Re: 2.1.111: IDE DMA disabled...BLAH...BLAH...

Shannon (shendrix@escape.widomaker.com)
Thu, 30 Jul 1998 00:25:08 -0400


In message <m3vhogs15p.fsf@k6.jhcloos.com>, "James H. Cloos Jr." writes:

> Linus> Another difference is that
> Linus> we react to interrupts a lot faster under SMP.
>
> Perhaps, since the problem seems dependent on both DMA and SMP, the
> real differnece is IO-APIC vs XT-PIC?

I think what we are finding out in the 2.1 kernel is just how bad
the quality of PeeCee hardware is. I have know that all along,
but I think the problems in 2.1 are often the hardware's fault.

A lot of commercial OS offerings are tuned ``slow'' for this reason.
Its not always because they suck... :)

The hardware is often incredibly marginal and rarely is a PeeCee
motherboard within specifications all around. I often marvel that
Linux or any other OS runs as well as they do.

Since PCI and PlugNPlay... I have yet to setup a PeeCee where any
one is not night and day different from another. Setting them up
is a black art.

--
csh - shendrix@widomaker.com - Dilbert is one of my coworkers...
----------------------------------------------------------------------
"Those who trade liberty for security will have neither -- B.F."

- 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.altern.org/andrebalsa/doc/lkml-faq.html