Re: Scheduled Transfer Protocol on Linux

From: Brandon S. Allbery KF8NH (allbery@kf8nh.apk.net)
Date: Sun Feb 13 2000 - 17:20:56 EST


In message <200002132204.OAA11808@work.bitmover.com>, Larry McVoy writes:
+-----
| OK, I think I get it. Your point is that SCSI is similar in complexity
| to STP so the fact that SCSI exists says that drives with STP (and
| perhaps Linux) are pretty much a done deal. Is that it? If so, excuse
| my slow brain, it takes me a while sometimes.
+--->8

That's exactly it. SCSI isn't *that* simple a protocol, so SCSI drives need
to have a fair amount of intelligence onboard; the incremental improvement
for fancier schemes such as STP is minimal.

| It's a good point, the only flaw is that SCSI drives are way more expensive
| than IDE drives. The question is if that is inherent or just mark up...
+--->8

Markup. SCSI has never been popular enough to get serious volume-based
price reductions; and those who *do* want it are willing to pay the markup.
But then, that's what the drive manufacturers would like to see, given the
nonexistent margins on (E)IDE. Make it "sexy" enough that it sells better
than SCSI, without making it so much of a commodity that margins fall
through the floor.

-- 
brandon s. allbery	   os/2,linux,solaris,perl	allbery@kf8nh.apk.net
system administrator	   kthkrb,heimdal,gnome,rt	  allbery@ece.cmu.edu
carnegie mellon / electrical and computer engineering			kf8nh
    We are Linux. Resistance is an indication that you missed the point.

- 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 Feb 15 2000 - 21:00:26 EST