负载下 CPU 时钟下降

Question

因此，我有一台双 Intel Silver 4116 CPU 服务器，它会随机将 MHz 设置为 132，此后服务器将无法使用。即使重新启动也无法恢复 MHz，只有开车到数据中心并关闭服务器 10 秒左右才能恢复到 800 MHz（空闲时钟速度）。

我有：

• 禁用 intel_pstate 驱动程序并验证 acpi-cpufreq 正在运行
• 将调控器设置为性能或用户空间
• 手动设置频率
• 将 bios 更新至最新版本

roderick@super:~$ cpupower frequency-info
analyzing CPU 0:
    driver: acpi-cpufreq
    CPUs which run at the same hardware frequency: 0
    CPUs which need to have their frequency coordinated by software: 0
    maximum transition latency: 10.0 us
    hardware limits: 800 MHz - 2.10 GHz
    available frequency steps:  2.10 GHz, 2.10 GHz, 2.00 GHz, 1.90 GHz, 1.80 GHz, 1.70 GHz, 1.60 GHz, 1.50 GHz, 1.40 GHz, 1.30 GHz, 1.20 GHz, 1.10 GHz, 1000 MHz, 900 MHz, 800 MHz
    available cpufreq governors: conservative ondemand userspace powersave performance schedutil
    current policy: frequency should be within 1.80 GHz and 1.80 GHz.
                    The governor "userspace" may decide which speed to use
                    within this range.
    current CPU frequency: Unable to call hardware
    current CPU frequency: 136 MHz (asserted by call to kernel)
    boost state support:
    Supported: yes
    Active: yes

roderick@super:~$ lscpu
Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              48
On-line CPU(s) list: 0-47
Thread(s) per core:  2
Core(s) per socket:  12
Socket(s):           2
NUMA node(s):        2
Vendor ID:           GenuineIntel
CPU family:          6
Model:               85
Model name:          Intel(R) Xeon(R) Silver 4116 CPU @ 2.10GHz
Stepping:            4
CPU MHz:             132.425
CPU max MHz:         2101.0000
CPU min MHz:         800.0000
BogoMIPS:            4200.00
Virtualisation:      VT-x
L1d cache:           32K
L1i cache:           32K
L2 cache:            1024K
L3 cache:            16896K
NUMA node0 CPU(s):   0-11,24-35
NUMA node1 CPU(s):   12-23,36-47
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke

我很困惑 CPU MHZ 怎么会下降成这样，这不是过热或过度使用，我正在记录温度和利用率。

在性能或用户空间管理器下设置频率没有效果。

roderick@super:~$ sudo cpupower --cpu all frequency-set --freq 800MHz
Setting cpu: 0
Setting cpu: 1
... omitted for clarity
Setting cpu: 46
Setting cpu: 47

• 看来我正在运行最新的微代码

roderick@super:~$ dmesg | grep microcode
[    0.000000] microcode: microcode updated early to revision 0x200004d, date = 2018-05-15
[  141.175011] microcode: sig=0x50654, pf=0x1, revision=0x200004d
[  141.359854] microcode: Microcode Update Driver: v2.2.

• 这种现象大约在一周前开始出现，这是一台 48 核计算机，以 80% 的容量连续运行了 48 小时，6 个月来没有出现任何问题。但现在我将其容量提高到大约 20%，它的时钟频率从 800-2100 MHz 降至 132 MHz。如果我重新启动它并让它闲置，它就没问题了，但当我在其上运行我的机器学习程序时，它就挂了。