Red Hat Bugzilla – Bug 232842
soft lockup when running 'service cpuspeed stop'
Last modified: 2007-11-30 17:11:59 EST
Description of problem:
A soft lockup occurs when stopping the cpuspeed daemon.
Version-Release number of selected component (if applicable):
Steps to Reproduce:
1. service cpuspeed stop (or attempt to shutdown computer)
2. the attached soft lockup occurs.
Created attachment 150339 [details]
kernel stack trace from soft lockup
Can you please give us some details as to what sort of system you're seeing this
on? (System vendor, cpu type, whether or not you're running the latest bios for
*** Bug 232903 has been marked as a duplicate of this bug. ***
Seeing this on an IBM ThinkPad X60s, Core Duo, 1.66GHz.
This is the first kernel to show this.
I am seeing it on a Dell Latitude D820, Centrino Duo 1.8GHz. Do you want the
output from /proc/cpuinfo as well?
Created attachment 150475 [details]
output of /proc/cpuinfo && uname -mrp
Don't know if you need it :-)
Okay, seems the breakage is Intel's fault, but they're looking into it, so just
sit tight and it ought to be sorted out shortly... :)
*** Bug 233225 has been marked as a duplicate of this bug. ***
So i have an AuthenticAMD can we still blame Intel?
vendor_id : AuthenticAMD
cpu family : 15
model : 95
model name : AMD Athlon(tm) 64 Processor 3200+
stepping : 2
cpu MHz : 1000.000
cache size : 512 KB
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 syscall nx mmxext fxsr_opt rdtscp lm
3dnowext 3dnow pni cx16 lahf_lm svm extapic cr8_legacy
bogomips : 2005.75
TLB size : 1024 4K pages
clflush size : 64
cache_alignment : 64
address sizes : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp tm stc
2.6.20-1.2999.fc7 x86_64 x86_64
Yep, these code changes were done in the frequency scaling code, not in any
intel-processor-specific code. From what davej tells me, w/o the change they
made, the ondemand governor was waking up about 100 times per second to do
pretty much nothing, so humorously, power saving code was needlessly sucking up
extra power. The attempted fix obviously wasn't quite complete and/or uncovered
another problem, which is being worked on now... :)
Okay, after the update from 2999 to 3016 it works now correctly. So from my
point of view it's closed.
It also works so me now.
Works for me