All Threads Core not showing

[Indteamhost]

Hey guys,

I have a little problem regarding the number of cpu threads that can bee read from the os.

Server spec

hpe dl360p gen8
cpu: 2 x E5-2680 v2
Debian Proxmox
Hyperthreading enabled

Threads cpu should be 40 threads from 20 cores, but when I checked from "lscpu and cat /proc/cpuinfo " it only show 20 threads.

before I rebooted the server, the threads still read 40, and after I rebooted it only read 20 threads.


Do you have idea to make all threads showing?

 

[oguz]

hi,

"lscpu and cat /proc/cpuinfo " it only show 20 threads.

could you show the outputs?

before I rebooted the server, the threads still read 40, and after I rebooted it only read 20 threads.

did you do an upgrade before this? what does it say when you run pveversion -v

 

[maxov777]

on my HP elitedesk 800 g2 is running proxmox version 8.1.3

uses 4 cores and 4 threads processor .. why i can use only 4 cores ( assign 4 cores to any VM) and not use also the threads from the processor ?

Architecture:            x86_64
  CPU op-mode(s):        32-bit, 64-bit
  Address sizes:         39 bits physical, 48 bits virtual
  Byte Order:            Little Endian
CPU(s):                  4
  On-line CPU(s) list:   0-3
Vendor ID:               GenuineIntel
  BIOS Vendor ID:        Intel(R) Corporation
  Model name:            Intel(R) Core(TM) i5-6600 CPU @ 3.30GHz
    BIOS Model name:     Intel(R) Core(TM) i5-6600 CPU @ 3.30GHz To Be Filled By O.E.M. CPU @ 3.3GHz
    BIOS CPU family:     205
    CPU family:          6
    Model:               94
    Thread(s) per core:  1
    Core(s) per socket:  4
    Socket(s):           1
    Stepping:            3
    CPU(s) scaling MHz:  59%
    CPU max MHz:         3900.0000
    CPU min MHz:         800.0000
    BogoMIPS:            6599.98
    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 p
                         dpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 mo
                         nitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f
                         16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow flexpriority ept vpid ept_ad
                          fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx rdseed adx smap clflushopt intel_pt xsaveopt xsavec xgetbv1 xsaves dtherm
                         ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp vnmi md_clear flush_l1d arch_capabilities
Virtualization features:
  Virtualization:        VT-x
Caches (sum of all):     
  L1d:                   128 KiB (4 instances)
  L1i:                   128 KiB (4 instances)
  L2:                    1 MiB (4 instances)
  L3:                    6 MiB (1 instance)
NUMA:                   
  NUMA node(s):          1
  NUMA node0 CPU(s):     0-3
Vulnerabilities:         
  Gather data sampling:  Vulnerable: No microcode
  Itlb multihit:         KVM: Mitigation: Split huge pages
  L1tf:                  Mitigation; PTE Inversion; VMX conditional cache flushes, SMT disabled
  Mds:                   Mitigation; Clear CPU buffers; SMT disabled
  Meltdown:              Mitigation; PTI
  Mmio stale data:       Mitigation; Clear CPU buffers; SMT disabled
  Retbleed:              Mitigation; IBRS
  Spec rstack overflow:  Not affected
  Spec store bypass:     Mitigation; Speculative Store Bypass disabled via prctl
  Spectre v1:            Mitigation; usercopy/swapgs barriers and __user pointer sanitization
  Spectre v2:            Mitigation; IBRS, IBPB conditional, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected
  Srbds:                 Mitigation; Microcode
  Tsx async abort:       Mitigation; TSX disabled

should I enable something on the hardware or software level on proxmox .. so i will be able to use 8 cored = 4 real + 4 threads from the CPU ?
I do vaguely recall that when virtualization was done on this computer with vmware .. it did allow me to assign 8 vcpu ( but i am not sure ) and i would like to use proxmox

thank you for your thoughts or help ..

 

[dcsapak]

uses 4 cores and 4 threads processor .. why i can use only 4 cores ( assign 4 cores to any VM) and not use also the threads from the processor ?

4 cores 4 thread does not mean it has 8 to give, it means it has 1 thread per core (as you can see in the lscpu output) and 4 cores, so you have 4 cores in total.
if the cpu would have hyper threading, you would have 2 threads per core and then it would have 8 threads (that you could assign) but your cpu does not have hyper-threading apparently

 

[maxov777]

4 cores 4 thread does not mean it has 8 to give, it means it has 1 thread per core (as you can see in the lscpu output) and 4 cores, so you have 4 cores in total.
if the cpu would have hyper threading, you would have 2 threads per core and then it would have 8 threads (that you could assign) but your cpu does not have hyper-threading apparently

you are correct .. my mistake .. this CPU lacks Hyper-threading

thank you

 

[pavlos]

if I may add to this puzzle ...

I have proxmox 8.1 with cpu E5 2696 v3 (18 cores with HT flag 36). cat /proc/cpuinfo shows me 36 cores (0-35 with HT flag)

sensors shows me fewer and numbers are skipped (missing 5,6,7,12,13,14,15,21 ...

root@pve5:~# sensors
coretemp-isa-0000
Adapter: ISA adapter
Package id 0:  +36.0°C  (high = +70.0°C, crit = +80.0°C)
Core 0:        +31.0°C  (high = +70.0°C, crit = +80.0°C)
Core 1:        +31.0°C  (high = +70.0°C, crit = +80.0°C)
Core 2:        +30.0°C  (high = +70.0°C, crit = +80.0°C)
Core 3:        +27.0°C  (high = +70.0°C, crit = +80.0°C)
Core 4:        +30.0°C  (high = +70.0°C, crit = +80.0°C)
Core 8:        +27.0°C  (high = +70.0°C, crit = +80.0°C)
Core 9:        +31.0°C  (high = +70.0°C, crit = +80.0°C)
Core 10:       +30.0°C  (high = +70.0°C, crit = +80.0°C)
Core 11:       +28.0°C  (high = +70.0°C, crit = +80.0°C)
Core 16:       +25.0°C  (high = +70.0°C, crit = +80.0°C)
Core 17:       +29.0°C  (high = +70.0°C, crit = +80.0°C)
Core 18:       +26.0°C  (high = +70.0°C, crit = +80.0°C)
Core 19:       +27.0°C  (high = +70.0°C, crit = +80.0°C)
Core 20:       +31.0°C  (high = +70.0°C, crit = +80.0°C)
Core 24:       +31.0°C  (high = +70.0°C, crit = +80.0°C)
Core 25:       +29.0°C  (high = +70.0°C, crit = +80.0°C)
Core 26:       +27.0°C  (high = +70.0°C, crit = +80.0°C)
Core 27:       +27.0°C  (high = +70.0°C, crit = +80.0°C)

 

[dcsapak]

sensors shows me fewer and numbers are skipped (missing 5,6,7,12,13,14,15,21 ...

yes it'll only show you 'real' cores (and it does show you 18 of them) the other numbers are the 'hyper-threads' and they don't have their own temperature sensor. idk why it's numbered that way, but i guess that is either baked into the hardware or some kernel enumeration thing