Re: NetBSD 5.0.2 can't handle 7455 CPU @ 1 GHz?

[Flavio Donadio <flavio%donadio.com.br@localhost>]

Donald,


Well... I am not really a "hacker". I would be in the same situation as you are 
now.

But I believe that someone on this list should have better ideas. At least, I 
hope so...


Cheers,
Flavio

On 22/12/2010, at 18:40, Donald Lee wrote:

> That's hard to say.  I smell a race, but I do not have enough data to say
> where that race might be.
> 
> The machine simply hangs up hard.  What would I have to do to
> get said stack trace?  My tool of choice in debugging the kernel
> is the "printf" - not so useful in this case.....
> 
> -dgl-
> 
>> Donald,
>> 
>> 
>> So, it seems the problem has something to do with disk I/O.
>> 
>> How can one get a stacktrace of the crash?
>> 
>> 
>> Cheers,
>> Flavio
>> 
>> 
>> On 22/12/2010, at 13:54, Donald Lee wrote:
>> 
>>> One more report.....
>>> 
>>> I re-installed the 2.1 stock kernel on a single disk on the internal ATA 
>>> bus,
>>> and fired up the newfs loop.  This time, though, I started up a background
>>> "CPU burner".  ("while true ; do : ; done")
>>> 
>>> With the cpu burner running, the newfs loop has been running a couple of
>>> hours and is still running.
>>> 
>>> Conclusion: new data point.
>>> 
>>> stock 5.0.2 kernel with CPU burner is stable.
>>> 
>>> I've run out of experiments for now.
>>> 
>>> Merry Christmas, all!
>>> 
>>> -dgl-
>