[rescue] Macs & IDE vs. SCSI

[Phil Stracchino]

On Sat, Apr 12, 2003 at 03:38:26PM -0400, Dave McGuire wrote:
> On Saturday, April 12, 2003, at 03:23 PM, Phil Stracchino wrote:
> >Actually, correct me if I'm wrong, but isn't Serial ATA a 
> >point-to-point
> >connection with no master/slave distinction?  (Or are you not counting
> >Serial ATA as IDE?)
> 
>   As far as I know, you're correct...but this basically boils down to 
> one drive per bus, neatly sweeping a very nasty design flaw under the 
> rug.

Point.

>   I firmly believe that the universe gives us clues here & there...and 
> that all too often, those clues are ignored.  With IDE, you have to 
> modify one of the major aspects of its design...ignore the master/slave 
> thing and put one drive on each bus...in order to gain any useful level 
> of performance.  There's a message there.

Now just suppose all the work that's been put into developing successive
generations of IDE/ATA had been put into improving SCSI instead, and
building less expensive SCSI hardware.  It's interesting to speculate
what the price/performance of SCSI would be right now.  I'm betting it'd
cost little, if any, more than IDE does.

I gotta admit, though, it'd be sweet to get rid of all these damned
ribbon cables and have little tiny 8mm ISDN-ish disk cables instead.
Imagine how much less cluttered PC cases would be if instead of being
full of airflow-blocking 50- and 68-pin ribbon cable, you just had an
input and an output port on each disk and little jumper cables that you
plugged from drive to drive, with an active terminator plugged directly
into the last disk's output port.


-- 
 .*********  Fight Back!  It may not be just YOUR life at risk.  *********.
 : phil stracchino : unix ronin : renaissance man : mystic zen biker geek :
 :  alaric at caerllewys.net : alaric-ruthven at earthlink.net : phil at latt.net  :
 :   2000 CBR929RR, 1991 VFR750F3 (foully murdered), 1986 VF500F (sold)   :
 :    Linux Now!   ...Because friends don't let friends use Microsoft.    :