On Fri, 11 Aug 2000, Mark Hahn wrote:
> > However I do get a problem when overclocking the bus to 110 MHz from 100.
> > But, this is probably expected--I start to get memory errors. I'm wondering if
> > that's because of non-prime RAM Chips or becuase the CPU can't handle the
> > speed.. I'm thinking it's the chips though.
>
> how is this kernel-related? overclocking is completely unsupported:
> by the chipset, ram, cpu vendors, probably even by the vendors of your
> PCI and ISA bus card vendors. it's also not a poor reflection
> on your ram dimms if they don't tolerate overclocking abuse:
> they'd be perfectly justified in simply blowing up! I have nothing
> against overclocking (I have several FSB100 celerons), but expecting
> it to work is just silly...
Of course. In fact, I seriously recommend NOT overclocking because of the
eventual wear on hardware that can occur, even if there Seems to be no
problems at first. But this has nothing to do with the kernel at all--
overclocking from my point of view was only a 3-minute experiment to see how
well the system would react to it, and believe me, it wasn't pretty. :)
Now if the board permitted me to increase the clock multiplier on just the
CPU, then I could find out exactly what the limits are of one piece of
hardware. But I don't, and any problems I find with the system at that point I
would attribute to overclocking (or degrade of hardware thereafter). As to
clarify someone else's email, none of my kernel bug reports or patches have
come from a system that has been overclocked. To me, that's just ludicrous.
One thing I had thought about after reading your email, however, was the ISA
bus speed. I would hopefully assume it's still running at 33 or 66 MHz in my
system, and not 100, because I'm sure my old ISA AWE32 card wouldn't care for
100. I don't think 100 MHz FSB was around at the time..or I could be wrong.
Interesting concept, though. :)
-- Byron Stanoszek Ph: (330) 644-3059 Systems Programmer Fax: (330) 644-8110 Commercial Timesharing Inc. Email: bstanoszek@comtime.com- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Aug 15 2000 - 21:00:26 EST