[libvirt] virGetNodeinfo .cpus

Gerrit Slomma roadrunner_gs at web.de
Fri Apr 17 13:39:47 UTC 2009


Zvi Dubitzky schrieb:
> virNodeGetInfo()  returns .cpus as 2  but the  /proc/cpuinfo of the node 
> shows 2 processors with 2 cores each  ('cpu cores')  . Or maybe the 'core 
> id' is what
> counts in the /proc/cpuinfo  and that  one gets vaue 0  , 1 only  i.e 
> totally 2 
>
> can you clarify  ?
>
> Here is the output of /proc/cpuinfo:
>
> processor       : 0
> vendor_id       : AuthenticAMD
> cpu family      : 15
> model           : 65
> model name      : Dual-Core AMD Opteron(tm) Processor 2210 HE
> stepping        : 2
> cpu MHz         : 1800.034
> cache size      : 1024 KB
> physical id     : 0
> siblings        : 2
> core id         : 0
> cpu cores       : 2
> apicid          : 0
> initial apicid  : 0
> fdiv_bug        : no
> hlt_bug         : no
> f00f_bug        : no
> coma_bug        : no
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 1
> wp              : yes
> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca 
> cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt 
> rdtscp lm 3dnowext 3dnow pni cx16 lahf_lm cmp_legacy svm extapic 
> cr8_legacy
> bogomips        : 3600.06
> clflush size    : 64
> power management: ts fid vid ttp tm stc
>
> processor       : 1
> vendor_id       : AuthenticAMD
> cpu family      : 15
> model           : 65
> model name      : Dual-Core AMD Opteron(tm) Processor 2210 HE
> stepping        : 2
> cpu MHz         : 1800.034
> cache size      : 1024 KB
> physical id     : 0
> siblings        : 2
> core id         : 1
> cpu cores       : 2
> apicid          : 1
> initial apicid  : 1
> fdiv_bug        : no
> hlt_bug         : no
> f00f_bug        : no
> coma_bug        : no
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 1
> wp              : yes
> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca 
> cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt 
> rdtscp lm 3dnowext 3dnow pni cx16 lahf_lm cmp_legacy svm extapic 
> cr8_legacy
> bogomips        : 3600.23
> clflush size    : 64
> power management: ts fid vid ttp tm stc
>
>
> Zvi Dubitzky 
> Virtualization and System Architecture   Email:dubi at il.ibm.com
> IBM Haifa Research Laboratory    Phone: +972-4-8296182
> Haifa, 31905, ISRAEL 
>
>
> --
> Libvir-list mailing list
> Libvir-list at redhat.com
> https://www.redhat.com/mailman/listinfo/libvir-list
>   
An Opteron 2210 HE only has two cores. Yours is a single-CPU. Each core 
is on Processor, the core-count is of all cores bound together (i.e. in 
one socket), also called the siblings in /proc/cpuinfo

2x AMD Opteron 2344 => 8 processors, each entry with 4 cores and 4 
siblings (2.6.18-92.1.22.el5)
1x Intel Xeon E5405 => 4 processors, each entry with 4 core and 4 
sibling (2.6.18-53.el5)
2x Intel Xeon E5450 => 8 processors, each etnry with 4 cores and 4 
siblings (2.6.18-53.el5)
1x Intel Core 2 Duo E6550 => 2 processors, each entry with 2 cores and 2 
siblings (2.6.18-128.el5)
1x Intel Core 2 Duo 6400 => 2 processors, each entry with 2 cores and 2 
siblings (2.6.18-128.1.6.el5)
1x Intel Core 2 Duo T8300 => 2 processors, each entry with 2 cores and 2 
siblings (2.6.18-128.el5)

Nothing unexpected here.
Anyways virNodeGetInfo().cpus returns the correct value in your case and 
in all mine tested too, it should be obtained iterating over the 
processor-ids as seen in /proc/cpuinfo.
My sole xen-Host returns for his E5405 1 core and 1 sibling for each 
processor via /proc/cpuinfo.




More information about the libvir-list mailing list