Re: Maturity of PCI_OPTIMIZE in 2.0.33

Martin Mares (mj@atrey.karlin.mff.cuni.cz)
Tue, 21 Apr 1998 14:03:42 +0200


Hi,

> It is listed as EXPERIMENTAL, but _how_ experiental is it? Is it stable to
> use it on a production system and exactly what does it optimize?

It sets several parameters related to CPU-to-PCI bridging (posted writes,
writeback caching etc.) on several chipsets. It has positive impact on speed
on the following chipsets and only when BIOS forgets to set it itself:

UMC 8891A
UMC 8881F
Intel Mercury/Neptune/Saturn

In general, unless you have one of these chipsets, it has no effect
at all. If you don't have a lazy BIOS, it has no effect even if you have
such chipset and if you have a lazy BIOS, it possibly could break some
things. So preferably don't turn it on.

Have a nice fortnight

-- 
Martin `MJ' Mares   <mj@ucw.cz>   http://atrey.karlin.mff.cuni.cz/~mj/
Faculty of Math and Physics, Charles University, Prague, Czech Rep., Earth
"If at first you don't succeed, redefine success."

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu