cpufreq problems

cpufreq problems

[Jan Killius]

Hello,
I'm using the cpufreq ondemand scaling governor for my athlon64 system. My 
problem is every time the governor is scaling up the cpu frequency, my sound 
is stuttering for a second. I'm using jack for my sound output. First 
everything is ok the daemon is starting up without a delay. But if the cpu 
speed goes high I'm getting a continuous delay of ~30694.000 usecs...
At the moment im using 2.6.9-ck1. The problem exists also in 2.6.9 and every     
other 2.6 kernel, that I've used before with this feature. Before 2.6.9 I had 
used the cpudyn daemon for it, there occur the same problem.

/proc/cpuinfo(low freq):
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 4
model name      : AMD Athlon(tm) 64 Processor 3200+
stepping        : 8
cpu MHz         : 879.954
cache size      : 1024 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 syscallnx mmxext lm 3dnowext 3dnow
bogomips        : 1730.15
TLB size        : 1088 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp

/proc/cpuinfo(high freq):
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 4
model name      : AMD Athlon(tm) 64 Processor 3200+
stepping        : 8
cpu MHz         : 2199.887
cache size      : 1024 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 syscallnx mmxext lm 3dnowext 3dnow
bogomips        : 4325.37
TLB size        : 1088 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp


--
        Jan

Re: cpufreq problems

[Jan Killius]

Ignore it, it was no kernel bug.