Greeting,
FYI, we noticed a 34.9% improvement of stress-ng.msg.ops_per_sec due to commit:
commit: 860d1bed91e88a3bbedb0a3a433a139e528514de ("io_uring: include cflags in completion trace event")
https://git.kernel.org/cgit/linux/kernel/git/axboe/linux-block.git for-5.13/io_uring
in testcase: stress-ng
on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 192G memory
with following parameters:
nr_threads: 10%
disk: 1HDD
testtime: 60s
fs: ext4
class: os
test: msg
cpufreq_governor: performance
ucode: 0x5003006
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp split-job --compatible job.yaml
bin/lkp run compatible-job.yaml
=========================================================================================
class/compiler/cpufreq_governor/disk/fs/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime/ucode:
os/gcc-9/performance/1HDD/ext4/x86_64-rhel-8.3/10%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp5/msg/stress-ng/60s/0x5003006
commit:
502f5faf89 ("io_uring: allocate memory for overflowed CQEs")
860d1bed91 ("io_uring: include cflags in completion trace event")
502f5faf89755be0 860d1bed91e88a3bbedb0a3a433
---------------- ---------------------------
%stddev %change %stddev
\ | \
2.281e+08 ? 2% +34.9% 3.078e+08 ? 5% stress-ng.msg.ops
3801919 ? 2% +34.9% 5129248 ? 5% stress-ng.msg.ops_per_sec
1701 ? 22% +36.5% 2322 ? 4% stress-ng.time.involuntary_context_switches
1614 +3.7% 1674 stress-ng.time.percent_of_cpu_this_job_got
984.43 +3.4% 1017 stress-ng.time.system_time
17.69 +22.4% 21.66 ? 5% stress-ng.time.user_time
24858803 ? 19% -90.9% 2269922 ? 74% stress-ng.time.voluntary_context_switches
0.31 +0.1 0.38 ? 4% mpstat.cpu.all.usr%
30195221 ? 23% -89.6% 3129791 ? 64% cpuidle.POLL.time
20499969 ? 22% -90.0% 2058412 ? 76% cpuidle.POLL.usage
83.25 -1.0% 82.45 iostat.cpu.idle
16.40 +4.5% 17.14 iostat.cpu.system
143262 ? 27% +106.6% 295999 ? 27% numa-numastat.node1.local_node
173213 ? 18% +84.6% 319734 ? 21% numa-numastat.node1.numa_hit
7460 ? 22% +30.7% 9754 ? 7% softirqs.CPU87.SCHED
13304 ? 20% -38.9% 8130 ? 29% softirqs.CPU90.SCHED
83.00 -1.2% 82.00 vmstat.cpu.id
765295 ? 20% -90.6% 71667 ? 72% vmstat.system.cs
234196 ? 2% -16.0% 196798 vmstat.system.in
13611 ? 11% +19.5% 16266 ? 9% slabinfo.kmalloc-512.active_objs
13735 ? 11% +19.3% 16391 ? 9% slabinfo.kmalloc-512.num_objs
58739 ? 7% +28.2% 75322 ? 9% slabinfo.kmalloc-64.active_objs
919.83 ? 7% +28.1% 1178 ? 9% slabinfo.kmalloc-64.active_slabs
58894 ? 7% +28.1% 75426 ? 9% slabinfo.kmalloc-64.num_objs
919.83 ? 7% +28.1% 1178 ? 9% slabinfo.kmalloc-64.num_slabs
2625583 ? 16% -90.6% 246762 ? 36% interrupts.CAL:Function_call_interrupts
54.00 ?133% -89.2% 5.83 ? 78% interrupts.CPU11.RES:Rescheduling_interrupts
23209 ? 91% -94.9% 1185 ?130% interrupts.CPU17.CAL:Function_call_interrupts
37330 ?129% -97.5% 931.67 ? 68% interrupts.CPU24.CAL:Function_call_interrupts
30468 ?128% -95.9% 1238 ? 75% interrupts.CPU36.CAL:Function_call_interrupts
202.00 ?180% -95.3% 9.50 ?109% interrupts.CPU42.RES:Rescheduling_interrupts
94.00 ? 36% +3739.4% 3609 ? 79% interrupts.CPU54.NMI:Non-maskable_interrupts
94.00 ? 36% +3739.4% 3609 ? 79% interrupts.CPU54.PMI:Performance_monitoring_interrupts
131.33 ? 21% +3245.1% 4393 ? 58% interrupts.CPU6.NMI:Non-maskable_interrupts
131.33 ? 21% +3245.1% 4393 ? 58% interrupts.CPU6.PMI:Performance_monitoring_interrupts
54748 ? 94% -98.9% 591.83 ? 20% interrupts.CPU93.CAL:Function_call_interrupts
13380 ? 14% -89.5% 1411 ? 24% interrupts.RES:Rescheduling_interrupts
3.549e+09 ? 2% +12.7% 3.998e+09 ? 5% perf-stat.i.branch-instructions
0.78 ? 4% -0.1 0.67 ? 4% perf-stat.i.branch-miss-rate%
26570992 ? 5% -9.0% 24189475 ? 4% perf-stat.i.branch-misses
791368 ? 19% -90.7% 73771 ? 72% perf-stat.i.context-switches
2.91 ? 2% -11.6% 2.57 ? 5% perf-stat.i.cpi
2.428e+09 ? 2% +8.7% 2.641e+09 ? 5% perf-stat.i.dTLB-stores
85.64 -3.4 82.28 perf-stat.i.iTLB-load-miss-rate%
15810507 ? 8% -28.3% 11341997 ? 5% perf-stat.i.iTLB-load-misses
1.729e+10 ? 2% +13.6% 1.963e+10 ? 5% perf-stat.i.instructions
1150 ? 9% +52.8% 1757 ? 4% perf-stat.i.instructions-per-iTLB-miss
0.35 +12.7% 0.40 ? 5% perf-stat.i.ipc
0.43 ? 38% +60.5% 0.69 ? 18% perf-stat.i.metric.K/sec
110.59 ? 2% +10.7% 122.43 ? 5% perf-stat.i.metric.M/sec
0.75 ? 4% -0.1 0.61 perf-stat.overall.branch-miss-rate%
2.93 ? 2% -12.1% 2.58 ? 5% perf-stat.overall.cpi
87.11 -3.7 83.41 perf-stat.overall.iTLB-load-miss-rate%
1102 ? 9% +57.2% 1733 ? 4% perf-stat.overall.instructions-per-iTLB-miss
0.34 ? 2% +14.0% 0.39 ? 5% perf-stat.overall.ipc
3.491e+09 ? 2% +12.7% 3.934e+09 ? 5% perf-stat.ps.branch-instructions
26142110 ? 5% -9.0% 23798599 ? 4% perf-stat.ps.branch-misses
778595 ? 19% -90.7% 72559 ? 72% perf-stat.ps.context-switches
2.389e+09 ? 2% +8.8% 2.598e+09 ? 5% perf-stat.ps.dTLB-stores
15556518 ? 8% -28.3% 11159416 ? 5% perf-stat.ps.iTLB-load-misses
1.701e+10 ? 2% +13.6% 1.932e+10 ? 5% perf-stat.ps.instructions
1.074e+12 ? 2% +13.9% 1.224e+12 ? 5% perf-stat.total.instructions
34.47 ? 3% -3.6 30.89 ? 7% perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
1.05 ? 10% -0.2 0.84 ? 7% perf-profile.calltrace.cycles-pp.menu_select.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
0.76 +0.4 1.13 ? 7% perf-profile.calltrace.cycles-pp.__radix_tree_lookup.sysvipc_find_ipc.seq_read_iter.seq_read.vfs_read
1.91 ? 12% +0.4 2.33 ? 2% perf-profile.calltrace.cycles-pp.kfree.free_msg.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.03 ? 2% +0.5 1.55 ? 5% perf-profile.calltrace.cycles-pp.sysvipc_find_ipc.seq_read_iter.seq_read.vfs_read.ksys_read
0.00 +0.5 0.55 ? 5% perf-profile.calltrace.cycles-pp._copy_from_user.load_msg.do_msgsnd.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.95 ? 14% +0.6 2.53 ? 14% perf-profile.calltrace.cycles-pp.do_msg_fill.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.24 ? 3% +0.6 1.84 ? 5% perf-profile.calltrace.cycles-pp.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.24 ? 3% +0.6 1.84 ? 5% perf-profile.calltrace.cycles-pp.seq_read_iter.seq_read.vfs_read.ksys_read.do_syscall_64
1.46 ? 17% +0.6 2.07 ? 19% perf-profile.calltrace.cycles-pp.store_msg.do_msg_fill.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.24 ? 3% +0.6 1.85 ? 5% perf-profile.calltrace.cycles-pp.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.24 ? 3% +0.6 1.84 ? 5% perf-profile.calltrace.cycles-pp.seq_read.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.18 ?141% +0.6 0.79 ? 18% perf-profile.calltrace.cycles-pp.__list_del_entry_valid.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.73 ? 9% +0.6 2.38 ? 12% perf-profile.calltrace.cycles-pp.ipc_obtain_object_check.do_msgsnd.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.00 +0.7 0.69 ? 9% perf-profile.calltrace.cycles-pp.get_obj_cgroup_from_current.__kmalloc.load_msg.do_msgsnd.do_syscall_64
2.49 ? 14% +1.2 3.73 ? 17% perf-profile.calltrace.cycles-pp.__kmalloc.load_msg.do_msgsnd.do_syscall_64.entry_SYSCALL_64_after_hwframe
3.45 ? 10% +1.6 5.05 ? 11% perf-profile.calltrace.cycles-pp.load_msg.do_msgsnd.do_syscall_64.entry_SYSCALL_64_after_hwframe
5.44 ? 3% +2.2 7.62 ? 5% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
5.52 ? 24% +2.9 8.44 ? 9% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.do_msgsnd.do_syscall_64.entry_SYSCALL_64_after_hwframe
29.00 ? 4% +2.9 31.94 ? 3% perf-profile.calltrace.cycles-pp.do_msgrcv.do_syscall_64.entry_SYSCALL_64_after_hwframe
34.47 ? 3% -3.6 30.89 ? 7% perf-profile.children.cycles-pp.secondary_startup_64_no_verify
34.47 ? 3% -3.6 30.89 ? 7% perf-profile.children.cycles-pp.cpu_startup_entry
34.46 ? 3% -3.6 30.89 ? 7% perf-profile.children.cycles-pp.do_idle
2.02 ? 28% -1.8 0.21 ? 76% perf-profile.children.cycles-pp.poll_idle
1.84 ? 25% -1.6 0.20 ? 89% perf-profile.children.cycles-pp.__schedule
1.15 ? 18% -1.0 0.12 ?102% perf-profile.children.cycles-pp.try_to_wake_up
1.23 ? 17% -1.0 0.20 ? 55% perf-profile.children.cycles-pp.wake_up_q
1.16 ? 28% -1.0 0.15 ? 90% perf-profile.children.cycles-pp.schedule
0.72 ? 22% -0.7 0.05 ?101% perf-profile.children.cycles-pp.schedule_idle
0.52 ? 23% -0.5 0.05 ?100% perf-profile.children.cycles-pp.wake_q_add
0.52 ? 31% -0.5 0.06 ?100% perf-profile.children.cycles-pp.dequeue_task_fair
0.46 ? 17% -0.4 0.04 ?100% perf-profile.children.cycles-pp.ttwu_do_activate
0.47 ? 31% -0.4 0.05 ?100% perf-profile.children.cycles-pp.dequeue_entity
0.45 ? 17% -0.4 0.04 ?100% perf-profile.children.cycles-pp.enqueue_task_fair
0.33 ? 16% -0.3 0.03 ? 99% perf-profile.children.cycles-pp.enqueue_entity
0.28 ? 40% -0.2 0.04 ?102% perf-profile.children.cycles-pp.ttwu_queue_wakelist
0.26 ? 19% -0.2 0.03 ? 99% perf-profile.children.cycles-pp.update_load_avg
0.26 ? 37% -0.2 0.04 ?101% perf-profile.children.cycles-pp.update_curr
1.06 ? 9% -0.2 0.84 ? 7% perf-profile.children.cycles-pp.menu_select
0.23 ? 18% -0.2 0.03 ?100% perf-profile.children.cycles-pp.update_rq_clock
0.20 ? 35% -0.2 0.03 ?100% perf-profile.children.cycles-pp.tick_nohz_idle_exit
0.18 ? 20% -0.1 0.04 ?100% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.16 ? 37% -0.1 0.03 ?100% perf-profile.children.cycles-pp.nr_iowait_cpu
0.15 ? 37% -0.1 0.03 ?100% perf-profile.children.cycles-pp.update_ts_time_stats
0.16 ? 20% -0.1 0.04 ? 73% perf-profile.children.cycles-pp.sched_clock
0.18 ? 19% -0.1 0.07 ? 22% perf-profile.children.cycles-pp.sched_clock_cpu
0.15 ? 22% -0.1 0.04 ? 72% perf-profile.children.cycles-pp.native_sched_clock
0.11 ? 13% -0.0 0.06 ? 6% perf-profile.children.cycles-pp.read_tsc
0.05 ? 7% +0.0 0.07 ? 5% perf-profile.children.cycles-pp.number
0.07 ? 14% +0.0 0.09 ? 12% perf-profile.children.cycles-pp.page_counter_cancel
0.07 ? 7% +0.0 0.09 ? 8% perf-profile.children.cycles-pp.format_decode
0.07 ? 12% +0.0 0.10 ? 9% perf-profile.children.cycles-pp.page_counter_try_charge
0.08 ? 11% +0.0 0.10 ? 6% perf-profile.children.cycles-pp.__memcg_kmem_charge
0.07 ? 5% +0.0 0.09 ? 7% perf-profile.children.cycles-pp.radix_tree_lookup
0.07 ? 14% +0.0 0.09 ? 8% perf-profile.children.cycles-pp.msgctl_stat
0.26 ? 4% +0.0 0.29 ? 3% perf-profile.children.cycles-pp.ksys_msgctl
0.11 ? 9% +0.0 0.14 ? 8% perf-profile.children.cycles-pp.syscall_enter_from_user_mode
0.09 ? 7% +0.0 0.12 ? 10% perf-profile.children.cycles-pp.rcu_read_unlock_strict
0.09 ? 14% +0.0 0.12 ? 5% perf-profile.children.cycles-pp.security_msg_msg_free
0.16 ? 8% +0.0 0.20 ? 7% perf-profile.children.cycles-pp.__virt_addr_valid
0.01 ?223% +0.0 0.05 ? 9% perf-profile.children.cycles-pp.security_ipc_permission
0.19 ? 9% +0.1 0.24 ? 9% perf-profile.children.cycles-pp.__put_user_nocheck_8
0.17 ? 4% +0.1 0.22 ? 8% perf-profile.children.cycles-pp.__might_sleep
0.17 ? 8% +0.1 0.22 ? 6% perf-profile.children.cycles-pp.obj_cgroup_charge
0.15 ? 5% +0.1 0.20 ? 8% perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack
0.12 ? 5% +0.1 0.18 ? 28% perf-profile.children.cycles-pp.__mod_memcg_state
0.20 ? 10% +0.1 0.27 ? 7% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string
0.26 ? 11% +0.1 0.32 ? 6% perf-profile.children.cycles-pp.___might_sleep
0.19 ? 6% +0.1 0.25 ? 4% perf-profile.children.cycles-pp.seq_printf
0.18 ? 7% +0.1 0.25 ? 5% perf-profile.children.cycles-pp.vsnprintf
0.18 ? 6% +0.1 0.25 ? 4% perf-profile.children.cycles-pp.seq_vprintf
0.19 ? 6% +0.1 0.27 ? 8% perf-profile.children.cycles-pp.__get_user_8
0.19 ? 5% +0.1 0.26 ? 4% perf-profile.children.cycles-pp.sysvipc_msg_proc_show
0.24 ? 6% +0.1 0.34 ? 11% perf-profile.children.cycles-pp.refill_obj_stock
0.44 ? 8% +0.1 0.53 ? 7% perf-profile.children.cycles-pp.__might_fault
0.24 ? 5% +0.1 0.33 ? 14% perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
0.39 ? 5% +0.1 0.51 ? 6% perf-profile.children.cycles-pp._copy_to_user
0.36 ? 5% +0.1 0.49 ? 5% perf-profile.children.cycles-pp.copy_user_generic_unrolled
0.38 ? 5% +0.1 0.53 ? 7% perf-profile.children.cycles-pp.ksys_msgsnd
0.41 ? 6% +0.1 0.56 ? 9% perf-profile.children.cycles-pp.__check_heap_object
0.36 ? 6% +0.2 0.52 ? 7% perf-profile.children.cycles-pp.__entry_text_start
0.40 ? 5% +0.2 0.56 ? 5% perf-profile.children.cycles-pp._copy_from_user
0.56 ? 3% +0.2 0.76 ? 6% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.44 ? 13% +0.2 0.65 ? 13% perf-profile.children.cycles-pp.idr_find
0.28 ? 9% +0.4 0.64 ? 29% perf-profile.children.cycles-pp.ipcperms
0.40 ? 26% +0.4 0.80 ? 18% perf-profile.children.cycles-pp.__list_del_entry_valid
0.26 ? 8% +0.4 0.70 ? 9% perf-profile.children.cycles-pp.get_obj_cgroup_from_current
1.98 ? 11% +0.4 2.43 ? 2% perf-profile.children.cycles-pp.kfree
1.12 ? 2% +0.5 1.64 ? 5% perf-profile.children.cycles-pp.__radix_tree_lookup
1.03 ? 2% +0.5 1.55 ? 5% perf-profile.children.cycles-pp.sysvipc_find_ipc
1.97 ? 14% +0.6 2.56 ? 14% perf-profile.children.cycles-pp.do_msg_fill
1.24 ? 3% +0.6 1.84 ? 5% perf-profile.children.cycles-pp.seq_read
1.37 ? 16% +0.6 1.98 ? 19% perf-profile.children.cycles-pp.__check_object_size
1.25 ? 3% +0.6 1.86 ? 5% perf-profile.children.cycles-pp.ksys_read
1.24 ? 3% +0.6 1.85 ? 5% perf-profile.children.cycles-pp.seq_read_iter
1.47 ? 17% +0.6 2.08 ? 19% perf-profile.children.cycles-pp.store_msg
1.25 ? 3% +0.6 1.86 ? 5% perf-profile.children.cycles-pp.vfs_read
2.55 ? 14% +1.3 3.81 ? 16% perf-profile.children.cycles-pp.__kmalloc
3.54 ? 11% +1.3 4.80 ? 13% perf-profile.children.cycles-pp.ipc_obtain_object_check
3.46 ? 10% +1.6 5.07 ? 12% perf-profile.children.cycles-pp.load_msg
29.06 ? 4% +2.9 31.99 ? 3% perf-profile.children.cycles-pp.do_msgrcv
11.01 ? 13% +5.1 16.12 ? 5% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
8.92 ? 14% -4.4 4.50 ? 13% perf-profile.self.cycles-pp._raw_spin_lock
13.59 ? 4% -2.0 11.61 ? 4% perf-profile.self.cycles-pp.do_msgsnd
1.93 ? 28% -1.7 0.20 ? 77% perf-profile.self.cycles-pp.poll_idle
0.52 ? 23% -0.5 0.05 ? 99% perf-profile.self.cycles-pp.wake_q_add
0.33 ? 25% -0.3 0.03 ?100% perf-profile.self.cycles-pp.__schedule
0.18 ? 22% -0.1 0.04 ?100% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.16 ? 37% -0.1 0.03 ?100% perf-profile.self.cycles-pp.nr_iowait_cpu
0.14 ? 20% -0.1 0.04 ? 72% perf-profile.self.cycles-pp.native_sched_clock
0.11 ? 11% -0.0 0.06 perf-profile.self.cycles-pp.read_tsc
0.16 ? 4% -0.0 0.13 ? 5% perf-profile.self.cycles-pp.msgctl_info
0.08 ? 8% +0.0 0.10 ? 8% perf-profile.self.cycles-pp.__might_fault
0.06 ? 9% +0.0 0.08 ? 10% perf-profile.self.cycles-pp.radix_tree_lookup
0.07 ? 7% +0.0 0.09 ? 7% perf-profile.self.cycles-pp.syscall_exit_to_user_mode
0.06 ? 8% +0.0 0.08 ? 8% perf-profile.self.cycles-pp._copy_from_user
0.05 ? 45% +0.0 0.07 ? 11% perf-profile.self.cycles-pp.drain_obj_stock
0.10 ? 9% +0.0 0.12 ? 10% perf-profile.self.cycles-pp.syscall_enter_from_user_mode
0.08 ? 7% +0.0 0.11 ? 7% perf-profile.self.cycles-pp.exit_to_user_mode_prepare
0.03 ? 70% +0.0 0.06 ? 7% perf-profile.self.cycles-pp.number
0.09 ? 12% +0.0 0.12 ? 7% perf-profile.self.cycles-pp.store_msg
0.05 ? 45% +0.0 0.08 ? 4% perf-profile.self.cycles-pp.ksys_msgsnd
0.11 ? 6% +0.0 0.14 ? 12% perf-profile.self.cycles-pp.__mod_memcg_lruvec_state
0.12 ? 13% +0.0 0.16 ? 8% perf-profile.self.cycles-pp.load_msg
0.02 ?141% +0.0 0.06 ? 11% perf-profile.self.cycles-pp.format_decode
0.13 ? 6% +0.0 0.18 ? 7% perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack
0.01 ?223% +0.0 0.06 ? 13% perf-profile.self.cycles-pp.vsnprintf
0.11 ? 10% +0.1 0.17 ? 12% perf-profile.self.cycles-pp.refill_obj_stock
0.00 +0.1 0.05 ? 9% perf-profile.self.cycles-pp.security_ipc_permission
0.15 ? 5% +0.1 0.21 ? 7% perf-profile.self.cycles-pp.__might_sleep
0.12 ? 5% +0.1 0.18 ? 28% perf-profile.self.cycles-pp.__mod_memcg_state
0.19 ? 9% +0.1 0.25 ? 7% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string
0.19 ? 5% +0.1 0.26 ? 8% perf-profile.self.cycles-pp.__get_user_8
0.25 ? 11% +0.1 0.32 ? 5% perf-profile.self.cycles-pp.___might_sleep
0.11 ? 10% +0.1 0.19 ? 9% perf-profile.self.cycles-pp.sysvipc_find_ipc
0.34 ? 6% +0.1 0.47 ? 5% perf-profile.self.cycles-pp.copy_user_generic_unrolled
0.40 ? 7% +0.1 0.54 ? 9% perf-profile.self.cycles-pp.__check_heap_object
0.36 ? 6% +0.2 0.52 ? 7% perf-profile.self.cycles-pp.__entry_text_start
0.56 ? 3% +0.2 0.76 ? 6% perf-profile.self.cycles-pp.syscall_return_via_sysret
0.43 ? 14% +0.2 0.64 ? 12% perf-profile.self.cycles-pp.idr_find
0.40 ? 25% +0.4 0.79 ? 18% perf-profile.self.cycles-pp.__list_del_entry_valid
0.24 ? 9% +0.4 0.65 ? 9% perf-profile.self.cycles-pp.get_obj_cgroup_from_current
1.06 ? 2% +0.5 1.55 ? 5% perf-profile.self.cycles-pp.__radix_tree_lookup
10.94 ? 13% +5.1 16.04 ? 5% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
stress-ng.time.voluntary_context_switches
4e+07 +-----------------------------------------------------------------+
| + + + + ++ + + +.+ + + +.+ |
3.5e+07 |-+ :+ :: : +. :: : : : :: : : :: : : : |
3e+07 |+.: + :: : + : + :: :: : : :: : : : : : : + |
|: + + :+ : : + + : .+ +.+ + + :+.+ : : + + :: |
2.5e+07 |-+ + +.: : + :: + :: :+: : +.+|
| + :: + : + :: :|
2e+07 |-+ + + + |
| |
1.5e+07 |-+ |
1e+07 |-+ |
| |
5e+06 |-+ O O O O O |
|O OO O O O O O O O O O OO O O O|
0 +-----------------------------------------------------------------+
stress-ng.msg.ops
3.4e+08 +-----------------------------------------------------------------+
| O O OO O O |
3.2e+08 |-+O O O O OO O OO O O |
|O O O |
3e+08 |-+ O O O OO O OO O|
| O O O O O O O O |
2.8e+08 |-+ O O O O O O O |
| O |
2.6e+08 |-+ |
| |
2.4e+08 |-+ .+ +. |
|+.+ .+ + +.++.++. + + .++.+++.+ + + .++.++ +.+++.+ + |
2.2e+08 |-+ + :+ + + + + + + :+ +. :+ +.+|
| + + + + + |
2e+08 +-----------------------------------------------------------------+
stress-ng.msg.ops_per_sec
5.5e+06 +-----------------------------------------------------------------+
| O O O O OO O OO O O |
|O O O O |
5e+06 |-+ O O O O O O OO O O O O|
| O O O O O O O O O O |
| OO |
4.5e+06 |-+ |
| |
4e+06 |-+ |
| .+ + +. +. + + +. +.+ + + .+ .++.+ .++ +. |
|+.++ :+ + ++.+ + + + + +.+ ++ :+ +. :+ + + +.+ ++. |
3.5e+06 |-+ + + + + + +|
| |
| |
3e+06 +-----------------------------------------------------------------+
[*] 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