From: kernel test robot <oliver.sang@intel.com>
To: Mel Gorman <mgorman@techsingularity.net>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>,
<linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Madadi Vineeth Reddy <vineethr@linux.ibm.com>,
<aubrey.li@linux.intel.com>, <yu.c.chen@intel.com>,
<oliver.sang@intel.com>
Subject: [linus:master] [sched/fair] 4f70f106bc: netperf.Throughput_Mbps 8.5% improvement
Date: Sat, 31 Jan 2026 21:29:46 +0800 [thread overview]
Message-ID: <202601312046.dea2a8bf-lkp@intel.com> (raw)
Hello,
kernel test robot noticed a 8.5% improvement of netperf.Throughput_Mbps on:
commit: 4f70f106bca1a56bd66d00830ac91680bd754974 ("sched/fair: Disable scheduler feature NEXT_BUDDY")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
testcase: netperf
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:
ip: ipv4
runtime: 300s
nr_threads: 200%
cluster: cs-localhost
test: TCP_STREAM
cpufreq_governor: performance
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260131/202601312046.dea2a8bf-lkp@intel.com
=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
cs-localhost/gcc-14/performance/ipv4/x86_64-rhel-9.4/200%/debian-13-x86_64-20250902.cgz/300s/lkp-srf-2sp3/TCP_STREAM/netperf
commit:
98c88dc8a1 ("sched/fair: Fix pelt clock sync when entering idle")
4f70f106bc ("sched/fair: Disable scheduler feature NEXT_BUDDY")
98c88dc8a1ace642 4f70f106bca1a56bd66d00830ac
---------------- ---------------------------
%stddev %change %stddev
\ | \
0.94 ± 2% +0.1 1.08 ± 2% mpstat.cpu.all.usr%
1546 ± 11% +30.3% 2015 ± 6% perf-c2c.HITM.local
91440 ± 2% +8.3% 99068 ± 3% vmstat.system.cs
0.08 ± 44% +33.3% 0.10 turbostat.IPC
338.84 ± 44% +21.4% 411.43 turbostat.PkgWatt
6.134e+08 +9.1% 6.692e+08 numa-numastat.node0.local_node
6.135e+08 +9.1% 6.693e+08 numa-numastat.node0.numa_hit
6.189e+08 +7.2% 6.637e+08 numa-numastat.node1.local_node
6.19e+08 +7.2% 6.638e+08 numa-numastat.node1.numa_hit
6.135e+08 +9.1% 6.692e+08 numa-vmstat.node0.numa_hit
6.134e+08 +9.1% 6.692e+08 numa-vmstat.node0.numa_local
6.19e+08 +7.2% 6.637e+08 numa-vmstat.node1.numa_hit
6.189e+08 +7.2% 6.636e+08 numa-vmstat.node1.numa_local
2244672 +6.4% 2388374 meminfo.Active
2244656 +6.4% 2388358 meminfo.Active(anon)
2608934 +5.6% 2756130 meminfo.Committed_AS
11862311 -10.9% 10566854 meminfo.Memused
1269914 +10.9% 1408300 ± 2% meminfo.Shmem
12102805 -12.0% 10644904 meminfo.max_used_kB
561006 +6.4% 597080 proc-vmstat.nr_active_anon
1235403 +2.8% 1270160 proc-vmstat.nr_file_pages
317342 +11.0% 352098 ± 2% proc-vmstat.nr_shmem
561006 +6.4% 597080 proc-vmstat.nr_zone_active_anon
1.232e+09 +8.2% 1.333e+09 proc-vmstat.numa_hit
1.232e+09 +8.2% 1.333e+09 proc-vmstat.numa_local
9.843e+09 +8.2% 1.065e+10 proc-vmstat.pgalloc_normal
9.842e+09 +8.2% 1.064e+10 proc-vmstat.pgfree
2799 +8.5% 3038 netperf.ThroughputBoth_Mbps
1075104 +8.5% 1166788 netperf.ThroughputBoth_total_Mbps
2799 +8.5% 3038 netperf.Throughput_Mbps
1075104 +8.5% 1166788 netperf.Throughput_total_Mbps
5393466 -16.6% 4498332 ± 3% netperf.time.involuntary_context_switches
8777 -2.3% 8573 netperf.time.percent_of_cpu_this_job_got
26432 -2.6% 25744 netperf.time.system_time
241.24 +18.7% 286.46 netperf.time.user_time
7798392 +29.3% 10081565 netperf.time.voluntary_context_switches
2.461e+09 +8.5% 2.671e+09 netperf.workload
5.81 -19.1% 4.70 perf-sched.sch_delay.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
32.01 ± 7% +3062.1% 1012 ± 63% perf-sched.sch_delay.max.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
5.81 -19.1% 4.70 perf-sched.total_sch_delay.average.ms
32.01 ± 7% +3062.1% 1012 ± 63% perf-sched.total_sch_delay.max.ms
17.05 -14.0% 14.67 ± 2% perf-sched.total_wait_and_delay.average.ms
432781 ± 2% +21.2% 524343 ± 5% perf-sched.total_wait_and_delay.count.ms
11.24 -11.3% 9.97 ± 2% perf-sched.total_wait_time.average.ms
17.05 -14.0% 14.67 ± 2% perf-sched.wait_and_delay.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
432781 ± 2% +21.2% 524343 ± 5% perf-sched.wait_and_delay.count.[unknown].[unknown].[unknown].[unknown].[unknown]
11.24 -11.3% 9.97 ± 2% perf-sched.wait_time.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
3.02 -8.1% 2.78 sched_debug.cfs_rq:/.h_nr_runnable.avg
5.44 ± 5% -7.1% 5.06 ± 2% sched_debug.cfs_rq:/.h_nr_runnable.max
0.84 ± 2% -13.6% 0.73 ± 2% sched_debug.cfs_rq:/.h_nr_runnable.stddev
3077 -8.3% 2822 sched_debug.cfs_rq:/.runnable_avg.avg
5181 ± 2% -11.2% 4602 ± 5% sched_debug.cfs_rq:/.runnable_avg.max
713.34 ± 3% -19.0% 577.80 ± 2% sched_debug.cfs_rq:/.runnable_avg.stddev
1907 ± 2% -5.6% 1801 ± 2% sched_debug.cfs_rq:/.util_est.avg
633.28 ± 4% -8.6% 578.69 ± 3% sched_debug.cfs_rq:/.util_est.stddev
791240 -8.3% 725705 ± 2% sched_debug.cpu.avg_idle.avg
247015 ± 3% +10.0% 271600 ± 2% sched_debug.cpu.avg_idle.stddev
130423 ± 10% +26.9% 165570 ± 7% sched_debug.cpu.nr_switches.max
8579 ± 36% +69.3% 14527 ± 21% sched_debug.cpu.nr_switches.stddev
51.90 -12.1% 45.62 perf-stat.i.MPKI
1.103e+10 +9.8% 1.211e+10 perf-stat.i.branch-instructions
0.32 -0.0 0.29 perf-stat.i.branch-miss-rate%
62.97 -6.4 56.58 perf-stat.i.cache-miss-rate%
2.908e+09 -3.0% 2.821e+09 perf-stat.i.cache-misses
4.614e+09 +8.0% 4.981e+09 perf-stat.i.cache-references
89826 ± 2% +7.6% 96633 ± 3% perf-stat.i.context-switches
10.89 -9.4% 9.86 perf-stat.i.cpi
211.22 +3.0% 217.51 perf-stat.i.cycles-between-cache-misses
5.591e+10 +10.3% 6.167e+10 perf-stat.i.instructions
0.10 +9.8% 0.11 perf-stat.i.ipc
52.02 -12.1% 45.75 perf-stat.overall.MPKI
0.32 -0.0 0.29 perf-stat.overall.branch-miss-rate%
63.04 -6.4 56.63 perf-stat.overall.cache-miss-rate%
10.91 -9.4% 9.89 perf-stat.overall.cpi
209.70 +3.1% 216.12 perf-stat.overall.cycles-between-cache-misses
0.09 +10.3% 0.10 perf-stat.overall.ipc
6872 +1.5% 6973 perf-stat.overall.path-length
1.096e+10 +9.8% 1.204e+10 perf-stat.ps.branch-instructions
2.892e+09 -3.0% 2.805e+09 perf-stat.ps.cache-misses
4.587e+09 +8.0% 4.953e+09 perf-stat.ps.cache-references
89124 ± 2% +7.5% 95840 ± 2% perf-stat.ps.context-switches
5.558e+10 +10.3% 6.132e+10 perf-stat.ps.instructions
1.691e+13 +10.1% 1.862e+13 perf-stat.total.instructions
9.28 -2.3 6.96 ± 2% perf-profile.calltrace.cycles-pp.free_pcppages_bulk.free_frozen_page_commit.__free_frozen_pages.skb_release_data.skb_attempt_defer_free
9.46 -2.3 7.14 ± 2% perf-profile.calltrace.cycles-pp.free_frozen_page_commit.__free_frozen_pages.skb_release_data.skb_attempt_defer_free.tcp_recvmsg_locked
8.78 -2.3 6.50 ± 2% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.free_pcppages_bulk.free_frozen_page_commit.__free_frozen_pages
8.81 -2.3 6.54 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.free_pcppages_bulk.free_frozen_page_commit.__free_frozen_pages.skb_release_data
10.82 -2.2 8.65 ± 2% perf-profile.calltrace.cycles-pp.skb_attempt_defer_free.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.sock_recvmsg
10.81 -2.2 8.65 ± 2% perf-profile.calltrace.cycles-pp.skb_release_data.skb_attempt_defer_free.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg
10.46 -2.1 8.32 ± 2% perf-profile.calltrace.cycles-pp.__free_frozen_pages.skb_release_data.skb_attempt_defer_free.tcp_recvmsg_locked.tcp_recvmsg
9.36 -2.1 7.25 ± 3% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.rmqueue_bulk.__rmqueue_pcplist.rmqueue
9.86 -2.1 7.74 ± 2% perf-profile.calltrace.cycles-pp.rmqueue_bulk.__rmqueue_pcplist.rmqueue.get_page_from_freelist.__alloc_frozen_pages_noprof
9.87 -2.1 7.76 ± 2% perf-profile.calltrace.cycles-pp.__rmqueue_pcplist.rmqueue.get_page_from_freelist.__alloc_frozen_pages_noprof.alloc_pages_mpol
9.40 -2.1 7.29 ± 3% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.rmqueue_bulk.__rmqueue_pcplist.rmqueue.get_page_from_freelist
9.95 -2.1 7.85 ± 2% perf-profile.calltrace.cycles-pp.rmqueue.get_page_from_freelist.__alloc_frozen_pages_noprof.alloc_pages_mpol.alloc_pages_noprof
10.56 -2.1 8.50 ± 2% perf-profile.calltrace.cycles-pp.alloc_pages_noprof.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg
10.53 -2.1 8.48 ± 2% perf-profile.calltrace.cycles-pp.__alloc_frozen_pages_noprof.alloc_pages_mpol.alloc_pages_noprof.skb_page_frag_refill.sk_page_frag_refill
10.54 -2.0 8.49 ± 2% perf-profile.calltrace.cycles-pp.alloc_pages_mpol.alloc_pages_noprof.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked
10.47 -2.0 8.42 ± 2% perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_frozen_pages_noprof.alloc_pages_mpol.alloc_pages_noprof.skb_page_frag_refill
10.71 -1.9 8.78 ± 2% perf-profile.calltrace.cycles-pp.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
10.71 -1.9 8.80 ± 2% perf-profile.calltrace.cycles-pp.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
28.86 -0.7 28.20 perf-profile.calltrace.cycles-pp._copy_from_iter.skb_do_copy_data_nocache.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
1.02 ± 14% -0.7 0.36 ±103% perf-profile.calltrace.cycles-pp.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.tcp_recvmsg_locked.tcp_recvmsg
1.01 ± 14% -0.7 0.36 ±103% perf-profile.calltrace.cycles-pp.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.tcp_recvmsg_locked
1.00 ± 14% -0.6 0.35 ±103% perf-profile.calltrace.cycles-pp.check_heap_object.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter
29.17 -0.6 28.53 perf-profile.calltrace.cycles-pp.skb_do_copy_data_nocache.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
47.34 -0.6 46.70 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.send_omni_inner.send_tcp_stream.main
47.36 -0.6 46.73 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.send_omni_inner.send_tcp_stream.main
47.22 -0.6 46.61 perf-profile.calltrace.cycles-pp.tcp_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe
46.89 -0.6 46.30 perf-profile.calltrace.cycles-pp.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64
47.45 -0.6 46.87 perf-profile.calltrace.cycles-pp.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.send_omni_inner.send_tcp_stream
47.44 -0.6 46.87 perf-profile.calltrace.cycles-pp.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.send_omni_inner
1.99 ± 2% -0.5 1.46 ± 7% perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked
1.99 ± 2% -0.5 1.46 ± 7% perf-profile.calltrace.cycles-pp.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked.tcp_recvmsg
1.99 ± 2% -0.5 1.46 ± 7% perf-profile.calltrace.cycles-pp.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg
1.86 ± 2% -0.4 1.45 ± 7% perf-profile.calltrace.cycles-pp.__tcp_transmit_skb.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.sock_recvmsg
3.02 -0.3 2.73 ± 9% perf-profile.calltrace.cycles-pp.ip_local_deliver_finish.ip_local_deliver.__netif_receive_skb_one_core.process_backlog.__napi_poll
3.02 -0.3 2.73 ± 9% perf-profile.calltrace.cycles-pp.ip_local_deliver.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action
3.00 ± 2% -0.3 2.72 ± 9% perf-profile.calltrace.cycles-pp.tcp_v4_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.ip_local_deliver.__netif_receive_skb_one_core
3.01 -0.3 2.73 ± 9% perf-profile.calltrace.cycles-pp.ip_protocol_deliver_rcu.ip_local_deliver_finish.ip_local_deliver.__netif_receive_skb_one_core.process_backlog
2.76 -0.2 2.52 ± 10% perf-profile.calltrace.cycles-pp.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish
3.54 ± 2% -0.2 3.32 ± 3% perf-profile.calltrace.cycles-pp.net_rx_action.handle_softirqs.do_softirq.__local_bh_enable_ip.__dev_queue_xmit
3.58 ± 2% -0.2 3.39 ± 3% perf-profile.calltrace.cycles-pp.handle_softirqs.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2
3.59 ± 2% -0.2 3.40 ± 3% perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.ip_output
3.09 -0.2 2.90 ± 3% perf-profile.calltrace.cycles-pp.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action.handle_softirqs
3.12 ± 2% -0.2 2.94 ± 4% perf-profile.calltrace.cycles-pp.__napi_poll.net_rx_action.handle_softirqs.do_softirq.__local_bh_enable_ip
3.11 -0.2 2.94 ± 4% perf-profile.calltrace.cycles-pp.process_backlog.__napi_poll.net_rx_action.handle_softirqs.do_softirq
0.64 -0.1 0.57 perf-profile.calltrace.cycles-pp.__alloc_skb.tcp_stream_alloc_skb.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
0.74 -0.0 0.70 perf-profile.calltrace.cycles-pp.tcp_stream_alloc_skb.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
3.52 +0.3 3.80 ± 3% perf-profile.calltrace.cycles-pp.__dev_queue_xmit.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb
0.68 ± 3% +0.4 1.07 ± 6% perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.tcp_try_rmem_schedule.tcp_data_queue.tcp_rcv_established
0.68 ± 3% +0.4 1.07 ± 6% perf-profile.calltrace.cycles-pp.__sk_mem_schedule.tcp_try_rmem_schedule.tcp_data_queue.tcp_rcv_established.tcp_v4_do_rcv
0.68 ± 3% +0.4 1.07 ± 6% perf-profile.calltrace.cycles-pp.tcp_try_rmem_schedule.tcp_data_queue.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv
0.17 ±141% +0.4 0.57 perf-profile.calltrace.cycles-pp.__tcp_push_pending_frames.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
0.73 ± 3% +0.4 1.17 ± 5% perf-profile.calltrace.cycles-pp.tcp_data_queue.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv.ip_protocol_deliver_rcu
0.00 +0.5 0.54 perf-profile.calltrace.cycles-pp.tcp_write_xmit.__tcp_push_pending_frames.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
0.17 ±141% +0.6 0.74 ± 8% perf-profile.calltrace.cycles-pp.mem_cgroup_sk_charge.__sk_mem_raise_allocated.__sk_mem_schedule.tcp_try_rmem_schedule.tcp_data_queue
0.09 ±223% +0.6 0.73 ± 8% perf-profile.calltrace.cycles-pp.try_charge_memcg.mem_cgroup_sk_charge.__sk_mem_raise_allocated.__sk_mem_schedule.tcp_try_rmem_schedule
51.15 +0.7 51.82 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.recv_omni.process_requests.spawn_child
50.99 +0.7 51.66 perf-profile.calltrace.cycles-pp.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64
50.99 +0.7 51.66 perf-profile.calltrace.cycles-pp.tcp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom
51.00 +0.7 51.68 perf-profile.calltrace.cycles-pp.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe
51.05 +0.7 51.74 perf-profile.calltrace.cycles-pp.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recv_omni
51.05 +0.7 51.74 perf-profile.calltrace.cycles-pp.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recv_omni.process_requests
2.08 +0.8 2.84 ± 3% perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.tcp_wmem_schedule.tcp_sendmsg_locked.tcp_sendmsg
2.09 +0.8 2.86 ± 3% perf-profile.calltrace.cycles-pp.__sk_mem_schedule.tcp_wmem_schedule.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
2.10 +0.8 2.87 ± 3% perf-profile.calltrace.cycles-pp.tcp_wmem_schedule.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
1.56 ± 2% +0.8 2.39 ± 2% perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit
1.57 ± 2% +0.8 2.41 ± 3% perf-profile.calltrace.cycles-pp.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked
50.68 +0.8 51.52 perf-profile.calltrace.cycles-pp.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
1.60 ± 2% +0.8 2.44 ± 2% perf-profile.calltrace.cycles-pp.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg
2.00 ± 2% +1.0 2.98 ± 2% perf-profile.calltrace.cycles-pp.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto
2.21 ± 2% +1.1 3.28 ± 2% perf-profile.calltrace.cycles-pp.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg.__sys_sendto.__x64_sys_sendto
36.33 +3.7 39.99 perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.sock_recvmsg
36.32 +3.7 39.99 perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg
34.51 +3.9 38.37 perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.tcp_recvmsg_locked.tcp_recvmsg
18.51 -4.6 13.93 ± 2% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
18.65 -4.6 14.10 ± 2% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
9.70 -2.5 7.24 ± 2% perf-profile.children.cycles-pp.free_frozen_page_commit
9.52 -2.5 7.06 ± 2% perf-profile.children.cycles-pp.free_pcppages_bulk
11.30 -2.4 8.89 ± 2% perf-profile.children.cycles-pp.skb_release_data
10.75 -2.3 8.45 ± 2% perf-profile.children.cycles-pp.__free_frozen_pages
10.82 -2.2 8.65 ± 2% perf-profile.children.cycles-pp.skb_attempt_defer_free
10.00 -2.2 7.85 ± 2% perf-profile.children.cycles-pp.__rmqueue_pcplist
9.99 -2.2 7.83 ± 2% perf-profile.children.cycles-pp.rmqueue_bulk
10.08 -2.1 7.94 ± 2% perf-profile.children.cycles-pp.rmqueue
10.62 -2.1 8.52 ± 2% perf-profile.children.cycles-pp.get_page_from_freelist
10.68 -2.1 8.58 ± 2% perf-profile.children.cycles-pp.__alloc_frozen_pages_noprof
10.69 -2.1 8.59 ± 2% perf-profile.children.cycles-pp.alloc_pages_mpol
10.69 -2.1 8.59 ± 2% perf-profile.children.cycles-pp.alloc_pages_noprof
10.84 -2.0 8.87 ± 2% perf-profile.children.cycles-pp.skb_page_frag_refill
10.85 -2.0 8.89 ± 2% perf-profile.children.cycles-pp.sk_page_frag_refill
29.32 -0.9 28.47 perf-profile.children.cycles-pp._copy_from_iter
29.53 -0.8 28.71 perf-profile.children.cycles-pp.skb_do_copy_data_nocache
47.58 -0.8 46.79 perf-profile.children.cycles-pp.tcp_sendmsg
47.81 -0.8 47.04 perf-profile.children.cycles-pp.__x64_sys_sendto
47.80 -0.8 47.04 perf-profile.children.cycles-pp.__sys_sendto
47.26 -0.8 46.50 perf-profile.children.cycles-pp.tcp_sendmsg_locked
48.33 -0.7 47.62 perf-profile.children.cycles-pp.send_omni_inner
1.58 ± 4% -0.7 0.88 ± 3% perf-profile.children.cycles-pp.__tcp_push_pending_frames
48.18 -0.6 47.60 perf-profile.children.cycles-pp.send_tcp_stream
3.21 ± 2% -0.3 2.92 ± 3% perf-profile.children.cycles-pp.tcp_rcv_established
3.28 ± 2% -0.3 2.99 ± 3% perf-profile.children.cycles-pp.tcp_v4_do_rcv
0.38 ± 5% -0.3 0.11 ± 9% perf-profile.children.cycles-pp.validate_xmit_skb
0.36 ± 5% -0.3 0.09 ± 7% perf-profile.children.cycles-pp.__skb_gso_segment
0.36 ± 5% -0.3 0.09 ± 9% perf-profile.children.cycles-pp.inet_gso_segment
0.36 ± 5% -0.3 0.09 ± 7% perf-profile.children.cycles-pp.skb_mac_gso_segment
0.34 ± 5% -0.3 0.08 ± 8% perf-profile.children.cycles-pp.skb_segment
0.35 ± 5% -0.3 0.09 ± 12% perf-profile.children.cycles-pp.tcp_gso_segment
0.43 ± 9% -0.2 0.22 ± 8% perf-profile.children.cycles-pp.__release_sock
0.49 ± 8% -0.2 0.28 ± 6% perf-profile.children.cycles-pp.release_sock
1.08 -0.2 0.88 perf-profile.children.cycles-pp.simple_copy_to_iter
1.21 -0.2 1.03 perf-profile.children.cycles-pp.check_heap_object
1.24 -0.2 1.07 perf-profile.children.cycles-pp.__check_object_size
0.32 ± 12% -0.2 0.15 ± 19% perf-profile.children.cycles-pp.napi_consume_skb
0.77 -0.1 0.62 perf-profile.children.cycles-pp.__alloc_skb
0.52 -0.1 0.37 perf-profile.children.cycles-pp.kmem_cache_free
0.20 ± 3% -0.1 0.11 perf-profile.children.cycles-pp.kmem_cache_alloc_node_noprof
0.54 ± 6% -0.1 0.45 ± 6% perf-profile.children.cycles-pp.skb_defer_free_flush
0.31 -0.1 0.23 perf-profile.children.cycles-pp.__slab_free
0.13 ± 3% -0.1 0.06 ± 9% perf-profile.children.cycles-pp.kmalloc_reserve
0.16 ± 4% -0.1 0.09 ± 4% perf-profile.children.cycles-pp.__kfree_skb
0.76 -0.1 0.70 perf-profile.children.cycles-pp.tcp_stream_alloc_skb
0.09 ± 8% -0.1 0.03 ± 70% perf-profile.children.cycles-pp.__irq_exit_rcu
0.14 ± 2% -0.1 0.09 perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
0.45 -0.1 0.40 perf-profile.children.cycles-pp.__free_one_page
0.26 ± 2% -0.0 0.22 ± 2% perf-profile.children.cycles-pp.sock_rfree
0.11 ± 4% -0.0 0.08 ± 6% perf-profile.children.cycles-pp.exit_to_user_mode_loop
0.18 ± 2% -0.0 0.16 ± 3% perf-profile.children.cycles-pp.skb_clone
0.18 ± 2% -0.0 0.16 ± 3% perf-profile.children.cycles-pp.prep_new_page
0.07 +0.0 0.08 perf-profile.children.cycles-pp.__inet_lookup_skb
0.07 +0.0 0.08 perf-profile.children.cycles-pp.lock_sock_nested
0.09 +0.0 0.10 perf-profile.children.cycles-pp.entry_SYSCALL_64
0.07 ± 6% +0.0 0.08 ± 5% perf-profile.children.cycles-pp.arch_exit_to_user_mode_prepare
0.06 +0.0 0.07 ± 5% perf-profile.children.cycles-pp.__inet_lookup_established
0.07 +0.0 0.08 ± 5% perf-profile.children.cycles-pp.__mod_timer
0.11 +0.0 0.13 ± 3% perf-profile.children.cycles-pp._raw_spin_lock_bh
0.07 ± 8% +0.0 0.09 ± 4% perf-profile.children.cycles-pp.tcp_check_space
0.28 +0.0 0.30 perf-profile.children.cycles-pp.__del_page_from_free_list
0.10 +0.0 0.12 perf-profile.children.cycles-pp.read_tsc
0.07 +0.0 0.09 perf-profile.children.cycles-pp._find_next_bit
0.06 +0.0 0.08 perf-profile.children.cycles-pp.rb_erase
0.07 +0.0 0.09 perf-profile.children.cycles-pp.sk_reset_timer
0.12 +0.0 0.14 perf-profile.children.cycles-pp.__virt_addr_valid
0.18 ± 2% +0.0 0.20 ± 2% perf-profile.children.cycles-pp.fdget
0.15 ± 3% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.__zone_watermark_ok
0.37 ± 3% +0.0 0.40 perf-profile.children.cycles-pp.hrtimer_interrupt
0.16 ± 3% +0.0 0.18 ± 2% perf-profile.children.cycles-pp.kfree_skbmem
0.21 ± 3% +0.0 0.24 perf-profile.children.cycles-pp.ktime_get
0.05 +0.0 0.08 perf-profile.children.cycles-pp.tcp_rbtree_insert
0.17 ± 2% +0.0 0.20 ± 2% perf-profile.children.cycles-pp.__schedule
0.08 ± 4% +0.0 0.11 ± 3% perf-profile.children.cycles-pp.sk_stream_wait_memory
0.18 ± 2% +0.0 0.21 ± 2% perf-profile.children.cycles-pp.schedule
0.00 +0.1 0.05 perf-profile.children.cycles-pp.irqtime_account_irq
0.00 +0.1 0.05 perf-profile.children.cycles-pp.sk_stream_write_space
0.12 ± 3% +0.1 0.18 ± 2% perf-profile.children.cycles-pp.tcp_event_new_data_sent
0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.sock_def_readable
0.00 +0.1 0.06 ± 6% perf-profile.children.cycles-pp.sk_wait_data
0.00 +0.1 0.07 perf-profile.children.cycles-pp.try_to_wake_up
0.07 +0.1 0.15 ± 3% perf-profile.children.cycles-pp.schedule_timeout
0.07 ± 5% +0.1 0.15 ± 2% perf-profile.children.cycles-pp.wait_woken
0.00 +0.1 0.08 perf-profile.children.cycles-pp.__wake_up_common
0.96 +0.1 1.10 ± 3% perf-profile.children.cycles-pp.tcp_clean_rtx_queue
1.02 +0.1 1.17 ± 3% perf-profile.children.cycles-pp.tcp_ack
0.77 ± 2% +0.2 0.95 ± 7% perf-profile.children.cycles-pp.__sk_mem_reduce_allocated
0.59 ± 3% +0.2 0.78 ± 8% perf-profile.children.cycles-pp.refill_stock
0.58 ± 3% +0.2 0.77 ± 8% perf-profile.children.cycles-pp.drain_stock
0.85 ± 3% +0.2 1.05 ± 8% perf-profile.children.cycles-pp.page_counter_try_charge
0.91 ± 3% +0.3 1.17 ± 6% perf-profile.children.cycles-pp.tcp_try_rmem_schedule
1.00 ± 2% +0.3 1.31 ± 5% perf-profile.children.cycles-pp.tcp_data_queue
3.81 +0.4 4.17 perf-profile.children.cycles-pp.tcp_write_xmit
51.25 +0.7 51.92 perf-profile.children.cycles-pp.process_requests
51.25 +0.7 51.92 perf-profile.children.cycles-pp.recv_omni
51.25 +0.7 51.92 perf-profile.children.cycles-pp.spawn_child
50.99 +0.7 51.67 perf-profile.children.cycles-pp.tcp_recvmsg
51.00 +0.7 51.68 perf-profile.children.cycles-pp.inet_recvmsg
51.00 +0.7 51.68 perf-profile.children.cycles-pp.sock_recvmsg
51.06 +0.7 51.74 perf-profile.children.cycles-pp.__x64_sys_recvfrom
51.05 +0.7 51.74 perf-profile.children.cycles-pp.__sys_recvfrom
2.13 +0.8 2.89 ± 4% perf-profile.children.cycles-pp.tcp_wmem_schedule
50.68 +0.8 51.53 perf-profile.children.cycles-pp.tcp_recvmsg_locked
3.10 +1.0 4.14 ± 4% perf-profile.children.cycles-pp.__sk_mem_schedule
3.09 +1.0 4.13 ± 4% perf-profile.children.cycles-pp.__sk_mem_raise_allocated
36.33 +3.7 39.99 perf-profile.children.cycles-pp.__skb_datagram_iter
36.33 +3.7 40.00 perf-profile.children.cycles-pp.skb_copy_datagram_iter
34.73 +3.9 38.65 perf-profile.children.cycles-pp._copy_to_iter
18.51 -4.6 13.93 ± 2% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
29.20 -0.9 28.34 perf-profile.self.cycles-pp._copy_from_iter
1.06 -0.2 0.87 perf-profile.self.cycles-pp.check_heap_object
0.31 -0.1 0.22 ± 2% perf-profile.self.cycles-pp.__slab_free
0.32 -0.1 0.26 perf-profile.self.cycles-pp.tcp_write_xmit
0.41 -0.1 0.35 perf-profile.self.cycles-pp.__free_one_page
0.51 -0.1 0.46 perf-profile.self.cycles-pp.__skb_datagram_iter
0.53 -0.0 0.48 perf-profile.self.cycles-pp.__alloc_skb
0.13 ± 3% -0.0 0.08 perf-profile.self.cycles-pp.kmem_cache_alloc_node_noprof
0.17 ± 2% -0.0 0.13 ± 2% perf-profile.self.cycles-pp.kmem_cache_free
0.26 ± 2% -0.0 0.22 perf-profile.self.cycles-pp.sock_rfree
0.18 ± 2% -0.0 0.15 ± 2% perf-profile.self.cycles-pp.skb_clone
0.17 ± 2% -0.0 0.15 ± 2% perf-profile.self.cycles-pp.prep_new_page
0.07 +0.0 0.08 perf-profile.self.cycles-pp.__sys_sendto
0.11 +0.0 0.12 perf-profile.self.cycles-pp.send_omni_inner
0.06 +0.0 0.07 perf-profile.self.cycles-pp.__inet_lookup_established
0.09 +0.0 0.10 perf-profile.self.cycles-pp.entry_SYSCALL_64
0.09 +0.0 0.10 perf-profile.self.cycles-pp.read_tsc
0.06 +0.0 0.07 perf-profile.self.cycles-pp.rmqueue
0.13 +0.0 0.14 ± 3% perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
0.11 +0.0 0.12 ± 4% perf-profile.self.cycles-pp._raw_spin_lock_bh
0.12 ± 5% +0.0 0.14 ± 2% perf-profile.self.cycles-pp.ktime_get
0.28 +0.0 0.30 perf-profile.self.cycles-pp.__del_page_from_free_list
0.17 ± 2% +0.0 0.19 perf-profile.self.cycles-pp.fdget
0.07 +0.0 0.09 perf-profile.self.cycles-pp._find_next_bit
0.06 +0.0 0.08 perf-profile.self.cycles-pp.rb_erase
0.12 +0.0 0.14 perf-profile.self.cycles-pp.__virt_addr_valid
0.15 ± 3% +0.0 0.17 perf-profile.self.cycles-pp.__zone_watermark_ok
0.16 ± 3% +0.0 0.18 ± 2% perf-profile.self.cycles-pp.kfree_skbmem
0.11 +0.0 0.13 ± 2% perf-profile.self.cycles-pp.free_frozen_page_commit
0.06 +0.0 0.09 ± 5% perf-profile.self.cycles-pp.__sk_mem_reduce_allocated
0.28 +0.0 0.31 ± 2% perf-profile.self.cycles-pp.tcp_recvmsg_locked
0.05 +0.0 0.08 perf-profile.self.cycles-pp.tcp_rbtree_insert
0.14 ± 3% +0.0 0.17 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.21 ± 2% +0.0 0.25 perf-profile.self.cycles-pp.get_page_from_freelist
0.41 +0.0 0.44 perf-profile.self.cycles-pp.__tcp_transmit_skb
0.00 +0.1 0.05 perf-profile.self.cycles-pp.__check_object_size
0.00 +0.1 0.05 perf-profile.self.cycles-pp.ip_finish_output2
0.15 +0.1 0.20 perf-profile.self.cycles-pp.skb_defer_free_flush
0.28 +0.1 0.35 perf-profile.self.cycles-pp.tcp_clean_rtx_queue
0.37 ± 2% +0.1 0.44 ± 3% perf-profile.self.cycles-pp.__dev_queue_xmit
1.11 +0.1 1.23 perf-profile.self.cycles-pp.tcp_sendmsg_locked
0.14 ± 3% +0.1 0.28 perf-profile.self.cycles-pp.skb_page_frag_refill
1.00 +0.2 1.16 perf-profile.self.cycles-pp.__free_frozen_pages
0.84 ± 3% +0.2 1.04 ± 8% perf-profile.self.cycles-pp.page_counter_try_charge
1.38 +0.8 2.15 ± 3% perf-profile.self.cycles-pp.__sk_mem_raise_allocated
34.57 +3.9 38.47 perf-profile.self.cycles-pp._copy_to_iter
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:[~2026-01-31 13:30 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=202601312046.dea2a8bf-lkp@intel.com \
--to=oliver.sang@intel.com \
--cc=aubrey.li@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@intel.com \
--cc=mgorman@techsingularity.net \
--cc=oe-lkp@lists.linux.dev \
--cc=peterz@infradead.org \
--cc=vineethr@linux.ibm.com \
--cc=yu.c.chen@intel.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.