0.8 2.07 ? 4% perf-profile.children.cycles-pp.skb_release_all
1.58 ? 7% +1.0 2.53 ? 8% perf-profile.children.cycles-pp.get_mem_cgroup_from_objcg
1.47 ? 9% +1.1 2.54 ? 5% perf-profile.children.cycles-pp.__slab_free
2.99 ? 5% +1.1 4.13 ? 4% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
7.88 ? 8% +2.4 10.33 ? 4% perf-profile.children.cycles-pp.kmem_cache_alloc_node
47.00 +3.5 50.55 perf-profile.children.cycles-pp.__libc_read
7.43 ? 12% +3.7 11.08 ? 7% perf-profile.children.cycles-pp.propagate_protected_usage
44.84 +3.9 48.70 perf-profile.children.cycles-pp.vfs_read
45.04 +3.9 48.91 perf-profile.children.cycles-pp.ksys_read
43.69 +3.9 47.56 perf-profile.children.cycles-pp.unix_stream_recvmsg
43.61 +3.9 47.49 perf-profile.children.cycles-pp.unix_stream_read_generic
44.12 +3.9 48.00 perf-profile.children.cycles-pp.sock_read_iter
44.34 +3.9 48.24 perf-profile.children.cycles-pp.new_sync_read
7.55 ? 9% +4.1 11.66 ? 4% perf-profile.children.cycles-pp.kmem_cache_free
14.24 ? 9% +4.5 18.76 ? 4% perf-profile.children.cycles-pp.kmalloc_reserve
14.20 ? 9% +4.5 18.72 ? 4% perf-profile.children.cycles-pp.__kmalloc_node_track_caller
11.62 ? 11% +5.2 16.83 ? 6% perf-profile.children.cycles-pp.page_counter_cancel
12.06 ? 9% +5.9 17.92 ? 4% perf-profile.children.cycles-pp.kfree
18.74 ? 10% +6.4 25.17 ? 5% perf-profile.children.cycles-pp.obj_cgroup_charge_pages
18.83 ? 10% +6.5 25.28 ? 5% perf-profile.children.cycles-pp.obj_cgroup_charge
13.12 ? 9% +6.5 19.62 ? 4% perf-profile.children.cycles-pp.skb_release_data
22.71 ? 8% +7.1 29.84 ? 4% perf-profile.children.cycles-pp.__alloc_skb
22.76 ? 8% +7.1 29.89 ? 4% perf-profile.children.cycles-pp.alloc_skb_with_frags
14.56 ? 9% +7.5 22.04 ? 4% perf-profile.children.cycles-pp.consume_skb
14.92 ? 11% +7.6 22.56 ? 5% perf-profile.children.cycles-pp.page_counter_uncharge
23.80 ? 8% +8.0 31.76 ? 4% perf-profile.children.cycles-pp.sock_alloc_send_pskb
16.54 ? 11% +8.6 25.14 ? 5% perf-profile.children.cycles-pp.obj_cgroup_uncharge_pages
0.00 +22.0 22.04 ? 5% perf-profile.children.cycles-pp.page_counter_charge
12.79 ? 10% -12.6 0.17 ? 9% perf-profile.self.cycles-pp.page_counter_try_charge
4.56 ? 13% -3.1 1.44 ? 33% perf-profile.self.cycles-pp.unwind_next_frame
3.43 ? 14% -2.3 1.14 ? 32% perf-profile.self.cycles-pp.__get_user_nocheck_8
2.98 ? 13% -2.0 0.99 ? 32% perf-profile.self.cycles-pp.__orc_find
3.89 ? 10% -1.5 2.38 ? 21% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
1.61 ? 13% -1.1 0.53 ? 32% perf-profile.self.cycles-pp.orc_find
1.22 ? 12% -0.8 0.39 ? 34% perf-profile.self.cycles-pp.perf_callchain_kernel
1.20 ? 10% -0.8 0.44 ? 28% perf-profile.self.cycles-pp.native_irq_return_iret
0.92 ? 13% -0.6 0.29 ? 33% perf-profile.self.cycles-pp.stack_access_ok
1.54 ? 5% -0.6 0.92 ? 6% perf-profile.self.cycles-pp.switch_mm_irqs_off
0.82 ? 9% -0.4 0.45 ? 9% perf-profile.self.cycles-pp.__schedule
0.50 ? 14% -0.3 0.16 ? 30% perf-profile.self.cycles-pp.cmp_ex_search
0.50 ? 12% -0.3 0.16 ? 30% perf-profile.self.cycles-pp.__unwind_start
0.48 ? 13% -0.3 0.16 ? 31% perf-profile.self.cycles-pp.kernel_text_address
0.49 ? 13% -0.3 0.22 ? 10% perf-profile.self.cycles-pp.update_curr
0.36 ? 12% -0.3 0.11 ? 31% perf-profile.self.cycles-pp.unwind_get_return_address
0.44 ? 10% -0.3 0.19 ? 10% perf-profile.self.cycles-pp.load_new_mm_cr3
0.34 ? 13% -0.2 0.10 ? 49% perf-profile.self.cycles-pp.bsearch
0.30 ? 17% -0.2 0.08 ? 47% perf-profile.self.cycles-pp.perf_callchain_user
0.45 ? 3% -0.2 0.25 ? 7% perf-profile.self.cycles-pp.__switch_to
0.27 ? 9% -0.2 0.08 ? 47% perf-profile.self.cycles-pp.get_perf_callchain
0.33 ? 10% -0.2 0.14 ? 21% perf-profile.self.cycles-pp.perf_tp_event
0.28 ? 12% -0.2 0.11 ? 30% perf-profile.self.cycles-pp.perf_output_begin_forward
0.28 ? 9% -0.2 0.11 ? 27% perf-profile.self.cycles-pp.__task_pid_nr_ns
0.26 ? 12% -0.2 0.09 ? 48% perf-profile.self.cycles-pp.ftrace_graph_ret_addr
0.26 ? 12% -0.2 0.10 ? 46% perf-profile.self.cycles-pp.__kernel_text_address
0.26 ? 17% -0.2 0.10 ? 21% perf-profile.self.cycles-pp.available_idle_cpu
0.27 ? 10% -0.2 0.11 ? 27% perf-profile.self.cycles-pp.perf_prepare_sample
0.26 ? 9% -0.2 0.10 ? 19% perf-profile.self.cycles-pp.native_sched_clock
0.22 ? 11% -0.2 0.07 ? 48% perf-profile.self.cycles-pp.asm_exc_page_fault
0.30 ? 6% -0.1 0.16 ? 3% perf-profile.self.cycles-pp.new_sync_write
0.28 ? 10% -0.1 0.14 ? 9% perf-profile.self.cycles-pp.__switch_to_asm
0.22 ? 12% -0.1 0.08 ? 49% perf-profile.self.cycles-pp.perf_trace_sched_switch
0.40 ? 12% -0.1 0.27 ? 9% perf-profile.self.cycles-pp.update_load_avg
0.28 ? 11% -0.1 0.14 ? 14% perf-profile.self.cycles-pp.try_to_wake_up
0.21 ? 16% -0.1 0.08 ? 8% perf-profile.self.cycles-pp.__enqueue_entity
0.24 ? 11% -0.1 0.11 ? 13% perf-profile.self.cycles-pp.__restore_fpregs_from_fpstate
0.24 ? 12% -0.1 0.12 ? 10% perf-profile.self.cycles-pp.__update_load_avg_se
0.17 ? 13% -0.1 0.05 ? 47% perf-profile.self.cycles-pp.error_entry
0.22 ? 14% -0.1 0.11 ? 16% perf-profile.self.cycles-pp.perf_trace_sched_stat_runtime
0.20 ? 16% -0.1 0.09 ? 16% perf-profile.self.cycles-pp.cpuacct_charge
0.21 ? 14% -0.1 0.10 ? 14% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
0.22 ? 6% -0.1 0.12 ? 8% perf-profile.self.cycles-pp.switch_fpu_return
0.13 ? 14% -0.1 0.03 ?102% perf-profile.self.cycles-pp.perf_tp_event_match
0.28 ? 6% -0.1 0.18 ? 5% perf-profile.self.cycles-pp.prepare_to_wait
0.17 ? 10% -0.1 0.07 ? 12% perf-profile.self.cycles-pp.reweight_entity
0.13 ? 8% -0.1 0.04 ? 71% perf-profile.self.cycles-pp.get_callchain_entry
0.13 ? 14% -0.1 0.04 ? 75% perf-profile.self.cycles-pp.save_fpregs_to_fpstate
0.14 ? 15% -0.1 0.05 ? 49% perf-profile.self.cycles-pp.bpf_ksym_find
0.19 ? 11% -0.1 0.10 ? 5% perf-profile.self.cycles-pp.pick_next_task_fair
0.16 ? 14% -0.1 0.08 ? 13% perf-profile.self.cycles-pp.update_rq_clock
0.16 ? 11% -0.1 0.08 ? 5% perf-profile.self.cycles-pp.enqueue_entity
0.15 ? 13% -0.1 0.07 ? 12% perf-profile.self.cycles-pp.select_idle_sibling
0.34 ? 5% -0.1 0.26 ? 3% perf-profile.self.cycles-pp.sock_write_iter
0.15 ? 16% -0.1 0.07 ? 18% perf-profile.self.cycles-pp.select_idle_cpu
0.16 ? 4% -0.1 0.08 ? 8% perf-profile.self.cycles-pp.resched_curr
0.15 ? 10% -0.1 0.08 ? 4% perf-profile.self.cycles-pp.select_task_rq_fair
0.14 ? 14% -0.1 0.08 ? 16% perf-profile.self.cycles-pp.enqueue_task_fair
0.13 ? 8% -0.1 0.06 ? 11% perf-profile.self.cycles-pp.schedule
0.10 ? 14% -0.1 0.04 ? 71% perf-profile.self.cycles-pp.tracing_gen_ctx_irq_test
0.14 ? 10% -0.1 0.07 ? 6% perf-profile.self.cycles-pp.dequeue_task_fair
0.12 ? 14% -0.1 0.06 ? 7% perf-profile.self.cycles-pp.update_min_vruntime
0.13 ? 7% -0.1 0.08 ? 7% perf-profile.self.cycles-pp.do_syscall_64
0.29 ? 6% -0.0 0.24 ? 2% perf-profile.self.cycles-pp.__libc_read
0.13 ? 12% -0.0 0.08 ? 8% perf-profile.self.cycles-pp.__list_del_entry_valid
0.10 ? 9% -0.0 0.05 ? 8% perf-profile.self.cycles-pp.__list_add_valid
0.11 ? 14% -0.0 0.06 ? 14% perf-profile.self.cycles-pp.perf_trace_sched_wakeup_template
0.10 ? 7% -0.0 0.06 ? 6% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore
0.08 ? 10% -0.0 0.03 ? 70% perf-profile.self.cycles-pp.iov_iter_init
0.10 ? 7% -0.0 0.06 ? 7% perf-profile.self.cycles-pp.__calc_delta
0.09 ? 7% -0.0 0.05 ? 8% perf-profile.self.cycles-pp.finish_task_switch
0.24 ? 3% -0.0 0.20 ? 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.08 ? 10% -0.0 0.04 ? 45% perf-profile.self.cycles-pp.dequeue_entity
0.08 ? 8% -0.0 0.04 ? 45% perf-profile.self.cycles-pp.check_preempt_wakeup
0.08 ? 11% -0.0 0.05 ? 46% perf-profile.self.cycles-pp.__perf_event_header__init_id
0.07 ? 5% -0.0 0.04 ? 44% perf-profile.self.cycles-pp.sock_sendmsg
0.11 ? 6% -0.0 0.09 ? 5% perf-profile.self.cycles-pp.exit_to_user_mode_prepare
0.07 ? 10% -0.0 0.05 ? 7% perf-profile.self.cycles-pp.schedule_timeout
0.21 ? 2% -0.0 0.18 ? 4% perf-profile.self.cycles-pp.sock_read_iter
0.08 ? 4% -0.0 0.06 ? 7% perf-profile.self.cycles-pp.rcu_read_unlock_strict
0.23 ? 3% -0.0 0.21 ? 3% perf-profile.self.cycles-pp.__libc_write
0.13 ? 6% -0.0 0.11 ? 6% perf-profile.self.cycles-pp.security_file_permission
0.06 ? 6% +0.0 0.07 perf-profile.self.cycles-pp.refill_obj_stock
0.05 ? 7% +0.0 0.06 ? 7% perf-profile.self.cycles-pp.check_stack_object
0.09 ? 7% +0.0 0.11 ? 6% perf-profile.self.cycles-pp.obj_cgroup_charge
0.05 ? 8% +0.0 0.07 perf-profile.self.cycles-pp.__cond_resched
0.05 ? 7% +0.0 0.07 ? 8% perf-profile.self.cycles-pp.rcu_all_qs
0.10 ? 4% +0.0 0.12 ? 6% perf-profile.self.cycles-pp._copy_from_iter
0.18 ? 2% +0.0 0.20 ? 4% perf-profile.self.cycles-pp.new_sync_read
0.14 ? 3% +0.0 0.16 ? 6% perf-profile.self.cycles-pp.__ksize
0.16 +0.0 0.19 ? 3% perf-profile.self.cycles-pp.__might_sleep
0.19 ? 4% +0.0 0.22 ? 3% perf-profile.self.cycles-pp.aa_sk_perm
0.18 ? 4% +0.0 0.21 ? 4% perf-profile.self.cycles-pp.__virt_addr_valid
0.17 ? 2% +0.0 0.21 ? 3% perf-profile.self.cycles-pp.__entry_text_start
0.27 ? 2% +0.0 0.31 ? 3% perf-profile.self.cycles-pp.__alloc_skb
0.34 +0.0 0.38 ? 4% perf-profile.self.cycles-pp.kmem_cache_alloc_node
0.04 ? 45% +0.0 0.09 ? 9% perf-profile.self.cycles-pp.skb_copy_datagram_from_iter
0.21 ? 2% +0.0 0.26 ? 4% perf-profile.self.cycles-pp.__check_heap_object
0.50 ? 2% +0.1 0.54 ? 2% perf-profile.self.cycles-pp.__kmalloc_node_track_caller
0.46 ? 4% +0.1 0.52 ? 5% perf-profile.self.cycles-pp.unix_stream_sendmsg
0.36 +0.1 0.42 ? 2% perf-profile.self.cycles-pp.syscall_return_via_sysret
0.32 ? 2% +0.1 0.38 ? 5% perf-profile.self.cycles-pp.___slab_alloc
0.22 ? 5% +0.1 0.28 ? 6% perf-profile.self.cycles-pp.unix_write_space
0.00 +0.1 0.07 ? 7% perf-profile.self.cycles-pp.refill_stock
0.14 ? 16% +0.1 0.21 ? 3% perf-profile.self.cycles-pp.page_counter_uncharge
0.19 ? 6% +0.1 0.27 ? 5% perf-profile.self.cycles-pp.__build_skb_around
0.40 ? 2% +0.1 0.50 ? 4% perf-profile.self.cycles-pp.kfree
0.37 ? 4% +0.1 0.49 ? 6% perf-profile.self.cycles-pp.mutex_lock
0.45 ? 3% +0.1 0.59 ? 2% perf-profile.self.cycles-pp.__check_object_size
0.21 ? 8% +0.1 0.35 ? 9% perf-profile.self.cycles-pp.consume_skb
0.02 ?223% +0.1 0.16 ? 45% perf-profile.self.cycles-pp.page_vma_mapped_walk
0.20 ? 11% +0.2 0.36 ? 7% perf-profile.self.cycles-pp.skb_release_data
1.02 ? 3% +0.2 1.22 ? 4% perf-profile.self.cycles-pp.unix_stream_read_generic
0.58 ? 2% +0.2 0.78 ? 3% perf-profile.self.cycles-pp.kmem_cache_free
0.86 ? 2% +0.3 1.19 ? 3% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string
1.25 ? 9% +0.4 1.60 ? 6% perf-profile.self.cycles-pp.__mod_memcg_lruvec_state
0.00 +0.4 0.43 ? 22% perf-profile.self.cycles-pp.intel_idle
0.57 ? 12% +0.4 1.00 ? 7% perf-profile.self.cycles-pp.mutex_unlock
0.76 ? 8% +0.4 1.20 ? 8% perf-profile.self.cycles-pp.obj_cgroup_uncharge_pages
0.64 ? 4% +0.5 1.14 ? 6% perf-profile.self.cycles-pp.skb_set_owner_w
0.73 ? 8% +0.5 1.25 ? 9% perf-profile.self.cycles-pp.obj_cgroup_charge_pages
0.74 ? 9% +0.6 1.30 ? 7% perf-profile.self.cycles-pp.sock_wfree
0.81 ? 11% +0.6 1.42 ? 7% perf-profile.self.cycles-pp.sock_def_readable
2.22 ? 4% +0.7 2.88 ? 6% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
2.79 ? 4% +0.9 3.68 ? 5% perf-profile.self.cycles-pp._raw_spin_lock
1.56 ? 7% +0.9 2.50 ? 8% perf-profile.self.cycles-pp.get_mem_cgroup_from_objcg
1.45 ? 9% +1.1 2.51 ? 5% perf-profile.self.cycles-pp.__slab_free
7.36 ? 12% +3.6 10.97 ? 7% perf-profile.self.cycles-pp.propagate_protected_usage
11.50 ? 11% +5.2 16.66 ? 6% perf-profile.self.cycles-pp.page_counter_cancel
0.00 +16.7 16.74 ? 6% perf-profile.self.cycles-pp.page_counter_charge
hackbench.throughput
145000 +------------------------------------------------------------------+
| O |
140000 |-+ O O O |
| OO OO O O O O O O |
135000 |-O O O OO O O O O |
| O O O O O O O |
130000 |-+ O O O O |
| OO O ++ .+.+ |
125000 |.++.+.+ +.+.++.+.++.+.+.++ : + + +.+.+ .+ |
| + ++.+ : O : : +.+ +.+ |
120000 |-+ :O : : : : : |
| : : :: : |
115000 |-+ :: : + |
| + + |
110000 +------------------------------------------------------------------+
hackbench.time.voluntary_context_switches
1.4e+09 +-----------------------------------------------------------------+
| + |
1.3e+09 |-+ + :: |
1.2e+09 |-+ :+ : : |
| : + +.+. |
1.1e+09 |.++. .+ ++.++. .++.+.+ .+ + |
1e+09 |-+ + + + + + : |
| + + : .++. .+. |
9e+08 |-+ +.+. : ++.+ ++ + |
8e+08 |-+ + |
| |
7e+08 |-+ |
6e+08 |-+ |
| OO O OO O OO O OO OO O OO O OO O OO O OO O OO O O OO O OO O OO |
5e+08 +-----------------------------------------------------------------+
hackbench.time.involuntary_context_switches
6.5e+08 +-----------------------------------------------------------------+
6e+08 |-+ + |
| + : |
5.5e+08 |-+ :: : : |
5e+08 |-+ :: : +.+. |
|. : + ++. +. |
4.5e+08 |-++. .+ ++. .+ +.+ .+ .+ |
4e+08 |-+ + + + + + : |
3.5e+08 |-+ + : : .++. .+. |
| +.+.: ++.+ ++ + |
3e+08 |-+ + |
2.5e+08 |-+ |
| |
2e+08 |-+ O O O O OO |
1.5e+08 +-----------------------------------------------------------------+
[*] 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.
---
0DAY/LKP+ Test Infrastructure Open Source Technology Center
https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation
Thanks,
Oliver Sang
On Wed 24-11-21 16:34:35, kernel test robot wrote:
>
>
> Greeting,
>
> FYI, we noticed a 10.3% improvement of hackbench.throughput due to commit:
>
>
> commit: 58056f77502f3567b760c9a8fc8d2e9081515b2d ("memcg, kmem: further deprecate kmem.limit_in_bytes")
> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
I am really surprised to see an improvement from this patch. I do not
expect your benchmarking would be using kmem limit. The above patch
hasn't really removed the page counter out of the picture so there
shouldn't be any real reason for performance improvement. I strongly
suspect this is just some benchmark artifact or unreliable evaluation.
--
Michal Hocko
SUSE Labs
On Fri 26-11-21 11:17:48, Oliver Sang wrote:
> Hi Michal Hocko,
>
> On Wed, Nov 24, 2021 at 06:01:12PM +0100, Michal Hocko wrote:
> > On Wed 24-11-21 16:34:35, kernel test robot wrote:
> > >
> > >
> > > Greeting,
> > >
> > > FYI, we noticed a 10.3% improvement of hackbench.throughput due to commit:
> > >
> > >
> > > commit: 58056f77502f3567b760c9a8fc8d2e9081515b2d ("memcg, kmem: further deprecate kmem.limit_in_bytes")
> > > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
> >
> > I am really surprised to see an improvement from this patch. I do not
> > expect your benchmarking would be using kmem limit. The above patch
> > hasn't really removed the page counter out of the picture so there
> > shouldn't be any real reason for performance improvement. I strongly
> > suspect this is just some benchmark artifact or unreliable evaluation.
>
> Fengwei Yin helped further analyze this improvement.
>
> The patch changed the behavior of function obj_cgroup_charge_pages. It's shown
> in the perf-callstack as following line:
>
> 5.63 ? 11% -5.6 0.00 perf-profile.calltrace.cycles-pp.page_counter_try_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb
>
> So Fengwei prepared a patch which reverting the changes in
> obj_cgroup_charge_pages in 58056f7750 (as attached mod.patch)
>
> by this patch, the performance is similar to 16f6bf266c, the improvement
> disappear.
I am still quite surprised and do not understand it. The only practical
difference the said commit has done is
s@page_counter_try_charge@page_counter_charge@
Withtout a limit in place the try_charge always succeeds. There
should be only a single if (new > c->max) branch executed and always
false.
The code is also slightly larger but all that sounds like to little to
make such a larger change. Maybe this is some microarchitecture specific
result. Or can you reproduce on other HW as well.
--
Michal Hocko
SUSE Labs
Hi Michal Hocko,
On Wed, Nov 24, 2021 at 06:01:12PM +0100, Michal Hocko wrote:
> On Wed 24-11-21 16:34:35, kernel test robot wrote:
> >
> >
> > Greeting,
> >
> > FYI, we noticed a 10.3% improvement of hackbench.throughput due to commit:
> >
> >
> > commit: 58056f77502f3567b760c9a8fc8d2e9081515b2d ("memcg, kmem: further deprecate kmem.limit_in_bytes")
> > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>
> I am really surprised to see an improvement from this patch. I do not
> expect your benchmarking would be using kmem limit. The above patch
> hasn't really removed the page counter out of the picture so there
> shouldn't be any real reason for performance improvement. I strongly
> suspect this is just some benchmark artifact or unreliable evaluation.
Fengwei Yin helped further analyze this improvement.
The patch changed the behavior of function obj_cgroup_charge_pages. It's shown
in the perf-callstack as following line:
5.63 ? 11% -5.6 0.00 perf-profile.calltrace.cycles-pp.page_counter_try_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb
So Fengwei prepared a patch which reverting the changes in
obj_cgroup_charge_pages in 58056f7750 (as attached mod.patch)
by this patch, the performance is similar to 16f6bf266c, the improvement
disappear.
=========================================================================================
compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase/ucode:
gcc-9/performance/socket/4/x86_64-rhel-8.3/process/100%/debian-10.4-x86_64-20200603.cgz/lkp-cpl-4sp1/hackbench/0x700001e
commit:
16f6bf266c ("mm/list_lru.c: prefer struct_size over open coded arithmetic")
58056f7750 ("memcg, kmem: further deprecate kmem.limit_in_bytes")
ae12af515d ('58056f7750' minus 'changes in obj_cgroup_charge_pages', attached mod.patch)
16f6bf266c94017c 58056f77502f3567b760c9a8fc8 ae12af515da0d557c25f86e89b0
---------------- --------------------------- ---------------------------
%stddev %change %stddev %change %stddev
\ | \ | \
124966 +8.8% 136017 ? 2% -0.1% 124791 ? 2% hackbench.throughput
...
5.41 ? 12% -5.4 0.00 +0.3 5.73 ? 13% perf-profile.calltrace.cycles-pp.page_counter_try_charge.obj_cgroup_charge_pages.obj_cgroup_charge.kmem_cache_alloc_node.__alloc_skb
detail comparison data as attached 16f6b-58056-ae12a
in brief, the result prove what we suspect. The original patch removed code
- !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {
which improved the hackbench throughput. Thanks.
> --
> Michal Hocko
> SUSE Labs