All of lore.kernel.org
 help / color / mirror / Atom feed
From: kernel test robot <oliver.sang@intel.com>
To: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>, <oliver.sang@intel.com>
Subject: [bigeasy-staging:futex_local_v4.5] [futex]  51319c5cb6: stress-ng.pthread.ops_per_sec 68.4% regression
Date: Fri, 20 Dec 2024 11:32:06 +0800	[thread overview]
Message-ID: <202412201111.1290bdf8-lkp@intel.com> (raw)



Hello,

kernel test robot noticed a 68.4% regression of stress-ng.pthread.ops_per_sec on:


commit: 51319c5cb6c2f84994a14d11de0fc26321bed99d ("futex: Resize futex hash table based on number of threads.")
https://git.kernel.org/cgit/linux/kernel/git/bigeasy/staging.git futex_local_v4.5

testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-12
test machine: 224 threads 2 sockets Intel(R) Xeon(R) Platinum 8480CTDX (Sapphire Rapids) with 256G memory
parameters:

	nr_threads: 100%
	testtime: 60s
	test: pthread
	cpufreq_governor: performance


In addition to that, the commit also has significant impact on the following tests:

+------------------+-----------------------------------------------------------------------------------------------+
| testcase: change | phoronix-test-suite: phoronix-test-suite.hmmer.0.seconds 1.1% improvement                     |
| test machine     | 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz (Cascade Lake) with 512G memory |
| test parameters  | cpufreq_governor=performance                                                                  |
|                  | test=hmmer-1.3.0                                                                              |
+------------------+-----------------------------------------------------------------------------------------------+


If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202412201111.1290bdf8-lkp@intel.com


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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20241220/202412201111.1290bdf8-lkp@intel.com

=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
  gcc-12/performance/x86_64-rhel-9.4/100%/debian-12-x86_64-20240206.cgz/lkp-spr-r02/pthread/stress-ng/60s

commit: 
  7ee6fb8b90 ("futex: Allow to make the number of slots invariant.")
  51319c5cb6 ("futex: Resize futex hash table based on number of threads.")

7ee6fb8b9098b494 51319c5cb6c2f84994a14d11de0 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
   6627322 ± 10%    +251.8%   23313668 ±  6%  cpuidle..usage
      1736 ±  5%   +3154.7%      56524        vmstat.procs.r
   1002783         +2452.7%   25598086        vmstat.system.cs
    771802            +6.1%     819086 ±  3%  vmstat.system.in
      0.52            +0.3        0.80 ±  3%  mpstat.cpu.all.irq%
      0.38 ±  5%      -0.1        0.31 ±  2%  mpstat.cpu.all.soft%
      1.93            -0.6        1.37 ±  2%  mpstat.cpu.all.usr%
      3.00          +946.7%      31.40 ± 47%  mpstat.max_utilization.seconds
  47826564           -63.6%   17393274        numa-numastat.node0.local_node
  47971208           -63.6%   17481098        numa-numastat.node0.numa_hit
  48725840           -56.2%   21335379        numa-numastat.node1.local_node
  48820666           -56.0%   21480221        numa-numastat.node1.numa_hit
     14704 ± 14%   +1161.9%     185562 ± 19%  perf-c2c.DRAM.local
      8884 ± 11%    +122.1%      19735 ± 22%  perf-c2c.DRAM.remote
     18619 ± 16%     +85.0%      34442 ± 16%  perf-c2c.HITM.local
     23012 ± 15%     +72.0%      39590 ± 17%  perf-c2c.HITM.total
    158127 ±  5%    +844.8%    1493924        stress-ng.pthread.nanosecs_to_start_a_pthread
  14216310           -68.3%    4502293        stress-ng.pthread.ops
    236217           -68.4%      74641        stress-ng.pthread.ops_per_sec
   6089793           +53.8%    9365827        stress-ng.time.involuntary_context_switches
  29592487           -62.3%   11154596        stress-ng.time.minor_page_faults
     12550           +65.4%      20762        stress-ng.time.percent_of_cpu_this_job_got
      7446           +67.5%      12474        stress-ng.time.system_time
    148.96           -22.7%     115.15 ±  4%  stress-ng.time.user_time
  32596229         +4863.2%  1.618e+09        stress-ng.time.voluntary_context_switches
 1.203e+09           +13.5%  1.366e+09        meminfo.Committed_AS
   1765877           +48.7%    2626290        meminfo.KernelStack
 2.375e+08           -12.3%  2.084e+08        meminfo.MemAvailable
 2.386e+08           -12.2%  2.094e+08        meminfo.MemFree
  25069098          +116.3%   54220471 ±  2%  meminfo.Memused
    600220           +11.1%     667063        meminfo.PageTables
   1554027         +1803.4%   29578809        meminfo.SUnreclaim
   1742425         +1609.4%   29784893        meminfo.Slab
   2087786           +39.8%    2919074        meminfo.VmallocUsed
  25723708          +121.6%   57009983 ±  2%  meminfo.max_used_kB
   5926603           -12.2%    5201076        proc-vmstat.nr_dirty_background_threshold
  11867698           -12.2%   10414870        proc-vmstat.nr_dirty_threshold
  59637204           -12.2%   52373165        proc-vmstat.nr_free_pages
   1768077           +47.7%    2611820 ±  2%  proc-vmstat.nr_kernel_stack
    151037           +10.1%     166306        proc-vmstat.nr_page_table_pages
     47080            +9.4%      51522 ±  2%  proc-vmstat.nr_slab_reclaimable
    390988         +1788.4%    7383371        proc-vmstat.nr_slab_unreclaimable
    511222 ±  9%    +165.0%    1354873 ±  4%  proc-vmstat.numa_hint_faults
    247485 ± 14%    +339.1%    1086767 ±  4%  proc-vmstat.numa_hint_faults_local
  96792237           -59.7%   38965430        proc-vmstat.numa_hit
  96552764           -59.9%   38732763        proc-vmstat.numa_local
    941658 ±  7%    +103.8%    1918950 ±  5%  proc-vmstat.numa_pte_updates
 1.006e+08          +226.2%   3.28e+08        proc-vmstat.pgalloc_normal
  30885650           -60.0%   12353268        proc-vmstat.pgfault
  96122369          +231.3%  3.185e+08        proc-vmstat.pgfree
   6602207 ± 13%     -30.1%    4612202 ± 25%  numa-meminfo.node0.Active
   6602207 ± 13%     -30.1%    4612202 ± 25%  numa-meminfo.node0.Active(anon)
   6714218 ± 12%     -43.0%    3828145 ± 30%  numa-meminfo.node0.FilePages
    869403 ±  2%     +61.0%    1399453 ±  7%  numa-meminfo.node0.KernelStack
 1.171e+08           -10.2%  1.051e+08        numa-meminfo.node0.MemFree
  14536244 ±  6%     +82.2%   26479857 ±  6%  numa-meminfo.node0.MemUsed
    299690 ±  4%     +19.1%     357071 ±  8%  numa-meminfo.node0.PageTables
    807013 ±  2%   +1742.8%   14871318        numa-meminfo.node0.SUnreclaim
   3325647 ± 25%     -72.0%     932404 ± 68%  numa-meminfo.node0.Shmem
    929664 ±  2%   +1512.6%   14991361        numa-meminfo.node0.Slab
   6263155 ± 13%     +40.0%    8770034 ± 16%  numa-meminfo.node1.Active
   6263155 ± 13%     +40.0%    8770034 ± 16%  numa-meminfo.node1.Active(anon)
   3258450 ± 22%    +105.0%    6678806 ± 23%  numa-meminfo.node1.FilePages
    889836 ±  3%     +37.2%    1220450 ±  7%  numa-meminfo.node1.KernelStack
 1.215e+08           -14.1%  1.044e+08        numa-meminfo.node1.MemFree
  10518712 ±  7%    +162.6%   27626797 ±  6%  numa-meminfo.node1.MemUsed
    752184 ±  3%   +1845.1%   14630586        numa-meminfo.node1.SUnreclaim
   3122767 ± 24%     +93.7%    6050307 ± 15%  numa-meminfo.node1.Shmem
    817807 ±  3%   +1699.5%   14716687        numa-meminfo.node1.Slab
   1649885 ± 13%     -30.4%    1148379 ± 24%  numa-vmstat.node0.nr_active_anon
   1681113 ± 12%     -43.0%     957709 ± 29%  numa-vmstat.node0.nr_file_pages
  29269344           -10.2%   26291832        numa-vmstat.node0.nr_free_pages
    875736 ±  4%     +59.5%    1396687 ±  7%  numa-vmstat.node0.nr_kernel_stack
    174604 ± 10%     -21.2%     137674 ± 19%  numa-vmstat.node0.nr_mapped
     74543 ±  4%     +19.0%      88714 ±  8%  numa-vmstat.node0.nr_page_table_pages
    833970 ± 25%     -72.0%     233774 ± 68%  numa-vmstat.node0.nr_shmem
    200505         +1753.1%    3715504        numa-vmstat.node0.nr_slab_unreclaimable
   1649883 ± 13%     -30.4%    1148372 ± 24%  numa-vmstat.node0.nr_zone_active_anon
  47972558           -63.6%   17481338        numa-vmstat.node0.numa_hit
  47827904           -63.6%   17393514        numa-vmstat.node0.numa_local
   1564782 ± 13%     +40.5%    2198813 ± 16%  numa-vmstat.node1.nr_active_anon
    819006 ± 22%    +105.1%    1679544 ± 23%  numa-vmstat.node1.nr_file_pages
  30387636           -14.1%   26098851        numa-vmstat.node1.nr_free_pages
    875763 ±  4%     +38.5%    1212808 ±  7%  numa-vmstat.node1.nr_kernel_stack
    785085 ± 24%     +93.9%    1522420 ± 15%  numa-vmstat.node1.nr_shmem
    186484 ±  3%   +1860.4%    3655787        numa-vmstat.node1.nr_slab_unreclaimable
   1564782 ± 13%     +40.5%    2198807 ± 16%  numa-vmstat.node1.nr_zone_active_anon
  48822084           -56.0%   21481434        numa-vmstat.node1.numa_hit
  48727258           -56.2%   21336593        numa-vmstat.node1.numa_local
      4.45          +142.1%      10.76        perf-stat.i.MPKI
  2.11e+10          +124.6%  4.738e+10        perf-stat.i.branch-instructions
      0.69            +0.1        0.81        perf-stat.i.branch-miss-rate%
 1.389e+08          +149.4%  3.465e+08        perf-stat.i.branch-misses
     38.81           +26.8       65.60        perf-stat.i.cache-miss-rate%
 4.202e+08          +490.4%  2.481e+09        perf-stat.i.cache-misses
  1.08e+09          +247.2%  3.751e+09        perf-stat.i.cache-references
   1032046         +2567.4%   27529155        perf-stat.i.context-switches
      6.56           -59.7%       2.65        perf-stat.i.cpi
    331767          +360.0%    1526105 ±  4%  perf-stat.i.cpu-migrations
      1470           -81.9%     266.14        perf-stat.i.cycles-between-cache-misses
 9.481e+10          +152.8%  2.396e+11        perf-stat.i.instructions
      0.16          +149.3%       0.39        perf-stat.i.ipc
     11.59         +1027.5%     130.68        perf-stat.i.metric.K/sec
    511111           -59.1%     209090        perf-stat.i.minor-faults
    742440           -62.1%     281069        perf-stat.i.page-faults
      6.59           -69.7%       1.99 ± 50%  perf-stat.overall.cpi
      1478           -86.5%     199.17 ± 50%  perf-stat.overall.cycles-between-cache-misses
    490890           -68.6%     154372 ± 50%  perf-stat.ps.minor-faults
    715995           -70.7%     209669 ± 50%  perf-stat.ps.page-faults
  19288614 ± 24%     -53.4%    8988794 ±  2%  sched_debug.cfs_rq:/.avg_vruntime.max
   2084347 ±  8%     +71.6%    3577758 ±  9%  sched_debug.cfs_rq:/.avg_vruntime.min
   1586306 ± 20%     -53.4%     739820 ±  5%  sched_debug.cfs_rq:/.avg_vruntime.stddev
      1.81 ± 14%    +430.3%       9.61 ± 37%  sched_debug.cfs_rq:/.h_nr_running.avg
     36.33 ± 48%    +923.9%     372.00 ± 13%  sched_debug.cfs_rq:/.h_nr_running.max
      4.14 ± 31%    +909.7%      41.80 ± 24%  sched_debug.cfs_rq:/.h_nr_running.stddev
  11695168 ± 36%     -44.4%    6499344 ± 10%  sched_debug.cfs_rq:/.left_deadline.max
   2365150 ±  8%     -12.1%    2078148 ± 12%  sched_debug.cfs_rq:/.left_deadline.stddev
  11682476 ± 36%     -44.4%    6497263 ± 10%  sched_debug.cfs_rq:/.left_vruntime.max
   2364078 ±  8%     -12.1%    2077864 ± 12%  sched_debug.cfs_rq:/.left_vruntime.stddev
   1524013 ± 10%     -27.3%    1107410 ±  2%  sched_debug.cfs_rq:/.load.max
  19288614 ± 24%     -53.4%    8988852 ±  2%  sched_debug.cfs_rq:/.min_vruntime.max
   2084347 ±  8%     +71.6%    3577758 ±  9%  sched_debug.cfs_rq:/.min_vruntime.min
   1586307 ± 20%     -53.4%     739814 ±  5%  sched_debug.cfs_rq:/.min_vruntime.stddev
      4.98 ± 45%     +97.5%       9.83 ± 37%  sched_debug.cfs_rq:/.removed.runnable_avg.avg
    367.83 ± 20%     +80.1%     662.30 ± 18%  sched_debug.cfs_rq:/.removed.runnable_avg.max
     36.85 ± 29%     +77.8%      65.51 ± 26%  sched_debug.cfs_rq:/.removed.runnable_avg.stddev
  11682479 ± 36%     -44.4%    6497263 ± 10%  sched_debug.cfs_rq:/.right_vruntime.max
   2364086 ±  8%     -12.1%    2078765 ± 12%  sched_debug.cfs_rq:/.right_vruntime.stddev
    753.78 ±  8%    +229.0%       2480 ± 39%  sched_debug.cfs_rq:/.runnable_avg.avg
      8411 ± 46%    +636.9%      61984 ± 43%  sched_debug.cfs_rq:/.runnable_avg.max
    871.19 ± 32%    +765.9%       7543 ± 39%  sched_debug.cfs_rq:/.runnable_avg.stddev
      5.06 ±127%   +9495.6%     485.06 ±143%  sched_debug.cfs_rq:/.spread.avg
    862.98 ±160%  +11728.8%     102080 ±150%  sched_debug.cfs_rq:/.spread.max
     61.14 ±150%  +11099.1%       6846 ±149%  sched_debug.cfs_rq:/.spread.stddev
    394.27           -21.0%     311.61 ±  5%  sched_debug.cfs_rq:/.util_avg.avg
      1715 ± 33%     -27.8%       1237 ± 12%  sched_debug.cfs_rq:/.util_avg.max
    280.86 ±  9%     -18.2%     229.80 ±  7%  sched_debug.cfs_rq:/.util_avg.stddev
      1338 ± 23%    +126.0%       3025 ± 16%  sched_debug.cfs_rq:/.util_est.max
    221.61 ±  6%     +70.1%     376.99 ± 18%  sched_debug.cfs_rq:/.util_est.stddev
    171.01 ±  3%     -47.8%      89.30 ± 21%  sched_debug.cpu.clock.stddev
    394914 ±  9%     -85.2%      58515 ± 54%  sched_debug.cpu.curr->pid.avg
      1.81 ± 14%    +430.8%       9.63 ± 38%  sched_debug.cpu.nr_running.avg
     36.33 ± 48%    +920.3%     370.70 ± 14%  sched_debug.cpu.nr_running.max
      4.13 ± 31%    +911.8%      41.75 ± 24%  sched_debug.cpu.nr_running.stddev
    141577         +2513.8%    3700534        sched_debug.cpu.nr_switches.avg
    304773 ±  4%   +1358.2%    4444193        sched_debug.cpu.nr_switches.max
     85203 ± 16%   +2768.7%    2444199 ± 13%  sched_debug.cpu.nr_switches.min
     43599 ± 11%    +692.4%     345497 ± 17%  sched_debug.cpu.nr_switches.stddev
    499.92 ±  8%     -57.4%     212.80 ±  8%  sched_debug.cpu.nr_uninterruptible.max
   -448.00           -55.5%    -199.20        sched_debug.cpu.nr_uninterruptible.min
    172.83 ± 13%     -64.2%      61.85 ±  7%  sched_debug.cpu.nr_uninterruptible.stddev


***************************************************************************************************
lkp-csl-2sp7: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz (Cascade Lake) with 512G memory
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
  gcc-12/performance/x86_64-rhel-9.4/debian-12-x86_64-phoronix/lkp-csl-2sp7/hmmer-1.3.0/phoronix-test-suite

commit: 
  7ee6fb8b90 ("futex: Allow to make the number of slots invariant.")
  51319c5cb6 ("futex: Resize futex hash table based on number of threads.")

7ee6fb8b9098b494 51319c5cb6c2f84994a14d11de0 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
    114508            +4.1%     119226        proc-vmstat.nr_slab_unreclaimable
     92533            +4.4%      96622        vmstat.system.cs
    324428 ± 20%     +28.8%     417804 ± 10%  numa-meminfo.node1.Inactive
    324428 ± 20%     +28.8%     417804 ± 10%  numa-meminfo.node1.Inactive(file)
     81107 ± 20%     +28.8%     104444 ± 10%  numa-vmstat.node1.nr_inactive_file
     81107 ± 20%     +28.8%     104444 ± 10%  numa-vmstat.node1.nr_zone_inactive_file
    198.40            -1.1%     196.26        phoronix-test-suite.hmmer.0.seconds
    640.39            -1.1%     633.62        phoronix-test-suite.time.elapsed_time
    640.39            -1.1%     633.62        phoronix-test-suite.time.elapsed_time.max
      0.02 ± 10%     -22.8%       0.02 ± 16%  perf-sched.sch_delay.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.x64_sys_call
      0.04 ±  9%     -48.3%       0.02 ± 10%  perf-sched.sch_delay.avg.ms.futex_wait_queue.__futex_wait.futex_wait.do_futex
    114.18 ±  8%     -23.7%      87.13 ±  7%  perf-sched.total_wait_and_delay.average.ms
      8149 ±  9%     +32.0%      10754 ±  6%  perf-sched.total_wait_and_delay.count.ms
    114.16 ±  9%     -23.7%      87.08 ±  7%  perf-sched.total_wait_time.average.ms
     10.10 ± 15%     -57.1%       4.33 ±  9%  perf-sched.wait_and_delay.avg.ms.futex_wait_queue.__futex_wait.futex_wait.do_futex
      1291 ± 21%    +182.2%       3645 ±  7%  perf-sched.wait_and_delay.count.futex_wait_queue.__futex_wait.futex_wait.do_futex
     10.06 ± 15%     -57.2%       4.31 ±  9%  perf-sched.wait_time.avg.ms.futex_wait_queue.__futex_wait.futex_wait.do_futex
    346.16 ±213%     -96.6%      11.64 ±  4%  perf-sched.wait_time.max.ms.io_schedule.folio_wait_bit_common.filemap_update_page.filemap_get_pages
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_deadline.avg
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_deadline.max
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_deadline.min
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_vruntime.avg
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_vruntime.max
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.left_vruntime.min
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.right_vruntime.avg
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.right_vruntime.max
      0.00 ±  9%     -58.7%       0.00 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.right_vruntime.min
      1.39 ±  9%     -58.7%       0.58 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.se->load.weight.avg
      1.39 ±  9%     -58.7%       0.58 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.se->load.weight.max
      1.39 ±  9%     -58.7%       0.58 ± 91%  sched_debug.cfs_rq:/system.slice/epmd.service.se->load.weight.min
      0.00 ±  5%      +8.7%       0.00 ±  4%  sched_debug.cpu.next_balance.stddev
     38.50            -0.5       38.00        perf-profile.calltrace.cycles-pp.forward_engine
     20.02            -0.5       19.53        perf-profile.calltrace.cycles-pp.p7_ViterbiFilter
      0.56            -0.0        0.54        perf-profile.calltrace.cycles-pp.p7_oprofile_Convert
     19.63            +1.1       20.72        perf-profile.calltrace.cycles-pp.common_startup_64
     18.32            +1.1       19.46 ±  2%  perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
     19.23            +1.2       20.39 ±  2%  perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
     19.22            +1.2       20.38 ±  2%  perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
     19.27            +1.2       20.43 ±  2%  perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.common_startup_64
     19.38            +1.2       20.54 ±  2%  perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.common_startup_64
     19.38            +1.2       20.54 ±  2%  perf-profile.calltrace.cycles-pp.start_secondary.common_startup_64
     19.38            +1.2       20.54 ±  2%  perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.common_startup_64
     38.51            -0.5       38.00        perf-profile.children.cycles-pp.forward_engine
     20.03            -0.5       19.53        perf-profile.children.cycles-pp.p7_ViterbiFilter
      0.57            -0.0        0.55        perf-profile.children.cycles-pp.p7_oprofile_Convert
     18.55            +1.1       19.63        perf-profile.children.cycles-pp.intel_idle
     19.48            +1.1       20.57        perf-profile.children.cycles-pp.cpuidle_enter
     19.48            +1.1       20.57        perf-profile.children.cycles-pp.cpuidle_enter_state
     19.52            +1.1       20.61        perf-profile.children.cycles-pp.cpuidle_idle_call
     19.63            +1.1       20.72        perf-profile.children.cycles-pp.common_startup_64
     19.63            +1.1       20.72        perf-profile.children.cycles-pp.cpu_startup_entry
     19.63            +1.1       20.72        perf-profile.children.cycles-pp.do_idle
     19.38            +1.2       20.54 ±  2%  perf-profile.children.cycles-pp.start_secondary
     38.27            -0.5       37.76        perf-profile.self.cycles-pp.forward_engine
     19.90            -0.5       19.40        perf-profile.self.cycles-pp.p7_ViterbiFilter
      0.56            -0.0        0.54        perf-profile.self.cycles-pp.p7_oprofile_Convert
     18.55            +1.1       19.63        perf-profile.self.cycles-pp.intel_idle
 2.141e+10            +0.9%   2.16e+10        perf-stat.i.branch-instructions
     92864            +4.4%      96993        perf-stat.i.context-switches
 6.607e+10            +0.9%  6.665e+10        perf-stat.i.dTLB-loads
 1.889e+10            +0.9%  1.905e+10        perf-stat.i.dTLB-stores
   1366409            +1.2%    1382929        perf-stat.i.iTLB-load-misses
   2248980            +3.8%    2334182        perf-stat.i.iTLB-loads
 2.313e+11            +0.9%  2.333e+11        perf-stat.i.instructions
      1.81            +0.9%       1.82        perf-stat.i.ipc
    609.30            +1.4%     617.69        perf-stat.i.metric.K/sec
      1107            +0.9%       1117        perf-stat.i.metric.M/sec
    957746            -3.5%     923807        perf-stat.i.node-load-misses
     48.43            -2.9       45.55        perf-stat.i.node-store-miss-rate%
    348221           +14.9%     400034        perf-stat.i.node-stores
      0.52            -1.2%       0.52        perf-stat.overall.cpi
      0.00            -0.0        0.00        perf-stat.overall.dTLB-store-miss-rate%
     37.81            -0.6       37.21        perf-stat.overall.iTLB-load-miss-rate%
      1.91            +1.2%       1.93        perf-stat.overall.ipc
     47.94            -3.2       44.70        perf-stat.overall.node-store-miss-rate%
 2.141e+10            +0.9%   2.16e+10        perf-stat.ps.branch-instructions
     92840            +4.4%      96972        perf-stat.ps.context-switches
 6.606e+10            +0.9%  6.664e+10        perf-stat.ps.dTLB-loads
 1.888e+10            +0.9%  1.905e+10        perf-stat.ps.dTLB-stores
   2247841            +3.8%    2333256        perf-stat.ps.iTLB-loads
 2.313e+11            +0.9%  2.333e+11        perf-stat.ps.instructions
    957556            -3.6%     923556        perf-stat.ps.node-load-misses
    348081           +14.9%     399895        perf-stat.ps.node-stores





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:[~2024-12-20  3:33 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=202412201111.1290bdf8-lkp@intel.com \
    --to=oliver.sang@intel.com \
    --cc=bigeasy@linutronix.de \
    --cc=lkp@intel.com \
    --cc=oe-lkp@lists.linux.dev \
    /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.