Hi Am 26.08.20 um 10:58 schrieb kernel test robot: > Greeting, > > FYI, we noticed a 26.2% improvement of vm-scalability.throughput due to > commit:
I guess this resolves the once-measured performance penalty of similar
magnitude. But do we really understand these tests? When I sent out
patches to resolve the problem, nothing changed. And suddenly the
performance is back to normal.
Best regards
Thomas
>
>
> commit: 913ec479bb5cc27f99f24d5fd111b3ef29a4deb9 ("drm/mgag200: Replace VRAM
> helpers with SHMEM helpers")
> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>
>
> in testcase: vm-scalability
> on test machine: 288 threads Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz with
> 80G memory
> with following parameters:
>
> runtime: 300s
> size: 8T
> test: anon-cow-seq-hugetlb
> cpufreq_governor: performance
> ucode: 0x11
>
> test-description: The motivation behind this suite is to exercise functions
> and regions of the mm/ of the Linux kernel which are of interest to us.
> test-url: https://git.kernel.org/cgit/linux/kernel/git/wfg/vm-scalability.git/
>
>
>
>
>
> Details are as below:
> -------------------------------------------------------------------------------------------------->
>
>
> To reproduce:
>
> git clone https://github.com/intel/lkp-tests.git
> cd lkp-tests
> bin/lkp install job.yaml # job file is attached in this email
> bin/lkp run job.yaml
>
> =========================================================================================
> compiler/cpufreq_governor/kconfig/rootfs/runtime/size/tbox_group/test/testcase/ucode:
>
> gcc-7/performance/x86_64-rhel-7.6/debian-x86_64-20191114.cgz/300s/8T/lkp-knm01/anon-cow-seq-hugetlb/vm-scalability/0x11
>
> commit:
> 88fabb75ea ("drm/mgag200: Convert to simple KMS helper")
> 913ec479bb ("drm/mgag200: Replace VRAM helpers with SHMEM helpers")
>
> 88fabb75ea9edf4a 913ec479bb5cc27f99f24d5fd11
> ---------------- ---------------------------
> %stddev %change %stddev
> \ | \
> 26138 ± 3% +26.8% 33155 vm-scalability.median
> 19.34 ± 18% -14.7 4.68 ± 10% vm-scalability.median_stddev%
> 19.51 ± 19% -14.2 5.28 ± 10% vm-scalability.stddev%
> 8319528 ± 4% +26.2% 10501934 vm-scalability.throughput
> 120228 +10.5% 132891
> vm-scalability.time.involuntary_context_switches
> 1361617 ± 5% +29.6% 1765048
> vm-scalability.time.minor_page_faults
> 10722 +8.2% 11596
> vm-scalability.time.percent_of_cpu_this_job_got
> 23798 +3.0% 24511 vm-scalability.time.system_time
> 9152 ± 2% +19.1% 10902 vm-scalability.time.user_time
> 907111 ± 4% +22.1% 1107928
> vm-scalability.time.voluntary_context_switches
> 1.972e+09 ± 5% +29.8% 2.561e+09 vm-scalability.workload
> 11.43 ± 3% +2.2 13.66 mpstat.cpu.all.usr%
> 2186600 ± 2% +17.9% 2578950 numa-numastat.node0.local_node
> 2186561 ± 2% +17.9% 2578936 numa-numastat.node0.numa_hit
> 58.75 -5.1% 55.75 vmstat.cpu.id
> 10.75 ± 4% +20.9% 13.00 vmstat.cpu.us
> 10814 ± 3% +13.7% 12296 vmstat.system.cs
> 726.00 ± 9% -20.8% 575.00 ± 8% slabinfo.UDP.active_objs
> 726.00 ± 9% -20.8% 575.00 ± 8% slabinfo.UDP.num_objs
> 135282 +13.8% 153971 slabinfo.anon_vma.active_objs
> 2940 +13.8% 3347 slabinfo.anon_vma.active_slabs
> 135282 +13.8% 153974 slabinfo.anon_vma.num_objs
> 2940 +13.8% 3347 slabinfo.anon_vma.num_slabs
> 1276 ± 4% +19.7% 1528
> slabinfo.hugetlbfs_inode_cache.active_objs
> 1276 ± 4% +19.7% 1528
> slabinfo.hugetlbfs_inode_cache.num_objs
> 37346 -12.4% 32714 slabinfo.vmap_area.active_objs
> 37802 -11.7% 33381 slabinfo.vmap_area.num_objs
> 864832 ± 5% +29.8% 1122765
> proc-vmstat.htlb_buddy_alloc_success
> 209.50 ± 2% +8.1% 226.50 proc-vmstat.nr_dirtied
> 17601 +6.4% 18734 ± 2% proc-vmstat.nr_inactive_anon
> 396.00 +2.7% 406.75 proc-vmstat.nr_inactive_file
> 2873 +4.1% 2991 ± 4% proc-vmstat.nr_page_table_pages
> 26710 ± 2% +4.4% 27891 proc-vmstat.nr_shmem
> 100611 +1.6% 102242
> proc-vmstat.nr_slab_unreclaimable
> 17601 +6.4% 18734 ± 2%
> proc-vmstat.nr_zone_inactive_anon
> 396.00 +2.7% 406.75
> proc-vmstat.nr_zone_inactive_file
> 2209041 ± 2% +17.8% 2601215 proc-vmstat.numa_hit
> 2209039 ± 2% +17.8% 2601213 proc-vmstat.numa_local
> 4.443e+08 ± 5% +29.8% 5.765e+08 proc-vmstat.pgalloc_normal
> 2188741 ± 3% +18.4% 2591635 proc-vmstat.pgfault
> 4.443e+08 ± 5% +29.8% 5.766e+08 proc-vmstat.pgfree
> 9260 ± 15% -30.3% 6456 softirqs.CPU113.RCU
> 9814 ± 8% -22.3% 7626 ± 10% softirqs.CPU16.RCU
> 8961 ± 17% -31.8% 6108 softirqs.CPU167.RCU
> 9410 ± 24% -34.7% 6142 ± 2% softirqs.CPU185.RCU
> 8572 ± 10% -29.0% 6084 ± 2% softirqs.CPU192.RCU
> 9877 ± 4% -20.5% 7856 ± 10% softirqs.CPU2.RCU
> 8615 ± 14% -29.4% 6085 softirqs.CPU218.RCU
> 9547 ± 8% -24.8% 7182 ± 2% softirqs.CPU22.RCU
> 8630 ± 13% -31.3% 5926 ± 2% softirqs.CPU251.RCU
> 8352 ± 14% -24.7% 6292 ± 10% softirqs.CPU253.RCU
> 10579 ± 19% -32.7% 7117 softirqs.CPU28.RCU
> 10533 ± 21% -30.9% 7276 ± 3% softirqs.CPU30.RCU
> 9505 ± 6% -25.9% 7039 ± 3% softirqs.CPU34.RCU
> 9683 ± 12% -22.8% 7474 ± 7% softirqs.CPU35.RCU
> 9921 ± 5% -23.5% 7593 ± 2% softirqs.CPU4.RCU
> 9143 ± 7% -24.3% 6919 softirqs.CPU40.RCU
> 9846 ± 16% -27.5% 7137 ± 7% softirqs.CPU43.RCU
> 125651 ± 5% -7.6% 116136 softirqs.CPU43.TIMER
> 9740 ± 5% -19.6% 7830 ± 8% softirqs.CPU5.RCU
> 9796 ± 17% -30.8% 6782 softirqs.CPU64.RCU
> 125735 ± 5% -7.8% 115896 softirqs.CPU64.TIMER
> 10505 ± 16% -29.1% 7451 softirqs.CPU7.RCU
> 9281 ± 17% -29.3% 6559 ± 4% softirqs.CPU72.RCU
> 9254 ± 9% -28.5% 6620 softirqs.CPU76.RCU
> 8966 ± 8% -26.4% 6602 softirqs.CPU80.RCU
> 2440341 -23.2% 1874298 softirqs.RCU
> 47786 ± 16% +19.7% 57184 ± 10%
> sched_debug.cfs_rq:/.exec_clock.avg
> 55043 ± 15% +37.4% 75652 ± 16%
> sched_debug.cfs_rq:/.exec_clock.max
> 2301 ± 15% +39.5% 3209 ± 14%
> sched_debug.cfs_rq:/.exec_clock.stddev
> 682444 ± 6% +32.4% 903612 ± 3% sched_debug.cfs_rq:/.load.max
> 51939 ± 6% +26.2% 65553 ± 4% sched_debug.cfs_rq:/.load.stddev
> 707.93 ± 12% +24.8% 883.35 ± 2%
> sched_debug.cfs_rq:/.load_avg.max
> 7053330 ± 15% +25.8% 8873751 ± 10%
> sched_debug.cfs_rq:/.min_vruntime.avg
> 7953721 ± 14% +26.2% 10040724 ± 10%
> sched_debug.cfs_rq:/.min_vruntime.max
> 322922 ± 12% +36.3% 440070 ± 10%
> sched_debug.cfs_rq:/.min_vruntime.stddev
> 1464090 ± 26% +64.9% 2414900 ± 8% sched_debug.cfs_rq:/.spread0.avg
> 2354621 ± 21% +52.2% 3584671 ± 10% sched_debug.cfs_rq:/.spread0.max
> 325700 ± 12% +35.7% 442066 ± 10%
> sched_debug.cfs_rq:/.spread0.stddev
> 234.31 ± 4% +12.3% 263.24 ± 3%
> sched_debug.cfs_rq:/.util_est_enqueued.stddev
> 4421799 ± 7% -35.6% 2848695 ± 2% sched_debug.cpu.avg_idle.avg
> 11041245 ± 7% -39.3% 6701506 ± 32% sched_debug.cpu.avg_idle.max
> 1237620 ± 5% -50.0% 618574 ± 15% sched_debug.cpu.avg_idle.stddev
> 12335 ± 10% +19.7% 14763 ± 7% sched_debug.cpu.curr->pid.max
> 4421 ± 3% +26.3% 5584 ± 5% sched_debug.cpu.curr->pid.stddev
> 2275100 ± 7% -35.6% 1466283 ± 2%
> sched_debug.cpu.max_idle_balance_cost.avg
> 1281746 ± 8% -29.4% 905511 ± 5%
> sched_debug.cpu.max_idle_balance_cost.min
> 619199 ± 5% -48.7% 317754 ± 26%
> sched_debug.cpu.max_idle_balance_cost.stddev
> 7348 ± 10% +16.3% 8547 ± 7% sched_debug.cpu.nr_switches.avg
> 4247 ± 15% +23.8% 5258 ± 8% sched_debug.cpu.nr_switches.min
> 1954 ± 16% +26.4% 2470 ± 18%
> sched_debug.cpu.nr_switches.stddev
> 35.14 ± 7% +17.2% 41.19 ± 5%
> sched_debug.cpu.nr_uninterruptible.stddev
> 4555 ± 17% +26.4% 5759 ± 11% sched_debug.cpu.sched_count.avg
> 15348 ± 19% +50.8% 23137 ± 24% sched_debug.cpu.sched_count.max
> 3317 ± 17% +21.5% 4031 ± 8% sched_debug.cpu.sched_count.min
> 1475 ± 22% +40.4% 2070 ± 21%
> sched_debug.cpu.sched_count.stddev
> 2024 ± 17% +26.8% 2567 ± 11% sched_debug.cpu.sched_goidle.avg
> 7428 ± 19% +51.2% 11230 ± 25% sched_debug.cpu.sched_goidle.max
> 728.91 ± 22% +39.9% 1019 ± 21%
> sched_debug.cpu.sched_goidle.stddev
> 2279 ± 17% +26.5% 2883 ± 11% sched_debug.cpu.ttwu_count.avg
> 1037 ± 19% +33.5% 1384 ± 16%
> sched_debug.cpu.ttwu_count.stddev
> 398.73 ± 17% +16.9% 466.07 ± 10% sched_debug.cpu.ttwu_local.avg
> 123.45 ± 12% +40.1% 172.95 ± 6%
> sched_debug.cpu.ttwu_local.stddev
> 8.88 ± 2% +9.4% 9.72 perf-stat.i.MPKI
> 1.257e+10 ± 2% +14.4% 1.438e+10 perf-stat.i.branch-instructions
> 1.972e+08 ± 6% +20.9% 2.384e+08 perf-stat.i.branch-misses
> 13.19 ± 2% -1.0 12.19 perf-stat.i.cache-miss-rate%
> 55435779 ± 6% +13.0% 62648038 perf-stat.i.cache-misses
> 4.227e+08 ± 4% +21.6% 5.138e+08 perf-stat.i.cache-references
> 11013 ± 3% +12.7% 12415 perf-stat.i.context-switches
> 4.11 ± 3% -5.8% 3.87 perf-stat.i.cpi
> 1.99e+11 ± 3% +5.3% 2.097e+11 perf-stat.i.cpu-cycles
> 1019 +8.4% 1104 perf-stat.i.cpu-migrations
> 3581 ± 2% -7.2% 3324
> perf-stat.i.cycles-between-cache-misses
> 4.913e+10 ± 2% +10.7% 5.441e+10 perf-stat.i.iTLB-loads
> 4.91e+10 ± 2% +10.7% 5.433e+10 perf-stat.i.instructions
> 0.25 ± 3% +5.7% 0.26 perf-stat.i.ipc
> 0.68 ± 2% +5.2% 0.71 perf-stat.i.metric.GHz
> 0.09 ± 2% +15.9% 0.11 perf-stat.i.metric.K/sec
> 211.98 ± 2% +11.5% 236.42 perf-stat.i.metric.M/sec
> 7299 ± 3% +18.8% 8671 perf-stat.i.minor-faults
> 7300 ± 3% +18.8% 8676 perf-stat.i.page-faults
> 8.56 ± 3% +10.3% 9.45 perf-stat.overall.MPKI
> 1.55 ± 4% +0.1 1.65
> perf-stat.overall.branch-miss-rate%
> 13.26 ± 2% -1.0 12.26
> perf-stat.overall.cache-miss-rate%
> 4.08 ± 2% -5.3% 3.87 perf-stat.overall.cpi
> 3599 ± 3% -7.3% 3335
> perf-stat.overall.cycles-between-cache-misses
> 0.25 ± 2% +5.5% 0.26 perf-stat.overall.ipc
> 7415 ± 2% -14.2% 6361 perf-stat.overall.path-length
> 1.215e+10 ± 2% +16.2% 1.412e+10 perf-stat.ps.branch-instructions
> 1.889e+08 ± 6% +23.3% 2.33e+08 perf-stat.ps.branch-misses
> 54049850 ± 5% +14.4% 61817571 perf-stat.ps.cache-misses
> 4.076e+08 ± 4% +23.7% 5.041e+08 perf-stat.ps.cache-references
> 10730 ± 3% +14.1% 12239 perf-stat.ps.context-switches
> 1.942e+11 ± 2% +6.2% 2.062e+11 perf-stat.ps.cpu-cycles
> 974.83 +8.9% 1061 perf-stat.ps.cpu-migrations
> 4.761e+10 ± 2% +12.2% 5.343e+10 perf-stat.ps.iTLB-loads
> 4.757e+10 ± 2% +12.1% 5.335e+10 perf-stat.ps.instructions
> 7000 ± 3% +19.3% 8351 perf-stat.ps.minor-faults
> 7001 ± 3% +19.3% 8352 perf-stat.ps.page-faults
> 1.461e+13 ± 2% +11.5% 1.629e+13 perf-stat.total.instructions
> 36.28 ± 5% -3.1 33.23 ± 4%
> perf-profile.calltrace.cycles-pp.osq_lock.__mutex_lock.hugetlb_fault.handle_mm_fault.do_page_fault
> 47.28 ± 2% -2.9 44.42 ± 4%
> perf-profile.calltrace.cycles-pp.__mutex_lock.hugetlb_fault.handle_mm_fault.do_page_fault.page_fault
> 0.78 ± 29% +0.4 1.17 ± 13%
> perf-profile.calltrace.cycles-pp.apic_timer_interrupt.do_access
> 0.51 ± 62% +0.5 1.04 ± 14%
> perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.do_access
> 0.14 ±173% +0.6 0.71 ± 18%
> perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.do_access
> 0.17 ±173% +0.7 0.85 ± 16%
> perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.do_access
> 0.61 ± 9% +0.7 1.33 ± 18%
> perf-profile.calltrace.cycles-pp.apic_timer_interrupt.mutex_spin_on_owner.__mutex_lock.hugetlb_fault.handle_mm_fault
> 0.00 +0.8 0.76 ± 12%
> perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.mutex_spin_on_owner
> 0.42 ± 57% +0.8 1.26 ± 18%
> perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.mutex_spin_on_owner.__mutex_lock.hugetlb_fault
> 0.12 ±173% +0.9 1.06 ± 17%
> perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.mutex_spin_on_owner.__mutex_lock
> 1.67 ± 19% +1.0 2.65 ± 6%
> perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.osq_lock
> 0.14 ±173% +1.1 1.22 ± 21%
> perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.do_rw_once
> 0.27 ±100% +1.1 1.38 ± 16%
> perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.copy_page.copy_subpage
> 0.00 +1.1 1.14 ± 16%
> perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.copy_page
> 2.20 ± 14% +1.2 3.35 ± 3%
> perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.osq_lock.__mutex_lock
> 0.30 ±102% +1.2 1.47 ± 18%
> perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.do_rw_once
> 0.82 ± 27% +1.2 1.99 ± 16%
> perf-profile.calltrace.cycles-pp.apic_timer_interrupt.do_rw_once
> 0.60 ± 8% +1.2 1.80 ± 8%
> perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.copy_page.copy_subpage.copy_user_huge_page
> 0.86 ± 14% +1.2 2.06 ± 9%
> perf-profile.calltrace.cycles-pp.apic_timer_interrupt.copy_page.copy_subpage.copy_user_huge_page.hugetlb_cow
> 3.02 ± 16% +1.2 4.22 ± 4%
> perf-profile.calltrace.cycles-pp.apic_timer_interrupt.osq_lock.__mutex_lock.hugetlb_fault.handle_mm_fault
> 0.53 ± 61% +1.3 1.79 ± 17%
> perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.do_rw_once
> 2.62 ± 16% +1.4 3.98 ± 3%
> perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.osq_lock.__mutex_lock.hugetlb_fault
> 2.80 ± 14% +2.5 5.31 ± 17%
> perf-profile.calltrace.cycles-pp.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt
> 3.04 ± 14% +2.6 5.61 ± 17%
> perf-profile.calltrace.cycles-pp.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt
> 3.41 ± 17% +2.7 6.15 ± 17%
> perf-profile.calltrace.cycles-pp.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt
> 9.16 ± 22% +3.9 13.04 ± 18%
> perf-profile.calltrace.cycles-pp.do_rw_once
> 36.60 ± 5% -3.2 33.42 ± 4%
> perf-profile.children.cycles-pp.osq_lock
> 47.28 ± 2% -2.9 44.42 ± 4%
> perf-profile.children.cycles-pp.__mutex_lock
> 0.58 ± 6% -0.5 0.03 ±102%
> perf-profile.children.cycles-pp.memcpy_erms
> 1.47 ± 5% -0.3 1.21 ± 6%
> perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
> 1.47 ± 5% -0.3 1.21 ± 6%
> perf-profile.children.cycles-pp.do_syscall_64
> 0.26 ± 11% -0.1 0.18 ± 8%
> perf-profile.children.cycles-pp.update_ts_time_stats
> 0.09 ± 12% -0.0 0.06 ± 7%
> perf-profile.children.cycles-pp.wake_up_q
> 0.08 ± 17% -0.0 0.05 ± 8%
> perf-profile.children.cycles-pp.pipe_write
> 0.17 ± 4% -0.0 0.14 ± 10%
> perf-profile.children.cycles-pp.write
> 0.08 ± 5% +0.0 0.11 ± 4%
> perf-profile.children.cycles-pp.raise_softirq
> 0.11 ± 6% +0.0 0.15 ± 22%
> perf-profile.children.cycles-pp.__update_load_avg_se
> 0.15 ± 10% +0.0 0.20 ± 7%
> perf-profile.children.cycles-pp.x86_pmu_disable
> 0.17 ± 25% +0.1 0.23 ± 4%
> perf-profile.children.cycles-pp.native_irq_return_iret
> 0.07 ± 58% +0.1 0.12 ± 13%
> perf-profile.children.cycles-pp.hrtimer_run_queues
> 0.33 ± 2% +0.1 0.39 ± 10%
> perf-profile.children.cycles-pp.timerqueue_add
> 0.21 ± 11% +0.1 0.27 ± 8%
> perf-profile.children.cycles-pp.tick_program_event
> 0.37 ± 3% +0.1 0.43 ± 9%
> perf-profile.children.cycles-pp.enqueue_hrtimer
> 0.24 ± 19% +0.1 0.30 ± 4%
> perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
> 0.18 ± 9% +0.1 0.25 ± 19%
> perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
> 0.28 ± 15% +0.1 0.35 ± 3%
> perf-profile.children.cycles-pp.read_tsc
> 0.03 ±100% +0.1 0.11 ± 30%
> perf-profile.children.cycles-pp.cpuacct_account_field
> 0.08 ± 5% +0.1 0.18 ± 13%
> perf-profile.children.cycles-pp.cpuacct_charge
> 0.41 ± 13% +0.1 0.52 ± 9%
> perf-profile.children.cycles-pp.ktime_get_update_offsets_now
> 0.05 ± 62% +0.1 0.18 ± 30%
> perf-profile.children.cycles-pp.account_user_time
> 0.13 ± 22% +0.1 0.28 ± 24%
> perf-profile.children.cycles-pp.account_system_index_time
> 0.49 ± 19% +0.2 0.68 ± 6%
> perf-profile.children.cycles-pp.rcu_irq_enter
> 0.50 ± 12% +0.2 0.69 ± 6%
> perf-profile.children.cycles-pp._raw_spin_lock_irqsave
> 1.05 ± 10% +0.2 1.24 ± 9%
> perf-profile.children.cycles-pp.perf_mux_hrtimer_handler
> 0.85 ± 11% +0.2 1.04 ± 9%
> perf-profile.children.cycles-pp.interrupt_entry
> 0.11 ± 18% +0.2 0.32 ± 27%
> perf-profile.children.cycles-pp.__acct_update_integrals
> 0.29 ± 38% +0.4 0.65 ± 18%
> perf-profile.children.cycles-pp.run_local_timers
> 0.40 ± 9% +0.5 0.86 ± 20%
> perf-profile.children.cycles-pp.update_curr
> 0.00 +0.5 0.54 ± 23%
> perf-profile.children.cycles-pp.memcpy_toio
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.drm_atomic_helper_commit
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.commit_tail
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.drm_atomic_helper_commit_tail
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.drm_atomic_helper_commit_planes
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.mgag200_simple_display_pipe_update
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.mgag200_handle_damage
> 0.00 +0.5 0.54 ± 24%
> perf-profile.children.cycles-pp.drm_fb_memcpy_dstclip
> 0.00 +0.5 0.55 ± 23%
> perf-profile.children.cycles-pp.drm_atomic_helper_dirtyfb
> 0.98 ± 12% +0.9 1.86 ± 26%
> perf-profile.children.cycles-pp.task_tick_fair
> 2.50 ± 7% +1.3 3.76 ± 22%
> perf-profile.children.cycles-pp.scheduler_tick
> 4.46 ± 7% +2.3 6.73 ± 14%
> perf-profile.children.cycles-pp.update_process_times
> 4.75 ± 8% +2.3 7.06 ± 14%
> perf-profile.children.cycles-pp.tick_sched_handle
> 5.24 ± 10% +2.5 7.70 ± 14%
> perf-profile.children.cycles-pp.tick_sched_timer
> 9.34 ± 7% +3.7 13.00 ± 8%
> perf-profile.children.cycles-pp.__hrtimer_run_queues
> 11.80 ± 9% +4.4 16.23 ± 7%
> perf-profile.children.cycles-pp.hrtimer_interrupt
> 19.20 ± 11% +4.8 23.96 ± 5%
> perf-profile.children.cycles-pp.apic_timer_interrupt
> 16.55 ± 10% +5.3 21.88 ± 6%
> perf-profile.children.cycles-pp.smp_apic_timer_interrupt
> 33.71 ± 4% -4.6 29.11 ± 4%
> perf-profile.self.cycles-pp.osq_lock
> 0.14 ± 11% -0.0 0.10 ± 12%
> perf-profile.self.cycles-pp.update_ts_time_stats
> 0.07 ± 16% +0.0 0.09 ± 5%
> perf-profile.self.cycles-pp.update_process_times
> 0.08 ± 5% +0.0 0.11 ± 4%
> perf-profile.self.cycles-pp.raise_softirq
> 0.15 ± 10% +0.0 0.20 ± 7%
> perf-profile.self.cycles-pp.x86_pmu_disable
> 0.17 ± 25% +0.1 0.23 ± 4%
> perf-profile.self.cycles-pp.native_irq_return_iret
> 0.27 +0.1 0.32 ± 12%
> perf-profile.self.cycles-pp.timerqueue_add
> 0.07 ± 58% +0.1 0.12 ± 13%
> perf-profile.self.cycles-pp.hrtimer_run_queues
> 0.22 ± 19% +0.1 0.28 ± 5%
> perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore
> 0.21 ± 11% +0.1 0.27 ± 8%
> perf-profile.self.cycles-pp.tick_program_event
> 0.27 ± 15% +0.1 0.33 ± 3%
> perf-profile.self.cycles-pp.read_tsc
> 0.16 ± 11% +0.1 0.23 ± 13%
> perf-profile.self.cycles-pp.scheduler_tick
> 0.17 ± 9% +0.1 0.24 ± 18%
> perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
> 0.03 ±100% +0.1 0.11 ± 30%
> perf-profile.self.cycles-pp.cpuacct_account_field
> 0.08 ± 5% +0.1 0.18 ± 13%
> perf-profile.self.cycles-pp.cpuacct_charge
> 0.23 ± 16% +0.1 0.34 ± 8%
> perf-profile.self.cycles-pp.apic_timer_interrupt
> 0.03 ±102% +0.1 0.14 ± 25%
> perf-profile.self.cycles-pp.account_user_time
> 0.58 ± 7% +0.1 0.70 ± 7%
> perf-profile.self.cycles-pp.perf_mux_hrtimer_handler
> 0.11 ± 19% +0.1 0.22 ± 24%
> perf-profile.self.cycles-pp.account_system_index_time
> 0.16 ± 13% +0.1 0.29 ± 14%
> perf-profile.self.cycles-pp.irq_enter
> 0.40 ± 22% +0.1 0.54 ± 8%
> perf-profile.self.cycles-pp._raw_spin_lock_irqsave
> 0.48 ± 3% +0.2 0.64
> perf-profile.self.cycles-pp._raw_spin_lock
> 0.39 ± 20% +0.2 0.55 ± 8%
> perf-profile.self.cycles-pp.rcu_irq_enter
> 0.84 ± 10% +0.2 1.02 ± 9%
> perf-profile.self.cycles-pp.interrupt_entry
> 0.11 ± 18% +0.2 0.32 ± 27%
> perf-profile.self.cycles-pp.__acct_update_integrals
> 0.28 ± 15% +0.3 0.54 ± 32%
> perf-profile.self.cycles-pp.task_tick_fair
> 0.23 ± 37% +0.3 0.53 ± 20%
> perf-profile.self.cycles-pp.run_local_timers
> 0.28 ± 14% +0.4 0.63 ± 21%
> perf-profile.self.cycles-pp.update_curr
> 1.03 ± 16% +0.5 1.50 ± 6%
> perf-profile.self.cycles-pp.smp_apic_timer_interrupt
> 0.00 +0.5 0.49 ± 24%
> perf-profile.self.cycles-pp.memcpy_toio
> 1.08 ± 14% +0.6 1.69 ± 9%
> perf-profile.self.cycles-pp.hrtimer_interrupt
> 1.31 ± 13% +0.6 1.94 ± 7%
> perf-profile.self.cycles-pp.__hrtimer_run_queues
> 3.00 ± 20% +0.8 3.84 ± 18%
> perf-profile.self.cycles-pp.do_access
> 379372 +16.8% 443167 ± 13%
> interrupts.CAL:Function_call_interrupts
> 820.75 ± 32% +92.6% 1581 ± 46%
> interrupts.CPU1.RES:Rescheduling_interrupts
> 292.75 ± 10% +23.7% 362.00 ± 7%
> interrupts.CPU100.TLB:TLB_shootdowns
> 249.00 ± 5% +40.4% 349.50 ± 15%
> interrupts.CPU101.TLB:TLB_shootdowns
> 240.75 ± 15% +36.1% 327.75 ± 10%
> interrupts.CPU105.TLB:TLB_shootdowns
> 251.75 ± 6% +27.4% 320.75 ± 6%
> interrupts.CPU108.TLB:TLB_shootdowns
> 257.50 ± 18% +25.1% 322.25 ± 12%
> interrupts.CPU109.TLB:TLB_shootdowns
> 960.50 ± 44% -35.6% 618.75 ± 11%
> interrupts.CPU11.RES:Rescheduling_interrupts
> 624.50 ± 27% -25.7% 464.00 ± 27%
> interrupts.CPU110.RES:Rescheduling_interrupts
> 243.50 ± 12% +29.7% 315.75 ± 6%
> interrupts.CPU111.TLB:TLB_shootdowns
> 2912 ± 27% -38.2% 1799 ± 3%
> interrupts.CPU113.NMI:Non-maskable_interrupts
> 2912 ± 27% -38.2% 1799 ± 3%
> interrupts.CPU113.PMI:Performance_monitoring_interrupts
> 257.25 ± 2% +26.8% 326.25 ± 5%
> interrupts.CPU113.TLB:TLB_shootdowns
> 2105 ± 33% -26.1% 1555 ± 8%
> interrupts.CPU115.NMI:Non-maskable_interrupts
> 2105 ± 33% -26.1% 1555 ± 8%
> interrupts.CPU115.PMI:Performance_monitoring_interrupts
> 250.00 ± 9% +38.2% 345.50 ± 11%
> interrupts.CPU115.TLB:TLB_shootdowns
> 241.75 ± 13% +59.4% 385.25 ± 11%
> interrupts.CPU116.TLB:TLB_shootdowns
> 1698 ± 30% +53.6% 2607 ± 35%
> interrupts.CPU12.NMI:Non-maskable_interrupts
> 1698 ± 30% +53.6% 2607 ± 35%
> interrupts.CPU12.PMI:Performance_monitoring_interrupts
> 266.25 ± 10% +30.6% 347.75 ± 6%
> interrupts.CPU120.TLB:TLB_shootdowns
> 254.25 ± 23% +34.7% 342.50 ± 10%
> interrupts.CPU122.TLB:TLB_shootdowns
> 1572 ± 7% +76.8% 2779 ± 23%
> interrupts.CPU123.NMI:Non-maskable_interrupts
> 1572 ± 7% +76.8% 2779 ± 23%
> interrupts.CPU123.PMI:Performance_monitoring_interrupts
> 233.75 ± 13% +40.7% 329.00 ± 14%
> interrupts.CPU123.TLB:TLB_shootdowns
> 1836 ± 38% +45.9% 2679 ± 26%
> interrupts.CPU124.NMI:Non-maskable_interrupts
> 1836 ± 38% +45.9% 2679 ± 26%
> interrupts.CPU124.PMI:Performance_monitoring_interrupts
> 276.50 ± 14% +23.1% 340.50 ± 7%
> interrupts.CPU124.TLB:TLB_shootdowns
> 256.00 ± 18% +44.8% 370.75 ± 13%
> interrupts.CPU125.TLB:TLB_shootdowns
> 249.00 ± 15% +38.4% 344.50 ± 5%
> interrupts.CPU127.TLB:TLB_shootdowns
> 253.75 ± 22% +70.8% 433.50 ± 47%
> interrupts.CPU129.TLB:TLB_shootdowns
> 1443 ± 14% +71.9% 2481 ± 20%
> interrupts.CPU130.NMI:Non-maskable_interrupts
> 1443 ± 14% +71.9% 2481 ± 20%
> interrupts.CPU130.PMI:Performance_monitoring_interrupts
> 1550 ± 5% +35.2% 2096 ± 21%
> interrupts.CPU133.NMI:Non-maskable_interrupts
> 1550 ± 5% +35.2% 2096 ± 21%
> interrupts.CPU133.PMI:Performance_monitoring_interrupts
> 243.25 ± 20% +61.6% 393.00 ± 5%
> interrupts.CPU134.TLB:TLB_shootdowns
> 2056 ± 23% -21.7% 1609 ± 18%
> interrupts.CPU135.NMI:Non-maskable_interrupts
> 2056 ± 23% -21.7% 1609 ± 18%
> interrupts.CPU135.PMI:Performance_monitoring_interrupts
> 258.75 ± 6% +35.7% 351.25 ± 14%
> interrupts.CPU135.TLB:TLB_shootdowns
> 2346 ± 32% +43.1% 3357 ± 5%
> interrupts.CPU139.NMI:Non-maskable_interrupts
> 2346 ± 32% +43.1% 3357 ± 5%
> interrupts.CPU139.PMI:Performance_monitoring_interrupts
> 507.00 ± 11% -15.0% 431.00 ± 7%
> interrupts.CPU142.RES:Rescheduling_interrupts
> 265.25 ± 13% +40.0% 371.25 ± 6%
> interrupts.CPU142.TLB:TLB_shootdowns
> 1453 ± 9% +54.0% 2238 ± 18%
> interrupts.CPU143.NMI:Non-maskable_interrupts
> 1453 ± 9% +54.0% 2238 ± 18%
> interrupts.CPU143.PMI:Performance_monitoring_interrupts
> 1572 ± 12% +57.7% 2479 ± 16%
> interrupts.CPU147.NMI:Non-maskable_interrupts
> 1572 ± 12% +57.7% 2479 ± 16%
> interrupts.CPU147.PMI:Performance_monitoring_interrupts
> 201.25 ± 13% +53.5% 309.00 ± 8%
> interrupts.CPU147.TLB:TLB_shootdowns
> 229.75 ± 7% +31.8% 302.75 ± 15%
> interrupts.CPU149.TLB:TLB_shootdowns
> 238.50 ± 3% +24.7% 297.50 ± 3%
> interrupts.CPU150.TLB:TLB_shootdowns
> 221.00 ± 14% +23.4% 272.75 ± 9%
> interrupts.CPU151.TLB:TLB_shootdowns
> 262.50 ± 13% +34.9% 354.00 ± 17%
> interrupts.CPU152.TLB:TLB_shootdowns
> 223.50 ± 17% +43.1% 319.75 ± 23%
> interrupts.CPU153.TLB:TLB_shootdowns
> 1408 ± 5% +85.5% 2612 ± 42%
> interrupts.CPU154.NMI:Non-maskable_interrupts
> 1408 ± 5% +85.5% 2612 ± 42%
> interrupts.CPU154.PMI:Performance_monitoring_interrupts
> 218.50 ± 20% +41.5% 309.25 ± 8%
> interrupts.CPU154.TLB:TLB_shootdowns
> 1788 ± 32% +38.7% 2480 ± 27%
> interrupts.CPU155.NMI:Non-maskable_interrupts
> 1788 ± 32% +38.7% 2480 ± 27%
> interrupts.CPU155.PMI:Performance_monitoring_interrupts
> 226.00 ± 8% +55.5% 351.50 ± 9%
> interrupts.CPU155.TLB:TLB_shootdowns
> 226.75 ± 15% +28.7% 291.75 ± 9%
> interrupts.CPU160.TLB:TLB_shootdowns
> 428.25 ± 15% +40.7% 602.50 ± 31%
> interrupts.CPU162.RES:Rescheduling_interrupts
> 214.75 ± 5% +36.0% 292.00 ± 15%
> interrupts.CPU163.TLB:TLB_shootdowns
> 233.75 ± 20% +38.8% 324.50 ± 6%
> interrupts.CPU164.TLB:TLB_shootdowns
> 223.75 ± 13% +36.0% 304.25 ± 13%
> interrupts.CPU168.TLB:TLB_shootdowns
> 1319 +17.4% 1548 ± 13%
> interrupts.CPU17.CAL:Function_call_interrupts
> 1515 ± 6% +40.0% 2121 ± 35%
> interrupts.CPU170.NMI:Non-maskable_interrupts
> 1515 ± 6% +40.0% 2121 ± 35%
> interrupts.CPU170.PMI:Performance_monitoring_interrupts
> 405.00 ± 11% +26.9% 513.75 ± 13%
> interrupts.CPU170.RES:Rescheduling_interrupts
> 251.00 ± 18% +21.5% 305.00 ± 8%
> interrupts.CPU170.TLB:TLB_shootdowns
> 219.50 ± 12% +73.7% 381.25 ± 45%
> interrupts.CPU172.TLB:TLB_shootdowns
> 225.25 ± 7% +51.6% 341.50 ± 9%
> interrupts.CPU175.TLB:TLB_shootdowns
> 229.50 ± 12% +34.5% 308.75 ± 7%
> interrupts.CPU177.TLB:TLB_shootdowns
> 210.25 ± 10% +32.0% 277.50 ± 8%
> interrupts.CPU179.TLB:TLB_shootdowns
> 227.75 ± 7% +29.3% 294.50 ± 8%
> interrupts.CPU184.TLB:TLB_shootdowns
> 204.25 ± 11% +50.9% 308.25 ± 18%
> interrupts.CPU188.TLB:TLB_shootdowns
> 219.50 ± 17% +55.7% 341.75 ± 10%
> interrupts.CPU189.TLB:TLB_shootdowns
> 230.50 ± 17% +42.0% 327.25 ± 9%
> interrupts.CPU192.TLB:TLB_shootdowns
> 248.50 ± 11% +24.6% 309.75 ± 13%
> interrupts.CPU193.TLB:TLB_shootdowns
> 193.00 ± 15% +42.9% 275.75 ± 18%
> interrupts.CPU194.TLB:TLB_shootdowns
> 218.25 ± 13% +46.8% 320.50 ± 7%
> interrupts.CPU196.TLB:TLB_shootdowns
> 446.00 ± 5% -14.0% 383.50 ± 7%
> interrupts.CPU197.RES:Rescheduling_interrupts
> 215.00 ± 8% +52.7% 328.25 ± 7%
> interrupts.CPU197.TLB:TLB_shootdowns
> 252.25 ± 8% +28.9% 325.25 ± 2%
> interrupts.CPU200.TLB:TLB_shootdowns
> 234.75 ± 5% +28.2% 301.00 ± 4%
> interrupts.CPU202.TLB:TLB_shootdowns
> 222.25 ± 5% +25.8% 279.50 ± 12%
> interrupts.CPU203.TLB:TLB_shootdowns
> 196.25 ± 12% +51.1% 296.50 ± 7%
> interrupts.CPU208.TLB:TLB_shootdowns
> 248.50 ± 12% +44.7% 359.50 ± 13%
> interrupts.CPU210.TLB:TLB_shootdowns
> 234.50 ± 12% +41.6% 332.00 ± 13%
> interrupts.CPU211.TLB:TLB_shootdowns
> 251.00 ± 16% +36.3% 342.00 ± 6%
> interrupts.CPU212.TLB:TLB_shootdowns
> 1546 ± 3% +16.4% 1801 ± 5%
> interrupts.CPU213.NMI:Non-maskable_interrupts
> 1546 ± 3% +16.4% 1801 ± 5%
> interrupts.CPU213.PMI:Performance_monitoring_interrupts
> 242.00 ± 16% +35.0% 326.75 ± 15%
> interrupts.CPU214.TLB:TLB_shootdowns
> 241.00 ± 5% +14.0% 274.75 ± 7%
> interrupts.CPU216.TLB:TLB_shootdowns
> 1606 ± 8% +59.7% 2565 ± 29%
> interrupts.CPU218.NMI:Non-maskable_interrupts
> 1606 ± 8% +59.7% 2565 ± 29%
> interrupts.CPU218.PMI:Performance_monitoring_interrupts
> 207.25 ± 17% +42.6% 295.50 ± 13%
> interrupts.CPU218.TLB:TLB_shootdowns
> 2282 ± 27% +59.4% 3638 ± 2%
> interrupts.CPU221.NMI:Non-maskable_interrupts
> 2282 ± 27% +59.4% 3638 ± 2%
> interrupts.CPU221.PMI:Performance_monitoring_interrupts
> 245.00 ± 11% +23.3% 302.00 ± 14%
> interrupts.CPU222.TLB:TLB_shootdowns
> 387.00 ± 12% +39.6% 540.25 ± 20%
> interrupts.CPU225.RES:Rescheduling_interrupts
> 224.50 ± 17% +42.0% 318.75 ± 17%
> interrupts.CPU226.TLB:TLB_shootdowns
> 234.25 ± 14% +19.4% 279.75 ± 6%
> interrupts.CPU228.TLB:TLB_shootdowns
> 410.75 ± 6% +17.1% 481.00 ± 4%
> interrupts.CPU23.TLB:TLB_shootdowns
> 233.25 ± 7% +27.1% 296.50 ± 17%
> interrupts.CPU231.TLB:TLB_shootdowns
> 205.00 ± 4% +40.7% 288.50 ± 13%
> interrupts.CPU232.TLB:TLB_shootdowns
> 1716 ± 32% +30.2% 2234 ± 22%
> interrupts.CPU233.NMI:Non-maskable_interrupts
> 1716 ± 32% +30.2% 2234 ± 22%
> interrupts.CPU233.PMI:Performance_monitoring_interrupts
> 233.50 ± 13% +27.2% 297.00 ± 8%
> interrupts.CPU233.TLB:TLB_shootdowns
> 230.00 ± 10% +23.5% 284.00 ± 6%
> interrupts.CPU236.TLB:TLB_shootdowns
> 220.25 ± 12% +27.4% 280.50 ± 12%
> interrupts.CPU237.TLB:TLB_shootdowns
> 526.75 ± 6% +19.4% 628.75 ± 8%
> interrupts.CPU24.RES:Rescheduling_interrupts
> 245.25 ± 10% +28.8% 316.00 ± 9%
> interrupts.CPU241.TLB:TLB_shootdowns
> 1666 ± 7% +44.9% 2414 ± 27%
> interrupts.CPU246.NMI:Non-maskable_interrupts
> 1666 ± 7% +44.9% 2414 ± 27%
> interrupts.CPU246.PMI:Performance_monitoring_interrupts
> 243.75 ± 7% +31.6% 320.75 ± 16%
> interrupts.CPU246.TLB:TLB_shootdowns
> 225.50 ± 4% +42.0% 320.25 ± 4%
> interrupts.CPU247.TLB:TLB_shootdowns
> 190.50 ± 26% +49.6% 285.00 ± 6%
> interrupts.CPU248.TLB:TLB_shootdowns
> 210.75 ± 12% +31.8% 277.75 ± 10%
> interrupts.CPU249.TLB:TLB_shootdowns
> 357.50 ± 17% +29.7% 463.50 ± 5%
> interrupts.CPU250.RES:Rescheduling_interrupts
> 220.50 ± 12% +40.8% 310.50 ± 13%
> interrupts.CPU251.TLB:TLB_shootdowns
> 235.25 ± 18% +35.4% 318.50 ± 8%
> interrupts.CPU252.TLB:TLB_shootdowns
> 234.75 ± 15% +35.1% 317.25 ± 7%
> interrupts.CPU253.TLB:TLB_shootdowns
> 1603 ± 10% +53.1% 2455 ± 34%
> interrupts.CPU254.NMI:Non-maskable_interrupts
> 1603 ± 10% +53.1% 2455 ± 34%
> interrupts.CPU254.PMI:Performance_monitoring_interrupts
> 198.50 ± 16% +39.2% 276.25 ± 6%
> interrupts.CPU254.TLB:TLB_shootdowns
> 211.50 ± 10% +52.5% 322.50 ± 14%
> interrupts.CPU255.TLB:TLB_shootdowns
> 370.25 ± 12% +24.2% 459.75 ± 9%
> interrupts.CPU256.RES:Rescheduling_interrupts
> 222.25 ± 8% +42.6% 317.00 ± 10%
> interrupts.CPU256.TLB:TLB_shootdowns
> 239.75 ± 9% +31.7% 315.75 ± 14%
> interrupts.CPU257.TLB:TLB_shootdowns
> 1767 ± 36% +36.5% 2412 ± 27%
> interrupts.CPU26.NMI:Non-maskable_interrupts
> 1767 ± 36% +36.5% 2412 ± 27%
> interrupts.CPU26.PMI:Performance_monitoring_interrupts
> 238.00 ± 18% +25.7% 299.25 ± 11%
> interrupts.CPU260.TLB:TLB_shootdowns
> 233.50 ± 7% +34.4% 313.75 ± 6%
> interrupts.CPU261.TLB:TLB_shootdowns
> 220.75 ± 12% +19.9% 264.75 ± 9%
> interrupts.CPU262.TLB:TLB_shootdowns
> 345.00 ± 16% +35.0% 465.75 ± 15%
> interrupts.CPU264.RES:Rescheduling_interrupts
> 213.00 ± 14% +35.9% 289.50 ± 17%
> interrupts.CPU266.TLB:TLB_shootdowns
> 244.00 ± 12% +27.6% 311.25 ± 11%
> interrupts.CPU267.TLB:TLB_shootdowns
> 209.00 ± 19% +52.0% 317.75 ± 11%
> interrupts.CPU268.TLB:TLB_shootdowns
> 214.00 ± 16% +46.0% 312.50 ± 9%
> interrupts.CPU269.TLB:TLB_shootdowns
> 1509 ± 8% +56.1% 2356 ± 27%
> interrupts.CPU27.NMI:Non-maskable_interrupts
> 1509 ± 8% +56.1% 2356 ± 27%
> interrupts.CPU27.PMI:Performance_monitoring_interrupts
> 465.75 ± 11% +20.7% 562.00 ± 6%
> interrupts.CPU27.TLB:TLB_shootdowns
> 226.50 ± 11% +28.7% 291.50 ± 9%
> interrupts.CPU273.TLB:TLB_shootdowns
> 219.50 ± 16% +31.0% 287.50 ± 14%
> interrupts.CPU274.TLB:TLB_shootdowns
> 385.25 ± 17% +149.0% 959.25 ± 69%
> interrupts.CPU275.RES:Rescheduling_interrupts
> 234.00 ± 12% +32.8% 310.75 ± 3%
> interrupts.CPU277.TLB:TLB_shootdowns
> 223.00 ± 19% +34.8% 300.50 ± 5%
> interrupts.CPU279.TLB:TLB_shootdowns
> 1321 +17.4% 1551 ± 12%
> interrupts.CPU28.CAL:Function_call_interrupts
> 235.75 ± 16% +37.3% 323.75 ± 8%
> interrupts.CPU280.TLB:TLB_shootdowns
> 1648 ± 5% -9.3% 1494 ± 5%
> interrupts.CPU282.NMI:Non-maskable_interrupts
> 1648 ± 5% -9.3% 1494 ± 5%
> interrupts.CPU282.PMI:Performance_monitoring_interrupts
> 230.00 ± 8% +48.7% 342.00 ± 16%
> interrupts.CPU282.TLB:TLB_shootdowns
> 2575 ± 34% -26.0% 1906 ± 42%
> interrupts.CPU283.NMI:Non-maskable_interrupts
> 2575 ± 34% -26.0% 1906 ± 42%
> interrupts.CPU283.PMI:Performance_monitoring_interrupts
> 234.75 ± 10% +25.8% 295.25 ± 12%
> interrupts.CPU283.TLB:TLB_shootdowns
> 1731 ± 55% +87.9% 3253 ± 24%
> interrupts.CPU284.NMI:Non-maskable_interrupts
> 1731 ± 55% +87.9% 3253 ± 24%
> interrupts.CPU284.PMI:Performance_monitoring_interrupts
> 1937 ± 37% +48.0% 2867 ± 28%
> interrupts.CPU30.NMI:Non-maskable_interrupts
> 1937 ± 37% +48.0% 2867 ± 28%
> interrupts.CPU30.PMI:Performance_monitoring_interrupts
> 1316 +17.7% 1549 ± 13%
> interrupts.CPU31.CAL:Function_call_interrupts
> 396.00 ± 4% +29.9% 514.50 ± 17%
> interrupts.CPU31.TLB:TLB_shootdowns
> 443.75 ± 4% +28.0% 568.00 ± 7%
> interrupts.CPU32.TLB:TLB_shootdowns
> 468.75 ± 4% +29.2% 605.50 ± 10%
> interrupts.CPU34.TLB:TLB_shootdowns
> 1507 ± 16% +52.9% 2303 ± 37%
> interrupts.CPU35.NMI:Non-maskable_interrupts
> 1507 ± 16% +52.9% 2303 ± 37%
> interrupts.CPU35.PMI:Performance_monitoring_interrupts
> 439.75 ± 2% +26.4% 556.00 ± 13%
> interrupts.CPU37.TLB:TLB_shootdowns
> 497.25 ± 12% +24.7% 620.00 ± 5%
> interrupts.CPU38.TLB:TLB_shootdowns
> 1470 ± 12% +111.5% 3110 ± 24%
> interrupts.CPU4.NMI:Non-maskable_interrupts
> 1470 ± 12% +111.5% 3110 ± 24%
> interrupts.CPU4.PMI:Performance_monitoring_interrupts
> 1322 +17.4% 1552 ± 12%
> interrupts.CPU42.CAL:Function_call_interrupts
> 525.75 ± 9% +17.0% 615.00 ± 8%
> interrupts.CPU44.TLB:TLB_shootdowns
> 496.50 ± 8% +19.4% 593.00 ± 5%
> interrupts.CPU48.TLB:TLB_shootdowns
> 452.75 ± 8% +20.6% 546.00 ± 3%
> interrupts.CPU50.TLB:TLB_shootdowns
> 461.00 ± 3% +38.2% 637.25 ± 3%
> interrupts.CPU52.TLB:TLB_shootdowns
> 472.50 ± 5% +22.8% 580.00 ± 10%
> interrupts.CPU56.TLB:TLB_shootdowns
> 727.50 ± 28% -38.7% 446.25 ± 11%
> interrupts.CPU57.RES:Rescheduling_interrupts
> 412.00 ± 8% +20.1% 495.00 ± 8%
> interrupts.CPU59.TLB:TLB_shootdowns
> 456.75 ± 6% +19.5% 546.00 ± 9%
> interrupts.CPU6.TLB:TLB_shootdowns
> 461.25 ± 8% +24.0% 572.00 ± 8%
> interrupts.CPU61.TLB:TLB_shootdowns
> 722.25 ± 12% -19.8% 579.50 ± 17%
> interrupts.CPU64.RES:Rescheduling_interrupts
> 851.00 ± 32% -43.3% 482.25 ± 8%
> interrupts.CPU65.RES:Rescheduling_interrupts
> 496.75 ± 10% +22.6% 609.25 ± 6%
> interrupts.CPU66.TLB:TLB_shootdowns
> 1426 ± 14% +53.2% 2184 ± 31%
> interrupts.CPU69.NMI:Non-maskable_interrupts
> 1426 ± 14% +53.2% 2184 ± 31%
> interrupts.CPU69.PMI:Performance_monitoring_interrupts
> 754.00 ± 13% -23.5% 576.75 ± 20%
> interrupts.CPU71.RES:Rescheduling_interrupts
> 1538 ± 10% +112.0% 3260 ± 21%
> interrupts.CPU76.NMI:Non-maskable_interrupts
> 1538 ± 10% +112.0% 3260 ± 21%
> interrupts.CPU76.PMI:Performance_monitoring_interrupts
> 230.00 ± 12% +38.5% 318.50 ± 16%
> interrupts.CPU76.TLB:TLB_shootdowns
> 635.00 ± 18% -25.6% 472.75 ± 10%
> interrupts.CPU78.RES:Rescheduling_interrupts
> 1414 ± 7% +114.8% 3037 ± 31%
> interrupts.CPU83.NMI:Non-maskable_interrupts
> 1414 ± 7% +114.8% 3037 ± 31%
> interrupts.CPU83.PMI:Performance_monitoring_interrupts
> 250.50 ± 14% +26.0% 315.75 ± 6%
> interrupts.CPU84.TLB:TLB_shootdowns
> 1691 ± 23% +72.8% 2922 ± 30%
> interrupts.CPU89.NMI:Non-maskable_interrupts
> 1691 ± 23% +72.8% 2922 ± 30%
> interrupts.CPU89.PMI:Performance_monitoring_interrupts
> 476.75 ± 4% +45.5% 693.50 ± 33%
> interrupts.CPU9.TLB:TLB_shootdowns
> 410.50 ± 11% +68.9% 693.50 ± 36%
> interrupts.CPU94.RES:Rescheduling_interrupts
> 264.50 ± 19% +26.2% 333.75 ± 9%
> interrupts.CPU94.TLB:TLB_shootdowns
> 255.00 ± 6% +37.3% 350.00 ± 8%
> interrupts.CPU95.TLB:TLB_shootdowns
> 309.50 ± 2% +17.0% 362.25 ± 7%
> interrupts.CPU96.TLB:TLB_shootdowns
> 1431 ± 11% +73.4% 2481 ± 31%
> interrupts.CPU98.NMI:Non-maskable_interrupts
> 1431 ± 11% +73.4% 2481 ± 31%
> interrupts.CPU98.PMI:Performance_monitoring_interrupts
> 424.75 ± 11% +36.1% 578.25 ± 10%
> interrupts.CPU98.RES:Rescheduling_interrupts
> 267.50 ± 10% +27.4% 340.75 ± 12%
> interrupts.CPU98.TLB:TLB_shootdowns
> 87577 ± 3% +19.4% 104533 interrupts.TLB:TLB_shootdowns
>
>
>
>
> vm-scalability.throughput
>
>
>
> 1.2e+07 +----------------------------------------------------------------+
>
> | O O O O O |
>
> 1.15e+07 |-+ O O |
>
> 1.1e+07 |-+ O O O O |
>
> | O O O O |
>
> 1.05e+07 |-+ O O O O O O O |
>
> 1e+07 |-+ |
>
> | |
>
> 9.5e+06 |-+ .+ .+ .+ |
>
> 9e+06 |.+ + + + + .+.+ + |
>
> | : : +.+.. + + +. + + .+ +..+ |
>
> 8.5e+06 |-+: : + + .. + + + + + |
>
> 8e+06 |-+ +..+. : +.+.+.+ + + +.+.|
>
> | + |
>
> 7.5e+06 +----------------------------------------------------------------+
>
>
>
>
>
> [*] bisect-good sample
> [O] bisect-bad sample
>
>
>
> Disclaimer:
> Results have been estimated based on internal Intel analysis and are provided
> for informational purposes only. Any difference in system hardware or software
> design or configuration may affect actual performance.
>
>
> Thanks,
> Rong Chen
>
--
Thomas Zimmermann
Graphics Driver Developer
SUSE Software Solutions Germany GmbH
Maxfeldstr. 5, 90409 Nürnberg, Germany
(HRB 36809, AG Nürnberg)
Geschäftsführer: Felix Imendörffer
signature.asc
Description: OpenPGP digital signature
