All of lore.kernel.org
 help / color / mirror / Atom feed
* [anolis-intel-cloud:devel-6.6] [sched/core]  2bbba4ed1a: hackbench.throughput 16.5% improvement
@ 2025-03-28  9:29 kernel test robot
  0 siblings, 0 replies; only message in thread
From: kernel test robot @ 2025-03-28  9:29 UTC (permalink / raw)
  To: aubrey.li; +Cc: oe-lkp, lkp, oliver.sang



Hello,

kernel test robot noticed a 16.5% improvement of hackbench.throughput on:


commit: 2bbba4ed1af8762acb6a4609428e5e68cbad9e1c ("sched/core: Prioritize migrating eligible tasks in sched_balance_rq()")
https://gitee.com/anolis/intel-cloud-kernel.git devel-6.6

testcase: hackbench
config: x86_64-anolis-intel-cloud-devel-6.6
compiler: gcc-12
test machine: 240 threads 1 sockets Genuine Intel(R) 0000 (Granite Rapids) with 192G memory
parameters:

	nr_threads: 100%
	iterations: 8
	mode: threads
	ipc: socket
	cpufreq_governor: performance



Details are as below:
-------------------------------------------------------------------------------------------------->


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250328/202503281610.cdaf2597-lkp@intel.com

=========================================================================================
compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase:
  gcc-12/performance/socket/8/x86_64-anolis-intel-cloud-devel-6.6/threads/100%/debian-12-x86_64-20240206.cgz/lkp-gnr-1ap1/hackbench

commit: 
  3b40c40b07 ("sched/fair: Fix update_cfs_group() vs DELAY_DEQUEUE")
  2bbba4ed1a ("sched/core: Prioritize migrating eligible tasks in sched_balance_rq()")

3b40c40b074ad510 2bbba4ed1af8762acb6a4609428 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      1101 ±  2%     -12.2%     966.93 ±  2%  uptime.boot
      0.74 ±  8%      +0.1        0.88 ±  7%  mpstat.cpu.all.idle%
      1.32 ±  2%      +0.2        1.53 ±  2%  mpstat.cpu.all.usr%
   3481937 ±  3%     +23.0%    4284294 ±  3%  vmstat.system.cs
    283458            +2.4%     290255        vmstat.system.in
   3379331            -3.2%    3269587        proc-vmstat.numa_hit
   3379263            -3.2%    3269586        proc-vmstat.numa_local
   5014552            -4.0%    4814510        proc-vmstat.pgalloc_normal
   2106380            -6.6%    1967239        proc-vmstat.pgfault
   3994058 ±  2%      -5.5%    3775204 ±  2%  proc-vmstat.pgfree
     77964 ±  2%      -9.9%      70219 ±  3%  proc-vmstat.pgreuse
    258987           +16.5%     301667        hackbench.throughput
    241051 ±  3%     +16.7%     281381 ±  3%  hackbench.throughput_avg
    258987           +16.5%     301667        hackbench.throughput_best
    221205 ±  6%     +18.3%     261772 ±  4%  hackbench.throughput_worst
    939.56 ±  3%     -14.3%     805.44 ±  3%  hackbench.time.elapsed_time
    939.56 ±  3%     -14.3%     805.44 ±  3%  hackbench.time.elapsed_time.max
    221035 ±  3%     -14.6%     188843 ±  3%  hackbench.time.system_time
    112.62 ±124%     -81.1%      21.30 ± 45%  perf-sched.sch_delay.avg.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
    777.68 ±177%     -87.3%      98.64 ± 32%  perf-sched.sch_delay.max.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
    225.24 ±124%     -94.8%      11.79 ±223%  perf-sched.wait_and_delay.avg.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
     15.83 ± 48%     -84.2%       2.50 ±223%  perf-sched.wait_and_delay.count.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
      1555 ±177%     -97.3%      41.66 ±223%  perf-sched.wait_and_delay.max.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
    112.62 ±124%     -81.1%      21.30 ± 45%  perf-sched.wait_time.avg.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
    777.68 ±177%     -87.3%      98.64 ± 32%  perf-sched.wait_time.max.ms.__cond_resched.__alloc_pages.__folio_alloc.vma_alloc_folio.shmem_alloc_folio
     31301 ± 10%     +17.2%      36678 ±  3%  sched_debug.cpu.avg_idle.min
    612334 ±  3%      -9.9%     552008 ±  2%  sched_debug.cpu.clock.avg
    614558 ±  3%      -9.8%     554156 ±  2%  sched_debug.cpu.clock.max
    610102 ±  3%      -9.9%     549882 ±  2%  sched_debug.cpu.clock.min
    611822 ±  3%      -9.9%     551531 ±  2%  sched_debug.cpu.clock_task.avg
    614099 ±  3%      -9.8%     553724 ±  2%  sched_debug.cpu.clock_task.max
    598998 ±  3%     -10.1%     538796 ±  2%  sched_debug.cpu.clock_task.min
    610092 ±  3%      -9.9%     549870 ±  2%  sched_debug.cpu_clk
    609212 ±  3%      -9.9%     548990 ±  2%  sched_debug.ktime
    611296 ±  3%      -9.9%     551072 ±  2%  sched_debug.sched_clk
      0.06 ±  3%      +8.0%       0.07 ±  3%  perf-stat.i.MPKI
 3.949e+10           +10.6%  4.367e+10        perf-stat.i.branch-instructions
      0.32            +0.0        0.35        perf-stat.i.branch-miss-rate%
 1.301e+08 ±  2%     +17.1%  1.523e+08        perf-stat.i.branch-misses
      1.51 ±  3%      +0.1        1.59 ±  3%  perf-stat.i.cache-miss-rate%
  11308788 ±  2%     +18.8%   13432573 ±  4%  perf-stat.i.cache-misses
 7.608e+08 ±  3%     +13.5%  8.638e+08 ±  3%  perf-stat.i.cache-references
   3487968 ±  3%     +22.8%    4283449 ±  3%  perf-stat.i.context-switches
      4.55 ±  3%     -12.7%       3.97 ±  3%  perf-stat.i.cpi
     52450 ±  2%     +27.0%      66632 ±  2%  perf-stat.i.cpu-migrations
     97825 ±  4%     -20.7%      77540 ±  6%  perf-stat.i.cycles-between-cache-misses
 1.914e+11           +11.7%  2.137e+11        perf-stat.i.instructions
      0.24 ±  2%     +11.7%       0.27        perf-stat.i.ipc
     14.61 ±  3%     +22.8%      17.94 ±  3%  perf-stat.i.metric.K/sec
      2247 ±  2%      +8.5%       2437        perf-stat.i.minor-faults
      2247 ±  2%      +8.5%       2437        perf-stat.i.page-faults
      0.33            +0.0        0.35        perf-stat.overall.branch-miss-rate%
      4.26 ±  2%     -10.6%       3.81        perf-stat.overall.cpi
     70448 ±  2%     -15.2%      59748 ±  5%  perf-stat.overall.cycles-between-cache-misses
      0.23 ±  2%     +11.9%       0.26        perf-stat.overall.ipc
 3.916e+10           +10.6%  4.332e+10        perf-stat.ps.branch-instructions
 1.282e+08 ±  2%     +17.2%  1.503e+08        perf-stat.ps.branch-misses
  11480788 ±  2%     +18.0%   13549830 ±  5%  perf-stat.ps.cache-misses
 7.498e+08 ±  3%     +13.6%  8.515e+08 ±  3%  perf-stat.ps.cache-references
   3423024 ±  3%     +23.1%    4214009 ±  3%  perf-stat.ps.context-switches
     50182 ±  2%     +27.4%      63951        perf-stat.ps.cpu-migrations
 1.896e+11 ±  2%     +11.7%  2.119e+11        perf-stat.ps.instructions
      2096 ±  2%      +8.5%       2274        perf-stat.ps.minor-faults
      2096 ±  2%      +8.5%       2274        perf-stat.ps.page-faults
 1.783e+14            -4.2%  1.708e+14        perf-stat.total.instructions
     38.54            -0.8       37.76        perf-profile.calltrace.cycles-pp.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write.do_syscall_64
     38.86            -0.6       38.24        perf-profile.calltrace.cycles-pp.sock_write_iter.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe
      0.80 ± 21%      +0.3        1.12 ±  9%  perf-profile.calltrace.cycles-pp.__kmem_cache_free.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg
      0.94 ± 26%      +0.4        1.31 ± 13%  perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.unix_stream_read_actor.unix_stream_read_generic
      0.19 ±142%      +0.5        0.66 ± 11%  perf-profile.calltrace.cycles-pp.skb_copy_datagram_from_iter.unix_stream_sendmsg.sock_write_iter.vfs_write.ksys_write
      0.24 ±146%      +0.5        0.76 ± 17%  perf-profile.calltrace.cycles-pp.__slab_free.skb_release_data.consume_skb.unix_stream_read_generic.unix_stream_recvmsg
      1.86 ± 18%      +0.5        2.39 ±  8%  perf-profile.calltrace.cycles-pp.kmem_cache_free.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter
      0.36 ±107%      +0.5        0.90 ± 27%  perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic
      0.38 ±106%      +0.6        0.94 ± 26%  perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg
      0.39 ±107%      +0.6        0.98 ± 26%  perf-profile.calltrace.cycles-pp.schedule_timeout.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg
      0.57 ± 81%      +0.6        1.18 ± 26%  perf-profile.calltrace.cycles-pp.unix_stream_data_wait.unix_stream_read_generic.unix_stream_recvmsg.sock_recvmsg.sock_read_iter
     38.60            -0.7       37.85        perf-profile.children.cycles-pp.unix_stream_sendmsg
     38.87            -0.6       38.26        perf-profile.children.cycles-pp.sock_write_iter
      0.07 ± 19%      +0.0        0.10 ± 11%  perf-profile.children.cycles-pp.kmalloc_slab
      0.05 ± 49%      +0.0        0.08 ± 10%  perf-profile.children.cycles-pp.__scm_recv_common
      0.04 ± 72%      +0.0        0.07 ± 12%  perf-profile.children.cycles-pp.kmalloc_size_roundup
      0.05 ± 49%      +0.0        0.08 ± 14%  perf-profile.children.cycles-pp.pick_task_fair
      0.08 ± 20%      +0.0        0.12 ± 10%  perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
      0.07 ± 24%      +0.0        0.11 ± 13%  perf-profile.children.cycles-pp.__get_task_ioprio
      0.07 ± 28%      +0.0        0.11 ± 14%  perf-profile.children.cycles-pp.aa_file_perm
      0.05 ± 51%      +0.0        0.09 ± 13%  perf-profile.children.cycles-pp.__get_obj_cgroup_from_memcg
      0.07 ± 23%      +0.0        0.11 ± 12%  perf-profile.children.cycles-pp.syscall_enter_from_user_mode
      0.03 ±100%      +0.0        0.06 ±  7%  perf-profile.children.cycles-pp.unix_scm_to_skb
      0.08 ± 22%      +0.0        0.11 ± 13%  perf-profile.children.cycles-pp.syscall_return_via_sysret
      0.06 ± 49%      +0.0        0.10 ± 17%  perf-profile.children.cycles-pp.__switch_to_asm
      0.08 ± 27%      +0.0        0.12 ± 14%  perf-profile.children.cycles-pp.obj_cgroup_uncharge_pages
      0.03 ±100%      +0.0        0.07 ± 11%  perf-profile.children.cycles-pp.os_xsave
      0.03 ±100%      +0.0        0.07 ± 13%  perf-profile.children.cycles-pp.perf_trace_sched_wakeup_template
      0.03 ±100%      +0.0        0.07 ± 13%  perf-profile.children.cycles-pp.rseq_get_rseq_cs
      0.02 ±141%      +0.0        0.06 ± 15%  perf-profile.children.cycles-pp.rseq_update_cpu_node_id
      0.06 ± 51%      +0.0        0.10 ± 16%  perf-profile.children.cycles-pp.__enqueue_entity
      0.13 ± 20%      +0.0        0.17 ± 10%  perf-profile.children.cycles-pp.__check_heap_object
      0.02 ±142%      +0.0        0.06 ± 14%  perf-profile.children.cycles-pp.kfree
      0.03 ±101%      +0.0        0.07 ± 10%  perf-profile.children.cycles-pp.rw_verify_area
      0.02 ±142%      +0.0        0.06 ± 14%  perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare
      0.10 ± 23%      +0.0        0.14 ± 10%  perf-profile.children.cycles-pp.x64_sys_call
      0.10 ± 21%      +0.0        0.14 ± 11%  perf-profile.children.cycles-pp.mutex_unlock
      0.06 ± 51%      +0.0        0.11 ± 13%  perf-profile.children.cycles-pp.__dequeue_entity
      0.02 ±142%      +0.0        0.06 ± 11%  perf-profile.children.cycles-pp.security_socket_getpeersec_dgram
      0.07 ± 48%      +0.0        0.11 ± 13%  perf-profile.children.cycles-pp.rseq_ip_fixup
      0.01 ±223%      +0.0        0.06 ±  9%  perf-profile.children.cycles-pp.put_pid
      0.10 ± 22%      +0.0        0.15 ± 12%  perf-profile.children.cycles-pp.__virt_addr_valid
      0.10 ± 24%      +0.1        0.15 ± 12%  perf-profile.children.cycles-pp.rcu_all_qs
      0.10 ± 27%      +0.1        0.16 ± 12%  perf-profile.children.cycles-pp.security_socket_recvmsg
      0.09 ± 41%      +0.1        0.14 ± 22%  perf-profile.children.cycles-pp.update_curr
      0.01 ±223%      +0.1        0.07 ± 16%  perf-profile.children.cycles-pp.__mod_memcg_lruvec_state
      0.12 ± 24%      +0.1        0.17 ± 11%  perf-profile.children.cycles-pp.__rseq_handle_notify_resume
      0.11 ± 24%      +0.1        0.17 ± 12%  perf-profile.children.cycles-pp.restore_fpregs_from_fpstate
      0.14 ± 23%      +0.1        0.20 ± 12%  perf-profile.children.cycles-pp.get_obj_cgroup_from_current
      0.12 ± 32%      +0.1        0.18 ± 15%  perf-profile.children.cycles-pp.set_next_entity
      0.10 ± 46%      +0.1        0.17 ± 25%  perf-profile.children.cycles-pp.dequeue_entity
      0.13 ± 27%      +0.1        0.20 ± 14%  perf-profile.children.cycles-pp.mutex_lock
      0.15 ± 22%      +0.1        0.22 ± 13%  perf-profile.children.cycles-pp.copyin
      0.14 ± 27%      +0.1        0.21 ± 14%  perf-profile.children.cycles-pp.switch_fpu_return
      0.18 ± 22%      +0.1        0.25 ± 11%  perf-profile.children.cycles-pp.skb_unlink
      0.17 ± 27%      +0.1        0.26 ± 14%  perf-profile.children.cycles-pp.apparmor_file_permission
      0.16 ± 26%      +0.1        0.25 ± 14%  perf-profile.children.cycles-pp.fput
      0.18 ± 22%      +0.1        0.26 ± 10%  perf-profile.children.cycles-pp.refill_obj_stock
      0.12 ± 51%      +0.1        0.21 ± 29%  perf-profile.children.cycles-pp.dequeue_entities
      0.13 ± 49%      +0.1        0.22 ± 28%  perf-profile.children.cycles-pp.dequeue_task_fair
      0.18 ± 23%      +0.1        0.26 ± 12%  perf-profile.children.cycles-pp._copy_from_iter
      0.03 ±163%      +0.1        0.12 ± 50%  perf-profile.children.cycles-pp.ordered_events__queue
      0.03 ±163%      +0.1        0.12 ± 50%  perf-profile.children.cycles-pp.process_simple
      0.03 ±163%      +0.1        0.12 ± 50%  perf-profile.children.cycles-pp.queue_event
      0.19 ± 24%      +0.1        0.28 ± 12%  perf-profile.children.cycles-pp.__cond_resched
      0.22 ± 23%      +0.1        0.34 ± 11%  perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack
      0.24 ± 26%      +0.1        0.36 ± 13%  perf-profile.children.cycles-pp.security_file_permission
      0.26 ± 22%      +0.1        0.38 ± 11%  perf-profile.children.cycles-pp.obj_cgroup_charge
      0.25 ± 36%      +0.1        0.39 ± 19%  perf-profile.children.cycles-pp.pick_next_task_fair
      0.25 ± 36%      +0.1        0.40 ± 19%  perf-profile.children.cycles-pp.pick_next_task
      0.37 ± 26%      +0.2        0.54 ± 13%  perf-profile.children.cycles-pp.skb_set_owner_w
      0.36 ± 29%      +0.2        0.55 ± 13%  perf-profile.children.cycles-pp.exit_to_user_mode_loop
      0.46 ± 23%      +0.2        0.67 ± 11%  perf-profile.children.cycles-pp.skb_copy_datagram_from_iter
      0.63 ± 20%      +0.2        0.87 ± 10%  perf-profile.children.cycles-pp.memcg_slab_post_alloc_hook
      0.62 ± 22%      +0.3        0.90 ± 10%  perf-profile.children.cycles-pp.mod_objcg_state
      0.56 ± 28%      +0.3        0.85 ± 13%  perf-profile.children.cycles-pp.exit_to_user_mode_prepare
      0.62 ± 22%      +0.3        0.91 ± 11%  perf-profile.children.cycles-pp.entry_SYSCALL_64
      0.82 ± 21%      +0.3        1.14 ± 10%  perf-profile.children.cycles-pp.__kmem_cache_free
      0.66 ± 27%      +0.3        1.00 ± 13%  perf-profile.children.cycles-pp.syscall_exit_to_user_mode
      0.88 ± 26%      +0.3        1.23 ± 13%  perf-profile.children.cycles-pp.copyout
      0.84 ± 29%      +0.4        1.19 ± 16%  perf-profile.children.cycles-pp.__slab_free
      0.96 ± 26%      +0.4        1.34 ± 13%  perf-profile.children.cycles-pp._copy_to_iter
      0.64 ± 44%      +0.4        1.06 ± 27%  perf-profile.children.cycles-pp.schedule_timeout
      0.72 ± 42%      +0.5        1.19 ± 25%  perf-profile.children.cycles-pp.unix_stream_data_wait
      0.80 ± 41%      +0.5        1.30 ± 24%  perf-profile.children.cycles-pp.schedule
      0.79 ± 42%      +0.5        1.29 ± 25%  perf-profile.children.cycles-pp.__schedule
      1.87 ± 18%      +0.5        2.41 ±  8%  perf-profile.children.cycles-pp.kmem_cache_free
      0.05 ± 49%      +0.0        0.08 ± 10%  perf-profile.self.cycles-pp.kmalloc_slab
      0.08 ± 20%      +0.0        0.11 ± 11%  perf-profile.self.cycles-pp.ksys_read
      0.07 ± 23%      +0.0        0.10 ±  8%  perf-profile.self.cycles-pp.ksys_write
      0.05 ± 48%      +0.0        0.08 ± 10%  perf-profile.self.cycles-pp.__skb_datagram_iter
      0.08 ± 24%      +0.0        0.11 ± 12%  perf-profile.self.cycles-pp.get_obj_cgroup_from_current
      0.07 ± 19%      +0.0        0.10 ±  8%  perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore
      0.05 ± 48%      +0.0        0.08 ± 13%  perf-profile.self.cycles-pp.syscall_exit_to_user_mode
      0.06 ± 48%      +0.0        0.09 ± 11%  perf-profile.self.cycles-pp.__get_task_ioprio
      0.08 ± 23%      +0.0        0.11 ± 12%  perf-profile.self.cycles-pp.security_file_permission
      0.08 ± 23%      +0.0        0.11 ±  9%  perf-profile.self.cycles-pp._copy_to_iter
      0.08 ± 26%      +0.0        0.11 ± 14%  perf-profile.self.cycles-pp.sock_alloc_send_pskb
      0.06 ± 48%      +0.0        0.09 ±  9%  perf-profile.self.cycles-pp.rcu_all_qs
      0.10 ± 18%      +0.0        0.14 ± 11%  perf-profile.self.cycles-pp.mutex_unlock
      0.04 ± 72%      +0.0        0.08 ± 12%  perf-profile.self.cycles-pp.__get_obj_cgroup_from_memcg
      0.08 ± 23%      +0.0        0.12 ± 10%  perf-profile.self.cycles-pp.x64_sys_call
      0.06 ± 50%      +0.0        0.09 ±  9%  perf-profile.self.cycles-pp.syscall_enter_from_user_mode
      0.06 ± 51%      +0.0        0.10 ± 15%  perf-profile.self.cycles-pp.aa_file_perm
      0.08 ± 22%      +0.0        0.11 ± 13%  perf-profile.self.cycles-pp.syscall_return_via_sysret
      0.12 ± 22%      +0.0        0.16 ±  9%  perf-profile.self.cycles-pp.__check_heap_object
      0.03 ±100%      +0.0        0.07 ± 11%  perf-profile.self.cycles-pp.__scm_recv_common
      0.10 ± 23%      +0.0        0.14 ±  9%  perf-profile.self.cycles-pp.do_syscall_64
      0.06 ± 49%      +0.0        0.10 ± 17%  perf-profile.self.cycles-pp.__switch_to_asm
      0.02 ±141%      +0.0        0.06 ± 13%  perf-profile.self.cycles-pp.rseq_update_cpu_node_id
      0.04 ± 73%      +0.0        0.08 ± 14%  perf-profile.self.cycles-pp.__dequeue_entity
      0.03 ±100%      +0.0        0.07 ± 10%  perf-profile.self.cycles-pp.__fdget_pos
      0.03 ±101%      +0.0        0.07 ± 12%  perf-profile.self.cycles-pp.alloc_skb_with_frags
      0.03 ±101%      +0.0        0.07 ± 12%  perf-profile.self.cycles-pp.exit_to_user_mode_prepare
      0.03 ±100%      +0.0        0.07 ± 13%  perf-profile.self.cycles-pp.os_xsave
      0.03 ±101%      +0.0        0.07 ± 12%  perf-profile.self.cycles-pp.sock_recvmsg
      0.09 ± 24%      +0.0        0.14 ± 11%  perf-profile.self.cycles-pp.__virt_addr_valid
      0.06 ± 51%      +0.0        0.10 ± 16%  perf-profile.self.cycles-pp.__enqueue_entity
      0.02 ±142%      +0.0        0.06 ± 14%  perf-profile.self.cycles-pp._copy_from_iter
      0.03 ±100%      +0.0        0.07 ± 11%  perf-profile.self.cycles-pp.kmalloc_reserve
      0.03 ±101%      +0.0        0.08 ± 12%  perf-profile.self.cycles-pp.memcg_account_kmem
      0.03 ±101%      +0.0        0.08 ± 12%  perf-profile.self.cycles-pp.skb_copy_datagram_from_iter
      0.01 ±223%      +0.0        0.06 ±  9%  perf-profile.self.cycles-pp.__build_skb_around
      0.01 ±223%      +0.0        0.06 ±  9%  perf-profile.self.cycles-pp.unix_scm_to_skb
      0.09 ± 27%      +0.1        0.14 ± 16%  perf-profile.self.cycles-pp.mutex_lock
      0.11 ± 23%      +0.1        0.16 ± 11%  perf-profile.self.cycles-pp.unix_write_space
      0.01 ±223%      +0.1        0.06 ± 15%  perf-profile.self.cycles-pp.__get_user_8
      0.10 ± 24%      +0.1        0.15 ± 11%  perf-profile.self.cycles-pp.consume_skb
      0.10 ± 24%      +0.1        0.16 ± 10%  perf-profile.self.cycles-pp.__cond_resched
      0.10 ± 24%      +0.1        0.16 ± 12%  perf-profile.self.cycles-pp.entry_SYSCALL_64
      0.13 ± 21%      +0.1        0.19 ± 10%  perf-profile.self.cycles-pp.__check_object_size
      0.11 ± 24%      +0.1        0.17 ± 12%  perf-profile.self.cycles-pp.restore_fpregs_from_fpstate
      0.12 ± 22%      +0.1        0.19 ±  9%  perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
      0.14 ± 24%      +0.1        0.20 ± 10%  perf-profile.self.cycles-pp.sock_read_iter
      0.15 ± 22%      +0.1        0.22 ± 15%  perf-profile.self.cycles-pp.copyin
      0.17 ± 22%      +0.1        0.24 ± 11%  perf-profile.self.cycles-pp.obj_cgroup_charge
      0.38 ± 12%      +0.1        0.45 ±  5%  perf-profile.self.cycles-pp.__kmem_cache_alloc_node
      0.16 ± 28%      +0.1        0.23 ± 15%  perf-profile.self.cycles-pp.fput
      0.23 ± 17%      +0.1        0.30 ±  8%  perf-profile.self.cycles-pp.kmem_cache_alloc_node
      0.16 ± 24%      +0.1        0.24 ± 11%  perf-profile.self.cycles-pp.sock_write_iter
      0.17 ± 22%      +0.1        0.25 ± 10%  perf-profile.self.cycles-pp.refill_obj_stock
      0.16 ± 25%      +0.1        0.23 ± 13%  perf-profile.self.cycles-pp.vfs_write
      0.16 ± 24%      +0.1        0.24 ± 12%  perf-profile.self.cycles-pp.vfs_read
      0.21 ± 24%      +0.1        0.30 ± 11%  perf-profile.self.cycles-pp.skb_release_data
      0.03 ±163%      +0.1        0.12 ± 52%  perf-profile.self.cycles-pp.queue_event
      0.22 ± 24%      +0.1        0.33 ± 12%  perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
      0.16 ± 37%      +0.1        0.28 ± 25%  perf-profile.self.cycles-pp.__schedule
      0.38 ± 19%      +0.1        0.50 ± 10%  perf-profile.self.cycles-pp.memcg_slab_post_alloc_hook
      0.31 ± 22%      +0.1        0.46 ± 11%  perf-profile.self.cycles-pp.write
      0.31 ± 22%      +0.1        0.46 ± 11%  perf-profile.self.cycles-pp.read
      0.51 ± 19%      +0.2        0.69 ±  9%  perf-profile.self.cycles-pp.__kmem_cache_free
      0.36 ± 27%      +0.2        0.54 ± 13%  perf-profile.self.cycles-pp.skb_set_owner_w
      0.56 ± 22%      +0.2        0.80 ± 10%  perf-profile.self.cycles-pp.mod_objcg_state
      0.60 ± 30%      +0.3        0.86 ± 16%  perf-profile.self.cycles-pp.sock_wfree
      0.83 ± 28%      +0.3        1.17 ± 16%  perf-profile.self.cycles-pp.__slab_free
      0.94 ± 27%      +0.4        1.38 ± 13%  perf-profile.self.cycles-pp.unix_stream_read_generic




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


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2025-03-28  9:29 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-03-28  9:29 [anolis-intel-cloud:devel-6.6] [sched/core] 2bbba4ed1a: hackbench.throughput 16.5% improvement kernel test robot

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.