Bug 239595

Summary:	xen dom0 kernel shows wrong values in /proc/cpuinfo
Product:	Red Hat Enterprise Linux 5	Reporter:	Hannes Kuehnemund <hannes.kuehnemund>
Component:	kernel	Assignee:	Rik van Riel <riel>
Status:	CLOSED WORKSFORME	QA Contact:	Red Hat Kernel QE team <kernel-qe>
Severity:	medium	Docs Contact:
Priority:	medium
Version:	5.0	CC:	clalance, linux, phil.coleman, rdoty, sputhenp, tao, tobias_moosherr
Target Milestone:	---
Target Release:	---
Hardware:	x86_64
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	Bug Fix
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2009-09-16 20:19:42 UTC	Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description Hannes Kuehnemund 2007-05-09 19:11:16 UTC

Description of problem:
Having a Intel x346 Server, 4 Socket holding a dualcore Xeon (Paxville) each,
using the -xen kernel does show wrong values in /proc/cpuinfo:

# uname -a
Linux ls3121 2.6.18-8.el5 #1 SMP Fri Jan 26 14:15:14 EST 2007 x86_64 x86_64
x86_64 GNU/Linux
# cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 15
model           : 4
model name      :                    Genuine Intel(R) CPU 3.00GHz
stepping        : 8
cpu MHz         : 3002.586
cache size      : 2048 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
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 lm constant_tsc
pni monitor ds_cpl vmx est tm2 cid cx16 xtpr lahf_lm
bogomips        : 6008.87
clflush size    : 64
cache_alignment : 128
address sizes   : 40 bits physical, 48 bits virtual
power management:

whereas:
# uname -a
Linux ls3121 2.6.18-8.el5xen #1 SMP Fri Jan 26 14:29:35 EST 2007 x86_64 x86_64
x86_64 GNU/Linux
# cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 15
model           : 4
model name      :                    Genuine Intel(R) CPU 3.00GHz
stepping        : 8
cpu MHz         : 4246.996
cache size      : 2048 KB
physical id     : 0
siblings        : 1
core id         : 0
cpu cores       : 1
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu tsc msr pae mce cx8 apic mtrr mca cmov pat pse36 clflush
dts acpi mmx fxsr sse sse2 ss ht tm syscall lm constant_tsc pni monitor ds_cpl
vmx est tm2 cid cx16 xtpr lahf_lm
bogomips        : 10598.66
clflush size    : 64
cache_alignment : 128
address sizes   : 40 bits physical, 48 bits virtual
power management:

Mhz differ for both kernels:
std: cpu MHz         : 3002.586 <-- correct
xen: cpu MHz         : 4246.996 <-- wrong!

Version-Release number of selected component (if applicable):
# rpm -q kernel
kernel-2.6.18-8.el5
# rpm -q kernel-xen
kernel-xen-2.6.18-8.el5

How reproducible:
always

Steps to Reproduce:
1. boot kernel (xen or standard)
2. cat /proc/cpuinfo
  
Actual results:
xen kernel shows wrong Mhz

Expected results:
xen kernel shows correct Mhz

Comment 3 Chris Lalancette 2009-09-10 16:16:14 UTC

Can you please check if this is still an issue with RHEL-5.4?  There have been many, many timer fixes since this was reported against 5.0, and those timer fixes have also fixed some situations where we would wrongly report CPU information.  If this works in 5.4, we can close this out.

Thanks,
Chris Lalancette

Comment 4 Hannes Kuehnemund 2009-09-16 20:19:42 UTC

Sorry, I cannot verify if the problem is fixed with RHEL5.4 because the particular machine with the particular CPU types showing this issue is no longer in our lab. Therefore I close this bug.