doadump at pcpu.h:165

[Daniel A.]

Peter Jeremy wrote:
> On Thu, 2006-Aug-24 17:39:56 +0200, Daniel A. wrote:
>> My server crashes very often and it's very random.
> ...
>> panic: machine check trap
> ...
>> As far as I understand, the issue is CPU-related, but that doesn't make 
>> sense, as my network interface cards are constantly giving me watchdog 
>> timeouts.
> 
> This sounds like flaky hardware.  Try checking cooling, PSU, RAM,
> cabling socketing etc.  Run memtest86 or similar and try swapping
> components.
> 
Hi Peter,
this is no doubt caused by flaky hardware. The reason I keep posting my 
kgdb results is that I want to see if someone has experienced something 
similar.

So far, I have had two crashes where I had saved the vmcore for 
debugging, and these two crashes are not identical. In fact, the only 
thing they have in common is that they are somehow related to networking.

Also, I have no extra hardware. And I have tried the regular debugging 
stuff - After all, this has been going on for several months now, and 
I'm not the type of person who wouldn't notice that something is wrong 
with his beloved server.

Sincerely,
Daniel.