From: kernel test robot <oliver.sang@intel.com>
To: Thomas Gleixner <tglx@kernel.org>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>,
<linux-kernel@vger.kernel.org>, <x86@kernel.org>,
Peter Zijlstra <peterz@infradead.org>, <oliver.sang@intel.com>
Subject: [tip:sched/hrtick] [x86/apic] 92d0e753d5: stress-ng.timermix.ops_per_sec 2.2% improvement
Date: Tue, 24 Mar 2026 21:52:45 +0800 [thread overview]
Message-ID: <202603242136.51c7f0d3-lkp@intel.com> (raw)
Hello,
kernel test robot noticed a 2.2% improvement of stress-ng.timermix.ops_per_sec on:
commit: 92d0e753d57ec581a424d9903afff5e17bd1e6e4 ("x86/apic: Remove pointless fence in lapic_next_deadline()")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git sched/hrtick
testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 192 threads 2 sockets Intel(R) Xeon(R) 6740E CPU @ 2.4GHz (Sierra Forest) with 256G memory
parameters:
nr_threads: 100%
testtime: 60s
test: timermix
cpufreq_governor: performance
In addition to that, the commit also has significant impact on the following tests:
+------------------+---------------------------------------------------------+
| testcase: change | stress-ng: stress-ng.timer.ops_per_sec 2.7% improvement |
| test parameters | cpufreq_governor=performance |
| | nr_threads=100% |
| | test=timer |
| | testtime=60s |
+------------------+---------------------------------------------------------+
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260324/202603242136.51c7f0d3-lkp@intel.com
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-srf-2sp3/timermix/stress-ng/60s
commit:
b27801189f ("x86: Inline TSC reads in timekeeping")
92d0e753d5 ("x86/apic: Remove pointless fence in lapic_next_deadline()")
b27801189f7fc97a 92d0e753d57ec581a424d9903af
---------------- ---------------------------
%stddev %change %stddev
\ | \
16781 +1.1% 16960 stress-ng.time.percent_of_cpu_this_job_got
4902 ± 2% -8.1% 4505 stress-ng.time.system_time
5186 ± 2% +9.7% 5688 stress-ng.time.user_time
113491 +2.2% 115938 stress-ng.timermix.CLOCK_BOOTTIME_ticks_per_sec
113612 +2.2% 116066 stress-ng.timermix.CLOCK_MONOTONIC_ticks_per_sec
113702 +2.2% 116160 stress-ng.timermix.CLOCK_REALTIME_ticks_per_sec
113456 +2.1% 115893 stress-ng.timermix.CLOCK_TAI_ticks_per_sec
5.245e+09 +2.2% 5.358e+09 stress-ng.timermix.ops
87449094 +2.2% 89334190 stress-ng.timermix.ops_per_sec
8989707 -6.2% 8429569 turbostat.NMI
81482294 +2.6% 83616517 vmstat.system.in
11.59 -0.9 10.71 mpstat.cpu.all.irq%
41.12 ± 2% -3.2 37.90 mpstat.cpu.all.sys%
43.83 ± 2% +4.3 48.17 mpstat.cpu.all.usr%
6.431e+10 +2.2% 6.576e+10 perf-stat.i.branch-instructions
1.78 -2.0% 1.74 perf-stat.i.cpi
3.393e+11 +2.1% 3.466e+11 perf-stat.i.instructions
0.56 +2.0% 0.57 perf-stat.i.ipc
1.78 -2.1% 1.74 perf-stat.overall.cpi
0.56 +2.1% 0.58 perf-stat.overall.ipc
6.239e+10 +1.8% 6.351e+10 perf-stat.ps.branch-instructions
3.292e+11 +1.7% 3.347e+11 perf-stat.ps.instructions
1.975e+13 +2.3% 2.022e+13 perf-stat.total.instructions
2.06 ± 20% -1.0 1.06 ± 19% perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal
2.68 ± 2% -0.9 1.79 perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt
3.71 ± 2% -0.8 2.94 perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
3.14 ± 10% -0.7 2.46 ± 3% perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal.get_signal
2.56 ± 12% -0.6 1.94 ± 9% perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigpending.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigpending
7.74 ± 2% -0.4 7.38 perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.62 ± 3% +0.1 0.68 perf-profile.calltrace.cycles-pp.sched_clock_cpu.irqtime_account_irq.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.58 ± 2% +0.1 0.64 perf-profile.calltrace.cycles-pp.irqtime_account_irq.__irq_exit_rcu.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.67 ± 3% +0.1 0.74 perf-profile.calltrace.cycles-pp.irqtime_account_irq.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.82 ± 2% +0.1 0.89 perf-profile.calltrace.cycles-pp.ktime_get_update_offsets_now.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
0.72 ± 2% +0.1 0.80 perf-profile.calltrace.cycles-pp.error_entry.sigpending
0.83 ± 3% +0.1 0.91 ± 2% perf-profile.calltrace.cycles-pp.sync_regs.asm_sysvec_apic_timer_interrupt.sigpending
0.75 ± 2% +0.1 0.84 ± 2% perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt
0.89 ± 2% +0.1 1.00 perf-profile.calltrace.cycles-pp.__irq_exit_rcu.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.98 ± 2% +0.1 1.09 ± 2% perf-profile.calltrace.cycles-pp.posixtimer_send_sigqueue.posix_timer_fn.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt
1.40 ± 2% +0.1 1.54 ± 2% perf-profile.calltrace.cycles-pp.posix_timer_fn.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt
1.74 ± 3% +0.2 1.89 perf-profile.calltrace.cycles-pp.native_apic_msr_eoi.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.sigpending
0.34 ± 70% +0.2 0.57 ± 2% perf-profile.calltrace.cycles-pp.sched_clock_cpu.irqtime_account_irq.__irq_exit_rcu.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
2.42 ± 2% +0.2 2.66 ± 2% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
0.26 ±100% +0.3 0.54 perf-profile.calltrace.cycles-pp.sched_clock.sched_clock_cpu.irqtime_account_irq.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
10.55 ± 8% +1.5 12.04 ± 4% perf-profile.calltrace.cycles-pp.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
6.10 -2.2 3.90 perf-profile.children.cycles-pp.lapic_next_deadline
7.71 ± 4% -1.8 5.89 perf-profile.children.cycles-pp.clockevents_program_event
8.53 ± 2% -0.8 7.69 perf-profile.children.cycles-pp.hrtimer_interrupt
10.93 ± 2% -0.8 10.14 perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
2.77 ± 13% -0.8 1.99 ± 10% perf-profile.children.cycles-pp.__x64_sys_rt_sigpending
4.98 ± 9% -0.7 4.26 perf-profile.children.cycles-pp.hrtimer_start_range_ns
12.98 ± 2% -0.7 12.26 perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
0.07 -0.0 0.06 perf-profile.children.cycles-pp.sched_clock_noinstr
0.08 ± 6% +0.0 0.09 perf-profile.children.cycles-pp.sched_core_idle_cpu
0.07 ± 6% +0.0 0.09 perf-profile.children.cycles-pp.x64_sys_call
0.42 +0.0 0.44 perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack
0.23 ± 3% +0.0 0.25 ± 2% perf-profile.children.cycles-pp.irqentry_exit
0.05 +0.0 0.07 ± 5% perf-profile.children.cycles-pp._raw_spin_unlock
1.09 ± 2% +0.0 1.12 perf-profile.children.cycles-pp.sched_clock
0.69 +0.0 0.72 perf-profile.children.cycles-pp._raw_spin_lock
0.93 ± 2% +0.0 0.96 perf-profile.children.cycles-pp.native_sched_clock
0.93 +0.0 0.97 perf-profile.children.cycles-pp.recalc_sigpending
0.83 ± 2% +0.0 0.88 perf-profile.children.cycles-pp.error_entry
1.24 ± 2% +0.0 1.29 perf-profile.children.cycles-pp.sched_clock_cpu
0.98 +0.0 1.03 perf-profile.children.cycles-pp.__irq_exit_rcu
1.08 ± 2% +0.1 1.13 perf-profile.children.cycles-pp.posixtimer_send_sigqueue
0.94 ± 2% +0.1 0.99 perf-profile.children.cycles-pp.__irqentry_text_end
1.64 +0.1 1.70 perf-profile.children.cycles-pp._raw_spin_lock_irq
1.37 ± 2% +0.1 1.42 perf-profile.children.cycles-pp.irqtime_account_irq
1.46 +0.1 1.52 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
1.52 ± 2% +0.1 1.59 perf-profile.children.cycles-pp.posix_timer_fn
0.83 ± 3% +0.1 0.92 perf-profile.children.cycles-pp.sync_regs
2.69 ± 2% +0.1 2.80 perf-profile.children.cycles-pp.__hrtimer_run_queues
2.22 +0.1 2.34 perf-profile.children.cycles-pp.ktime_get
2.27 +0.1 2.40 ± 2% perf-profile.children.cycles-pp.entry_SYSCALL_64
9.40 +0.3 9.66 ± 2% perf-profile.children.cycles-pp.__restore_fpregs_from_user
9.53 ± 8% +0.9 10.46 ± 2% perf-profile.children.cycles-pp.restore_fpregs_from_user
12.03 ± 8% +1.1 13.13 ± 2% perf-profile.children.cycles-pp.fpu__restore_sig
13.87 ± 7% +1.2 15.09 ± 2% perf-profile.children.cycles-pp.restore_sigcontext
6.09 -2.2 3.90 perf-profile.self.cycles-pp.lapic_next_deadline
0.31 ± 19% -0.2 0.16 ± 11% perf-profile.self.cycles-pp.__x64_sys_rt_sigpending
0.65 ± 4% -0.1 0.54 ± 2% perf-profile.self.cycles-pp.do_syscall_64
0.26 -0.0 0.23 ± 2% perf-profile.self.cycles-pp.__x64_sys_rt_sigreturn
0.16 ± 2% -0.0 0.15 perf-profile.self.cycles-pp.hrtimer_start_range_ns
0.06 -0.0 0.05 perf-profile.self.cycles-pp.get_nohz_timer_target
0.05 +0.0 0.06 perf-profile.self.cycles-pp.hrtimer_reprogram
0.07 +0.0 0.08 perf-profile.self.cycles-pp.x64_sys_call
0.27 ± 2% +0.0 0.28 perf-profile.self.cycles-pp.hrtimer_interrupt
0.08 ± 6% +0.0 0.09 perf-profile.self.cycles-pp.sched_core_idle_cpu
0.11 ± 4% +0.0 0.13 perf-profile.self.cycles-pp.__hrtimer_start_range_ns
0.12 ± 4% +0.0 0.14 ± 3% perf-profile.self.cycles-pp.irqtime_account_irq
0.20 ± 3% +0.0 0.22 ± 4% perf-profile.self.cycles-pp._raw_spin_unlock_irq
0.45 ± 2% +0.0 0.48 perf-profile.self.cycles-pp.posixtimer_deliver_signal
0.92 +0.0 0.95 perf-profile.self.cycles-pp.recalc_sigpending
0.55 ± 2% +0.0 0.58 perf-profile.self.cycles-pp.get_signal
0.91 ± 2% +0.0 0.96 perf-profile.self.cycles-pp.native_sched_clock
1.64 +0.0 1.68 perf-profile.self.cycles-pp._raw_spin_lock_irq
0.83 ± 2% +0.0 0.88 perf-profile.self.cycles-pp.error_entry
0.00 +0.1 0.05 perf-profile.self.cycles-pp.sigismember
1.59 +0.1 1.64 perf-profile.self.cycles-pp.entry_SYSCALL_64
1.45 +0.1 1.51 perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.92 ± 2% +0.1 0.98 perf-profile.self.cycles-pp.__irqentry_text_end
0.82 ± 2% +0.1 0.91 perf-profile.self.cycles-pp.sync_regs
2.21 +0.1 2.33 perf-profile.self.cycles-pp.ktime_get
1.10 ± 2% +0.1 1.23 ± 2% perf-profile.self.cycles-pp.stress_timermix_timer_action
9.40 +0.3 9.66 ± 2% perf-profile.self.cycles-pp.__restore_fpregs_from_user
6.10 ± 3% +0.5 6.58 perf-profile.self.cycles-pp.sigpending
***************************************************************************************************
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-srf-2sp3/timer/stress-ng/60s
commit:
b27801189f ("x86: Inline TSC reads in timekeeping")
92d0e753d5 ("x86/apic: Remove pointless fence in lapic_next_deadline()")
b27801189f7fc97a 92d0e753d57ec581a424d9903af
---------------- ---------------------------
%stddev %change %stddev
\ | \
16799 +1.1% 16987 stress-ng.time.percent_of_cpu_this_job_got
9917 +1.7% 10087 stress-ng.time.system_time
180.39 ± 10% -31.6% 123.46 ± 7% stress-ng.time.user_time
5.305e+09 +2.7% 5.445e+09 stress-ng.timer.ops
88451716 +2.7% 90801513 stress-ng.timer.ops_per_sec
8993987 -6.3% 8425030 turbostat.NMI
83170419 +2.4% 85130223 vmstat.system.in
11.56 -1.0 10.54 mpstat.cpu.all.irq%
1.84 ± 9% -0.5 1.35 ± 5% mpstat.cpu.all.usr%
6.867e+10 +2.6% 7.044e+10 perf-stat.i.branch-instructions
1.006e+08 +3.7% 1.044e+08 perf-stat.i.branch-misses
1.67 -2.4% 1.63 perf-stat.i.cpi
3.611e+11 +2.5% 3.701e+11 perf-stat.i.instructions
0.60 +2.5% 0.61 perf-stat.i.ipc
1.67 -2.5% 1.63 perf-stat.overall.cpi
0.60 +2.5% 0.61 perf-stat.overall.ipc
6.676e+10 +2.1% 6.817e+10 perf-stat.ps.branch-instructions
97272637 +3.2% 1.004e+08 perf-stat.ps.branch-misses
3.51e+11 +2.0% 3.581e+11 perf-stat.ps.instructions
18.58 ± 4% -5.6 13.03 perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
10.18 ± 4% -3.3 6.86 perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
8.59 ± 4% -2.9 5.71 perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.do_syscall_64.entry_SYSCALL_64_after_hwframe
6.76 ± 3% -2.4 4.32 ± 2% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.do_syscall_64
2.98 -1.2 1.83 perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal
4.13 -1.1 3.04 perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal.get_signal
5.35 -1.1 4.30 perf-profile.calltrace.cycles-pp.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal.get_signal.arch_do_signal_or_restart
7.97 ± 2% -1.0 7.01 perf-profile.calltrace.cycles-pp.posixtimer_deliver_signal.dequeue_signal.get_signal.arch_do_signal_or_restart.exit_to_user_mode_loop
8.55 ± 2% -0.9 7.66 perf-profile.calltrace.cycles-pp.dequeue_signal.get_signal.arch_do_signal_or_restart.exit_to_user_mode_loop.do_syscall_64
9.57 ± 2% -0.9 8.70 perf-profile.calltrace.cycles-pp.get_signal.arch_do_signal_or_restart.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.38 ± 3% -0.8 1.55 perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt
3.28 ± 3% -0.7 2.55 perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
1.48 ± 5% -0.4 1.12 perf-profile.calltrace.cycles-pp.native_apic_msr_eoi.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.do_syscall_64
0.98 ± 4% -0.3 0.72 perf-profile.calltrace.cycles-pp.posixtimer_send_sigqueue.posix_timer_fn.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt
0.74 ± 2% -0.2 0.54 ± 2% perf-profile.calltrace.cycles-pp.__irq_exit_rcu.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.74 ± 4% -0.2 0.57 ± 2% perf-profile.calltrace.cycles-pp.ktime_get_update_offsets_now.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
0.75 ± 3% -0.0 0.70 perf-profile.calltrace.cycles-pp.__put_user_nocheck_4.copy_fpstate_to_sigframe.get_sigframe.x64_setup_rt_frame.arch_do_signal_or_restart
0.79 ± 3% -0.0 0.74 perf-profile.calltrace.cycles-pp.__put_user_nocheck_8.copy_fpstate_to_sigframe.get_sigframe.x64_setup_rt_frame.arch_do_signal_or_restart
0.84 +0.0 0.89 perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_start_range_ns.posixtimer_deliver_signal.dequeue_signal
0.93 ± 2% +0.0 0.98 perf-profile.calltrace.cycles-pp._copy_to_user.__x64_sys_rt_sigpending.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigpending
0.76 ± 2% +0.1 0.81 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64.timer_getoverrun
1.09 ± 2% +0.1 1.14 perf-profile.calltrace.cycles-pp._copy_from_user.restore_altstack.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.88 ± 2% +0.1 0.93 perf-profile.calltrace.cycles-pp.ktime_get.common_hrtimer_rearm.posixtimer_deliver_signal.dequeue_signal.get_signal
0.61 ± 3% +0.1 0.68 perf-profile.calltrace.cycles-pp.x64_sys_call.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
1.39 ± 2% +0.1 1.47 perf-profile.calltrace.cycles-pp.restore_altstack.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.63 ± 2% +0.1 1.72 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigpending.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigpending
0.93 ± 3% +0.1 1.02 ± 2% perf-profile.calltrace.cycles-pp.__get_user_nocheck_4.check_xstate_in_sigframe.__fpu_restore_sig.fpu__restore_sig.restore_sigcontext
1.32 ± 2% +0.1 1.43 perf-profile.calltrace.cycles-pp.common_hrtimer_rearm.posixtimer_deliver_signal.dequeue_signal.get_signal.arch_do_signal_or_restart
1.60 ± 2% +0.1 1.70 perf-profile.calltrace.cycles-pp._copy_from_user.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.26 ± 2% +0.1 2.38 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigpending
2.28 ± 3% +0.1 2.40 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64.stress_timer_handler
2.45 ± 2% +0.1 2.58 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.sigpending
0.62 ± 5% +0.2 0.77 perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.hash_bucket
2.07 ± 3% +0.2 2.26 perf-profile.calltrace.cycles-pp.__get_user_nocheck_8.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
2.00 ± 4% +0.2 2.20 perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
2.17 ± 3% +0.2 2.38 perf-profile.calltrace.cycles-pp.check_xstate_in_sigframe.__fpu_restore_sig.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn
2.27 ± 3% +0.2 2.50 perf-profile.calltrace.cycles-pp.__fpu_restore_sig.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64
0.79 ± 5% +0.2 1.02 perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.hash_bucket.lock_timer
0.93 ± 5% +0.3 1.23 perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.hash_bucket.lock_timer.__x64_sys_timer_getoverrun
1.42 ± 4% +0.4 1.82 perf-profile.calltrace.cycles-pp.hash_bucket.lock_timer.__x64_sys_timer_getoverrun.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.11 ±200% +0.5 0.60 perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.x64_sys_call.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
0.00 +0.6 0.57 ± 2% perf-profile.calltrace.cycles-pp.native_apic_msr_eoi.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.lock_timer
8.61 ± 2% +0.7 9.34 perf-profile.calltrace.cycles-pp.__restore_fpregs_from_user.restore_fpregs_from_user.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn
12.21 ± 3% +0.8 13.02 perf-profile.calltrace.cycles-pp.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
9.57 ± 2% +0.8 10.39 perf-profile.calltrace.cycles-pp.restore_fpregs_from_user.fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64
1.34 ± 5% +1.0 2.36 perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.hash_bucket.lock_timer.__x64_sys_timer_getoverrun.do_syscall_64
14.00 ± 2% +1.2 15.18 perf-profile.calltrace.cycles-pp.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.90 ± 5% +1.2 2.11 ± 2% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.lock_timer
18.73 ± 2% +1.5 20.20 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.16 ± 5% +1.7 2.84 ± 2% perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.lock_timer.__x64_sys_timer_getoverrun
1.37 ± 5% +2.0 3.41 ± 2% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.lock_timer.__x64_sys_timer_getoverrun.do_syscall_64
4.18 ± 2% +4.0 8.14 perf-profile.calltrace.cycles-pp.lock_timer.__x64_sys_timer_getoverrun.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
2.51 ± 3% +4.1 6.58 ± 2% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.lock_timer.__x64_sys_timer_getoverrun.do_syscall_64.entry_SYSCALL_64_after_hwframe
4.94 ± 2% +4.6 9.50 perf-profile.calltrace.cycles-pp.__x64_sys_timer_getoverrun.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_getoverrun
6.48 -2.5 3.98 perf-profile.children.cycles-pp.lapic_next_deadline
8.64 -2.4 6.24 perf-profile.children.cycles-pp.clockevents_program_event
41.55 -1.4 40.12 perf-profile.children.cycles-pp.arch_do_signal_or_restart
41.69 -1.4 40.26 perf-profile.children.cycles-pp.exit_to_user_mode_loop
5.68 -1.2 4.45 perf-profile.children.cycles-pp.hrtimer_start_range_ns
8.48 -1.2 7.28 perf-profile.children.cycles-pp.posixtimer_deliver_signal
9.09 -1.2 7.92 perf-profile.children.cycles-pp.dequeue_signal
10.15 -1.2 8.99 perf-profile.children.cycles-pp.get_signal
8.70 ± 3% -1.0 7.72 perf-profile.children.cycles-pp.hrtimer_interrupt
11.08 ± 3% -0.8 10.26 perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
13.08 ± 3% -0.8 12.30 perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
87.49 -0.5 86.98 perf-profile.children.cycles-pp.do_syscall_64
88.02 -0.5 87.54 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
0.19 ± 3% -0.0 0.17 ± 2% perf-profile.children.cycles-pp.clockevents_program_min_delta
0.72 -0.0 0.70 perf-profile.children.cycles-pp.__local_bh_enable_ip
0.05 +0.0 0.06 perf-profile.children.cycles-pp._raw_spin_unlock
0.05 +0.0 0.06 perf-profile.children.cycles-pp.sched_clock_noinstr
0.63 +0.0 0.66 perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack
0.19 ± 2% +0.0 0.22 perf-profile.children.cycles-pp.syscall_return_via_sysret
0.78 ± 3% +0.0 0.82 ± 2% perf-profile.children.cycles-pp.set_current_blocked
0.72 ± 2% +0.0 0.76 perf-profile.children.cycles-pp.recalc_sigpending
1.06 ± 2% +0.1 1.12 perf-profile.children.cycles-pp._copy_to_user
1.41 ± 2% +0.1 1.48 perf-profile.children.cycles-pp.restore_altstack
1.13 ± 2% +0.1 1.21 perf-profile.children.cycles-pp.__get_user_nocheck_4
2.04 +0.1 2.12 perf-profile.children.cycles-pp._raw_spin_lock_irq
1.65 ± 2% +0.1 1.74 perf-profile.children.cycles-pp.__x64_sys_rt_sigpending
2.73 +0.1 2.84 perf-profile.children.cycles-pp.ktime_get
0.83 ± 3% +0.1 0.96 perf-profile.children.cycles-pp.x64_sys_call
2.43 +0.1 2.56 perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack
2.80 ± 2% +0.1 2.94 perf-profile.children.cycles-pp._copy_from_user
2.32 ± 2% +0.2 2.49 perf-profile.children.cycles-pp.check_xstate_in_sigframe
2.41 ± 2% +0.2 2.59 perf-profile.children.cycles-pp.__fpu_restore_sig
3.85 ± 2% +0.2 4.03 perf-profile.children.cycles-pp.entry_SYSCALL_64
5.05 +0.2 5.24 perf-profile.children.cycles-pp.native_irq_return_iret
0.22 +0.3 0.49 ± 5% perf-profile.children.cycles-pp._raw_spin_unlock_irq
9.31 +0.5 9.85 perf-profile.children.cycles-pp.__restore_fpregs_from_user
1.77 ± 4% +0.6 2.34 perf-profile.children.cycles-pp.hash_bucket
10.17 +0.6 10.75 perf-profile.children.cycles-pp.restore_fpregs_from_user
12.72 ± 2% +0.7 13.47 perf-profile.children.cycles-pp.fpu__restore_sig
14.75 ± 2% +0.9 15.62 perf-profile.children.cycles-pp.restore_sigcontext
19.52 ± 2% +1.2 20.73 perf-profile.children.cycles-pp.__x64_sys_rt_sigreturn
4.71 ± 2% +4.3 9.00 perf-profile.children.cycles-pp.lock_timer
4.99 ± 2% +4.6 9.55 perf-profile.children.cycles-pp.__x64_sys_timer_getoverrun
6.45 -2.5 3.97 perf-profile.self.cycles-pp.lapic_next_deadline
4.78 ± 4% -1.0 3.75 perf-profile.self.cycles-pp.do_syscall_64
0.06 -0.0 0.05 perf-profile.self.cycles-pp.restore_regs_and_return_to_kernel
0.05 +0.0 0.06 perf-profile.self.cycles-pp.hrtimer_reprogram
0.14 +0.0 0.15 ± 2% perf-profile.self.cycles-pp.exit_to_user_mode_loop
0.40 +0.0 0.42 perf-profile.self.cycles-pp.hrtimer_forward
0.26 ± 3% +0.0 0.28 perf-profile.self.cycles-pp.__irq_exit_rcu
0.48 +0.0 0.50 perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack
0.24 ± 2% +0.0 0.26 perf-profile.self.cycles-pp.__x64_sys_rt_sigreturn
0.47 +0.0 0.50 perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.33 ± 3% +0.0 0.36 perf-profile.self.cycles-pp.x64_sys_call
0.19 ± 2% +0.0 0.22 perf-profile.self.cycles-pp.syscall_return_via_sysret
1.61 +0.0 1.65 perf-profile.self.cycles-pp.get_sigframe
0.71 ± 2% +0.0 0.74 perf-profile.self.cycles-pp.recalc_sigpending
1.06 ± 2% +0.1 1.12 perf-profile.self.cycles-pp._copy_to_user
2.01 +0.1 2.08 perf-profile.self.cycles-pp._raw_spin_lock_irq
1.21 ± 2% +0.1 1.28 perf-profile.self.cycles-pp.check_xstate_in_sigframe
1.12 ± 2% +0.1 1.21 perf-profile.self.cycles-pp.__get_user_nocheck_4
0.22 +0.1 0.31 ± 2% perf-profile.self.cycles-pp._raw_spin_unlock_irq
2.72 +0.1 2.83 perf-profile.self.cycles-pp.ktime_get
2.43 +0.1 2.54 perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
2.39 +0.1 2.51 perf-profile.self.cycles-pp.entry_SYSCALL_64
0.59 ± 4% +0.2 0.75 perf-profile.self.cycles-pp.hash_bucket
2.78 ± 2% +0.2 2.94 perf-profile.self.cycles-pp._copy_from_user
5.03 +0.2 5.22 perf-profile.self.cycles-pp.native_irq_return_iret
9.31 +0.5 9.85 perf-profile.self.cycles-pp.__restore_fpregs_from_user
0.89 +1.0 1.88 ± 2% perf-profile.self.cycles-pp.lock_timer
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.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
reply other threads:[~2026-03-24 13:53 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=202603242136.51c7f0d3-lkp@intel.com \
--to=oliver.sang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@intel.com \
--cc=oe-lkp@lists.linux.dev \
--cc=peterz@infradead.org \
--cc=tglx@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox