On Sat, May 12, 2001 at 09:52:00AM -0400, Mark Hahn wrote:
> y> > > you're being a bit terse today. What you're saying is that we
> > > > shouldn't need any "hdparm": The driver should figure out the best
> > > > configuration all by itself?
> >
> > I think Andre enjoys setting puzzles, I always have to ponder the
>
> no, he's just irritated by this kind of superstitious hdparm-black-art crap.
> on a modern kernel, with the appopriate controller-specific driver that can
> autotune, with auto-dma on, you *do*not*need*hdparm*. it can do more harm
> than good, these days.
>From my experience, 'hdparm -d1' (DMA) option is what counts. The rest
makes no difference in 'hdparm -tT' test.
--William Park, Open Geometry Consulting, Mississauga, Ontario, Canada.
8 CPU cluster, (Slackware) Linux, Python, LaTeX, vim, mutt
--
=- To unsubscribe, email [EMAIL PROTECTED] with the -=
=- body of "unsubscribe linux-abit". -=
