Re: about K6 bug
-----BEGIN PGP SIGNED MESSAGE-----
On Tue, 02 Jun 1998, Nils Rennebarth wrote:
>>On Tue, Jun 02, 1998 at 12:22:15PM +0400, Eugene Sevinian wrote:
>> Recently, there were a lot of post in email@example.com
>> concerning new K6 bug. Tests was done by 'crashme'. Here is excerption
>> from Andreas Haumer <firstname.lastname@example.org> report.
>> # OS CPU result
>> 11 Linux-2.0 K6 crash
>> 0 Linux-2.0 K6 no crash
>> 0 Linux-2.1 K6 crash
>> 3 Linux-2.1 K6 no crash
>> 0 Linux-2.0 Pentium crash
>> 6 Linux-2.0 Pentium no crash
>> 1 Linux-2.0 K6 unclear
>> Sincerly speaking I have now idea how cricual is this, but as far as
>> I consider K6 as a choice for upgrating my PC, I would like to know how
>> reliable is this assuming that I have no intention to run this testing
>> program very often.
>I followed this thread from when it started and my conclusions up to now
>1) It appears to show up only under circumstances not easily found in real
> life. Someone now posted a short test program that will crash a K6. This
> is not worse than the Intel F0 0F bug.
>2) 2.1 kernels are immune to this crash, and as these are in almost as deep
> freeze as debian 2.0 is now :-), 2.2 is not too far away and the problem
> goes away.
>I do not yet see a reason to buy an Intel instead.
besides I have been running an overclocked K6 (233 -> 266) for 4 Months now.
Whereas win95 crashes regularly (it does so anyway), Linux didn't crash once.
During this time I compiled several kernels, created highly compressed MP3s
played Quake2 for hours, burned a gazillion of CDs. I don't know what this
testing program is about, but the highly customized 2.0.33 kernel I use never
complained about the K6.
One man's "simple" is another man's "huh?"
* web: ishmael.ml.org/~zander
* email: email@example.com
-----BEGIN PGP SIGNATURE-----
-----END PGP SIGNATURE-----
To UNSUBSCRIBE, email to firstname.lastname@example.org
with a subject of "unsubscribe". Trouble? Contact email@example.com