[gentoo-user] Interpreting /proc/cpuinfo

[gentoo-user] Interpreting /proc/cpuinfo

[Florian Philipp]

[-- Attachment #1: Type: text/plain, Size: 1100 bytes --]

Hi list!

Does this output from /proc/cpuinfo make any sense:

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 26
model name      : Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
stepping        : 5
cpu MHz         : 141.318
cache size      : 8192 KB
physical id     : 1
siblings        : 8
core id         : 0
cpu cores       : 4
apicid          : 16
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
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 syscall
nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx est tm2
cx16 xtpr popcnt lahf_lm
bogomips        : 4525.39
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management: [8]

[...]

Shouldn't the E5520 be Nehalem based and therefore have a flag for ssse3
and sse4?

Could the missing flags be related to a too old kernel (2.6.18)?

Thanks in advance!

Florian Philipp


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 261 bytes --]

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Keith Dart]

=== On Fri, 10/09, Florian Philipp wrote: ===
> Could the missing flags be related to a too old kernel (2.6.18)?

===

Yes, and also how you compile it (what processor type you choose).
Also, some CPU features are altered by the BIOS settings. 

-- Keith Dart

-- 
-- --------------------
Keith Dart
<keith@dartworks.biz>
=======================

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Volker Armin Hemmann]

On Samstag 10 Oktober 2009, Keith Dart wrote:
> === On Fri, 10/09, Florian Philipp wrote: ===
> 
> > Could the missing flags be related to a too old kernel (2.6.18)?
> 
> ===
> 
> Yes, and also how you compile it (what processor type you choose).

not really

> Also, some CPU features are altered by the BIOS settings.

seldomly.

First of all 2.6.18 is not only old, it is a security risk. Seriously, why do 
you (OP) even bother to sent an email to the list without first upgrading to a 
more recent one and checking if the problem persists?

Re: [gentoo-user] Interpreting /proc/cpuinfo

[kashani]

Volker Armin Hemmann wrote:
> On Samstag 10 Oktober 2009, Keith Dart wrote:
>> === On Fri, 10/09, Florian Philipp wrote: ===
>>
>>> Could the missing flags be related to a too old kernel (2.6.18)?
>> ===
>>
>> Yes, and also how you compile it (what processor type you choose).
> 
> not really
> 
>> Also, some CPU features are altered by the BIOS settings.
> 
> seldomly.
> 
> First of all 2.6.18 is not only old, it is a security risk. Seriously, why do 
> you (OP) even bother to sent an email to the list without first upgrading to a 
> more recent one and checking if the problem persists?
> 

Cause if you've been following Florian's post you'd see that he's 
running a VPS which is probably a heavily patched 2.6.18. At least my 
VPS is like that. Come on, don't you read everyone's post?

Yeah BIOS can effect it, the kernel not so much. Not sure about an 
openvz style VPS.

kashani

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Keith Dart]

=== On Sat, 10/10, Volker Armin Hemmann wrote: ===
> First of all 2.6.18 is not only old, it is a security risk.
> Seriously, why do you (OP) even bother to sent an email to the list
> without first upgrading to a more recent one and checking if the
> problem persists?

===

It's possible he's running Xen kernel or something in which case he's
stuck with that version. 


-- Keith Dart

-- 
-- --------------------
Keith Dart
<keith@dartworks.biz>
=======================

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Florian Philipp]

[-- Attachment #1: Type: text/plain, Size: 797 bytes --]

Volker Armin Hemmann schrieb:
> On Samstag 10 Oktober 2009, Keith Dart wrote:
>> === On Fri, 10/09, Florian Philipp wrote: ===
>>
>>> Could the missing flags be related to a too old kernel (2.6.18)?
>> ===
>>
>> Yes, and also how you compile it (what processor type you choose).
> 
> not really
> 
>> Also, some CPU features are altered by the BIOS settings.
> 
> seldomly.
> 
> First of all 2.6.18 is not only old, it is a security risk. Seriously, why do 
> you (OP) even bother to sent an email to the list without first upgrading to a 
> more recent one and checking if the problem persists?
> 

It's exactly like Kashani and Keith suspected: It's a VPS and I have no
influence on the kernel. Well, at least it's no longer version 2.6.9
like it was with the last VPS.


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 261 bytes --]

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Renat Golubchyk]

[-- Attachment #1: Type: text/plain, Size: 2311 bytes --]

Hi!

On Fri, 09 Oct 2009 20:40:44 +0200 Florian Philipp
<lists@f_philipp.fastmail.net> wrote:
> Does this output from /proc/cpuinfo make any sense:
> 
> processor       : 0
> vendor_id       : GenuineIntel
> cpu family      : 6
> model           : 26
> model name      : Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
> stepping        : 5
> cpu MHz         : 141.318
> cache size      : 8192 KB
> physical id     : 1
> siblings        : 8
> core id         : 0
> cpu cores       : 4
> apicid          : 16
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 11
> wp              : yes
> 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 syscall
> nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx est
> tm2 cx16 xtpr popcnt lahf_lm
> bogomips        : 4525.39
> clflush size    : 64
> cache_alignment : 64
> address sizes   : 40 bits physical, 48 bits virtual
> power management: [8]

This is what I have on a patched Ubuntu server with a custom
kernel 2.6.29:

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 26
model name      : Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
stepping        : 5
cpu MHz         : 2261.139
cache size      : 8192 KB
physical id     : 1
siblings        : 8
core id         : 0
cpu cores       : 4
apicid          : 16
initial apicid  : 16
fpu             : yes
fpu_exception   : yes
cpuid level     : 11
wp              : yes
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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
xtopology nonstop_tsc pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16
xtpr pdcm dca sse4_1 sse4_2 lahf_lm ida tpr_shadow vnmi flexpriority
ept vpid
bogomips        : 4522.27
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management:


/proc/cpuinfo shows 8 CPUs because of HyperThreading.


Cheers,
Renat

-- 
Probleme kann man niemals mit derselben Denkweise loesen,
durch die sie entstanden sind.
                                              (Einstein)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 198 bytes --]

Re: [gentoo-user] Interpreting /proc/cpuinfo

[Florian Philipp]

[-- Attachment #1: Type: text/plain, Size: 2313 bytes --]

Renat Golubchyk schrieb:
> Hi!
> 
> On Fri, 09 Oct 2009 20:40:44 +0200 Florian Philipp
> <lists@f_philipp.fastmail.net> wrote:
>> Does this output from /proc/cpuinfo make any sense:
>>
>> processor       : 0
>> vendor_id       : GenuineIntel
>> cpu family      : 6
>> model           : 26
>> model name      : Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
>> stepping        : 5
>> cpu MHz         : 141.318
>> cache size      : 8192 KB
>> physical id     : 1
>> siblings        : 8
>> core id         : 0
>> cpu cores       : 4
>> apicid          : 16
>> fpu             : yes
>> fpu_exception   : yes
>> cpuid level     : 11
>> wp              : yes
>> 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 syscall
>> nx rdtscp lm constant_tsc ida nonstop_tsc pni monitor ds_cpl vmx est
>> tm2 cx16 xtpr popcnt lahf_lm
>> bogomips        : 4525.39
>> clflush size    : 64
>> cache_alignment : 64
>> address sizes   : 40 bits physical, 48 bits virtual
>> power management: [8]
> 
> This is what I have on a patched Ubuntu server with a custom
> kernel 2.6.29:
> 
> processor       : 0
> vendor_id       : GenuineIntel
> cpu family      : 6
> model           : 26
> model name      : Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
> stepping        : 5
> cpu MHz         : 2261.139
> cache size      : 8192 KB
> physical id     : 1
> siblings        : 8
> core id         : 0
> cpu cores       : 4
> apicid          : 16
> initial apicid  : 16
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 11
> wp              : yes
> 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 rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> xtopology nonstop_tsc pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16
> xtpr pdcm dca sse4_1 sse4_2 lahf_lm ida tpr_shadow vnmi flexpriority
> ept vpid
> bogomips        : 4522.27
> clflush size    : 64
> cache_alignment : 64
> address sizes   : 40 bits physical, 48 bits virtual
> power management:
> 
> 
> /proc/cpuinfo shows 8 CPUs because of HyperThreading.
> 
> 
> Cheers,
> Renat
> 

Thanks!


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 261 bytes --]