>>>>>> The latter seems to be utime ...decreasing. No wonder if
>>>>>> arithmetics will give strange results (probably top is using
>>>>>> unsigned delta?)...
>>>>> Hmm, minor miscounting from my side, stime seems more appropriate...
>>>> So, is it normal that stime decreases sometimes or a kernel bug?
>>>> /me expects the last...
>>> Let me guess... Dual core AMD64 ?
>> Nope: Intel(R) Pentium(R) D CPU 3.20GHz
>
> I just notice the same thing here, with a Core2 Duo (which is supposed
> to have synced TSCs) and working HPET.
>
>> The following may well be relevant.
>> With 2.6.22 and early 2.6.23-rc kernels (rc3-rc6) I often had this in my
>> kernel log (see
http://lkml.org/lkml/2007/9/16/45):
>> checking TSC synchronization [CPU#0 -> CPU#1]:
>> Measured 248 cycles TSC warp between CPUs, turning off TSC clock.
>> Marking TSC unstable due to check_tsc_sync_source failed
>
> I don't see this though, TSCs are always syncronized between the 2
> cores.
>
